Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9904153354632586,
+    "total_flos": 3.9082027465048064e+17,
+    "train_loss": 0.0,
+    "train_runtime": 6.1081,
+    "train_samples_per_second": 4911.493,
+    "train_steps_per_second": 51.08
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/eguha/models_cache/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba032319013c7c760e292838740bcda2cb4cab0f2f1279942e678f157ae8522
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5845ec226a0842c1a0f0b03aac6db1ccf09b487dc0a9a804d145079b70c7e10
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca09190bf26bb0e9ba3a41005e9d6a27380e34e90b404a52326fbf97a22b775
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be037905145883a6ec3d2f481228a5b977e89e8cbcea6af1f1627bbf17ce8dd8
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9904153354632586,
+    "total_flos": 3.9082027465048064e+17,
+    "train_loss": 0.0,
+    "train_runtime": 6.1081,
+    "train_samples_per_second": 4911.493,
+    "train_steps_per_second": 51.08
+}

trainer_log.jsonl

@@ -0,0 +1,315 @@
+{"current_steps": 1, "total_steps": 312, "loss": 1.1263, "lr": 3.125e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:39", "remaining_time": "3:23:29"}
+{"current_steps": 2, "total_steps": 312, "loss": 1.0931, "lr": 6.25e-07, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:04", "remaining_time": "2:46:55"}
+{"current_steps": 3, "total_steps": 312, "loss": 1.1248, "lr": 9.375000000000001e-07, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:33", "remaining_time": "2:39:43"}
+{"current_steps": 4, "total_steps": 312, "loss": 1.0913, "lr": 1.25e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:00", "remaining_time": "2:35:06"}
+{"current_steps": 5, "total_steps": 312, "loss": 1.0767, "lr": 1.5625e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:31", "remaining_time": "2:35:08"}
+{"current_steps": 6, "total_steps": 312, "loss": 1.0705, "lr": 1.8750000000000003e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:02:59", "remaining_time": "2:32:12"}
+{"current_steps": 7, "total_steps": 312, "loss": 1.0487, "lr": 2.1875000000000002e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:30", "remaining_time": "2:32:46"}
+{"current_steps": 8, "total_steps": 312, "loss": 1.0214, "lr": 2.5e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:02", "remaining_time": "2:33:23"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.9842, "lr": 2.8125e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:04:29", "remaining_time": "2:31:24"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.9671, "lr": 3.125e-06, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:04:57", "remaining_time": "2:29:53"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.9597, "lr": 3.4375e-06, "epoch": 0.10543130990415335, "percentage": 3.53, "elapsed_time": "0:05:25", "remaining_time": "2:28:27"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.9319, "lr": 3.7500000000000005e-06, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:05:58", "remaining_time": "2:29:22"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.9196, "lr": 4.0625000000000005e-06, "epoch": 0.12460063897763578, "percentage": 4.17, "elapsed_time": "0:06:32", "remaining_time": "2:30:19"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.9054, "lr": 4.3750000000000005e-06, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:06:56", "remaining_time": "2:27:49"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.8922, "lr": 4.6875000000000004e-06, "epoch": 0.14376996805111822, "percentage": 4.81, "elapsed_time": "0:07:27", "remaining_time": "2:27:39"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.8626, "lr": 5e-06, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:07:54", "remaining_time": "2:26:25"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.8325, "lr": 5.3125e-06, "epoch": 0.16293929712460065, "percentage": 5.45, "elapsed_time": "0:08:22", "remaining_time": "2:25:25"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.8278, "lr": 5.625e-06, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:08:55", "remaining_time": "2:25:46"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.801, "lr": 5.9375e-06, "epoch": 0.18210862619808307, "percentage": 6.09, "elapsed_time": "0:09:20", "remaining_time": "2:23:57"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.7924, "lr": 6.25e-06, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:09:49", "remaining_time": "2:23:24"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.7778, "lr": 6.5625e-06, "epoch": 0.2012779552715655, "percentage": 6.73, "elapsed_time": "0:10:19", "remaining_time": "2:23:06"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.7677, "lr": 6.875e-06, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:10:50", "remaining_time": "2:22:59"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.765, "lr": 7.1875e-06, "epoch": 0.22044728434504793, "percentage": 7.37, "elapsed_time": "0:11:20", "remaining_time": "2:22:32"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.7434, "lr": 7.500000000000001e-06, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:11:53", "remaining_time": "2:22:38"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.7524, "lr": 7.8125e-06, "epoch": 0.23961661341853036, "percentage": 8.01, "elapsed_time": "0:12:25", "remaining_time": "2:22:34"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.7231, "lr": 8.125000000000001e-06, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:12:48", "remaining_time": "2:20:50"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.7251, "lr": 8.4375e-06, "epoch": 0.25878594249201275, "percentage": 8.65, "elapsed_time": "0:13:22", "remaining_time": "2:21:08"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.722, "lr": 8.750000000000001e-06, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:13:55", "remaining_time": "2:21:12"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.7107, "lr": 9.0625e-06, "epoch": 0.2779552715654952, "percentage": 9.29, "elapsed_time": "0:14:23", "remaining_time": "2:20:21"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.6975, "lr": 9.375000000000001e-06, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:14:53", "remaining_time": "2:19:58"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.7019, "lr": 9.6875e-06, "epoch": 0.2971246006389776, "percentage": 9.94, "elapsed_time": "0:15:25", "remaining_time": "2:19:45"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.7015, "lr": 1e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:15:57", "remaining_time": "2:19:34"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.7084, "lr": 9.999685283773504e-06, "epoch": 0.31629392971246006, "percentage": 10.58, "elapsed_time": "0:16:24", "remaining_time": "2:18:40"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.7011, "lr": 9.998741174712534e-06, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:16:55", "remaining_time": "2:18:20"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.696, "lr": 9.997167791667668e-06, "epoch": 0.3354632587859425, "percentage": 11.22, "elapsed_time": "0:17:23", "remaining_time": "2:17:35"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.6928, "lr": 9.994965332706574e-06, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:17:54", "remaining_time": "2:17:14"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.699, "lr": 9.992134075089085e-06, "epoch": 0.3546325878594249, "percentage": 11.86, "elapsed_time": "0:18:27", "remaining_time": "2:17:08"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.6843, "lr": 9.98867437523228e-06, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:18:58", "remaining_time": "2:16:49"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.6867, "lr": 9.984586668665641e-06, "epoch": 0.3738019169329074, "percentage": 12.5, "elapsed_time": "0:19:29", "remaining_time": "2:16:27"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.6628, "lr": 9.979871469976197e-06, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:19:54", "remaining_time": "2:15:22"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.6578, "lr": 9.974529372743762e-06, "epoch": 0.3929712460063898, "percentage": 13.14, "elapsed_time": "0:20:26", "remaining_time": "2:15:04"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.6671, "lr": 9.968561049466214e-06, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:20:55", "remaining_time": "2:14:33"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.6648, "lr": 9.961967251474823e-06, "epoch": 0.41214057507987223, "percentage": 13.78, "elapsed_time": "0:21:28", "remaining_time": "2:14:17"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.6499, "lr": 9.954748808839675e-06, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:21:53", "remaining_time": "2:13:19"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.6605, "lr": 9.946906630265184e-06, "epoch": 0.43130990415335463, "percentage": 14.42, "elapsed_time": "0:22:21", "remaining_time": "2:12:41"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.6774, "lr": 9.938441702975689e-06, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:22:53", "remaining_time": "2:12:22"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.6646, "lr": 9.92935509259118e-06, "epoch": 0.4504792332268371, "percentage": 15.06, "elapsed_time": "0:23:23", "remaining_time": "2:11:54"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.6593, "lr": 9.91964794299315e-06, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:23:50", "remaining_time": "2:11:09"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.6569, "lr": 9.909321476180594e-06, "epoch": 0.4696485623003195, "percentage": 15.71, "elapsed_time": "0:24:21", "remaining_time": "2:10:43"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.6644, "lr": 9.898376992116179e-06, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:24:48", "remaining_time": "2:10:01"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.6522, "lr": 9.886815868562596e-06, "epoch": 0.48881789137380194, "percentage": 16.35, "elapsed_time": "0:25:15", "remaining_time": "2:09:16"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.6584, "lr": 9.874639560909118e-06, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:25:45", "remaining_time": "2:08:47"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.6504, "lr": 9.861849601988384e-06, "epoch": 0.5079872204472844, "percentage": 16.99, "elapsed_time": "0:26:13", "remaining_time": "2:08:08"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.6642, "lr": 9.848447601883436e-06, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:26:46", "remaining_time": "2:07:54"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.6349, "lr": 9.834435247725032e-06, "epoch": 0.5271565495207667, "percentage": 17.63, "elapsed_time": "0:27:14", "remaining_time": "2:07:15"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.625, "lr": 9.819814303479268e-06, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:27:49", "remaining_time": "2:07:10"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.6583, "lr": 9.804586609725499e-06, "epoch": 0.5463258785942492, "percentage": 18.27, "elapsed_time": "0:28:14", "remaining_time": "2:06:20"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.6352, "lr": 9.788754083424654e-06, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:28:40", "remaining_time": "2:05:32"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.6464, "lr": 9.772318717677905e-06, "epoch": 0.5654952076677316, "percentage": 18.91, "elapsed_time": "0:29:07", "remaining_time": "2:04:52"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.6242, "lr": 9.755282581475769e-06, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:29:35", "remaining_time": "2:04:17"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.6585, "lr": 9.737647819437645e-06, "epoch": 0.5846645367412141, "percentage": 19.55, "elapsed_time": "0:30:05", "remaining_time": "2:03:47"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.6463, "lr": 9.719416651541839e-06, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:30:29", "remaining_time": "2:02:58"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.6503, "lr": 9.700591372846096e-06, "epoch": 0.6038338658146964, "percentage": 20.19, "elapsed_time": "0:30:58", "remaining_time": "2:02:25"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.6306, "lr": 9.681174353198687e-06, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:31:31", "remaining_time": "2:02:07"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.6462, "lr": 9.661168036940071e-06, "epoch": 0.6230031948881789, "percentage": 20.83, "elapsed_time": "0:31:57", "remaining_time": "2:01:25"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.6363, "lr": 9.640574942595195e-06, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:32:31", "remaining_time": "2:01:14"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.6312, "lr": 9.619397662556434e-06, "epoch": 0.6421725239616614, "percentage": 21.47, "elapsed_time": "0:33:04", "remaining_time": "2:00:55"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.6485, "lr": 9.597638862757255e-06, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:33:31", "remaining_time": "2:00:16"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.6271, "lr": 9.5753012823366e-06, "epoch": 0.6613418530351438, "percentage": 22.12, "elapsed_time": "0:34:02", "remaining_time": "1:59:52"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.6405, "lr": 9.552387733294081e-06, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:34:28", "remaining_time": "1:59:10"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.6462, "lr": 9.528901100135971e-06, "epoch": 0.6805111821086262, "percentage": 22.76, "elapsed_time": "0:34:57", "remaining_time": "1:58:38"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.6494, "lr": 9.504844339512096e-06, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:35:28", "remaining_time": "1:58:13"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.643, "lr": 9.480220479843627e-06, "epoch": 0.6996805111821086, "percentage": 23.4, "elapsed_time": "0:35:59", "remaining_time": "1:57:50"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.6449, "lr": 9.45503262094184e-06, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:36:26", "remaining_time": "1:57:12"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.6438, "lr": 9.4292839336179e-06, "epoch": 0.7188498402555911, "percentage": 24.04, "elapsed_time": "0:36:49", "remaining_time": "1:56:21"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.6277, "lr": 9.40297765928369e-06, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:37:19", "remaining_time": "1:55:52"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.6346, "lr": 9.376117109543769e-06, "epoch": 0.7380191693290735, "percentage": 24.68, "elapsed_time": "0:37:51", "remaining_time": "1:55:32"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.6398, "lr": 9.348705665778479e-06, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:38:14", "remaining_time": "1:54:42"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.6214, "lr": 9.320746778718274e-06, "epoch": 0.7571884984025559, "percentage": 25.32, "elapsed_time": "0:38:36", "remaining_time": "1:53:52"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.6359, "lr": 9.292243968009332e-06, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:39:08", "remaining_time": "1:53:30"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.6387, "lr": 9.263200821770462e-06, "epoch": 0.7763578274760383, "percentage": 25.96, "elapsed_time": "0:39:39", "remaining_time": "1:53:06"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.6336, "lr": 9.233620996141421e-06, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:40:06", "remaining_time": "1:52:30"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.6361, "lr": 9.203508214822652e-06, "epoch": 0.7955271565495208, "percentage": 26.6, "elapsed_time": "0:40:35", "remaining_time": "1:52:00"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.6283, "lr": 9.172866268606514e-06, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:41:01", "remaining_time": "1:51:22"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.6334, "lr": 9.141699014900084e-06, "epoch": 0.8146964856230032, "percentage": 27.24, "elapsed_time": "0:41:26", "remaining_time": "1:50:40"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.6166, "lr": 9.110010377239552e-06, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:41:57", "remaining_time": "1:50:14"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.6454, "lr": 9.077804344796302e-06, "epoch": 0.8338658146964856, "percentage": 27.88, "elapsed_time": "0:42:25", "remaining_time": "1:49:42"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.6384, "lr": 9.045084971874738e-06, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:42:56", "remaining_time": "1:49:18"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.6347, "lr": 9.011856377401891e-06, "epoch": 0.853035143769968, "percentage": 28.53, "elapsed_time": "0:43:25", "remaining_time": "1:48:47"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.6206, "lr": 8.978122744408905e-06, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:43:54", "remaining_time": "1:48:17"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.6217, "lr": 8.943888319504456e-06, "epoch": 0.8722044728434505, "percentage": 29.17, "elapsed_time": "0:44:27", "remaining_time": "1:47:58"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.6326, "lr": 8.90915741234015e-06, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:44:56", "remaining_time": "1:47:29"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.6109, "lr": 8.873934395068006e-06, "epoch": 0.8913738019169329, "percentage": 29.81, "elapsed_time": "0:45:23", "remaining_time": "1:46:54"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.6316, "lr": 8.838223701790057e-06, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:45:47", "remaining_time": "1:46:11"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.6261, "lr": 8.802029828000157e-06, "epoch": 0.9105431309904153, "percentage": 30.45, "elapsed_time": "0:46:08", "remaining_time": "1:45:24"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.6406, "lr": 8.765357330018056e-06, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:46:35", "remaining_time": "1:44:49"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.6357, "lr": 8.728210824415829e-06, "epoch": 0.9297124600638977, "percentage": 31.09, "elapsed_time": "0:47:03", "remaining_time": "1:44:19"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.6032, "lr": 8.690594987436705e-06, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:47:32", "remaining_time": "1:43:48"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.5996, "lr": 8.652514554406388e-06, "epoch": 0.9488817891373802, "percentage": 31.73, "elapsed_time": "0:48:06", "remaining_time": "1:43:29"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.6229, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:48:38", "remaining_time": "1:43:07"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.6317, "lr": 8.574979133323378e-06, "epoch": 0.9680511182108626, "percentage": 32.37, "elapsed_time": "0:49:05", "remaining_time": "1:42:33"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.631, "lr": 8.535533905932739e-06, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:49:35", "remaining_time": "1:42:06"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.6205, "lr": 8.495643602586287e-06, "epoch": 0.987220447284345, "percentage": 33.01, "elapsed_time": "0:50:06", "remaining_time": "1:41:41"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.614, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:50:37", "remaining_time": "1:41:15"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.5928, "lr": 8.414547910024035e-06, "epoch": 1.0063897763578276, "percentage": 33.65, "elapsed_time": "0:51:35", "remaining_time": "1:41:43"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.587, "lr": 8.373352729660373e-06, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:52:02", "remaining_time": "1:41:08"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.5827, "lr": 8.331732889760021e-06, "epoch": 1.0255591054313098, "percentage": 34.29, "elapsed_time": "0:52:36", "remaining_time": "1:40:48"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.5899, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:53:07", "remaining_time": "1:40:20"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.588, "lr": 8.247240241650918e-06, "epoch": 1.0447284345047922, "percentage": 34.94, "elapsed_time": "0:53:39", "remaining_time": "1:39:56"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.5913, "lr": 8.204378069925121e-06, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:54:12", "remaining_time": "1:39:31"}
+{"current_steps": 111, "total_steps": 312, "loss": 0.5808, "lr": 8.16111251028955e-06, "epoch": 1.0638977635782747, "percentage": 35.58, "elapsed_time": "0:54:41", "remaining_time": "1:39:02"}
+{"current_steps": 112, "total_steps": 312, "loss": 0.5791, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:55:11", "remaining_time": "1:38:32"}
+{"current_steps": 113, "total_steps": 312, "loss": 0.5707, "lr": 8.073393063582386e-06, "epoch": 1.0830670926517572, "percentage": 36.22, "elapsed_time": "0:55:43", "remaining_time": "1:38:08"}
+{"current_steps": 114, "total_steps": 312, "loss": 0.5739, "lr": 8.0289502192041e-06, "epoch": 1.0926517571884984, "percentage": 36.54, "elapsed_time": "0:56:14", "remaining_time": "1:37:40"}
+{"current_steps": 115, "total_steps": 312, "loss": 0.5665, "lr": 7.984126070912519e-06, "epoch": 1.1022364217252396, "percentage": 36.86, "elapsed_time": "0:56:38", "remaining_time": "1:37:02"}
+{"current_steps": 116, "total_steps": 312, "loss": 0.5648, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:57:10", "remaining_time": "1:36:36"}
+{"current_steps": 117, "total_steps": 312, "loss": 0.5893, "lr": 7.89335648089903e-06, "epoch": 1.121405750798722, "percentage": 37.5, "elapsed_time": "0:57:36", "remaining_time": "1:36:00"}
+{"current_steps": 118, "total_steps": 312, "loss": 0.5847, "lr": 7.84742246584226e-06, "epoch": 1.1309904153354633, "percentage": 37.82, "elapsed_time": "0:58:03", "remaining_time": "1:35:27"}
+{"current_steps": 119, "total_steps": 312, "loss": 0.5734, "lr": 7.801129998764014e-06, "epoch": 1.1405750798722045, "percentage": 38.14, "elapsed_time": "0:58:36", "remaining_time": "1:35:03"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.5751, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:59:05", "remaining_time": "1:34:32"}
+{"current_steps": 121, "total_steps": 312, "loss": 0.5652, "lr": 7.70749306331863e-06, "epoch": 1.159744408945687, "percentage": 38.78, "elapsed_time": "0:59:27", "remaining_time": "1:33:51"}
+{"current_steps": 122, "total_steps": 312, "loss": 0.5717, "lr": 7.660160382576683e-06, "epoch": 1.1693290734824282, "percentage": 39.1, "elapsed_time": "1:00:01", "remaining_time": "1:33:28"}
+{"current_steps": 123, "total_steps": 312, "loss": 0.5789, "lr": 7.612492823579744e-06, "epoch": 1.1789137380191694, "percentage": 39.42, "elapsed_time": "1:00:34", "remaining_time": "1:33:04"}
+{"current_steps": 124, "total_steps": 312, "loss": 0.5678, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "1:00:58", "remaining_time": "1:32:26"}
+{"current_steps": 125, "total_steps": 312, "loss": 0.5741, "lr": 7.516177115029002e-06, "epoch": 1.1980830670926517, "percentage": 40.06, "elapsed_time": "1:01:31", "remaining_time": "1:32:02"}
+{"current_steps": 126, "total_steps": 312, "loss": 0.5587, "lr": 7.467541090321735e-06, "epoch": 1.207667731629393, "percentage": 40.38, "elapsed_time": "1:02:03", "remaining_time": "1:31:36"}
+{"current_steps": 127, "total_steps": 312, "loss": 0.5796, "lr": 7.4185944355261996e-06, "epoch": 1.2172523961661341, "percentage": 40.71, "elapsed_time": "1:02:28", "remaining_time": "1:31:00"}
+{"current_steps": 128, "total_steps": 312, "loss": 0.5808, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "1:02:57", "remaining_time": "1:30:29"}
+{"current_steps": 129, "total_steps": 312, "loss": 0.5783, "lr": 7.319793920889171e-06, "epoch": 1.2364217252396166, "percentage": 41.35, "elapsed_time": "1:03:24", "remaining_time": "1:29:56"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.5577, "lr": 7.269952498697734e-06, "epoch": 1.2460063897763578, "percentage": 41.67, "elapsed_time": "1:03:52", "remaining_time": "1:29:24"}
+{"current_steps": 131, "total_steps": 312, "loss": 0.5508, "lr": 7.219825320152411e-06, "epoch": 1.255591054313099, "percentage": 41.99, "elapsed_time": "1:04:18", "remaining_time": "1:28:50"}
+{"current_steps": 132, "total_steps": 312, "loss": 0.5682, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "1:04:52", "remaining_time": "1:28:27"}
+{"current_steps": 133, "total_steps": 312, "loss": 0.5719, "lr": 7.118738970516944e-06, "epoch": 1.2747603833865815, "percentage": 42.63, "elapsed_time": "1:05:18", "remaining_time": "1:27:53"}
+{"current_steps": 134, "total_steps": 312, "loss": 0.566, "lr": 7.067792524832604e-06, "epoch": 1.2843450479233227, "percentage": 42.95, "elapsed_time": "1:05:47", "remaining_time": "1:27:23"}
+{"current_steps": 135, "total_steps": 312, "loss": 0.5792, "lr": 7.016585772004026e-06, "epoch": 1.293929712460064, "percentage": 43.27, "elapsed_time": "1:06:15", "remaining_time": "1:26:51"}
+{"current_steps": 136, "total_steps": 312, "loss": 0.579, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "1:06:42", "remaining_time": "1:26:19"}
+{"current_steps": 137, "total_steps": 312, "loss": 0.5663, "lr": 6.913417161825449e-06, "epoch": 1.3130990415335464, "percentage": 43.91, "elapsed_time": "1:07:06", "remaining_time": "1:25:42"}
+{"current_steps": 138, "total_steps": 312, "loss": 0.581, "lr": 6.8614682920097265e-06, "epoch": 1.3226837060702876, "percentage": 44.23, "elapsed_time": "1:07:34", "remaining_time": "1:25:11"}
+{"current_steps": 139, "total_steps": 312, "loss": 0.5713, "lr": 6.809285088483361e-06, "epoch": 1.3322683706070286, "percentage": 44.55, "elapsed_time": "1:08:01", "remaining_time": "1:24:40"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.5703, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "1:08:33", "remaining_time": "1:24:13"}
+{"current_steps": 141, "total_steps": 312, "loss": 0.5561, "lr": 6.704241985612625e-06, "epoch": 1.351437699680511, "percentage": 45.19, "elapsed_time": "1:09:02", "remaining_time": "1:23:44"}
+{"current_steps": 142, "total_steps": 312, "loss": 0.5614, "lr": 6.651395309775837e-06, "epoch": 1.3610223642172525, "percentage": 45.51, "elapsed_time": "1:09:27", "remaining_time": "1:23:08"}
+{"current_steps": 143, "total_steps": 312, "loss": 0.5766, "lr": 6.598340745578908e-06, "epoch": 1.3706070287539935, "percentage": 45.83, "elapsed_time": "1:09:55", "remaining_time": "1:22:38"}
+{"current_steps": 144, "total_steps": 312, "loss": 0.5611, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "1:10:30", "remaining_time": "1:22:15"}
+{"current_steps": 145, "total_steps": 312, "loss": 0.5691, "lr": 6.491634692845781e-06, "epoch": 1.389776357827476, "percentage": 46.47, "elapsed_time": "1:11:01", "remaining_time": "1:21:48"}
+{"current_steps": 146, "total_steps": 312, "loss": 0.5694, "lr": 6.437996637160086e-06, "epoch": 1.3993610223642172, "percentage": 46.79, "elapsed_time": "1:11:29", "remaining_time": "1:21:17"}
+{"current_steps": 147, "total_steps": 312, "loss": 0.5592, "lr": 6.384177557124247e-06, "epoch": 1.4089456869009584, "percentage": 47.12, "elapsed_time": "1:12:01", "remaining_time": "1:20:50"}
+{"current_steps": 148, "total_steps": 312, "loss": 0.5804, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "1:12:31", "remaining_time": "1:20:22"}
+{"current_steps": 149, "total_steps": 312, "loss": 0.5581, "lr": 6.276023446318214e-06, "epoch": 1.428115015974441, "percentage": 47.76, "elapsed_time": "1:13:02", "remaining_time": "1:19:54"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.5688, "lr": 6.2217020306894705e-06, "epoch": 1.4376996805111821, "percentage": 48.08, "elapsed_time": "1:13:34", "remaining_time": "1:19:27"}
+{"current_steps": 151, "total_steps": 312, "loss": 0.5635, "lr": 6.1672268192795285e-06, "epoch": 1.4472843450479234, "percentage": 48.4, "elapsed_time": "1:13:59", "remaining_time": "1:18:53"}
+{"current_steps": 152, "total_steps": 312, "loss": 0.577, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:14:30", "remaining_time": "1:18:25"}
+{"current_steps": 153, "total_steps": 312, "loss": 0.5775, "lr": 6.057842458386315e-06, "epoch": 1.4664536741214058, "percentage": 49.04, "elapsed_time": "1:14:57", "remaining_time": "1:17:53"}
+{"current_steps": 154, "total_steps": 312, "loss": 0.5714, "lr": 6.002947078916365e-06, "epoch": 1.476038338658147, "percentage": 49.36, "elapsed_time": "1:15:27", "remaining_time": "1:17:25"}
+{"current_steps": 155, "total_steps": 312, "loss": 0.5621, "lr": 5.947925441958393e-06, "epoch": 1.4856230031948883, "percentage": 49.68, "elapsed_time": "1:15:58", "remaining_time": "1:16:57"}
+{"current_steps": 156, "total_steps": 312, "loss": 0.566, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:16:28", "remaining_time": "1:16:28"}
+{"current_steps": 157, "total_steps": 312, "loss": 0.5796, "lr": 5.837531116523683e-06, "epoch": 1.5047923322683707, "percentage": 50.32, "elapsed_time": "1:16:57", "remaining_time": "1:15:58"}
+{"current_steps": 158, "total_steps": 312, "loss": 0.5699, "lr": 5.782172325201155e-06, "epoch": 1.5143769968051117, "percentage": 50.64, "elapsed_time": "1:17:25", "remaining_time": "1:15:28"}
+{"current_steps": 159, "total_steps": 312, "loss": 0.5639, "lr": 5.726715068949564e-06, "epoch": 1.5239616613418532, "percentage": 50.96, "elapsed_time": "1:17:52", "remaining_time": "1:14:56"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.5747, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:18:22", "remaining_time": "1:14:27"}
+{"current_steps": 161, "total_steps": 312, "loss": 0.5574, "lr": 5.615533098453215e-06, "epoch": 1.5431309904153354, "percentage": 51.6, "elapsed_time": "1:18:56", "remaining_time": "1:14:01"}
+{"current_steps": 162, "total_steps": 312, "loss": 0.5602, "lr": 5.559822380516539e-06, "epoch": 1.5527156549520766, "percentage": 51.92, "elapsed_time": "1:19:26", "remaining_time": "1:13:33"}
+{"current_steps": 163, "total_steps": 312, "loss": 0.5751, "lr": 5.504041188505022e-06, "epoch": 1.5623003194888179, "percentage": 52.24, "elapsed_time": "1:19:52", "remaining_time": "1:13:00"}
+{"current_steps": 164, "total_steps": 312, "loss": 0.5731, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:20:20", "remaining_time": "1:12:29"}
+{"current_steps": 165, "total_steps": 312, "loss": 0.5751, "lr": 5.392295478639226e-06, "epoch": 1.5814696485623003, "percentage": 52.88, "elapsed_time": "1:20:50", "remaining_time": "1:12:01"}
+{"current_steps": 166, "total_steps": 312, "loss": 0.5701, "lr": 5.336345028060199e-06, "epoch": 1.5910543130990416, "percentage": 53.21, "elapsed_time": "1:21:22", "remaining_time": "1:11:34"}
+{"current_steps": 167, "total_steps": 312, "loss": 0.5745, "lr": 5.2803522361859596e-06, "epoch": 1.6006389776357828, "percentage": 53.53, "elapsed_time": "1:21:51", "remaining_time": "1:11:04"}
+{"current_steps": 168, "total_steps": 312, "loss": 0.5622, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:22:19", "remaining_time": "1:10:34"}
+{"current_steps": 169, "total_steps": 312, "loss": 0.5571, "lr": 5.168267827938971e-06, "epoch": 1.619808306709265, "percentage": 54.17, "elapsed_time": "1:22:50", "remaining_time": "1:10:06"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.5696, "lr": 5.112190321479026e-06, "epoch": 1.6293929712460065, "percentage": 54.49, "elapsed_time": "1:23:22", "remaining_time": "1:09:38"}
+{"current_steps": 171, "total_steps": 312, "loss": 0.6019, "lr": 5.05609869177323e-06, "epoch": 1.6389776357827475, "percentage": 54.81, "elapsed_time": "1:23:47", "remaining_time": "1:09:05"}
+{"current_steps": 172, "total_steps": 312, "loss": 0.5767, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:24:15", "remaining_time": "1:08:34"}
+{"current_steps": 173, "total_steps": 312, "loss": 0.5611, "lr": 4.943901308226771e-06, "epoch": 1.65814696485623, "percentage": 55.45, "elapsed_time": "1:24:44", "remaining_time": "1:08:05"}
+{"current_steps": 174, "total_steps": 312, "loss": 0.5498, "lr": 4.887809678520976e-06, "epoch": 1.6677316293929714, "percentage": 55.77, "elapsed_time": "1:25:15", "remaining_time": "1:07:36"}
+{"current_steps": 175, "total_steps": 312, "loss": 0.5793, "lr": 4.831732172061032e-06, "epoch": 1.6773162939297124, "percentage": 56.09, "elapsed_time": "1:25:48", "remaining_time": "1:07:10"}
+{"current_steps": 176, "total_steps": 312, "loss": 0.5616, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:26:15", "remaining_time": "1:06:38"}
+{"current_steps": 177, "total_steps": 312, "loss": 0.5763, "lr": 4.719647763814041e-06, "epoch": 1.6964856230031948, "percentage": 56.73, "elapsed_time": "1:26:42", "remaining_time": "1:06:08"}
+{"current_steps": 178, "total_steps": 312, "loss": 0.579, "lr": 4.663654971939802e-06, "epoch": 1.706070287539936, "percentage": 57.05, "elapsed_time": "1:27:13", "remaining_time": "1:05:39"}
+{"current_steps": 179, "total_steps": 312, "loss": 0.5611, "lr": 4.6077045213607765e-06, "epoch": 1.7156549520766773, "percentage": 57.37, "elapsed_time": "1:27:44", "remaining_time": "1:05:11"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.5778, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:28:15", "remaining_time": "1:04:43"}
+{"current_steps": 181, "total_steps": 312, "loss": 0.5686, "lr": 4.4959588114949785e-06, "epoch": 1.7348242811501597, "percentage": 58.01, "elapsed_time": "1:28:39", "remaining_time": "1:04:09"}
+{"current_steps": 182, "total_steps": 312, "loss": 0.5692, "lr": 4.4401776194834615e-06, "epoch": 1.744408945686901, "percentage": 58.33, "elapsed_time": "1:29:10", "remaining_time": "1:03:41"}
+{"current_steps": 183, "total_steps": 312, "loss": 0.5762, "lr": 4.384466901546786e-06, "epoch": 1.7539936102236422, "percentage": 58.65, "elapsed_time": "1:29:43", "remaining_time": "1:03:14"}
+{"current_steps": 184, "total_steps": 312, "loss": 0.5489, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:30:13", "remaining_time": "1:02:45"}
+{"current_steps": 185, "total_steps": 312, "loss": 0.5634, "lr": 4.273284931050438e-06, "epoch": 1.7731629392971247, "percentage": 59.29, "elapsed_time": "1:30:40", "remaining_time": "1:02:14"}
+{"current_steps": 186, "total_steps": 312, "loss": 0.566, "lr": 4.217827674798845e-06, "epoch": 1.7827476038338657, "percentage": 59.62, "elapsed_time": "1:31:09", "remaining_time": "1:01:45"}
+{"current_steps": 187, "total_steps": 312, "loss": 0.5837, "lr": 4.162468883476319e-06, "epoch": 1.792332268370607, "percentage": 59.94, "elapsed_time": "1:31:39", "remaining_time": "1:01:16"}
+{"current_steps": 188, "total_steps": 312, "loss": 0.5646, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:32:02", "remaining_time": "1:00:42"}
+{"current_steps": 189, "total_steps": 312, "loss": 0.5644, "lr": 4.052074558041608e-06, "epoch": 1.8115015974440896, "percentage": 60.58, "elapsed_time": "1:32:30", "remaining_time": "1:00:12"}
+{"current_steps": 190, "total_steps": 312, "loss": 0.5576, "lr": 3.997052921083637e-06, "epoch": 1.8210862619808306, "percentage": 60.9, "elapsed_time": "1:32:58", "remaining_time": "0:59:42"}
+{"current_steps": 191, "total_steps": 312, "loss": 0.5701, "lr": 3.9421575416136866e-06, "epoch": 1.830670926517572, "percentage": 61.22, "elapsed_time": "1:33:31", "remaining_time": "0:59:14"}
+{"current_steps": 192, "total_steps": 312, "loss": 0.5578, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:34:00", "remaining_time": "0:58:45"}
+{"current_steps": 193, "total_steps": 312, "loss": 0.5652, "lr": 3.832773180720475e-06, "epoch": 1.8498402555910545, "percentage": 61.86, "elapsed_time": "1:34:32", "remaining_time": "0:58:17"}
+{"current_steps": 194, "total_steps": 312, "loss": 0.5649, "lr": 3.778297969310529e-06, "epoch": 1.8594249201277955, "percentage": 62.18, "elapsed_time": "1:35:02", "remaining_time": "0:57:48"}
+{"current_steps": 195, "total_steps": 312, "loss": 0.5648, "lr": 3.723976553681787e-06, "epoch": 1.8690095846645367, "percentage": 62.5, "elapsed_time": "1:35:32", "remaining_time": "0:57:19"}
+{"current_steps": 196, "total_steps": 312, "loss": 0.5738, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:35:58", "remaining_time": "0:56:48"}
+{"current_steps": 197, "total_steps": 312, "loss": 0.5735, "lr": 3.6158224428757538e-06, "epoch": 1.8881789137380192, "percentage": 63.14, "elapsed_time": "1:36:22", "remaining_time": "0:56:15"}
+{"current_steps": 198, "total_steps": 312, "loss": 0.5731, "lr": 3.562003362839914e-06, "epoch": 1.8977635782747604, "percentage": 63.46, "elapsed_time": "1:36:48", "remaining_time": "0:55:44"}
+{"current_steps": 199, "total_steps": 312, "loss": 0.5617, "lr": 3.50836530715422e-06, "epoch": 1.9073482428115016, "percentage": 63.78, "elapsed_time": "1:37:15", "remaining_time": "0:55:13"}
+{"current_steps": 200, "total_steps": 312, "loss": 0.5692, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:37:45", "remaining_time": "0:54:44"}
+{"current_steps": 201, "total_steps": 312, "loss": 0.5784, "lr": 3.4016592544210937e-06, "epoch": 1.926517571884984, "percentage": 64.42, "elapsed_time": "1:38:13", "remaining_time": "0:54:14"}
+{"current_steps": 202, "total_steps": 312, "loss": 0.5664, "lr": 3.3486046902241663e-06, "epoch": 1.9361022364217253, "percentage": 64.74, "elapsed_time": "1:38:40", "remaining_time": "0:53:44"}
+{"current_steps": 203, "total_steps": 312, "loss": 0.5673, "lr": 3.295758014387375e-06, "epoch": 1.9456869009584663, "percentage": 65.06, "elapsed_time": "1:39:03", "remaining_time": "0:53:11"}
+{"current_steps": 204, "total_steps": 312, "loss": 0.5604, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:39:34", "remaining_time": "0:52:42"}
+{"current_steps": 205, "total_steps": 312, "loss": 0.5622, "lr": 3.1907149115166403e-06, "epoch": 1.9648562300319488, "percentage": 65.71, "elapsed_time": "1:40:04", "remaining_time": "0:52:13"}
+{"current_steps": 206, "total_steps": 312, "loss": 0.5767, "lr": 3.1385317079902743e-06, "epoch": 1.9744408945686902, "percentage": 66.03, "elapsed_time": "1:40:32", "remaining_time": "0:51:43"}
+{"current_steps": 207, "total_steps": 312, "loss": 0.5667, "lr": 3.0865828381745515e-06, "epoch": 1.9840255591054312, "percentage": 66.35, "elapsed_time": "1:41:00", "remaining_time": "0:51:13"}
+{"current_steps": 208, "total_steps": 312, "loss": 0.5576, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:41:30", "remaining_time": "0:50:45"}
+{"current_steps": 209, "total_steps": 312, "loss": 0.5433, "lr": 2.9834142279959754e-06, "epoch": 2.0031948881789137, "percentage": 66.99, "elapsed_time": "1:42:29", "remaining_time": "0:50:30"}
+{"current_steps": 210, "total_steps": 312, "loss": 0.5361, "lr": 2.932207475167398e-06, "epoch": 2.012779552715655, "percentage": 67.31, "elapsed_time": "1:42:53", "remaining_time": "0:49:58"}
+{"current_steps": 211, "total_steps": 312, "loss": 0.5192, "lr": 2.8812610294830568e-06, "epoch": 2.022364217252396, "percentage": 67.63, "elapsed_time": "1:43:17", "remaining_time": "0:49:26"}
+{"current_steps": 212, "total_steps": 312, "loss": 0.5419, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:43:46", "remaining_time": "0:48:57"}
+{"current_steps": 213, "total_steps": 312, "loss": 0.5036, "lr": 2.7801746798475905e-06, "epoch": 2.0415335463258786, "percentage": 68.27, "elapsed_time": "1:44:13", "remaining_time": "0:48:26"}
+{"current_steps": 214, "total_steps": 312, "loss": 0.5332, "lr": 2.7300475013022666e-06, "epoch": 2.0511182108626196, "percentage": 68.59, "elapsed_time": "1:44:44", "remaining_time": "0:47:58"}
+{"current_steps": 215, "total_steps": 312, "loss": 0.5387, "lr": 2.6802060791108304e-06, "epoch": 2.060702875399361, "percentage": 68.91, "elapsed_time": "1:45:11", "remaining_time": "0:47:27"}
+{"current_steps": 216, "total_steps": 312, "loss": 0.5017, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "1:45:37", "remaining_time": "0:46:56"}
+{"current_steps": 217, "total_steps": 312, "loss": 0.5279, "lr": 2.5814055644738013e-06, "epoch": 2.0798722044728435, "percentage": 69.55, "elapsed_time": "1:46:07", "remaining_time": "0:46:27"}
+{"current_steps": 218, "total_steps": 312, "loss": 0.5164, "lr": 2.532458909678266e-06, "epoch": 2.0894568690095845, "percentage": 69.87, "elapsed_time": "1:46:37", "remaining_time": "0:45:58"}
+{"current_steps": 219, "total_steps": 312, "loss": 0.5454, "lr": 2.483822884971e-06, "epoch": 2.099041533546326, "percentage": 70.19, "elapsed_time": "1:47:07", "remaining_time": "0:45:29"}
+{"current_steps": 220, "total_steps": 312, "loss": 0.5244, "lr": 2.43550361297047e-06, "epoch": 2.108626198083067, "percentage": 70.51, "elapsed_time": "1:47:41", "remaining_time": "0:45:02"}
+{"current_steps": 221, "total_steps": 312, "loss": 0.5386, "lr": 2.387507176420256e-06, "epoch": 2.1182108626198084, "percentage": 70.83, "elapsed_time": "1:48:07", "remaining_time": "0:44:31"}
+{"current_steps": 222, "total_steps": 312, "loss": 0.5231, "lr": 2.339839617423318e-06, "epoch": 2.1277955271565494, "percentage": 71.15, "elapsed_time": "1:48:36", "remaining_time": "0:44:01"}
+{"current_steps": 223, "total_steps": 312, "loss": 0.5303, "lr": 2.2925069366813718e-06, "epoch": 2.137380191693291, "percentage": 71.47, "elapsed_time": "1:49:04", "remaining_time": "0:43:32"}
+{"current_steps": 224, "total_steps": 312, "loss": 0.5139, "lr": 2.245515092739488e-06, "epoch": 2.146964856230032, "percentage": 71.79, "elapsed_time": "1:49:32", "remaining_time": "0:43:02"}
+{"current_steps": 225, "total_steps": 312, "loss": 0.5277, "lr": 2.1988700012359865e-06, "epoch": 2.1565495207667733, "percentage": 72.12, "elapsed_time": "1:50:04", "remaining_time": "0:42:33"}
+{"current_steps": 226, "total_steps": 312, "loss": 0.53, "lr": 2.1525775341577404e-06, "epoch": 2.1661341853035143, "percentage": 72.44, "elapsed_time": "1:50:32", "remaining_time": "0:42:04"}
+{"current_steps": 227, "total_steps": 312, "loss": 0.5287, "lr": 2.1066435191009717e-06, "epoch": 2.1757188498402558, "percentage": 72.76, "elapsed_time": "1:51:02", "remaining_time": "0:41:34"}
+{"current_steps": 228, "total_steps": 312, "loss": 0.5112, "lr": 2.061073738537635e-06, "epoch": 2.1853035143769968, "percentage": 73.08, "elapsed_time": "1:51:34", "remaining_time": "0:41:06"}
+{"current_steps": 229, "total_steps": 312, "loss": 0.5221, "lr": 2.0158739290874822e-06, "epoch": 2.194888178913738, "percentage": 73.4, "elapsed_time": "1:52:06", "remaining_time": "0:40:38"}
+{"current_steps": 230, "total_steps": 312, "loss": 0.5184, "lr": 1.971049780795901e-06, "epoch": 2.2044728434504792, "percentage": 73.72, "elapsed_time": "1:52:38", "remaining_time": "0:40:09"}
+{"current_steps": 231, "total_steps": 312, "loss": 0.533, "lr": 1.9266069364176144e-06, "epoch": 2.2140575079872207, "percentage": 74.04, "elapsed_time": "1:53:13", "remaining_time": "0:39:42"}
+{"current_steps": 232, "total_steps": 312, "loss": 0.5029, "lr": 1.8825509907063328e-06, "epoch": 2.2236421725239617, "percentage": 74.36, "elapsed_time": "1:53:44", "remaining_time": "0:39:13"}
+{"current_steps": 233, "total_steps": 312, "loss": 0.525, "lr": 1.838887489710452e-06, "epoch": 2.2332268370607027, "percentage": 74.68, "elapsed_time": "1:54:15", "remaining_time": "0:38:44"}
+{"current_steps": 234, "total_steps": 312, "loss": 0.5082, "lr": 1.7956219300748796e-06, "epoch": 2.242811501597444, "percentage": 75.0, "elapsed_time": "1:54:42", "remaining_time": "0:38:14"}
+{"current_steps": 235, "total_steps": 312, "loss": 0.5324, "lr": 1.7527597583490825e-06, "epoch": 2.252396166134185, "percentage": 75.32, "elapsed_time": "1:55:07", "remaining_time": "0:37:43"}
+{"current_steps": 236, "total_steps": 312, "loss": 0.534, "lr": 1.7103063703014372e-06, "epoch": 2.2619808306709266, "percentage": 75.64, "elapsed_time": "1:55:35", "remaining_time": "0:37:13"}
+{"current_steps": 237, "total_steps": 312, "loss": 0.5375, "lr": 1.6682671102399806e-06, "epoch": 2.2715654952076676, "percentage": 75.96, "elapsed_time": "1:56:07", "remaining_time": "0:36:44"}
+{"current_steps": 238, "total_steps": 312, "loss": 0.539, "lr": 1.6266472703396286e-06, "epoch": 2.281150159744409, "percentage": 76.28, "elapsed_time": "1:56:32", "remaining_time": "0:36:14"}
+{"current_steps": 239, "total_steps": 312, "loss": 0.5456, "lr": 1.5854520899759656e-06, "epoch": 2.29073482428115, "percentage": 76.6, "elapsed_time": "1:57:04", "remaining_time": "0:35:45"}
+{"current_steps": 240, "total_steps": 312, "loss": 0.5117, "lr": 1.544686755065677e-06, "epoch": 2.3003194888178915, "percentage": 76.92, "elapsed_time": "1:57:32", "remaining_time": "0:35:15"}
+{"current_steps": 241, "total_steps": 312, "loss": 0.5448, "lr": 1.5043563974137132e-06, "epoch": 2.3099041533546325, "percentage": 77.24, "elapsed_time": "1:58:04", "remaining_time": "0:34:47"}
+{"current_steps": 242, "total_steps": 312, "loss": 0.5259, "lr": 1.4644660940672628e-06, "epoch": 2.319488817891374, "percentage": 77.56, "elapsed_time": "1:58:33", "remaining_time": "0:34:17"}
+{"current_steps": 243, "total_steps": 312, "loss": 0.5177, "lr": 1.4250208666766235e-06, "epoch": 2.329073482428115, "percentage": 77.88, "elapsed_time": "1:59:05", "remaining_time": "0:33:49"}
+{"current_steps": 244, "total_steps": 312, "loss": 0.5201, "lr": 1.3860256808630429e-06, "epoch": 2.3386581469648564, "percentage": 78.21, "elapsed_time": "1:59:36", "remaining_time": "0:33:20"}
+{"current_steps": 245, "total_steps": 312, "loss": 0.5359, "lr": 1.3474854455936126e-06, "epoch": 2.3482428115015974, "percentage": 78.53, "elapsed_time": "2:00:07", "remaining_time": "0:32:51"}
+{"current_steps": 246, "total_steps": 312, "loss": 0.5185, "lr": 1.3094050125632973e-06, "epoch": 2.357827476038339, "percentage": 78.85, "elapsed_time": "2:00:31", "remaining_time": "0:32:20"}
+{"current_steps": 247, "total_steps": 312, "loss": 0.5141, "lr": 1.2717891755841722e-06, "epoch": 2.36741214057508, "percentage": 79.17, "elapsed_time": "2:01:00", "remaining_time": "0:31:50"}
+{"current_steps": 248, "total_steps": 312, "loss": 0.5053, "lr": 1.234642669981946e-06, "epoch": 2.376996805111821, "percentage": 79.49, "elapsed_time": "2:01:28", "remaining_time": "0:31:20"}
+{"current_steps": 249, "total_steps": 312, "loss": 0.5369, "lr": 1.1979701719998454e-06, "epoch": 2.3865814696485623, "percentage": 79.81, "elapsed_time": "2:02:01", "remaining_time": "0:30:52"}
+{"current_steps": 250, "total_steps": 312, "loss": 0.5194, "lr": 1.1617762982099446e-06, "epoch": 2.3961661341853033, "percentage": 80.13, "elapsed_time": "2:02:29", "remaining_time": "0:30:22"}
+{"current_steps": 251, "total_steps": 312, "loss": 0.5162, "lr": 1.1260656049319957e-06, "epoch": 2.405750798722045, "percentage": 80.45, "elapsed_time": "2:02:57", "remaining_time": "0:29:52"}
+{"current_steps": 252, "total_steps": 312, "loss": 0.5252, "lr": 1.0908425876598512e-06, "epoch": 2.415335463258786, "percentage": 80.77, "elapsed_time": "2:03:25", "remaining_time": "0:29:23"}
+{"current_steps": 253, "total_steps": 312, "loss": 0.5318, "lr": 1.0561116804955451e-06, "epoch": 2.4249201277955272, "percentage": 81.09, "elapsed_time": "2:03:54", "remaining_time": "0:28:53"}
+{"current_steps": 254, "total_steps": 312, "loss": 0.5145, "lr": 1.0218772555910955e-06, "epoch": 2.4345047923322682, "percentage": 81.41, "elapsed_time": "2:04:23", "remaining_time": "0:28:24"}
+{"current_steps": 255, "total_steps": 312, "loss": 0.5252, "lr": 9.881436225981107e-07, "epoch": 2.4440894568690097, "percentage": 81.73, "elapsed_time": "2:04:55", "remaining_time": "0:27:55"}
+{"current_steps": 256, "total_steps": 312, "loss": 0.5261, "lr": 9.549150281252633e-07, "epoch": 2.4536741214057507, "percentage": 82.05, "elapsed_time": "2:05:27", "remaining_time": "0:27:26"}
+{"current_steps": 257, "total_steps": 312, "loss": 0.5209, "lr": 9.221956552036992e-07, "epoch": 2.463258785942492, "percentage": 82.37, "elapsed_time": "2:05:57", "remaining_time": "0:26:57"}
+{"current_steps": 258, "total_steps": 312, "loss": 0.516, "lr": 8.899896227604509e-07, "epoch": 2.472843450479233, "percentage": 82.69, "elapsed_time": "2:06:28", "remaining_time": "0:26:28"}
+{"current_steps": 259, "total_steps": 312, "loss": 0.5253, "lr": 8.58300985099918e-07, "epoch": 2.4824281150159746, "percentage": 83.01, "elapsed_time": "2:06:53", "remaining_time": "0:25:58"}
+{"current_steps": 260, "total_steps": 312, "loss": 0.5119, "lr": 8.271337313934869e-07, "epoch": 2.4920127795527156, "percentage": 83.33, "elapsed_time": "2:07:24", "remaining_time": "0:25:28"}
+{"current_steps": 261, "total_steps": 312, "loss": 0.526, "lr": 7.964917851773496e-07, "epoch": 2.501597444089457, "percentage": 83.65, "elapsed_time": "2:07:54", "remaining_time": "0:24:59"}
+{"current_steps": 262, "total_steps": 312, "loss": 0.512, "lr": 7.663790038585794e-07, "epoch": 2.511182108626198, "percentage": 83.97, "elapsed_time": "2:08:25", "remaining_time": "0:24:30"}
+{"current_steps": 263, "total_steps": 312, "loss": 0.5292, "lr": 7.367991782295392e-07, "epoch": 2.520766773162939, "percentage": 84.29, "elapsed_time": "2:08:52", "remaining_time": "0:24:00"}
+{"current_steps": 264, "total_steps": 312, "loss": 0.5347, "lr": 7.077560319906696e-07, "epoch": 2.5303514376996805, "percentage": 84.62, "elapsed_time": "2:09:22", "remaining_time": "0:23:31"}
+{"current_steps": 265, "total_steps": 312, "loss": 0.5176, "lr": 6.792532212817271e-07, "epoch": 2.539936102236422, "percentage": 84.94, "elapsed_time": "2:09:48", "remaining_time": "0:23:01"}
+{"current_steps": 266, "total_steps": 312, "loss": 0.5404, "lr": 6.512943342215234e-07, "epoch": 2.549520766773163, "percentage": 85.26, "elapsed_time": "2:10:20", "remaining_time": "0:22:32"}
+{"current_steps": 267, "total_steps": 312, "loss": 0.5133, "lr": 6.238828904562316e-07, "epoch": 2.559105431309904, "percentage": 85.58, "elapsed_time": "2:10:54", "remaining_time": "0:22:03"}
+{"current_steps": 268, "total_steps": 312, "loss": 0.5377, "lr": 5.9702234071631e-07, "epoch": 2.5686900958466454, "percentage": 85.9, "elapsed_time": "2:11:21", "remaining_time": "0:21:34"}
+{"current_steps": 269, "total_steps": 312, "loss": 0.5087, "lr": 5.707160663821009e-07, "epoch": 2.5782747603833864, "percentage": 86.22, "elapsed_time": "2:11:43", "remaining_time": "0:21:03"}
+{"current_steps": 270, "total_steps": 312, "loss": 0.5164, "lr": 5.449673790581611e-07, "epoch": 2.587859424920128, "percentage": 86.54, "elapsed_time": "2:12:17", "remaining_time": "0:20:34"}
+{"current_steps": 271, "total_steps": 312, "loss": 0.5303, "lr": 5.197795201563744e-07, "epoch": 2.597444089456869, "percentage": 86.86, "elapsed_time": "2:12:44", "remaining_time": "0:20:04"}
+{"current_steps": 272, "total_steps": 312, "loss": 0.5029, "lr": 4.951556604879049e-07, "epoch": 2.6070287539936103, "percentage": 87.18, "elapsed_time": "2:13:14", "remaining_time": "0:19:35"}
+{"current_steps": 273, "total_steps": 312, "loss": 0.5261, "lr": 4.710988998640298e-07, "epoch": 2.6166134185303513, "percentage": 87.5, "elapsed_time": "2:13:45", "remaining_time": "0:19:06"}
+{"current_steps": 274, "total_steps": 312, "loss": 0.525, "lr": 4.4761226670592074e-07, "epoch": 2.626198083067093, "percentage": 87.82, "elapsed_time": "2:14:08", "remaining_time": "0:18:36"}
+{"current_steps": 275, "total_steps": 312, "loss": 0.5155, "lr": 4.2469871766340096e-07, "epoch": 2.635782747603834, "percentage": 88.14, "elapsed_time": "2:14:37", "remaining_time": "0:18:06"}
+{"current_steps": 276, "total_steps": 312, "loss": 0.5245, "lr": 4.0236113724274716e-07, "epoch": 2.6453674121405752, "percentage": 88.46, "elapsed_time": "2:15:07", "remaining_time": "0:17:37"}
+{"current_steps": 277, "total_steps": 312, "loss": 0.5092, "lr": 3.8060233744356634e-07, "epoch": 2.6549520766773163, "percentage": 88.78, "elapsed_time": "2:15:35", "remaining_time": "0:17:07"}
+{"current_steps": 278, "total_steps": 312, "loss": 0.5106, "lr": 3.5942505740480583e-07, "epoch": 2.6645367412140573, "percentage": 89.1, "elapsed_time": "2:16:01", "remaining_time": "0:16:38"}
+{"current_steps": 279, "total_steps": 312, "loss": 0.5048, "lr": 3.3883196305992906e-07, "epoch": 2.6741214057507987, "percentage": 89.42, "elapsed_time": "2:16:30", "remaining_time": "0:16:08"}
+{"current_steps": 280, "total_steps": 312, "loss": 0.5451, "lr": 3.18825646801314e-07, "epoch": 2.68370607028754, "percentage": 89.74, "elapsed_time": "2:17:01", "remaining_time": "0:15:39"}
+{"current_steps": 281, "total_steps": 312, "loss": 0.5415, "lr": 2.9940862715390483e-07, "epoch": 2.693290734824281, "percentage": 90.06, "elapsed_time": "2:17:34", "remaining_time": "0:15:10"}
+{"current_steps": 282, "total_steps": 312, "loss": 0.53, "lr": 2.8058334845816214e-07, "epoch": 2.702875399361022, "percentage": 90.38, "elapsed_time": "2:17:59", "remaining_time": "0:14:40"}
+{"current_steps": 283, "total_steps": 312, "loss": 0.5235, "lr": 2.6235218056235633e-07, "epoch": 2.7124600638977636, "percentage": 90.71, "elapsed_time": "2:18:29", "remaining_time": "0:14:11"}
+{"current_steps": 284, "total_steps": 312, "loss": 0.5296, "lr": 2.447174185242324e-07, "epoch": 2.722044728434505, "percentage": 91.03, "elapsed_time": "2:18:56", "remaining_time": "0:13:41"}
+{"current_steps": 285, "total_steps": 312, "loss": 0.5248, "lr": 2.276812823220964e-07, "epoch": 2.731629392971246, "percentage": 91.35, "elapsed_time": "2:19:23", "remaining_time": "0:13:12"}
+{"current_steps": 286, "total_steps": 312, "loss": 0.5079, "lr": 2.1124591657534776e-07, "epoch": 2.741214057507987, "percentage": 91.67, "elapsed_time": "2:19:49", "remaining_time": "0:12:42"}
+{"current_steps": 287, "total_steps": 312, "loss": 0.5086, "lr": 1.9541339027450256e-07, "epoch": 2.7507987220447285, "percentage": 91.99, "elapsed_time": "2:20:17", "remaining_time": "0:12:13"}
+{"current_steps": 288, "total_steps": 312, "loss": 0.527, "lr": 1.801856965207338e-07, "epoch": 2.7603833865814695, "percentage": 92.31, "elapsed_time": "2:20:52", "remaining_time": "0:11:44"}
+{"current_steps": 289, "total_steps": 312, "loss": 0.5202, "lr": 1.6556475227496816e-07, "epoch": 2.769968051118211, "percentage": 92.63, "elapsed_time": "2:21:22", "remaining_time": "0:11:15"}
+{"current_steps": 290, "total_steps": 312, "loss": 0.5402, "lr": 1.5155239811656562e-07, "epoch": 2.779552715654952, "percentage": 92.95, "elapsed_time": "2:21:48", "remaining_time": "0:10:45"}
+{"current_steps": 291, "total_steps": 312, "loss": 0.5311, "lr": 1.3815039801161723e-07, "epoch": 2.7891373801916934, "percentage": 93.27, "elapsed_time": "2:22:13", "remaining_time": "0:10:15"}
+{"current_steps": 292, "total_steps": 312, "loss": 0.5438, "lr": 1.253604390908819e-07, "epoch": 2.7987220447284344, "percentage": 93.59, "elapsed_time": "2:22:42", "remaining_time": "0:09:46"}
+{"current_steps": 293, "total_steps": 312, "loss": 0.5327, "lr": 1.1318413143740436e-07, "epoch": 2.8083067092651754, "percentage": 93.91, "elapsed_time": "2:23:10", "remaining_time": "0:09:17"}
+{"current_steps": 294, "total_steps": 312, "loss": 0.5078, "lr": 1.0162300788382263e-07, "epoch": 2.817891373801917, "percentage": 94.23, "elapsed_time": "2:23:33", "remaining_time": "0:08:47"}
+{"current_steps": 295, "total_steps": 312, "loss": 0.5227, "lr": 9.0678523819408e-08, "epoch": 2.8274760383386583, "percentage": 94.55, "elapsed_time": "2:23:59", "remaining_time": "0:08:17"}
+{"current_steps": 296, "total_steps": 312, "loss": 0.5124, "lr": 8.035205700685167e-08, "epoch": 2.8370607028753994, "percentage": 94.87, "elapsed_time": "2:24:25", "remaining_time": "0:07:48"}
+{"current_steps": 297, "total_steps": 312, "loss": 0.5514, "lr": 7.064490740882057e-08, "epoch": 2.8466453674121404, "percentage": 95.19, "elapsed_time": "2:24:50", "remaining_time": "0:07:18"}
+{"current_steps": 298, "total_steps": 312, "loss": 0.5235, "lr": 6.15582970243117e-08, "epoch": 2.856230031948882, "percentage": 95.51, "elapsed_time": "2:25:13", "remaining_time": "0:06:49"}
+{"current_steps": 299, "total_steps": 312, "loss": 0.5121, "lr": 5.3093369734816824e-08, "epoch": 2.8658146964856233, "percentage": 95.83, "elapsed_time": "2:25:43", "remaining_time": "0:06:20"}
+{"current_steps": 300, "total_steps": 312, "loss": 0.5276, "lr": 4.52511911603265e-08, "epoch": 2.8753993610223643, "percentage": 96.15, "elapsed_time": "2:26:14", "remaining_time": "0:05:50"}
+{"current_steps": 301, "total_steps": 312, "loss": 0.5266, "lr": 3.8032748525179684e-08, "epoch": 2.8849840255591053, "percentage": 96.47, "elapsed_time": "2:26:46", "remaining_time": "0:05:21"}
+{"current_steps": 302, "total_steps": 312, "loss": 0.5162, "lr": 3.143895053378698e-08, "epoch": 2.8945686900958467, "percentage": 96.79, "elapsed_time": "2:27:17", "remaining_time": "0:04:52"}
+{"current_steps": 303, "total_steps": 312, "loss": 0.5252, "lr": 2.547062725623828e-08, "epoch": 2.9041533546325877, "percentage": 97.12, "elapsed_time": "2:27:48", "remaining_time": "0:04:23"}
+{"current_steps": 304, "total_steps": 312, "loss": 0.5069, "lr": 2.012853002380466e-08, "epoch": 2.913738019169329, "percentage": 97.44, "elapsed_time": "2:28:21", "remaining_time": "0:03:54"}
+{"current_steps": 305, "total_steps": 312, "loss": 0.5177, "lr": 1.541333133436018e-08, "epoch": 2.92332268370607, "percentage": 97.76, "elapsed_time": "2:28:51", "remaining_time": "0:03:24"}
+{"current_steps": 306, "total_steps": 312, "loss": 0.5119, "lr": 1.132562476771959e-08, "epoch": 2.9329073482428116, "percentage": 98.08, "elapsed_time": "2:29:15", "remaining_time": "0:02:55"}
+{"current_steps": 307, "total_steps": 312, "loss": 0.5153, "lr": 7.865924910916977e-09, "epoch": 2.9424920127795526, "percentage": 98.4, "elapsed_time": "2:29:45", "remaining_time": "0:02:26"}
+{"current_steps": 308, "total_steps": 312, "loss": 0.5322, "lr": 5.034667293427053e-09, "epoch": 2.952076677316294, "percentage": 98.72, "elapsed_time": "2:30:18", "remaining_time": "0:01:57"}
+{"current_steps": 309, "total_steps": 312, "loss": 0.5244, "lr": 2.8322083323334417e-09, "epoch": 2.961661341853035, "percentage": 99.04, "elapsed_time": "2:30:49", "remaining_time": "0:01:27"}
+{"current_steps": 310, "total_steps": 312, "loss": 0.508, "lr": 1.2588252874673469e-09, "epoch": 2.9712460063897765, "percentage": 99.36, "elapsed_time": "2:31:18", "remaining_time": "0:00:58"}
+{"current_steps": 311, "total_steps": 312, "loss": 0.5463, "lr": 3.147162264971471e-10, "epoch": 2.9808306709265175, "percentage": 99.68, "elapsed_time": "2:31:50", "remaining_time": "0:00:29"}
+{"current_steps": 312, "total_steps": 312, "loss": 0.5152, "lr": 0.0, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:32:14", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:33:12", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2226 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9904153354632586,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009584664536741214,
+      "grad_norm": 8.150485038757324,
+      "learning_rate": 3.125e-07,
+      "loss": 1.1263,
+      "step": 1
+    },
+    {
+      "epoch": 0.019169329073482427,
+      "grad_norm": 7.807866096496582,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0931,
+      "step": 2
+    },
+    {
+      "epoch": 0.02875399361022364,
+      "grad_norm": 8.187647819519043,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.1248,
+      "step": 3
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 7.566376209259033,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0913,
+      "step": 4
+    },
+    {
+      "epoch": 0.04792332268370607,
+      "grad_norm": 7.314204216003418,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.0767,
+      "step": 5
+    },
+    {
+      "epoch": 0.05750798722044728,
+      "grad_norm": 7.0795745849609375,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.0705,
+      "step": 6
+    },
+    {
+      "epoch": 0.0670926517571885,
+      "grad_norm": 5.6739606857299805,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 1.0487,
+      "step": 7
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 5.160563945770264,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0214,
+      "step": 8
+    },
+    {
+      "epoch": 0.08626198083067092,
+      "grad_norm": 3.2819786071777344,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.9842,
+      "step": 9
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 3.097018003463745,
+      "learning_rate": 3.125e-06,
+      "loss": 0.9671,
+      "step": 10
+    },
+    {
+      "epoch": 0.10543130990415335,
+      "grad_norm": 2.9452693462371826,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.9597,
+      "step": 11
+    },
+    {
+      "epoch": 0.11501597444089456,
+      "grad_norm": 3.434796094894409,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.9319,
+      "step": 12
+    },
+    {
+      "epoch": 0.12460063897763578,
+      "grad_norm": 4.0431108474731445,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.9196,
+      "step": 13
+    },
+    {
+      "epoch": 0.134185303514377,
+      "grad_norm": 3.556278705596924,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.9054,
+      "step": 14
+    },
+    {
+      "epoch": 0.14376996805111822,
+      "grad_norm": 3.114114761352539,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.8922,
+      "step": 15
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 2.207472801208496,
+      "learning_rate": 5e-06,
+      "loss": 0.8626,
+      "step": 16
+    },
+    {
+      "epoch": 0.16293929712460065,
+      "grad_norm": 2.376880645751953,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.8325,
+      "step": 17
+    },
+    {
+      "epoch": 0.17252396166134185,
+      "grad_norm": 2.03688907623291,
+      "learning_rate": 5.625e-06,
+      "loss": 0.8278,
+      "step": 18
+    },
+    {
+      "epoch": 0.18210862619808307,
+      "grad_norm": 1.3376281261444092,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.801,
+      "step": 19
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 1.331655502319336,
+      "learning_rate": 6.25e-06,
+      "loss": 0.7924,
+      "step": 20
+    },
+    {
+      "epoch": 0.2012779552715655,
+      "grad_norm": 1.3158297538757324,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.7778,
+      "step": 21
+    },
+    {
+      "epoch": 0.2108626198083067,
+      "grad_norm": 1.407170295715332,
+      "learning_rate": 6.875e-06,
+      "loss": 0.7677,
+      "step": 22
+    },
+    {
+      "epoch": 0.22044728434504793,
+      "grad_norm": 1.3406498432159424,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.765,
+      "step": 23
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 1.0355418920516968,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7434,
+      "step": 24
+    },
+    {
+      "epoch": 0.23961661341853036,
+      "grad_norm": 1.086203932762146,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.7524,
+      "step": 25
+    },
+    {
+      "epoch": 0.24920127795527156,
+      "grad_norm": 1.0376132726669312,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.7231,
+      "step": 26
+    },
+    {
+      "epoch": 0.25878594249201275,
+      "grad_norm": 1.0266880989074707,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.7251,
+      "step": 27
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.8888912796974182,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.722,
+      "step": 28
+    },
+    {
+      "epoch": 0.2779552715654952,
+      "grad_norm": 0.8433630466461182,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.7107,
+      "step": 29
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.0001300573349,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.6975,
+      "step": 30
+    },
+    {
+      "epoch": 0.2971246006389776,
+      "grad_norm": 1.0221211910247803,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.7019,
+      "step": 31
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.7957472801208496,
+      "learning_rate": 1e-05,
+      "loss": 0.7015,
+      "step": 32
+    },
+    {
+      "epoch": 0.31629392971246006,
+      "grad_norm": 0.8188865184783936,
+      "learning_rate": 9.999685283773504e-06,
+      "loss": 0.7084,
+      "step": 33
+    },
+    {
+      "epoch": 0.3258785942492013,
+      "grad_norm": 0.7626446485519409,
+      "learning_rate": 9.998741174712534e-06,
+      "loss": 0.7011,
+      "step": 34
+    },
+    {
+      "epoch": 0.3354632587859425,
+      "grad_norm": 0.8135344386100769,
+      "learning_rate": 9.997167791667668e-06,
+      "loss": 0.696,
+      "step": 35
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 0.7661399841308594,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.6928,
+      "step": 36
+    },
+    {
+      "epoch": 0.3546325878594249,
+      "grad_norm": 0.8579995632171631,
+      "learning_rate": 9.992134075089085e-06,
+      "loss": 0.699,
+      "step": 37
+    },
+    {
+      "epoch": 0.36421725239616615,
+      "grad_norm": 0.7115493416786194,
+      "learning_rate": 9.98867437523228e-06,
+      "loss": 0.6843,
+      "step": 38
+    },
+    {
+      "epoch": 0.3738019169329074,
+      "grad_norm": 0.7873193025588989,
+      "learning_rate": 9.984586668665641e-06,
+      "loss": 0.6867,
+      "step": 39
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.7836501002311707,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.6628,
+      "step": 40
+    },
+    {
+      "epoch": 0.3929712460063898,
+      "grad_norm": 0.6418578028678894,
+      "learning_rate": 9.974529372743762e-06,
+      "loss": 0.6578,
+      "step": 41
+    },
+    {
+      "epoch": 0.402555910543131,
+      "grad_norm": 0.7128148078918457,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.6671,
+      "step": 42
+    },
+    {
+      "epoch": 0.41214057507987223,
+      "grad_norm": 0.6487117409706116,
+      "learning_rate": 9.961967251474823e-06,
+      "loss": 0.6648,
+      "step": 43
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 0.6714372634887695,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.6499,
+      "step": 44
+    },
+    {
+      "epoch": 0.43130990415335463,
+      "grad_norm": 0.7654340267181396,
+      "learning_rate": 9.946906630265184e-06,
+      "loss": 0.6605,
+      "step": 45
+    },
+    {
+      "epoch": 0.44089456869009586,
+      "grad_norm": 0.7319685816764832,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.6774,
+      "step": 46
+    },
+    {
+      "epoch": 0.4504792332268371,
+      "grad_norm": 0.7591245174407959,
+      "learning_rate": 9.92935509259118e-06,
+      "loss": 0.6646,
+      "step": 47
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.7330446839332581,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.6593,
+      "step": 48
+    },
+    {
+      "epoch": 0.4696485623003195,
+      "grad_norm": 0.7684568166732788,
+      "learning_rate": 9.909321476180594e-06,
+      "loss": 0.6569,
+      "step": 49
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.8853203654289246,
+      "learning_rate": 9.898376992116179e-06,
+      "loss": 0.6644,
+      "step": 50
+    },
+    {
+      "epoch": 0.48881789137380194,
+      "grad_norm": 0.6971675157546997,
+      "learning_rate": 9.886815868562596e-06,
+      "loss": 0.6522,
+      "step": 51
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 0.7527298331260681,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.6584,
+      "step": 52
+    },
+    {
+      "epoch": 0.5079872204472844,
+      "grad_norm": 0.9225770831108093,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 0.6504,
+      "step": 53
+    },
+    {
+      "epoch": 0.5175718849840255,
+      "grad_norm": 0.860784113407135,
+      "learning_rate": 9.848447601883436e-06,
+      "loss": 0.6642,
+      "step": 54
+    },
+    {
+      "epoch": 0.5271565495207667,
+      "grad_norm": 0.7279204726219177,
+      "learning_rate": 9.834435247725032e-06,
+      "loss": 0.6349,
+      "step": 55
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 0.8378774523735046,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.625,
+      "step": 56
+    },
+    {
+      "epoch": 0.5463258785942492,
+      "grad_norm": 0.6531175971031189,
+      "learning_rate": 9.804586609725499e-06,
+      "loss": 0.6583,
+      "step": 57
+    },
+    {
+      "epoch": 0.5559105431309904,
+      "grad_norm": 0.7052546739578247,
+      "learning_rate": 9.788754083424654e-06,
+      "loss": 0.6352,
+      "step": 58
+    },
+    {
+      "epoch": 0.5654952076677316,
+      "grad_norm": 0.7330588698387146,
+      "learning_rate": 9.772318717677905e-06,
+      "loss": 0.6464,
+      "step": 59
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.6029200553894043,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.6242,
+      "step": 60
+    },
+    {
+      "epoch": 0.5846645367412141,
+      "grad_norm": 0.6845069527626038,
+      "learning_rate": 9.737647819437645e-06,
+      "loss": 0.6585,
+      "step": 61
+    },
+    {
+      "epoch": 0.5942492012779552,
+      "grad_norm": 0.7698150873184204,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.6463,
+      "step": 62
+    },
+    {
+      "epoch": 0.6038338658146964,
+      "grad_norm": 0.6855467557907104,
+      "learning_rate": 9.700591372846096e-06,
+      "loss": 0.6503,
+      "step": 63
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.669455885887146,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.6306,
+      "step": 64
+    },
+    {
+      "epoch": 0.6230031948881789,
+      "grad_norm": 0.7016051411628723,
+      "learning_rate": 9.661168036940071e-06,
+      "loss": 0.6462,
+      "step": 65
+    },
+    {
+      "epoch": 0.6325878594249201,
+      "grad_norm": 0.6591147184371948,
+      "learning_rate": 9.640574942595195e-06,
+      "loss": 0.6363,
+      "step": 66
+    },
+    {
+      "epoch": 0.6421725239616614,
+      "grad_norm": 0.6269323825836182,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.6312,
+      "step": 67
+    },
+    {
+      "epoch": 0.6517571884984026,
+      "grad_norm": 0.6276299953460693,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.6485,
+      "step": 68
+    },
+    {
+      "epoch": 0.6613418530351438,
+      "grad_norm": 0.6555031538009644,
+      "learning_rate": 9.5753012823366e-06,
+      "loss": 0.6271,
+      "step": 69
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 0.617702841758728,
+      "learning_rate": 9.552387733294081e-06,
+      "loss": 0.6405,
+      "step": 70
+    },
+    {
+      "epoch": 0.6805111821086262,
+      "grad_norm": 0.5773834586143494,
+      "learning_rate": 9.528901100135971e-06,
+      "loss": 0.6462,
+      "step": 71
+    },
+    {
+      "epoch": 0.6900958466453674,
+      "grad_norm": 0.5768316388130188,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.6494,
+      "step": 72
+    },
+    {
+      "epoch": 0.6996805111821086,
+      "grad_norm": 0.6002576947212219,
+      "learning_rate": 9.480220479843627e-06,
+      "loss": 0.643,
+      "step": 73
+    },
+    {
+      "epoch": 0.7092651757188498,
+      "grad_norm": 0.6929178833961487,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.6449,
+      "step": 74
+    },
+    {
+      "epoch": 0.7188498402555911,
+      "grad_norm": 0.633795440196991,
+      "learning_rate": 9.4292839336179e-06,
+      "loss": 0.6438,
+      "step": 75
+    },
+    {
+      "epoch": 0.7284345047923323,
+      "grad_norm": 0.6836037635803223,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.6277,
+      "step": 76
+    },
+    {
+      "epoch": 0.7380191693290735,
+      "grad_norm": 0.5767949223518372,
+      "learning_rate": 9.376117109543769e-06,
+      "loss": 0.6346,
+      "step": 77
+    },
+    {
+      "epoch": 0.7476038338658147,
+      "grad_norm": 0.6540945172309875,
+      "learning_rate": 9.348705665778479e-06,
+      "loss": 0.6398,
+      "step": 78
+    },
+    {
+      "epoch": 0.7571884984025559,
+      "grad_norm": 0.6413583159446716,
+      "learning_rate": 9.320746778718274e-06,
+      "loss": 0.6214,
+      "step": 79
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.6472015380859375,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.6359,
+      "step": 80
+    },
+    {
+      "epoch": 0.7763578274760383,
+      "grad_norm": 0.5751689672470093,
+      "learning_rate": 9.263200821770462e-06,
+      "loss": 0.6387,
+      "step": 81
+    },
+    {
+      "epoch": 0.7859424920127795,
+      "grad_norm": 0.8359308242797852,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.6336,
+      "step": 82
+    },
+    {
+      "epoch": 0.7955271565495208,
+      "grad_norm": 0.7323636412620544,
+      "learning_rate": 9.203508214822652e-06,
+      "loss": 0.6361,
+      "step": 83
+    },
+    {
+      "epoch": 0.805111821086262,
+      "grad_norm": 0.6433335542678833,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.6283,
+      "step": 84
+    },
+    {
+      "epoch": 0.8146964856230032,
+      "grad_norm": 0.7690201997756958,
+      "learning_rate": 9.141699014900084e-06,
+      "loss": 0.6334,
+      "step": 85
+    },
+    {
+      "epoch": 0.8242811501597445,
+      "grad_norm": 0.7022820115089417,
+      "learning_rate": 9.110010377239552e-06,
+      "loss": 0.6166,
+      "step": 86
+    },
+    {
+      "epoch": 0.8338658146964856,
+      "grad_norm": 0.7924836277961731,
+      "learning_rate": 9.077804344796302e-06,
+      "loss": 0.6454,
+      "step": 87
+    },
+    {
+      "epoch": 0.8434504792332268,
+      "grad_norm": 0.7118843197822571,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.6384,
+      "step": 88
+    },
+    {
+      "epoch": 0.853035143769968,
+      "grad_norm": 0.717670202255249,
+      "learning_rate": 9.011856377401891e-06,
+      "loss": 0.6347,
+      "step": 89
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 0.7034146189689636,
+      "learning_rate": 8.978122744408905e-06,
+      "loss": 0.6206,
+      "step": 90
+    },
+    {
+      "epoch": 0.8722044728434505,
+      "grad_norm": 0.674736499786377,
+      "learning_rate": 8.943888319504456e-06,
+      "loss": 0.6217,
+      "step": 91
+    },
+    {
+      "epoch": 0.8817891373801917,
+      "grad_norm": 0.6070693731307983,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.6326,
+      "step": 92
+    },
+    {
+      "epoch": 0.8913738019169329,
+      "grad_norm": 0.6934514045715332,
+      "learning_rate": 8.873934395068006e-06,
+      "loss": 0.6109,
+      "step": 93
+    },
+    {
+      "epoch": 0.9009584664536742,
+      "grad_norm": 0.6248501539230347,
+      "learning_rate": 8.838223701790057e-06,
+      "loss": 0.6316,
+      "step": 94
+    },
+    {
+      "epoch": 0.9105431309904153,
+      "grad_norm": 0.5615552663803101,
+      "learning_rate": 8.802029828000157e-06,
+      "loss": 0.6261,
+      "step": 95
+    },
+    {
+      "epoch": 0.9201277955271565,
+      "grad_norm": 0.598068118095398,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.6406,
+      "step": 96
+    },
+    {
+      "epoch": 0.9297124600638977,
+      "grad_norm": 0.8680521249771118,
+      "learning_rate": 8.728210824415829e-06,
+      "loss": 0.6357,
+      "step": 97
+    },
+    {
+      "epoch": 0.939297124600639,
+      "grad_norm": 0.5738173127174377,
+      "learning_rate": 8.690594987436705e-06,
+      "loss": 0.6032,
+      "step": 98
+    },
+    {
+      "epoch": 0.9488817891373802,
+      "grad_norm": 0.73792564868927,
+      "learning_rate": 8.652514554406388e-06,
+      "loss": 0.5996,
+      "step": 99
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 0.7462478876113892,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.6229,
+      "step": 100
+    },
+    {
+      "epoch": 0.9680511182108626,
+      "grad_norm": 0.6320640444755554,
+      "learning_rate": 8.574979133323378e-06,
+      "loss": 0.6317,
+      "step": 101
+    },
+    {
+      "epoch": 0.9776357827476039,
+      "grad_norm": 0.7389762997627258,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.631,
+      "step": 102
+    },
+    {
+      "epoch": 0.987220447284345,
+      "grad_norm": 0.6447233557701111,
+      "learning_rate": 8.495643602586287e-06,
+      "loss": 0.6205,
+      "step": 103
+    },
+    {
+      "epoch": 0.9968051118210862,
+      "grad_norm": 0.6227617859840393,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.614,
+      "step": 104
+    },
+    {
+      "epoch": 1.0063897763578276,
+      "grad_norm": 0.7328119277954102,
+      "learning_rate": 8.414547910024035e-06,
+      "loss": 0.5928,
+      "step": 105
+    },
+    {
+      "epoch": 1.0159744408945688,
+      "grad_norm": 0.6177286505699158,
+      "learning_rate": 8.373352729660373e-06,
+      "loss": 0.587,
+      "step": 106
+    },
+    {
+      "epoch": 1.0255591054313098,
+      "grad_norm": 0.6559479236602783,
+      "learning_rate": 8.331732889760021e-06,
+      "loss": 0.5827,
+      "step": 107
+    },
+    {
+      "epoch": 1.035143769968051,
+      "grad_norm": 0.718102753162384,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.5899,
+      "step": 108
+    },
+    {
+      "epoch": 1.0447284345047922,
+      "grad_norm": 0.6655651926994324,
+      "learning_rate": 8.247240241650918e-06,
+      "loss": 0.588,
+      "step": 109
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.7050108909606934,
+      "learning_rate": 8.204378069925121e-06,
+      "loss": 0.5913,
+      "step": 110
+    },
+    {
+      "epoch": 1.0638977635782747,
+      "grad_norm": 0.715863049030304,
+      "learning_rate": 8.16111251028955e-06,
+      "loss": 0.5808,
+      "step": 111
+    },
+    {
+      "epoch": 1.073482428115016,
+      "grad_norm": 0.6538060903549194,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5791,
+      "step": 112
+    },
+    {
+      "epoch": 1.0830670926517572,
+      "grad_norm": 0.6200713515281677,
+      "learning_rate": 8.073393063582386e-06,
+      "loss": 0.5707,
+      "step": 113
+    },
+    {
+      "epoch": 1.0926517571884984,
+      "grad_norm": 0.6361571550369263,
+      "learning_rate": 8.0289502192041e-06,
+      "loss": 0.5739,
+      "step": 114
+    },
+    {
+      "epoch": 1.1022364217252396,
+      "grad_norm": 0.6072981953620911,
+      "learning_rate": 7.984126070912519e-06,
+      "loss": 0.5665,
+      "step": 115
+    },
+    {
+      "epoch": 1.1118210862619808,
+      "grad_norm": 0.5768544673919678,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.5648,
+      "step": 116
+    },
+    {
+      "epoch": 1.121405750798722,
+      "grad_norm": 0.6660125255584717,
+      "learning_rate": 7.89335648089903e-06,
+      "loss": 0.5893,
+      "step": 117
+    },
+    {
+      "epoch": 1.1309904153354633,
+      "grad_norm": 0.6252293586730957,
+      "learning_rate": 7.84742246584226e-06,
+      "loss": 0.5847,
+      "step": 118
+    },
+    {
+      "epoch": 1.1405750798722045,
+      "grad_norm": 0.5960403680801392,
+      "learning_rate": 7.801129998764014e-06,
+      "loss": 0.5734,
+      "step": 119
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.7005594372749329,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.5751,
+      "step": 120
+    },
+    {
+      "epoch": 1.159744408945687,
+      "grad_norm": 0.6234583258628845,
+      "learning_rate": 7.70749306331863e-06,
+      "loss": 0.5652,
+      "step": 121
+    },
+    {
+      "epoch": 1.1693290734824282,
+      "grad_norm": 0.5803803205490112,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.5717,
+      "step": 122
+    },
+    {
+      "epoch": 1.1789137380191694,
+      "grad_norm": 0.6783732175827026,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.5789,
+      "step": 123
+    },
+    {
+      "epoch": 1.1884984025559104,
+      "grad_norm": 0.5564832091331482,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.5678,
+      "step": 124
+    },
+    {
+      "epoch": 1.1980830670926517,
+      "grad_norm": 0.675945520401001,
+      "learning_rate": 7.516177115029002e-06,
+      "loss": 0.5741,
+      "step": 125
+    },
+    {
+      "epoch": 1.207667731629393,
+      "grad_norm": 0.6526042819023132,
+      "learning_rate": 7.467541090321735e-06,
+      "loss": 0.5587,
+      "step": 126
+    },
+    {
+      "epoch": 1.2172523961661341,
+      "grad_norm": 0.6318403482437134,
+      "learning_rate": 7.4185944355261996e-06,
+      "loss": 0.5796,
+      "step": 127
+    },
+    {
+      "epoch": 1.2268370607028753,
+      "grad_norm": 0.6410267949104309,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.5808,
+      "step": 128
+    },
+    {
+      "epoch": 1.2364217252396166,
+      "grad_norm": 0.6449666023254395,
+      "learning_rate": 7.319793920889171e-06,
+      "loss": 0.5783,
+      "step": 129
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.6435701847076416,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.5577,
+      "step": 130
+    },
+    {
+      "epoch": 1.255591054313099,
+      "grad_norm": 0.7610958814620972,
+      "learning_rate": 7.219825320152411e-06,
+      "loss": 0.5508,
+      "step": 131
+    },
+    {
+      "epoch": 1.2651757188498403,
+      "grad_norm": 0.5984666347503662,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.5682,
+      "step": 132
+    },
+    {
+      "epoch": 1.2747603833865815,
+      "grad_norm": 0.6728739738464355,
+      "learning_rate": 7.118738970516944e-06,
+      "loss": 0.5719,
+      "step": 133
+    },
+    {
+      "epoch": 1.2843450479233227,
+      "grad_norm": 0.544328510761261,
+      "learning_rate": 7.067792524832604e-06,
+      "loss": 0.566,
+      "step": 134
+    },
+    {
+      "epoch": 1.293929712460064,
+      "grad_norm": 0.6412566900253296,
+      "learning_rate": 7.016585772004026e-06,
+      "loss": 0.5792,
+      "step": 135
+    },
+    {
+      "epoch": 1.3035143769968052,
+      "grad_norm": 0.6340923309326172,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.579,
+      "step": 136
+    },
+    {
+      "epoch": 1.3130990415335464,
+      "grad_norm": 0.634636640548706,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.5663,
+      "step": 137
+    },
+    {
+      "epoch": 1.3226837060702876,
+      "grad_norm": 0.6472147703170776,
+      "learning_rate": 6.8614682920097265e-06,
+      "loss": 0.581,
+      "step": 138
+    },
+    {
+      "epoch": 1.3322683706070286,
+      "grad_norm": 0.5313640832901001,
+      "learning_rate": 6.809285088483361e-06,
+      "loss": 0.5713,
+      "step": 139
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.6307949423789978,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.5703,
+      "step": 140
+    },
+    {
+      "epoch": 1.351437699680511,
+      "grad_norm": 0.5627026557922363,
+      "learning_rate": 6.704241985612625e-06,
+      "loss": 0.5561,
+      "step": 141
+    },
+    {
+      "epoch": 1.3610223642172525,
+      "grad_norm": 0.6823342442512512,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.5614,
+      "step": 142
+    },
+    {
+      "epoch": 1.3706070287539935,
+      "grad_norm": 0.5905282497406006,
+      "learning_rate": 6.598340745578908e-06,
+      "loss": 0.5766,
+      "step": 143
+    },
+    {
+      "epoch": 1.3801916932907348,
+      "grad_norm": 0.7758175134658813,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5611,
+      "step": 144
+    },
+    {
+      "epoch": 1.389776357827476,
+      "grad_norm": 0.518359363079071,
+      "learning_rate": 6.491634692845781e-06,
+      "loss": 0.5691,
+      "step": 145
+    },
+    {
+      "epoch": 1.3993610223642172,
+      "grad_norm": 0.7256923317909241,
+      "learning_rate": 6.437996637160086e-06,
+      "loss": 0.5694,
+      "step": 146
+    },
+    {
+      "epoch": 1.4089456869009584,
+      "grad_norm": 0.6003644466400146,
+      "learning_rate": 6.384177557124247e-06,
+      "loss": 0.5592,
+      "step": 147
+    },
+    {
+      "epoch": 1.4185303514376997,
+      "grad_norm": 0.6105974912643433,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.5804,
+      "step": 148
+    },
+    {
+      "epoch": 1.428115015974441,
+      "grad_norm": 0.6344504356384277,
+      "learning_rate": 6.276023446318214e-06,
+      "loss": 0.5581,
+      "step": 149
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 0.6138957142829895,
+      "learning_rate": 6.2217020306894705e-06,
+      "loss": 0.5688,
+      "step": 150
+    },
+    {
+      "epoch": 1.4472843450479234,
+      "grad_norm": 0.547579824924469,
+      "learning_rate": 6.1672268192795285e-06,
+      "loss": 0.5635,
+      "step": 151
+    },
+    {
+      "epoch": 1.4568690095846646,
+      "grad_norm": 0.5572775602340698,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.577,
+      "step": 152
+    },
+    {
+      "epoch": 1.4664536741214058,
+      "grad_norm": 0.5766530632972717,
+      "learning_rate": 6.057842458386315e-06,
+      "loss": 0.5775,
+      "step": 153
+    },
+    {
+      "epoch": 1.476038338658147,
+      "grad_norm": 0.5293987989425659,
+      "learning_rate": 6.002947078916365e-06,
+      "loss": 0.5714,
+      "step": 154
+    },
+    {
+      "epoch": 1.4856230031948883,
+      "grad_norm": 0.5267698764801025,
+      "learning_rate": 5.947925441958393e-06,
+      "loss": 0.5621,
+      "step": 155
+    },
+    {
+      "epoch": 1.4952076677316293,
+      "grad_norm": 0.5576557517051697,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.566,
+      "step": 156
+    },
+    {
+      "epoch": 1.5047923322683707,
+      "grad_norm": 0.5801796317100525,
+      "learning_rate": 5.837531116523683e-06,
+      "loss": 0.5796,
+      "step": 157
+    },
+    {
+      "epoch": 1.5143769968051117,
+      "grad_norm": 0.546893298625946,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.5699,
+      "step": 158
+    },
+    {
+      "epoch": 1.5239616613418532,
+      "grad_norm": 0.5638102293014526,
+      "learning_rate": 5.726715068949564e-06,
+      "loss": 0.5639,
+      "step": 159
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 0.6294999718666077,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.5747,
+      "step": 160
+    },
+    {
+      "epoch": 1.5431309904153354,
+      "grad_norm": 0.5858036875724792,
+      "learning_rate": 5.615533098453215e-06,
+      "loss": 0.5574,
+      "step": 161
+    },
+    {
+      "epoch": 1.5527156549520766,
+      "grad_norm": 0.6968753933906555,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.5602,
+      "step": 162
+    },
+    {
+      "epoch": 1.5623003194888179,
+      "grad_norm": 0.5758054852485657,
+      "learning_rate": 5.504041188505022e-06,
+      "loss": 0.5751,
+      "step": 163
+    },
+    {
+      "epoch": 1.571884984025559,
+      "grad_norm": 0.5420729517936707,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.5731,
+      "step": 164
+    },
+    {
+      "epoch": 1.5814696485623003,
+      "grad_norm": 0.6788923144340515,
+      "learning_rate": 5.392295478639226e-06,
+      "loss": 0.5751,
+      "step": 165
+    },
+    {
+      "epoch": 1.5910543130990416,
+      "grad_norm": 0.6043679714202881,
+      "learning_rate": 5.336345028060199e-06,
+      "loss": 0.5701,
+      "step": 166
+    },
+    {
+      "epoch": 1.6006389776357828,
+      "grad_norm": 0.528847873210907,
+      "learning_rate": 5.2803522361859596e-06,
+      "loss": 0.5745,
+      "step": 167
+    },
+    {
+      "epoch": 1.610223642172524,
+      "grad_norm": 0.5885607600212097,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 1.619808306709265,
+      "grad_norm": 0.5792953372001648,
+      "learning_rate": 5.168267827938971e-06,
+      "loss": 0.5571,
+      "step": 169
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.5489832162857056,
+      "learning_rate": 5.112190321479026e-06,
+      "loss": 0.5696,
+      "step": 170
+    },
+    {
+      "epoch": 1.6389776357827475,
+      "grad_norm": 0.6276931166648865,
+      "learning_rate": 5.05609869177323e-06,
+      "loss": 0.6019,
+      "step": 171
+    },
+    {
+      "epoch": 1.648562300319489,
+      "grad_norm": 0.5779969692230225,
+      "learning_rate": 5e-06,
+      "loss": 0.5767,
+      "step": 172
+    },
+    {
+      "epoch": 1.65814696485623,
+      "grad_norm": 0.5757343173027039,
+      "learning_rate": 4.943901308226771e-06,
+      "loss": 0.5611,
+      "step": 173
+    },
+    {
+      "epoch": 1.6677316293929714,
+      "grad_norm": 0.585114598274231,
+      "learning_rate": 4.887809678520976e-06,
+      "loss": 0.5498,
+      "step": 174
+    },
+    {
+      "epoch": 1.6773162939297124,
+      "grad_norm": 0.5320142507553101,
+      "learning_rate": 4.831732172061032e-06,
+      "loss": 0.5793,
+      "step": 175
+    },
+    {
+      "epoch": 1.6869009584664538,
+      "grad_norm": 0.6053058505058289,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.5616,
+      "step": 176
+    },
+    {
+      "epoch": 1.6964856230031948,
+      "grad_norm": 0.663553774356842,
+      "learning_rate": 4.719647763814041e-06,
+      "loss": 0.5763,
+      "step": 177
+    },
+    {
+      "epoch": 1.706070287539936,
+      "grad_norm": 0.5003867149353027,
+      "learning_rate": 4.663654971939802e-06,
+      "loss": 0.579,
+      "step": 178
+    },
+    {
+      "epoch": 1.7156549520766773,
+      "grad_norm": 0.6177144646644592,
+      "learning_rate": 4.6077045213607765e-06,
+      "loss": 0.5611,
+      "step": 179
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 0.5344464182853699,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.5778,
+      "step": 180
+    },
+    {
+      "epoch": 1.7348242811501597,
+      "grad_norm": 0.5539312362670898,
+      "learning_rate": 4.4959588114949785e-06,
+      "loss": 0.5686,
+      "step": 181
+    },
+    {
+      "epoch": 1.744408945686901,
+      "grad_norm": 0.5916006565093994,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.5692,
+      "step": 182
+    },
+    {
+      "epoch": 1.7539936102236422,
+      "grad_norm": 0.6805198192596436,
+      "learning_rate": 4.384466901546786e-06,
+      "loss": 0.5762,
+      "step": 183
+    },
+    {
+      "epoch": 1.7635782747603834,
+      "grad_norm": 0.5966302156448364,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.5489,
+      "step": 184
+    },
+    {
+      "epoch": 1.7731629392971247,
+      "grad_norm": 0.6216447949409485,
+      "learning_rate": 4.273284931050438e-06,
+      "loss": 0.5634,
+      "step": 185
+    },
+    {
+      "epoch": 1.7827476038338657,
+      "grad_norm": 0.7536059617996216,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.566,
+      "step": 186
+    },
+    {
+      "epoch": 1.792332268370607,
+      "grad_norm": 0.5549724698066711,
+      "learning_rate": 4.162468883476319e-06,
+      "loss": 0.5837,
+      "step": 187
+    },
+    {
+      "epoch": 1.8019169329073481,
+      "grad_norm": 0.599871814250946,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.5646,
+      "step": 188
+    },
+    {
+      "epoch": 1.8115015974440896,
+      "grad_norm": 0.6804283261299133,
+      "learning_rate": 4.052074558041608e-06,
+      "loss": 0.5644,
+      "step": 189
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 0.5554932951927185,
+      "learning_rate": 3.997052921083637e-06,
+      "loss": 0.5576,
+      "step": 190
+    },
+    {
+      "epoch": 1.830670926517572,
+      "grad_norm": 0.5054816007614136,
+      "learning_rate": 3.9421575416136866e-06,
+      "loss": 0.5701,
+      "step": 191
+    },
+    {
+      "epoch": 1.840255591054313,
+      "grad_norm": 0.5952098965644836,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.5578,
+      "step": 192
+    },
+    {
+      "epoch": 1.8498402555910545,
+      "grad_norm": 0.5662181377410889,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.5652,
+      "step": 193
+    },
+    {
+      "epoch": 1.8594249201277955,
+      "grad_norm": 0.5168705582618713,
+      "learning_rate": 3.778297969310529e-06,
+      "loss": 0.5649,
+      "step": 194
+    },
+    {
+      "epoch": 1.8690095846645367,
+      "grad_norm": 0.5198647975921631,
+      "learning_rate": 3.723976553681787e-06,
+      "loss": 0.5648,
+      "step": 195
+    },
+    {
+      "epoch": 1.878594249201278,
+      "grad_norm": 0.5528584122657776,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.5738,
+      "step": 196
+    },
+    {
+      "epoch": 1.8881789137380192,
+      "grad_norm": 0.6017258167266846,
+      "learning_rate": 3.6158224428757538e-06,
+      "loss": 0.5735,
+      "step": 197
+    },
+    {
+      "epoch": 1.8977635782747604,
+      "grad_norm": 0.5080370306968689,
+      "learning_rate": 3.562003362839914e-06,
+      "loss": 0.5731,
+      "step": 198
+    },
+    {
+      "epoch": 1.9073482428115016,
+      "grad_norm": 0.5272023677825928,
+      "learning_rate": 3.50836530715422e-06,
+      "loss": 0.5617,
+      "step": 199
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.5592118501663208,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.5692,
+      "step": 200
+    },
+    {
+      "epoch": 1.926517571884984,
+      "grad_norm": 0.4761984646320343,
+      "learning_rate": 3.4016592544210937e-06,
+      "loss": 0.5784,
+      "step": 201
+    },
+    {
+      "epoch": 1.9361022364217253,
+      "grad_norm": 0.4980798661708832,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.5664,
+      "step": 202
+    },
+    {
+      "epoch": 1.9456869009584663,
+      "grad_norm": 0.49683818221092224,
+      "learning_rate": 3.295758014387375e-06,
+      "loss": 0.5673,
+      "step": 203
+    },
+    {
+      "epoch": 1.9552715654952078,
+      "grad_norm": 0.49688446521759033,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.5604,
+      "step": 204
+    },
+    {
+      "epoch": 1.9648562300319488,
+      "grad_norm": 0.5208616256713867,
+      "learning_rate": 3.1907149115166403e-06,
+      "loss": 0.5622,
+      "step": 205
+    },
+    {
+      "epoch": 1.9744408945686902,
+      "grad_norm": 0.5107452869415283,
+      "learning_rate": 3.1385317079902743e-06,
+      "loss": 0.5767,
+      "step": 206
+    },
+    {
+      "epoch": 1.9840255591054312,
+      "grad_norm": 0.5208856463432312,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.5667,
+      "step": 207
+    },
+    {
+      "epoch": 1.9936102236421727,
+      "grad_norm": 0.48777708411216736,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.5576,
+      "step": 208
+    },
+    {
+      "epoch": 2.0031948881789137,
+      "grad_norm": 0.5471110939979553,
+      "learning_rate": 2.9834142279959754e-06,
+      "loss": 0.5433,
+      "step": 209
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.5684826374053955,
+      "learning_rate": 2.932207475167398e-06,
+      "loss": 0.5361,
+      "step": 210
+    },
+    {
+      "epoch": 2.022364217252396,
+      "grad_norm": 0.5112109184265137,
+      "learning_rate": 2.8812610294830568e-06,
+      "loss": 0.5192,
+      "step": 211
+    },
+    {
+      "epoch": 2.0319488817891376,
+      "grad_norm": 0.494600385427475,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.5419,
+      "step": 212
+    },
+    {
+      "epoch": 2.0415335463258786,
+      "grad_norm": 0.4980970323085785,
+      "learning_rate": 2.7801746798475905e-06,
+      "loss": 0.5036,
+      "step": 213
+    },
+    {
+      "epoch": 2.0511182108626196,
+      "grad_norm": 0.5328761339187622,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.5332,
+      "step": 214
+    },
+    {
+      "epoch": 2.060702875399361,
+      "grad_norm": 0.5595293045043945,
+      "learning_rate": 2.6802060791108304e-06,
+      "loss": 0.5387,
+      "step": 215
+    },
+    {
+      "epoch": 2.070287539936102,
+      "grad_norm": 0.4666793644428253,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.5017,
+      "step": 216
+    },
+    {
+      "epoch": 2.0798722044728435,
+      "grad_norm": 0.4883419871330261,
+      "learning_rate": 2.5814055644738013e-06,
+      "loss": 0.5279,
+      "step": 217
+    },
+    {
+      "epoch": 2.0894568690095845,
+      "grad_norm": 0.5053743720054626,
+      "learning_rate": 2.532458909678266e-06,
+      "loss": 0.5164,
+      "step": 218
+    },
+    {
+      "epoch": 2.099041533546326,
+      "grad_norm": 0.4824915826320648,
+      "learning_rate": 2.483822884971e-06,
+      "loss": 0.5454,
+      "step": 219
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.5914897322654724,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.5244,
+      "step": 220
+    },
+    {
+      "epoch": 2.1182108626198084,
+      "grad_norm": 0.5082386136054993,
+      "learning_rate": 2.387507176420256e-06,
+      "loss": 0.5386,
+      "step": 221
+    },
+    {
+      "epoch": 2.1277955271565494,
+      "grad_norm": 0.4908734858036041,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.5231,
+      "step": 222
+    },
+    {
+      "epoch": 2.137380191693291,
+      "grad_norm": 0.5613354444503784,
+      "learning_rate": 2.2925069366813718e-06,
+      "loss": 0.5303,
+      "step": 223
+    },
+    {
+      "epoch": 2.146964856230032,
+      "grad_norm": 0.47516801953315735,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.5139,
+      "step": 224
+    },
+    {
+      "epoch": 2.1565495207667733,
+      "grad_norm": 0.4658454656600952,
+      "learning_rate": 2.1988700012359865e-06,
+      "loss": 0.5277,
+      "step": 225
+    },
+    {
+      "epoch": 2.1661341853035143,
+      "grad_norm": 0.4728820323944092,
+      "learning_rate": 2.1525775341577404e-06,
+      "loss": 0.53,
+      "step": 226
+    },
+    {
+      "epoch": 2.1757188498402558,
+      "grad_norm": 0.6010584235191345,
+      "learning_rate": 2.1066435191009717e-06,
+      "loss": 0.5287,
+      "step": 227
+    },
+    {
+      "epoch": 2.1853035143769968,
+      "grad_norm": 0.5559404492378235,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.5112,
+      "step": 228
+    },
+    {
+      "epoch": 2.194888178913738,
+      "grad_norm": 0.48023709654808044,
+      "learning_rate": 2.0158739290874822e-06,
+      "loss": 0.5221,
+      "step": 229
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 0.44798821210861206,
+      "learning_rate": 1.971049780795901e-06,
+      "loss": 0.5184,
+      "step": 230
+    },
+    {
+      "epoch": 2.2140575079872207,
+      "grad_norm": 0.4652976393699646,
+      "learning_rate": 1.9266069364176144e-06,
+      "loss": 0.533,
+      "step": 231
+    },
+    {
+      "epoch": 2.2236421725239617,
+      "grad_norm": 0.47819817066192627,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.5029,
+      "step": 232
+    },
+    {
+      "epoch": 2.2332268370607027,
+      "grad_norm": 0.4362553656101227,
+      "learning_rate": 1.838887489710452e-06,
+      "loss": 0.525,
+      "step": 233
+    },
+    {
+      "epoch": 2.242811501597444,
+      "grad_norm": 0.5460666418075562,
+      "learning_rate": 1.7956219300748796e-06,
+      "loss": 0.5082,
+      "step": 234
+    },
+    {
+      "epoch": 2.252396166134185,
+      "grad_norm": 0.516977846622467,
+      "learning_rate": 1.7527597583490825e-06,
+      "loss": 0.5324,
+      "step": 235
+    },
+    {
+      "epoch": 2.2619808306709266,
+      "grad_norm": 0.4478202760219574,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.534,
+      "step": 236
+    },
+    {
+      "epoch": 2.2715654952076676,
+      "grad_norm": 0.4357537031173706,
+      "learning_rate": 1.6682671102399806e-06,
+      "loss": 0.5375,
+      "step": 237
+    },
+    {
+      "epoch": 2.281150159744409,
+      "grad_norm": 0.4697173535823822,
+      "learning_rate": 1.6266472703396286e-06,
+      "loss": 0.539,
+      "step": 238
+    },
+    {
+      "epoch": 2.29073482428115,
+      "grad_norm": 0.4569830298423767,
+      "learning_rate": 1.5854520899759656e-06,
+      "loss": 0.5456,
+      "step": 239
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 0.4430941641330719,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.5117,
+      "step": 240
+    },
+    {
+      "epoch": 2.3099041533546325,
+      "grad_norm": 0.4393070340156555,
+      "learning_rate": 1.5043563974137132e-06,
+      "loss": 0.5448,
+      "step": 241
+    },
+    {
+      "epoch": 2.319488817891374,
+      "grad_norm": 0.43000754714012146,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5259,
+      "step": 242
+    },
+    {
+      "epoch": 2.329073482428115,
+      "grad_norm": 0.4374457001686096,
+      "learning_rate": 1.4250208666766235e-06,
+      "loss": 0.5177,
+      "step": 243
+    },
+    {
+      "epoch": 2.3386581469648564,
+      "grad_norm": 0.46506327390670776,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.5201,
+      "step": 244
+    },
+    {
+      "epoch": 2.3482428115015974,
+      "grad_norm": 0.4384128749370575,
+      "learning_rate": 1.3474854455936126e-06,
+      "loss": 0.5359,
+      "step": 245
+    },
+    {
+      "epoch": 2.357827476038339,
+      "grad_norm": 0.4446409344673157,
+      "learning_rate": 1.3094050125632973e-06,
+      "loss": 0.5185,
+      "step": 246
+    },
+    {
+      "epoch": 2.36741214057508,
+      "grad_norm": 0.4300197660923004,
+      "learning_rate": 1.2717891755841722e-06,
+      "loss": 0.5141,
+      "step": 247
+    },
+    {
+      "epoch": 2.376996805111821,
+      "grad_norm": 0.44469180703163147,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.5053,
+      "step": 248
+    },
+    {
+      "epoch": 2.3865814696485623,
+      "grad_norm": 0.4117085933685303,
+      "learning_rate": 1.1979701719998454e-06,
+      "loss": 0.5369,
+      "step": 249
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.431255042552948,
+      "learning_rate": 1.1617762982099446e-06,
+      "loss": 0.5194,
+      "step": 250
+    },
+    {
+      "epoch": 2.405750798722045,
+      "grad_norm": 0.4269045889377594,
+      "learning_rate": 1.1260656049319957e-06,
+      "loss": 0.5162,
+      "step": 251
+    },
+    {
+      "epoch": 2.415335463258786,
+      "grad_norm": 0.4201407730579376,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5252,
+      "step": 252
+    },
+    {
+      "epoch": 2.4249201277955272,
+      "grad_norm": 0.42810115218162537,
+      "learning_rate": 1.0561116804955451e-06,
+      "loss": 0.5318,
+      "step": 253
+    },
+    {
+      "epoch": 2.4345047923322682,
+      "grad_norm": 0.4129791855812073,
+      "learning_rate": 1.0218772555910955e-06,
+      "loss": 0.5145,
+      "step": 254
+    },
+    {
+      "epoch": 2.4440894568690097,
+      "grad_norm": 0.39486438035964966,
+      "learning_rate": 9.881436225981107e-07,
+      "loss": 0.5252,
+      "step": 255
+    },
+    {
+      "epoch": 2.4536741214057507,
+      "grad_norm": 0.4195745289325714,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5261,
+      "step": 256
+    },
+    {
+      "epoch": 2.463258785942492,
+      "grad_norm": 0.3990418314933777,
+      "learning_rate": 9.221956552036992e-07,
+      "loss": 0.5209,
+      "step": 257
+    },
+    {
+      "epoch": 2.472843450479233,
+      "grad_norm": 0.44864341616630554,
+      "learning_rate": 8.899896227604509e-07,
+      "loss": 0.516,
+      "step": 258
+    },
+    {
+      "epoch": 2.4824281150159746,
+      "grad_norm": 0.4024929404258728,
+      "learning_rate": 8.58300985099918e-07,
+      "loss": 0.5253,
+      "step": 259
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 0.4194217026233673,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.5119,
+      "step": 260
+    },
+    {
+      "epoch": 2.501597444089457,
+      "grad_norm": 0.4190581440925598,
+      "learning_rate": 7.964917851773496e-07,
+      "loss": 0.526,
+      "step": 261
+    },
+    {
+      "epoch": 2.511182108626198,
+      "grad_norm": 0.4602578580379486,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.512,
+      "step": 262
+    },
+    {
+      "epoch": 2.520766773162939,
+      "grad_norm": 0.38818320631980896,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.5292,
+      "step": 263
+    },
+    {
+      "epoch": 2.5303514376996805,
+      "grad_norm": 0.40392065048217773,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.5347,
+      "step": 264
+    },
+    {
+      "epoch": 2.539936102236422,
+      "grad_norm": 0.41519656777381897,
+      "learning_rate": 6.792532212817271e-07,
+      "loss": 0.5176,
+      "step": 265
+    },
+    {
+      "epoch": 2.549520766773163,
+      "grad_norm": 0.44370123744010925,
+      "learning_rate": 6.512943342215234e-07,
+      "loss": 0.5404,
+      "step": 266
+    },
+    {
+      "epoch": 2.559105431309904,
+      "grad_norm": 0.4083189070224762,
+      "learning_rate": 6.238828904562316e-07,
+      "loss": 0.5133,
+      "step": 267
+    },
+    {
+      "epoch": 2.5686900958466454,
+      "grad_norm": 0.4141216576099396,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.5377,
+      "step": 268
+    },
+    {
+      "epoch": 2.5782747603833864,
+      "grad_norm": 0.45661696791648865,
+      "learning_rate": 5.707160663821009e-07,
+      "loss": 0.5087,
+      "step": 269
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 0.426259845495224,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.5164,
+      "step": 270
+    },
+    {
+      "epoch": 2.597444089456869,
+      "grad_norm": 0.3987196385860443,
+      "learning_rate": 5.197795201563744e-07,
+      "loss": 0.5303,
+      "step": 271
+    },
+    {
+      "epoch": 2.6070287539936103,
+      "grad_norm": 0.43403735756874084,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.5029,
+      "step": 272
+    },
+    {
+      "epoch": 2.6166134185303513,
+      "grad_norm": 0.4055974781513214,
+      "learning_rate": 4.710988998640298e-07,
+      "loss": 0.5261,
+      "step": 273
+    },
+    {
+      "epoch": 2.626198083067093,
+      "grad_norm": 0.3974541425704956,
+      "learning_rate": 4.4761226670592074e-07,
+      "loss": 0.525,
+      "step": 274
+    },
+    {
+      "epoch": 2.635782747603834,
+      "grad_norm": 0.419546514749527,
+      "learning_rate": 4.2469871766340096e-07,
+      "loss": 0.5155,
+      "step": 275
+    },
+    {
+      "epoch": 2.6453674121405752,
+      "grad_norm": 0.43064308166503906,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.5245,
+      "step": 276
+    },
+    {
+      "epoch": 2.6549520766773163,
+      "grad_norm": 0.42868760228157043,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.5092,
+      "step": 277
+    },
+    {
+      "epoch": 2.6645367412140573,
+      "grad_norm": 0.4428861737251282,
+      "learning_rate": 3.5942505740480583e-07,
+      "loss": 0.5106,
+      "step": 278
+    },
+    {
+      "epoch": 2.6741214057507987,
+      "grad_norm": 0.42494478821754456,
+      "learning_rate": 3.3883196305992906e-07,
+      "loss": 0.5048,
+      "step": 279
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 0.4355878531932831,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.5451,
+      "step": 280
+    },
+    {
+      "epoch": 2.693290734824281,
+      "grad_norm": 0.42539212107658386,
+      "learning_rate": 2.9940862715390483e-07,
+      "loss": 0.5415,
+      "step": 281
+    },
+    {
+      "epoch": 2.702875399361022,
+      "grad_norm": 0.4196220636367798,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.53,
+      "step": 282
+    },
+    {
+      "epoch": 2.7124600638977636,
+      "grad_norm": 0.404574453830719,
+      "learning_rate": 2.6235218056235633e-07,
+      "loss": 0.5235,
+      "step": 283
+    },
+    {
+      "epoch": 2.722044728434505,
+      "grad_norm": 0.4026959538459778,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5296,
+      "step": 284
+    },
+    {
+      "epoch": 2.731629392971246,
+      "grad_norm": 0.39630454778671265,
+      "learning_rate": 2.276812823220964e-07,
+      "loss": 0.5248,
+      "step": 285
+    },
+    {
+      "epoch": 2.741214057507987,
+      "grad_norm": 0.4264671504497528,
+      "learning_rate": 2.1124591657534776e-07,
+      "loss": 0.5079,
+      "step": 286
+    },
+    {
+      "epoch": 2.7507987220447285,
+      "grad_norm": 0.4322397708892822,
+      "learning_rate": 1.9541339027450256e-07,
+      "loss": 0.5086,
+      "step": 287
+    },
+    {
+      "epoch": 2.7603833865814695,
+      "grad_norm": 0.44492900371551514,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.527,
+      "step": 288
+    },
+    {
+      "epoch": 2.769968051118211,
+      "grad_norm": 0.4282550811767578,
+      "learning_rate": 1.6556475227496816e-07,
+      "loss": 0.5202,
+      "step": 289
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 0.4308444857597351,
+      "learning_rate": 1.5155239811656562e-07,
+      "loss": 0.5402,
+      "step": 290
+    },
+    {
+      "epoch": 2.7891373801916934,
+      "grad_norm": 0.40583133697509766,
+      "learning_rate": 1.3815039801161723e-07,
+      "loss": 0.5311,
+      "step": 291
+    },
+    {
+      "epoch": 2.7987220447284344,
+      "grad_norm": 0.39951369166374207,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.5438,
+      "step": 292
+    },
+    {
+      "epoch": 2.8083067092651754,
+      "grad_norm": 0.3861788511276245,
+      "learning_rate": 1.1318413143740436e-07,
+      "loss": 0.5327,
+      "step": 293
+    },
+    {
+      "epoch": 2.817891373801917,
+      "grad_norm": 0.4173254668712616,
+      "learning_rate": 1.0162300788382263e-07,
+      "loss": 0.5078,
+      "step": 294
+    },
+    {
+      "epoch": 2.8274760383386583,
+      "grad_norm": 0.40433382987976074,
+      "learning_rate": 9.0678523819408e-08,
+      "loss": 0.5227,
+      "step": 295
+    },
+    {
+      "epoch": 2.8370607028753994,
+      "grad_norm": 0.410818874835968,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.5124,
+      "step": 296
+    },
+    {
+      "epoch": 2.8466453674121404,
+      "grad_norm": 0.38880231976509094,
+      "learning_rate": 7.064490740882057e-08,
+      "loss": 0.5514,
+      "step": 297
+    },
+    {
+      "epoch": 2.856230031948882,
+      "grad_norm": 0.4121662974357605,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.5235,
+      "step": 298
+    },
+    {
+      "epoch": 2.8658146964856233,
+      "grad_norm": 0.4136061668395996,
+      "learning_rate": 5.3093369734816824e-08,
+      "loss": 0.5121,
+      "step": 299
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 0.3969224989414215,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.5276,
+      "step": 300
+    },
+    {
+      "epoch": 2.8849840255591053,
+      "grad_norm": 0.3935069143772125,
+      "learning_rate": 3.8032748525179684e-08,
+      "loss": 0.5266,
+      "step": 301
+    },
+    {
+      "epoch": 2.8945686900958467,
+      "grad_norm": 0.4016058146953583,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.5162,
+      "step": 302
+    },
+    {
+      "epoch": 2.9041533546325877,
+      "grad_norm": 0.39917394518852234,
+      "learning_rate": 2.547062725623828e-08,
+      "loss": 0.5252,
+      "step": 303
+    },
+    {
+      "epoch": 2.913738019169329,
+      "grad_norm": 0.44093358516693115,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.5069,
+      "step": 304
+    },
+    {
+      "epoch": 2.92332268370607,
+      "grad_norm": 0.39468714594841003,
+      "learning_rate": 1.541333133436018e-08,
+      "loss": 0.5177,
+      "step": 305
+    },
+    {
+      "epoch": 2.9329073482428116,
+      "grad_norm": 0.41948553919792175,
+      "learning_rate": 1.132562476771959e-08,
+      "loss": 0.5119,
+      "step": 306
+    },
+    {
+      "epoch": 2.9424920127795526,
+      "grad_norm": 0.4047912359237671,
+      "learning_rate": 7.865924910916977e-09,
+      "loss": 0.5153,
+      "step": 307
+    },
+    {
+      "epoch": 2.952076677316294,
+      "grad_norm": 0.4035501182079315,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.5322,
+      "step": 308
+    },
+    {
+      "epoch": 2.961661341853035,
+      "grad_norm": 0.415784627199173,
+      "learning_rate": 2.8322083323334417e-09,
+      "loss": 0.5244,
+      "step": 309
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 0.40659230947494507,
+      "learning_rate": 1.2588252874673469e-09,
+      "loss": 0.508,
+      "step": 310
+    },
+    {
+      "epoch": 2.9808306709265175,
+      "grad_norm": 0.3864118754863739,
+      "learning_rate": 3.147162264971471e-10,
+      "loss": 0.5463,
+      "step": 311
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "grad_norm": 0.40317609906196594,
+      "learning_rate": 0.0,
+      "loss": 0.5152,
+      "step": 312
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "step": 312,
+      "total_flos": 3.9082027465048064e+17,
+      "train_loss": 0.0,
+      "train_runtime": 6.1081,
+      "train_samples_per_second": 4911.493,
+      "train_steps_per_second": 51.08
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.9082027465048064e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d958d249049f036bd52404b199e82bdfd1a57de9803938ae282191f59e66c614
+size 7672