Training in progress, epoch 0

.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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "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
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22d65d1adb17a80da7e7ba8f916d63c32d03b3a7d8d0c21b3f2dd4b0b07c9e7
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79068a2407f42a68ae5741ffb849a1e49946f9d71d16bc7359ffde1ca7738ec4
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae7782bfe0317daf8fae051fe2322e6b4688cf8ab62a8b89ab64094ce98bc37
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd928ea44b0e76803f18095ebde80fa2a79998a34277b6ebdd5d914c5507bba
+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
+}

trainer_log.jsonl

@@ -0,0 +1,154 @@
+{"current_steps": 1, "total_steps": 760, "loss": 1.0344, "lr": 1.0526315789473685e-06, "epoch": 0.006557377049180328, "percentage": 0.13, "elapsed_time": "0:01:48", "remaining_time": "22:56:13"}
+{"current_steps": 2, "total_steps": 760, "loss": 1.0244, "lr": 2.105263157894737e-06, "epoch": 0.013114754098360656, "percentage": 0.26, "elapsed_time": "0:03:27", "remaining_time": "21:53:43"}
+{"current_steps": 3, "total_steps": 760, "loss": 1.0332, "lr": 3.157894736842105e-06, "epoch": 0.019672131147540985, "percentage": 0.39, "elapsed_time": "0:05:08", "remaining_time": "21:38:35"}
+{"current_steps": 4, "total_steps": 760, "loss": 1.0018, "lr": 4.210526315789474e-06, "epoch": 0.02622950819672131, "percentage": 0.53, "elapsed_time": "0:06:48", "remaining_time": "21:26:38"}
+{"current_steps": 5, "total_steps": 760, "loss": 0.9788, "lr": 5.263157894736842e-06, "epoch": 0.03278688524590164, "percentage": 0.66, "elapsed_time": "0:08:28", "remaining_time": "21:19:00"}
+{"current_steps": 6, "total_steps": 760, "loss": 0.9217, "lr": 6.31578947368421e-06, "epoch": 0.03934426229508197, "percentage": 0.79, "elapsed_time": "0:10:07", "remaining_time": "21:13:03"}
+{"current_steps": 7, "total_steps": 760, "loss": 0.9045, "lr": 7.368421052631579e-06, "epoch": 0.04590163934426229, "percentage": 0.92, "elapsed_time": "0:11:47", "remaining_time": "21:08:07"}
+{"current_steps": 8, "total_steps": 760, "loss": 0.9149, "lr": 8.421052631578948e-06, "epoch": 0.05245901639344262, "percentage": 1.05, "elapsed_time": "0:13:27", "remaining_time": "21:05:20"}
+{"current_steps": 9, "total_steps": 760, "loss": 0.9088, "lr": 9.473684210526315e-06, "epoch": 0.05901639344262295, "percentage": 1.18, "elapsed_time": "0:15:07", "remaining_time": "21:02:31"}
+{"current_steps": 10, "total_steps": 760, "loss": 0.8551, "lr": 1.0526315789473684e-05, "epoch": 0.06557377049180328, "percentage": 1.32, "elapsed_time": "0:16:47", "remaining_time": "20:59:25"}
+{"current_steps": 11, "total_steps": 760, "loss": 0.842, "lr": 1.1578947368421053e-05, "epoch": 0.07213114754098361, "percentage": 1.45, "elapsed_time": "0:18:28", "remaining_time": "20:58:26"}
+{"current_steps": 12, "total_steps": 760, "loss": 0.8279, "lr": 1.263157894736842e-05, "epoch": 0.07868852459016394, "percentage": 1.58, "elapsed_time": "0:20:08", "remaining_time": "20:55:45"}
+{"current_steps": 13, "total_steps": 760, "loss": 0.7931, "lr": 1.3684210526315791e-05, "epoch": 0.08524590163934426, "percentage": 1.71, "elapsed_time": "0:21:48", "remaining_time": "20:52:44"}
+{"current_steps": 14, "total_steps": 760, "loss": 0.7755, "lr": 1.4736842105263159e-05, "epoch": 0.09180327868852459, "percentage": 1.84, "elapsed_time": "0:23:27", "remaining_time": "20:50:16"}
+{"current_steps": 15, "total_steps": 760, "loss": 0.7664, "lr": 1.578947368421053e-05, "epoch": 0.09836065573770492, "percentage": 1.97, "elapsed_time": "0:25:07", "remaining_time": "20:47:57"}
+{"current_steps": 16, "total_steps": 760, "loss": 0.763, "lr": 1.6842105263157896e-05, "epoch": 0.10491803278688525, "percentage": 2.11, "elapsed_time": "0:26:47", "remaining_time": "20:45:57"}
+{"current_steps": 17, "total_steps": 760, "loss": 0.7491, "lr": 1.7894736842105264e-05, "epoch": 0.11147540983606558, "percentage": 2.24, "elapsed_time": "0:28:27", "remaining_time": "20:44:01"}
+{"current_steps": 18, "total_steps": 760, "loss": 0.7325, "lr": 1.894736842105263e-05, "epoch": 0.1180327868852459, "percentage": 2.37, "elapsed_time": "0:30:07", "remaining_time": "20:41:51"}
+{"current_steps": 19, "total_steps": 760, "loss": 0.7315, "lr": 2e-05, "epoch": 0.12459016393442623, "percentage": 2.5, "elapsed_time": "0:31:48", "remaining_time": "20:40:34"}
+{"current_steps": 20, "total_steps": 760, "loss": 0.7183, "lr": 2.105263157894737e-05, "epoch": 0.13114754098360656, "percentage": 2.63, "elapsed_time": "0:33:28", "remaining_time": "20:38:24"}
+{"current_steps": 21, "total_steps": 760, "loss": 0.725, "lr": 2.210526315789474e-05, "epoch": 0.1377049180327869, "percentage": 2.76, "elapsed_time": "0:35:07", "remaining_time": "20:36:13"}
+{"current_steps": 22, "total_steps": 760, "loss": 0.7047, "lr": 2.3157894736842107e-05, "epoch": 0.14426229508196722, "percentage": 2.89, "elapsed_time": "0:36:47", "remaining_time": "20:34:06"}
+{"current_steps": 23, "total_steps": 760, "loss": 0.6984, "lr": 2.4210526315789474e-05, "epoch": 0.15081967213114755, "percentage": 3.03, "elapsed_time": "0:38:26", "remaining_time": "20:31:58"}
+{"current_steps": 24, "total_steps": 760, "loss": 0.7086, "lr": 2.526315789473684e-05, "epoch": 0.15737704918032788, "percentage": 3.16, "elapsed_time": "0:40:06", "remaining_time": "20:29:54"}
+{"current_steps": 25, "total_steps": 760, "loss": 0.6958, "lr": 2.6315789473684215e-05, "epoch": 0.16393442622950818, "percentage": 3.29, "elapsed_time": "0:41:46", "remaining_time": "20:28:03"}
+{"current_steps": 26, "total_steps": 760, "loss": 0.693, "lr": 2.7368421052631583e-05, "epoch": 0.17049180327868851, "percentage": 3.42, "elapsed_time": "0:43:25", "remaining_time": "20:26:03"}
+{"current_steps": 27, "total_steps": 760, "loss": 0.6839, "lr": 2.842105263157895e-05, "epoch": 0.17704918032786884, "percentage": 3.55, "elapsed_time": "0:45:05", "remaining_time": "20:24:14"}
+{"current_steps": 28, "total_steps": 760, "loss": 0.6843, "lr": 2.9473684210526317e-05, "epoch": 0.18360655737704917, "percentage": 3.68, "elapsed_time": "0:46:45", "remaining_time": "20:22:29"}
+{"current_steps": 29, "total_steps": 760, "loss": 0.6824, "lr": 3.052631578947369e-05, "epoch": 0.1901639344262295, "percentage": 3.82, "elapsed_time": "0:48:25", "remaining_time": "20:20:28"}
+{"current_steps": 30, "total_steps": 760, "loss": 0.6758, "lr": 3.157894736842106e-05, "epoch": 0.19672131147540983, "percentage": 3.95, "elapsed_time": "0:50:05", "remaining_time": "20:19:01"}
+{"current_steps": 31, "total_steps": 760, "loss": 0.6662, "lr": 3.2631578947368426e-05, "epoch": 0.20327868852459016, "percentage": 4.08, "elapsed_time": "0:51:45", "remaining_time": "20:17:02"}
+{"current_steps": 32, "total_steps": 760, "loss": 0.6613, "lr": 3.368421052631579e-05, "epoch": 0.2098360655737705, "percentage": 4.21, "elapsed_time": "0:53:24", "remaining_time": "20:15:06"}
+{"current_steps": 33, "total_steps": 760, "loss": 0.6593, "lr": 3.473684210526316e-05, "epoch": 0.21639344262295082, "percentage": 4.34, "elapsed_time": "0:55:05", "remaining_time": "20:13:31"}
+{"current_steps": 34, "total_steps": 760, "loss": 0.66, "lr": 3.578947368421053e-05, "epoch": 0.22295081967213115, "percentage": 4.47, "elapsed_time": "0:56:44", "remaining_time": "20:11:44"}
+{"current_steps": 35, "total_steps": 760, "loss": 0.6623, "lr": 3.6842105263157895e-05, "epoch": 0.22950819672131148, "percentage": 4.61, "elapsed_time": "0:58:24", "remaining_time": "20:10:00"}
+{"current_steps": 36, "total_steps": 760, "loss": 0.6585, "lr": 3.789473684210526e-05, "epoch": 0.2360655737704918, "percentage": 4.74, "elapsed_time": "1:00:04", "remaining_time": "20:08:13"}
+{"current_steps": 37, "total_steps": 760, "loss": 0.6517, "lr": 3.8947368421052636e-05, "epoch": 0.24262295081967214, "percentage": 4.87, "elapsed_time": "1:01:46", "remaining_time": "20:07:04"}
+{"current_steps": 38, "total_steps": 760, "loss": 0.6623, "lr": 4e-05, "epoch": 0.24918032786885247, "percentage": 5.0, "elapsed_time": "1:03:26", "remaining_time": "20:05:31"}
+{"current_steps": 39, "total_steps": 760, "loss": 0.6477, "lr": 4.105263157894738e-05, "epoch": 0.25573770491803277, "percentage": 5.13, "elapsed_time": "1:05:09", "remaining_time": "20:04:32"}
+{"current_steps": 40, "total_steps": 760, "loss": 0.6541, "lr": 4.210526315789474e-05, "epoch": 0.26229508196721313, "percentage": 5.26, "elapsed_time": "1:06:50", "remaining_time": "20:03:06"}
+{"current_steps": 41, "total_steps": 760, "loss": 0.6558, "lr": 4.315789473684211e-05, "epoch": 0.26885245901639343, "percentage": 5.39, "elapsed_time": "1:08:29", "remaining_time": "20:01:12"}
+{"current_steps": 42, "total_steps": 760, "loss": 0.6607, "lr": 4.421052631578948e-05, "epoch": 0.2754098360655738, "percentage": 5.53, "elapsed_time": "1:10:09", "remaining_time": "19:59:24"}
+{"current_steps": 43, "total_steps": 760, "loss": 0.6555, "lr": 4.5263157894736846e-05, "epoch": 0.2819672131147541, "percentage": 5.66, "elapsed_time": "1:11:49", "remaining_time": "19:57:32"}
+{"current_steps": 44, "total_steps": 760, "loss": 0.6379, "lr": 4.6315789473684214e-05, "epoch": 0.28852459016393445, "percentage": 5.79, "elapsed_time": "1:13:28", "remaining_time": "19:55:37"}
+{"current_steps": 45, "total_steps": 760, "loss": 0.6482, "lr": 4.736842105263158e-05, "epoch": 0.29508196721311475, "percentage": 5.92, "elapsed_time": "1:15:08", "remaining_time": "19:53:51"}
+{"current_steps": 46, "total_steps": 760, "loss": 0.6414, "lr": 4.842105263157895e-05, "epoch": 0.3016393442622951, "percentage": 6.05, "elapsed_time": "1:16:49", "remaining_time": "19:52:26"}
+{"current_steps": 47, "total_steps": 760, "loss": 0.6508, "lr": 4.947368421052632e-05, "epoch": 0.3081967213114754, "percentage": 6.18, "elapsed_time": "1:18:29", "remaining_time": "19:50:39"}
+{"current_steps": 48, "total_steps": 760, "loss": 0.649, "lr": 5.052631578947368e-05, "epoch": 0.31475409836065577, "percentage": 6.32, "elapsed_time": "1:20:08", "remaining_time": "19:48:51"}
+{"current_steps": 49, "total_steps": 760, "loss": 0.6435, "lr": 5.157894736842106e-05, "epoch": 0.32131147540983607, "percentage": 6.45, "elapsed_time": "1:21:48", "remaining_time": "19:47:07"}
+{"current_steps": 50, "total_steps": 760, "loss": 0.6446, "lr": 5.263157894736843e-05, "epoch": 0.32786885245901637, "percentage": 6.58, "elapsed_time": "1:23:28", "remaining_time": "19:45:19"}
+{"current_steps": 51, "total_steps": 760, "loss": 0.6484, "lr": 5.368421052631579e-05, "epoch": 0.3344262295081967, "percentage": 6.71, "elapsed_time": "1:25:08", "remaining_time": "19:43:35"}
+{"current_steps": 52, "total_steps": 760, "loss": 0.6452, "lr": 5.4736842105263165e-05, "epoch": 0.34098360655737703, "percentage": 6.84, "elapsed_time": "1:26:47", "remaining_time": "19:41:47"}
+{"current_steps": 53, "total_steps": 760, "loss": 0.645, "lr": 5.5789473684210526e-05, "epoch": 0.3475409836065574, "percentage": 6.97, "elapsed_time": "1:28:27", "remaining_time": "19:39:57"}
+{"current_steps": 54, "total_steps": 760, "loss": 0.6454, "lr": 5.68421052631579e-05, "epoch": 0.3540983606557377, "percentage": 7.11, "elapsed_time": "1:30:08", "remaining_time": "19:38:36"}
+{"current_steps": 55, "total_steps": 760, "loss": 0.6435, "lr": 5.789473684210527e-05, "epoch": 0.36065573770491804, "percentage": 7.24, "elapsed_time": "1:31:48", "remaining_time": "19:36:51"}
+{"current_steps": 56, "total_steps": 760, "loss": 0.6383, "lr": 5.8947368421052634e-05, "epoch": 0.36721311475409835, "percentage": 7.37, "elapsed_time": "1:33:28", "remaining_time": "19:35:08"}
+{"current_steps": 57, "total_steps": 760, "loss": 0.6405, "lr": 6.000000000000001e-05, "epoch": 0.3737704918032787, "percentage": 7.5, "elapsed_time": "1:35:08", "remaining_time": "19:33:27"}
+{"current_steps": 58, "total_steps": 760, "loss": 0.6362, "lr": 6.105263157894738e-05, "epoch": 0.380327868852459, "percentage": 7.63, "elapsed_time": "1:36:48", "remaining_time": "19:31:37"}
+{"current_steps": 59, "total_steps": 760, "loss": 0.638, "lr": 6.210526315789474e-05, "epoch": 0.38688524590163936, "percentage": 7.76, "elapsed_time": "1:38:27", "remaining_time": "19:29:54"}
+{"current_steps": 60, "total_steps": 760, "loss": 0.6286, "lr": 6.315789473684212e-05, "epoch": 0.39344262295081966, "percentage": 7.89, "elapsed_time": "1:40:07", "remaining_time": "19:28:10"}
+{"current_steps": 61, "total_steps": 760, "loss": 0.6301, "lr": 6.421052631578948e-05, "epoch": 0.4, "percentage": 8.03, "elapsed_time": "1:41:47", "remaining_time": "19:26:23"}
+{"current_steps": 62, "total_steps": 760, "loss": 0.6313, "lr": 6.526315789473685e-05, "epoch": 0.4065573770491803, "percentage": 8.16, "elapsed_time": "1:43:27", "remaining_time": "19:24:49"}
+{"current_steps": 63, "total_steps": 760, "loss": 0.6287, "lr": 6.631578947368421e-05, "epoch": 0.4131147540983607, "percentage": 8.29, "elapsed_time": "1:45:07", "remaining_time": "19:23:06"}
+{"current_steps": 64, "total_steps": 760, "loss": 0.6347, "lr": 6.736842105263159e-05, "epoch": 0.419672131147541, "percentage": 8.42, "elapsed_time": "1:46:47", "remaining_time": "19:21:21"}
+{"current_steps": 65, "total_steps": 760, "loss": 0.6381, "lr": 6.842105263157895e-05, "epoch": 0.4262295081967213, "percentage": 8.55, "elapsed_time": "1:48:27", "remaining_time": "19:19:39"}
+{"current_steps": 66, "total_steps": 760, "loss": 0.643, "lr": 6.947368421052632e-05, "epoch": 0.43278688524590164, "percentage": 8.68, "elapsed_time": "1:50:07", "remaining_time": "19:17:54"}
+{"current_steps": 67, "total_steps": 760, "loss": 0.6325, "lr": 7.052631578947368e-05, "epoch": 0.43934426229508194, "percentage": 8.82, "elapsed_time": "1:51:46", "remaining_time": "19:16:09"}
+{"current_steps": 68, "total_steps": 760, "loss": 0.634, "lr": 7.157894736842105e-05, "epoch": 0.4459016393442623, "percentage": 8.95, "elapsed_time": "1:53:26", "remaining_time": "19:14:25"}
+{"current_steps": 69, "total_steps": 760, "loss": 0.6285, "lr": 7.263157894736843e-05, "epoch": 0.4524590163934426, "percentage": 9.08, "elapsed_time": "1:55:06", "remaining_time": "19:12:43"}
+{"current_steps": 70, "total_steps": 760, "loss": 0.6295, "lr": 7.368421052631579e-05, "epoch": 0.45901639344262296, "percentage": 9.21, "elapsed_time": "1:56:46", "remaining_time": "19:11:01"}
+{"current_steps": 71, "total_steps": 760, "loss": 0.6312, "lr": 7.473684210526316e-05, "epoch": 0.46557377049180326, "percentage": 9.34, "elapsed_time": "1:58:25", "remaining_time": "19:09:16"}
+{"current_steps": 72, "total_steps": 760, "loss": 0.6259, "lr": 7.578947368421052e-05, "epoch": 0.4721311475409836, "percentage": 9.47, "elapsed_time": "2:00:05", "remaining_time": "19:07:32"}
+{"current_steps": 73, "total_steps": 760, "loss": 0.6285, "lr": 7.68421052631579e-05, "epoch": 0.4786885245901639, "percentage": 9.61, "elapsed_time": "2:01:44", "remaining_time": "19:05:46"}
+{"current_steps": 74, "total_steps": 760, "loss": 0.626, "lr": 7.789473684210527e-05, "epoch": 0.4852459016393443, "percentage": 9.74, "elapsed_time": "2:03:24", "remaining_time": "19:04:01"}
+{"current_steps": 75, "total_steps": 760, "loss": 0.6284, "lr": 7.894736842105263e-05, "epoch": 0.4918032786885246, "percentage": 9.87, "elapsed_time": "2:05:03", "remaining_time": "19:02:16"}
+{"current_steps": 76, "total_steps": 760, "loss": 0.6273, "lr": 8e-05, "epoch": 0.49836065573770494, "percentage": 10.0, "elapsed_time": "2:06:46", "remaining_time": "19:00:58"}
+{"current_steps": 77, "total_steps": 760, "loss": 0.6253, "lr": 7.999957809295807e-05, "epoch": 0.5049180327868853, "percentage": 10.13, "elapsed_time": "2:08:27", "remaining_time": "18:59:25"}
+{"current_steps": 78, "total_steps": 760, "loss": 0.6292, "lr": 7.99983123807325e-05, "epoch": 0.5114754098360655, "percentage": 10.26, "elapsed_time": "2:10:08", "remaining_time": "18:57:57"}
+{"current_steps": 79, "total_steps": 760, "loss": 0.6267, "lr": 7.999620289002397e-05, "epoch": 0.5180327868852459, "percentage": 10.39, "elapsed_time": "2:11:49", "remaining_time": "18:56:20"}
+{"current_steps": 80, "total_steps": 760, "loss": 0.621, "lr": 7.999324966533291e-05, "epoch": 0.5245901639344263, "percentage": 10.53, "elapsed_time": "2:13:30", "remaining_time": "18:54:46"}
+{"current_steps": 81, "total_steps": 760, "loss": 0.6294, "lr": 7.998945276895866e-05, "epoch": 0.5311475409836065, "percentage": 10.66, "elapsed_time": "2:15:09", "remaining_time": "18:53:00"}
+{"current_steps": 82, "total_steps": 760, "loss": 0.6248, "lr": 7.998481228099806e-05, "epoch": 0.5377049180327869, "percentage": 10.79, "elapsed_time": "2:16:48", "remaining_time": "18:51:13"}
+{"current_steps": 83, "total_steps": 760, "loss": 0.6299, "lr": 7.997932829934386e-05, "epoch": 0.5442622950819672, "percentage": 10.92, "elapsed_time": "2:18:28", "remaining_time": "18:49:31"}
+{"current_steps": 84, "total_steps": 760, "loss": 0.6353, "lr": 7.997300093968255e-05, "epoch": 0.5508196721311476, "percentage": 11.05, "elapsed_time": "2:20:08", "remaining_time": "18:47:50"}
+{"current_steps": 85, "total_steps": 760, "loss": 0.6319, "lr": 7.996583033549204e-05, "epoch": 0.5573770491803278, "percentage": 11.18, "elapsed_time": "2:21:47", "remaining_time": "18:46:01"}
+{"current_steps": 86, "total_steps": 760, "loss": 0.6232, "lr": 7.995781663803876e-05, "epoch": 0.5639344262295082, "percentage": 11.32, "elapsed_time": "2:23:29", "remaining_time": "18:44:31"}
+{"current_steps": 87, "total_steps": 760, "loss": 0.6235, "lr": 7.994896001637443e-05, "epoch": 0.5704918032786885, "percentage": 11.45, "elapsed_time": "2:25:08", "remaining_time": "18:42:48"}
+{"current_steps": 88, "total_steps": 760, "loss": 0.6164, "lr": 7.993926065733265e-05, "epoch": 0.5770491803278689, "percentage": 11.58, "elapsed_time": "2:26:48", "remaining_time": "18:41:02"}
+{"current_steps": 89, "total_steps": 760, "loss": 0.6166, "lr": 7.99287187655248e-05, "epoch": 0.5836065573770491, "percentage": 11.71, "elapsed_time": "2:28:27", "remaining_time": "18:39:19"}
+{"current_steps": 90, "total_steps": 760, "loss": 0.6156, "lr": 7.991733456333579e-05, "epoch": 0.5901639344262295, "percentage": 11.84, "elapsed_time": "2:30:07", "remaining_time": "18:37:34"}
+{"current_steps": 91, "total_steps": 760, "loss": 0.6325, "lr": 7.990510829091938e-05, "epoch": 0.5967213114754099, "percentage": 11.97, "elapsed_time": "2:31:47", "remaining_time": "18:35:54"}
+{"current_steps": 92, "total_steps": 760, "loss": 0.6177, "lr": 7.98920402061931e-05, "epoch": 0.6032786885245902, "percentage": 12.11, "elapsed_time": "2:33:27", "remaining_time": "18:34:11"}
+{"current_steps": 93, "total_steps": 760, "loss": 0.6156, "lr": 7.987813058483278e-05, "epoch": 0.6098360655737705, "percentage": 12.24, "elapsed_time": "2:35:06", "remaining_time": "18:32:24"}
+{"current_steps": 94, "total_steps": 760, "loss": 0.6153, "lr": 7.98633797202668e-05, "epoch": 0.6163934426229508, "percentage": 12.37, "elapsed_time": "2:36:46", "remaining_time": "18:30:45"}
+{"current_steps": 95, "total_steps": 760, "loss": 0.6119, "lr": 7.984778792366983e-05, "epoch": 0.6229508196721312, "percentage": 12.5, "elapsed_time": "2:38:26", "remaining_time": "18:29:04"}
+{"current_steps": 96, "total_steps": 760, "loss": 0.6193, "lr": 7.98313555239563e-05, "epoch": 0.6295081967213115, "percentage": 12.63, "elapsed_time": "2:40:05", "remaining_time": "18:27:20"}
+{"current_steps": 97, "total_steps": 760, "loss": 0.6241, "lr": 7.98140828677735e-05, "epoch": 0.6360655737704918, "percentage": 12.76, "elapsed_time": "2:41:46", "remaining_time": "18:25:46"}
+{"current_steps": 98, "total_steps": 760, "loss": 0.607, "lr": 7.979597031949415e-05, "epoch": 0.6426229508196721, "percentage": 12.89, "elapsed_time": "2:43:26", "remaining_time": "18:24:01"}
+{"current_steps": 99, "total_steps": 760, "loss": 0.6081, "lr": 7.977701826120888e-05, "epoch": 0.6491803278688525, "percentage": 13.03, "elapsed_time": "2:45:05", "remaining_time": "18:22:17"}
+{"current_steps": 100, "total_steps": 760, "loss": 0.6105, "lr": 7.975722709271799e-05, "epoch": 0.6557377049180327, "percentage": 13.16, "elapsed_time": "2:46:45", "remaining_time": "18:20:37"}
+{"current_steps": 101, "total_steps": 760, "loss": 0.6104, "lr": 7.973659723152317e-05, "epoch": 0.6622950819672131, "percentage": 13.29, "elapsed_time": "2:48:25", "remaining_time": "18:18:56"}
+{"current_steps": 102, "total_steps": 760, "loss": 0.608, "lr": 7.97151291128186e-05, "epoch": 0.6688524590163935, "percentage": 13.42, "elapsed_time": "2:50:05", "remaining_time": "18:17:13"}
+{"current_steps": 103, "total_steps": 760, "loss": 0.6044, "lr": 7.96928231894818e-05, "epoch": 0.6754098360655738, "percentage": 13.55, "elapsed_time": "2:51:44", "remaining_time": "18:15:30"}
+{"current_steps": 104, "total_steps": 760, "loss": 0.6026, "lr": 7.96696799320641e-05, "epoch": 0.6819672131147541, "percentage": 13.68, "elapsed_time": "2:53:24", "remaining_time": "18:13:47"}
+{"current_steps": 105, "total_steps": 760, "loss": 0.6065, "lr": 7.964569982878063e-05, "epoch": 0.6885245901639344, "percentage": 13.82, "elapsed_time": "2:55:04", "remaining_time": "18:12:05"}
+{"current_steps": 106, "total_steps": 760, "loss": 0.5965, "lr": 7.962088338550013e-05, "epoch": 0.6950819672131148, "percentage": 13.95, "elapsed_time": "2:56:43", "remaining_time": "18:10:24"}
+{"current_steps": 107, "total_steps": 760, "loss": 0.5929, "lr": 7.959523112573422e-05, "epoch": 0.7016393442622951, "percentage": 14.08, "elapsed_time": "2:58:23", "remaining_time": "18:08:42"}
+{"current_steps": 108, "total_steps": 760, "loss": 0.6035, "lr": 7.956874359062632e-05, "epoch": 0.7081967213114754, "percentage": 14.21, "elapsed_time": "3:00:04", "remaining_time": "18:07:08"}
+{"current_steps": 109, "total_steps": 760, "loss": 0.598, "lr": 7.954142133894033e-05, "epoch": 0.7147540983606557, "percentage": 14.34, "elapsed_time": "3:01:44", "remaining_time": "18:05:28"}
+{"current_steps": 110, "total_steps": 760, "loss": 0.5953, "lr": 7.951326494704878e-05, "epoch": 0.7213114754098361, "percentage": 14.47, "elapsed_time": "3:03:23", "remaining_time": "18:03:43"}
+{"current_steps": 111, "total_steps": 760, "loss": 0.5961, "lr": 7.948427500892065e-05, "epoch": 0.7278688524590164, "percentage": 14.61, "elapsed_time": "3:05:03", "remaining_time": "18:02:02"}
+{"current_steps": 112, "total_steps": 760, "loss": 0.5978, "lr": 7.94544521361089e-05, "epoch": 0.7344262295081967, "percentage": 14.74, "elapsed_time": "3:06:43", "remaining_time": "18:00:21"}
+{"current_steps": 113, "total_steps": 760, "loss": 0.5975, "lr": 7.942379695773753e-05, "epoch": 0.740983606557377, "percentage": 14.87, "elapsed_time": "3:08:23", "remaining_time": "17:58:40"}
+{"current_steps": 114, "total_steps": 760, "loss": 0.5936, "lr": 7.939231012048833e-05, "epoch": 0.7475409836065574, "percentage": 15.0, "elapsed_time": "3:10:03", "remaining_time": "17:57:01"}
+{"current_steps": 115, "total_steps": 760, "loss": 0.5943, "lr": 7.93599922885872e-05, "epoch": 0.7540983606557377, "percentage": 15.13, "elapsed_time": "3:11:44", "remaining_time": "17:55:24"}
+{"current_steps": 116, "total_steps": 760, "loss": 0.5953, "lr": 7.932684414379021e-05, "epoch": 0.760655737704918, "percentage": 15.26, "elapsed_time": "3:13:26", "remaining_time": "17:53:56"}
+{"current_steps": 117, "total_steps": 760, "loss": 0.5939, "lr": 7.929286638536913e-05, "epoch": 0.7672131147540984, "percentage": 15.39, "elapsed_time": "3:15:07", "remaining_time": "17:52:21"}
+{"current_steps": 118, "total_steps": 760, "loss": 0.5911, "lr": 7.925805973009672e-05, "epoch": 0.7737704918032787, "percentage": 15.53, "elapsed_time": "3:16:48", "remaining_time": "17:50:46"}
+{"current_steps": 119, "total_steps": 760, "loss": 0.6001, "lr": 7.922242491223167e-05, "epoch": 0.780327868852459, "percentage": 15.66, "elapsed_time": "3:18:29", "remaining_time": "17:49:10"}
+{"current_steps": 120, "total_steps": 760, "loss": 0.6023, "lr": 7.918596268350296e-05, "epoch": 0.7868852459016393, "percentage": 15.79, "elapsed_time": "3:20:09", "remaining_time": "17:47:29"}
+{"current_steps": 121, "total_steps": 760, "loss": 0.5946, "lr": 7.914867381309418e-05, "epoch": 0.7934426229508197, "percentage": 15.92, "elapsed_time": "3:21:50", "remaining_time": "17:45:54"}
+{"current_steps": 122, "total_steps": 760, "loss": 0.5888, "lr": 7.911055908762718e-05, "epoch": 0.8, "percentage": 16.05, "elapsed_time": "3:23:30", "remaining_time": "17:44:12"}
+{"current_steps": 123, "total_steps": 760, "loss": 0.5995, "lr": 7.90716193111455e-05, "epoch": 0.8065573770491803, "percentage": 16.18, "elapsed_time": "3:25:09", "remaining_time": "17:42:30"}
+{"current_steps": 124, "total_steps": 760, "loss": 0.5932, "lr": 7.903185530509743e-05, "epoch": 0.8131147540983606, "percentage": 16.32, "elapsed_time": "3:26:49", "remaining_time": "17:40:48"}
+{"current_steps": 125, "total_steps": 760, "loss": 0.5988, "lr": 7.899126790831869e-05, "epoch": 0.819672131147541, "percentage": 16.45, "elapsed_time": "3:28:29", "remaining_time": "17:39:06"}
+{"current_steps": 126, "total_steps": 760, "loss": 0.5986, "lr": 7.894985797701472e-05, "epoch": 0.8262295081967214, "percentage": 16.58, "elapsed_time": "3:30:09", "remaining_time": "17:37:26"}
+{"current_steps": 127, "total_steps": 760, "loss": 0.5918, "lr": 7.890762638474256e-05, "epoch": 0.8327868852459016, "percentage": 16.71, "elapsed_time": "3:31:48", "remaining_time": "17:35:44"}
+{"current_steps": 128, "total_steps": 760, "loss": 0.5971, "lr": 7.886457402239256e-05, "epoch": 0.839344262295082, "percentage": 16.84, "elapsed_time": "3:33:28", "remaining_time": "17:34:03"}
+{"current_steps": 129, "total_steps": 760, "loss": 0.5896, "lr": 7.882070179816944e-05, "epoch": 0.8459016393442623, "percentage": 16.97, "elapsed_time": "3:35:09", "remaining_time": "17:32:26"}
+{"current_steps": 130, "total_steps": 760, "loss": 0.5914, "lr": 7.877601063757323e-05, "epoch": 0.8524590163934426, "percentage": 17.11, "elapsed_time": "3:36:49", "remaining_time": "17:30:44"}
+{"current_steps": 131, "total_steps": 760, "loss": 0.59, "lr": 7.873050148337967e-05, "epoch": 0.8590163934426229, "percentage": 17.24, "elapsed_time": "3:38:28", "remaining_time": "17:29:02"}
+{"current_steps": 132, "total_steps": 760, "loss": 0.5906, "lr": 7.868417529562043e-05, "epoch": 0.8655737704918033, "percentage": 17.37, "elapsed_time": "3:40:08", "remaining_time": "17:27:20"}
+{"current_steps": 133, "total_steps": 760, "loss": 0.5881, "lr": 7.863703305156273e-05, "epoch": 0.8721311475409836, "percentage": 17.5, "elapsed_time": "3:41:47", "remaining_time": "17:25:36"}
+{"current_steps": 134, "total_steps": 760, "loss": 0.5902, "lr": 7.858907574568882e-05, "epoch": 0.8786885245901639, "percentage": 17.63, "elapsed_time": "3:43:27", "remaining_time": "17:23:54"}
+{"current_steps": 135, "total_steps": 760, "loss": 0.579, "lr": 7.854030438967494e-05, "epoch": 0.8852459016393442, "percentage": 17.76, "elapsed_time": "3:45:06", "remaining_time": "17:22:11"}
+{"current_steps": 136, "total_steps": 760, "loss": 0.5807, "lr": 7.849072001237001e-05, "epoch": 0.8918032786885246, "percentage": 17.89, "elapsed_time": "3:46:46", "remaining_time": "17:20:30"}
+{"current_steps": 137, "total_steps": 760, "loss": 0.5886, "lr": 7.844032365977396e-05, "epoch": 0.898360655737705, "percentage": 18.03, "elapsed_time": "3:48:26", "remaining_time": "17:18:48"}
+{"current_steps": 138, "total_steps": 760, "loss": 0.5873, "lr": 7.838911639501557e-05, "epoch": 0.9049180327868852, "percentage": 18.16, "elapsed_time": "3:50:06", "remaining_time": "17:17:07"}
+{"current_steps": 139, "total_steps": 760, "loss": 0.594, "lr": 7.833709929833012e-05, "epoch": 0.9114754098360656, "percentage": 18.29, "elapsed_time": "3:51:45", "remaining_time": "17:15:24"}
+{"current_steps": 140, "total_steps": 760, "loss": 0.5915, "lr": 7.828427346703657e-05, "epoch": 0.9180327868852459, "percentage": 18.42, "elapsed_time": "3:53:27", "remaining_time": "17:13:51"}
+{"current_steps": 141, "total_steps": 760, "loss": 0.578, "lr": 7.823064001551445e-05, "epoch": 0.9245901639344263, "percentage": 18.55, "elapsed_time": "3:55:06", "remaining_time": "17:12:10"}
+{"current_steps": 142, "total_steps": 760, "loss": 0.5849, "lr": 7.81762000751803e-05, "epoch": 0.9311475409836065, "percentage": 18.68, "elapsed_time": "3:56:46", "remaining_time": "17:10:29"}
+{"current_steps": 143, "total_steps": 760, "loss": 0.582, "lr": 7.812095479446383e-05, "epoch": 0.9377049180327869, "percentage": 18.82, "elapsed_time": "3:58:26", "remaining_time": "17:08:48"}
+{"current_steps": 144, "total_steps": 760, "loss": 0.5836, "lr": 7.806490533878368e-05, "epoch": 0.9442622950819672, "percentage": 18.95, "elapsed_time": "4:00:10", "remaining_time": "17:07:23"}
+{"current_steps": 145, "total_steps": 760, "loss": 0.577, "lr": 7.800805289052286e-05, "epoch": 0.9508196721311475, "percentage": 19.08, "elapsed_time": "4:01:55", "remaining_time": "17:06:04"}
+{"current_steps": 146, "total_steps": 760, "loss": 0.5827, "lr": 7.795039864900378e-05, "epoch": 0.9573770491803278, "percentage": 19.21, "elapsed_time": "4:03:40", "remaining_time": "17:04:47"}
+{"current_steps": 147, "total_steps": 760, "loss": 0.5877, "lr": 7.789194383046295e-05, "epoch": 0.9639344262295082, "percentage": 19.34, "elapsed_time": "4:05:26", "remaining_time": "17:03:28"}
+{"current_steps": 148, "total_steps": 760, "loss": 0.582, "lr": 7.783268966802539e-05, "epoch": 0.9704918032786886, "percentage": 19.47, "elapsed_time": "4:07:05", "remaining_time": "17:01:46"}
+{"current_steps": 149, "total_steps": 760, "loss": 0.5876, "lr": 7.777263741167849e-05, "epoch": 0.9770491803278688, "percentage": 19.61, "elapsed_time": "4:08:47", "remaining_time": "17:00:11"}
+{"current_steps": 150, "total_steps": 760, "loss": 0.5846, "lr": 7.771178832824573e-05, "epoch": 0.9836065573770492, "percentage": 19.74, "elapsed_time": "4:10:26", "remaining_time": "16:58:29"}
+{"current_steps": 151, "total_steps": 760, "loss": 0.5897, "lr": 7.765014370135999e-05, "epoch": 0.9901639344262295, "percentage": 19.87, "elapsed_time": "4:12:06", "remaining_time": "16:56:47"}
+{"current_steps": 152, "total_steps": 760, "loss": 0.5883, "lr": 7.758770483143634e-05, "epoch": 0.9967213114754099, "percentage": 20.0, "elapsed_time": "4:13:46", "remaining_time": "16:55:05"}
+{"current_steps": 153, "total_steps": 760, "loss": 0.5696, "lr": 7.752447303564475e-05, "epoch": 1.0032786885245901, "percentage": 20.13, "elapsed_time": "4:17:16", "remaining_time": "17:00:40"}
+{"current_steps": 154, "total_steps": 760, "loss": 0.5479, "lr": 7.74604496478822e-05, "epoch": 1.0098360655737706, "percentage": 20.26, "elapsed_time": "4:18:57", "remaining_time": "16:59:01"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76c9cfed787a6712fc9e3e482c3d2c54d87e16a1b88f72023fa81e18f8c5ef2
+size 7224