Upload model

.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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: opencodereasoning_3k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# opencodereasoning_3k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/opencodereasoning_3k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

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": 6.850632911392405,
+    "total_flos": 5.742441502835999e+17,
+    "train_loss": 0.5152867310015219,
+    "train_runtime": 24342.4741,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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 sha256:0c0b7f8d8c95d84bde059aacf486f48a92f9d0821f3df45fb5920c7a0d11c4e1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ddd1ad0582a93818131ee9e592b27b07eba7e682803b8953956e7b17cc5afb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bee044af6d0cabaf5ea5965e4005e3c103bd1fc5d8a762b416033610841a0a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3754e6814382daa22cffba10fe4672f1d9a7b25b7409efadaf8c38bf6c1512
+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"
+  }
+}

runs/Apr28_06-58-35_jrc0915/events.out.tfevents.1745816348.jrc0915.3029619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b03841d4e9a7a09c227161905ea6ed6a676c29f51e4a5c297d0392e570e725
+size 52619

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
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-28 06:58:35", "end_time": "2025-04-28 13:45:03"}

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": 6.850632911392405,
+    "total_flos": 5.742441502835999e+17,
+    "train_loss": 0.5152867310015219,
+    "train_runtime": 24342.4741,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.009
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 1.0411, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:02:10", "remaining_time": "8:03:13"}
+{"current_steps": 2, "total_steps": 224, "loss": 1.06, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:04:01", "remaining_time": "7:25:58"}
+{"current_steps": 3, "total_steps": 224, "loss": 1.0539, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:05:44", "remaining_time": "7:03:27"}
+{"current_steps": 4, "total_steps": 224, "loss": 1.0234, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:07:36", "remaining_time": "6:58:35"}
+{"current_steps": 5, "total_steps": 224, "loss": 1.005, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:09:35", "remaining_time": "6:59:55"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.9606, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:11:40", "remaining_time": "7:04:13"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.9667, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:13:31", "remaining_time": "6:59:10"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.9328, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:15:13", "remaining_time": "6:51:04"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.9416, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:17:05", "remaining_time": "6:48:26"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.9104, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:18:54", "remaining_time": "6:44:41"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.8779, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:20:53", "remaining_time": "6:44:39"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.8779, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:22:35", "remaining_time": "6:39:02"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.8229, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:24:29", "remaining_time": "6:37:23"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.8052, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:26:11", "remaining_time": "6:32:51"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.8185, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:28:16", "remaining_time": "6:34:01"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.7857, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:30:06", "remaining_time": "6:31:24"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.784, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:32:15", "remaining_time": "6:32:53"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.7581, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:34:11", "remaining_time": "6:31:17"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.7633, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:35:57", "remaining_time": "6:27:59"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.7508, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:37:56", "remaining_time": "6:27:03"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.756, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:39:43", "remaining_time": "6:23:58"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.7484, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:41:38", "remaining_time": "6:22:24"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.7437, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:43:37", "remaining_time": "6:21:13"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.7342, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:45:21", "remaining_time": "6:18:02"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.7267, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:47:07", "remaining_time": "6:15:08"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.7148, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:48:59", "remaining_time": "6:13:04"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.7305, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:50:43", "remaining_time": "6:10:05"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.7112, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:52:34", "remaining_time": "6:08:03"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.7131, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:54:34", "remaining_time": "6:07:01"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.7068, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:56:32", "remaining_time": "6:05:36"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.7023, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:58:20", "remaining_time": "6:03:14"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.7089, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:00:10", "remaining_time": "6:01:04"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.9312, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:02:35", "remaining_time": "6:02:16"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.6469, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:04:24", "remaining_time": "5:59:57"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.6854, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "1:06:10", "remaining_time": "5:57:22"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.6264, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "1:08:00", "remaining_time": "5:55:06"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.6853, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:09:50", "remaining_time": "5:53:00"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.6191, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:11:49", "remaining_time": "5:51:34"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.6562, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:13:27", "remaining_time": "5:48:25"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.6591, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:15:19", "remaining_time": "5:46:30"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.6612, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:17:17", "remaining_time": "5:44:59"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.6241, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:19:00", "remaining_time": "5:42:23"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.6607, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:20:49", "remaining_time": "5:40:13"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.5973, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:22:36", "remaining_time": "5:37:57"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.6609, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:24:42", "remaining_time": "5:36:58"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.6566, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:26:41", "remaining_time": "5:35:28"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.5956, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:28:25", "remaining_time": "5:32:59"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.6094, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:30:08", "remaining_time": "5:30:31"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.6534, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:31:55", "remaining_time": "5:28:19"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.6472, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:33:50", "remaining_time": "5:26:32"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.6351, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:35:37", "remaining_time": "5:24:21"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.6369, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:37:34", "remaining_time": "5:22:44"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.6105, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:39:17", "remaining_time": "5:20:20"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.6305, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:41:00", "remaining_time": "5:18:00"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.6107, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:42:48", "remaining_time": "5:15:53"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.6388, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:44:30", "remaining_time": "5:13:32"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.5825, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:46:15", "remaining_time": "5:11:19"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.6686, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:48:12", "remaining_time": "5:09:40"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.6024, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:49:56", "remaining_time": "5:07:28"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.6166, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:51:48", "remaining_time": "5:05:36"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.6062, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "1:53:35", "remaining_time": "5:03:31"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.6111, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "1:55:21", "remaining_time": "5:01:24"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.6015, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "1:56:52", "remaining_time": "4:58:42"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.6214, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "1:58:36", "remaining_time": "4:56:32"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.7401, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:00:32", "remaining_time": "4:54:52"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.6623, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:02:46", "remaining_time": "4:53:54"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.5927, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "2:04:29", "remaining_time": "4:51:42"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.5582, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "2:06:17", "remaining_time": "4:49:44"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.5404, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "2:08:01", "remaining_time": "4:47:34"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.6123, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "2:09:56", "remaining_time": "4:45:53"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.5055, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "2:11:29", "remaining_time": "4:43:20"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.5698, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:13:23", "remaining_time": "4:41:36"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.4924, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:14:56", "remaining_time": "4:39:07"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.5793, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:16:51", "remaining_time": "4:37:24"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.5658, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:18:37", "remaining_time": "4:35:24"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.5228, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:20:28", "remaining_time": "4:33:33"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.5833, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:22:34", "remaining_time": "4:32:10"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.5486, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:24:19", "remaining_time": "4:30:08"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.5026, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:26:00", "remaining_time": "4:27:59"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.5361, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:27:51", "remaining_time": "4:26:08"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.5752, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:29:34", "remaining_time": "4:24:03"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.5008, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:31:21", "remaining_time": "4:22:07"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.5641, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:33:16", "remaining_time": "4:20:23"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.5247, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:35:03", "remaining_time": "4:18:26"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.5518, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:37:09", "remaining_time": "4:17:00"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.5802, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:38:57", "remaining_time": "4:15:03"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.4849, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:40:38", "remaining_time": "4:12:57"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.53, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:42:28", "remaining_time": "4:11:05"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.577, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:44:22", "remaining_time": "4:09:19"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.5144, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:46:04", "remaining_time": "4:07:16"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.504, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "2:47:40", "remaining_time": "4:05:04"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.5807, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "2:49:36", "remaining_time": "4:03:20"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.5403, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "2:51:21", "remaining_time": "4:01:23"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.5283, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "2:53:14", "remaining_time": "3:59:35"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.5485, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "2:55:05", "remaining_time": "3:57:44"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.5511, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "2:56:39", "remaining_time": "3:55:33"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.5387, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "2:58:34", "remaining_time": "3:53:47"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.7318, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:00:29", "remaining_time": "3:52:03"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.4751, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:02:35", "remaining_time": "3:50:33"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.482, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:04:22", "remaining_time": "3:48:38"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.4803, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:06:11", "remaining_time": "3:46:45"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.4788, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:07:56", "remaining_time": "3:44:47"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.4749, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:09:34", "remaining_time": "3:42:42"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.4676, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:11:35", "remaining_time": "3:41:04"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.4607, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:13:17", "remaining_time": "3:39:03"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.4734, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:15:17", "remaining_time": "3:37:24"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.4784, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:17:01", "remaining_time": "3:35:26"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.4598, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:18:47", "remaining_time": "3:33:30"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.4547, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:20:28", "remaining_time": "3:31:31"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.4659, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:22:10", "remaining_time": "3:29:31"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.4647, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:23:59", "remaining_time": "3:27:40"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.4707, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:26:00", "remaining_time": "3:26:00"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.4654, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:27:47", "remaining_time": "3:24:06"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.4663, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:29:38", "remaining_time": "3:22:16"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.4712, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:31:25", "remaining_time": "3:20:23"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.4743, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:33:08", "remaining_time": "3:18:26"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.4617, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:34:55", "remaining_time": "3:16:33"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.4745, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:36:37", "remaining_time": "3:14:35"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.4527, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:38:18", "remaining_time": "3:12:37"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.4708, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "3:40:14", "remaining_time": "3:10:52"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.4584, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "3:41:52", "remaining_time": "3:08:52"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.4712, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "3:43:43", "remaining_time": "3:07:03"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.4615, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "3:45:31", "remaining_time": "3:05:11"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.4625, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "3:47:10", "remaining_time": "3:03:12"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.4751, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "3:49:03", "remaining_time": "3:01:24"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.476, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "3:50:53", "remaining_time": "2:59:34"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.4764, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "3:52:45", "remaining_time": "2:57:46"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.4693, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "3:54:28", "remaining_time": "2:55:51"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.4707, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "3:56:06", "remaining_time": "2:53:52"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.4651, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "3:58:03", "remaining_time": "2:52:08"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.6193, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:00:16", "remaining_time": "2:50:34"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.4262, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:01:55", "remaining_time": "2:48:37"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.3715, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:03:35", "remaining_time": "2:46:39"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.4212, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:05:22", "remaining_time": "2:44:48"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.398, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:07:15", "remaining_time": "2:43:00"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.3865, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:08:46", "remaining_time": "2:40:58"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.407, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:10:41", "remaining_time": "2:39:12"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.38, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:12:21", "remaining_time": "2:37:16"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.4108, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:14:06", "remaining_time": "2:35:23"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.4117, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:15:58", "remaining_time": "2:33:34"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.3829, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:17:41", "remaining_time": "2:31:41"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.4057, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:19:27", "remaining_time": "2:29:49"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.3917, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:21:21", "remaining_time": "2:28:02"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.4182, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:23:11", "remaining_time": "2:26:13"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.3778, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:25:02", "remaining_time": "2:24:23"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.372, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:26:42", "remaining_time": "2:22:29"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.408, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:28:37", "remaining_time": "2:20:42"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.3948, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:30:23", "remaining_time": "2:18:50"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.3861, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "4:32:06", "remaining_time": "2:16:57"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.4038, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "4:33:43", "remaining_time": "2:15:02"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.3865, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "4:35:10", "remaining_time": "2:13:01"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.4039, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "4:37:02", "remaining_time": "2:11:13"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.3861, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "4:38:56", "remaining_time": "2:09:26"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.4395, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "4:40:59", "remaining_time": "2:07:43"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.4035, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "4:42:40", "remaining_time": "2:05:49"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.3661, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "4:44:14", "remaining_time": "2:03:53"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.4107, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "4:46:08", "remaining_time": "2:02:06"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.3779, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "4:48:00", "remaining_time": "2:00:18"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.4036, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "4:49:50", "remaining_time": "1:58:29"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.4067, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "4:51:34", "remaining_time": "1:56:37"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.4307, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "4:53:30", "remaining_time": "1:54:51"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.3579, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "4:55:06", "remaining_time": "1:52:56"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.5092, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "4:56:45", "remaining_time": "1:51:03"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.3992, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "4:58:57", "remaining_time": "1:49:22"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.3741, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:00:42", "remaining_time": "1:47:31"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.3439, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:02:32", "remaining_time": "1:45:42"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.3518, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:04:31", "remaining_time": "1:43:56"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.3535, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:06:13", "remaining_time": "1:42:04"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.3497, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:08:07", "remaining_time": "1:40:16"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.3744, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:09:50", "remaining_time": "1:38:25"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.3417, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:11:37", "remaining_time": "1:36:35"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.3453, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:13:26", "remaining_time": "1:34:45"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.3755, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:15:19", "remaining_time": "1:32:57"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.3329, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:17:04", "remaining_time": "1:31:06"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.3386, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:18:43", "remaining_time": "1:29:14"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.3327, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "5:20:21", "remaining_time": "1:27:22"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.3602, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "5:22:01", "remaining_time": "1:25:30"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.3285, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "5:23:51", "remaining_time": "1:23:41"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.3701, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "5:25:52", "remaining_time": "1:21:55"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.3447, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "5:27:29", "remaining_time": "1:20:03"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.3332, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "5:29:12", "remaining_time": "1:18:12"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.3255, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "5:31:00", "remaining_time": "1:16:23"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.3236, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "5:32:50", "remaining_time": "1:14:34"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.3343, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "5:34:42", "remaining_time": "1:12:45"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.3671, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "5:36:31", "remaining_time": "1:10:56"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.3627, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "5:38:17", "remaining_time": "1:09:06"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.3452, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "5:40:02", "remaining_time": "1:07:16"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.3251, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "5:41:44", "remaining_time": "1:05:26"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.3543, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "5:43:49", "remaining_time": "1:03:40"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.3578, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "5:45:34", "remaining_time": "1:01:50"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.336, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "5:47:09", "remaining_time": "0:59:58"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.3468, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "5:48:47", "remaining_time": "0:58:07"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.335, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "5:50:21", "remaining_time": "0:56:16"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.3708, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "5:52:14", "remaining_time": "0:54:28"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.3713, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "5:53:58", "remaining_time": "0:52:38"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.4364, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "5:55:41", "remaining_time": "0:50:48"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.3312, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "5:57:59", "remaining_time": "0:49:03"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.3133, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "5:59:48", "remaining_time": "0:47:14"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.3235, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "6:01:40", "remaining_time": "0:45:26"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.3187, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "6:03:16", "remaining_time": "0:43:35"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.3285, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "6:04:56", "remaining_time": "0:41:45"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.3165, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "6:06:30", "remaining_time": "0:39:54"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.3267, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "6:08:17", "remaining_time": "0:38:05"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.3341, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "6:10:08", "remaining_time": "0:36:17"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.3216, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "6:11:36", "remaining_time": "0:34:26"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.3374, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "6:13:17", "remaining_time": "0:32:37"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.3172, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "6:14:54", "remaining_time": "0:30:47"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.3332, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "6:16:31", "remaining_time": "0:28:57"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.3177, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "6:18:22", "remaining_time": "0:27:09"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.3235, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "6:20:06", "remaining_time": "0:25:20"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.3299, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "6:21:55", "remaining_time": "0:23:31"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.3187, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "6:23:42", "remaining_time": "0:21:43"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.3283, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "6:25:23", "remaining_time": "0:19:54"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.3212, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "6:26:52", "remaining_time": "0:18:04"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.327, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "6:28:43", "remaining_time": "0:16:16"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.3241, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "6:30:27", "remaining_time": "0:14:27"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.3321, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "6:32:22", "remaining_time": "0:12:39"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.3053, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "6:34:01", "remaining_time": "0:10:50"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.325, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "6:35:46", "remaining_time": "0:09:02"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.3388, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "6:37:24", "remaining_time": "0:07:13"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.329, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "6:39:20", "remaining_time": "0:05:25"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.3282, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "6:41:18", "remaining_time": "0:03:36"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.32, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "6:43:10", "remaining_time": "0:01:48"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.3219, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "6:44:48", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "6:45:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1610 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.850632911392405,
+  "eval_steps": 500,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030379746835443037,
+      "grad_norm": 6.689875551000949,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.0411,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.849445220821603,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.06,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.688986607415651,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.0539,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 6.17295057672458,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.0234,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.824631636118133,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.005,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.967109228386207,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.9606,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.7133339652521626,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.9667,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 4.307067552348288,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.9328,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 4.39815824714185,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.9416,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 3.868518252302564,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.9104,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 3.7340752710348415,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.8779,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.156388934200001,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.8779,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 2.0918790985857574,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.8229,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 1.7591308291267982,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.8052,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.008219302115603,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.8185,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 1.4175773471523028,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.7857,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 1.2508900858180383,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.784,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.3351400529703412,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.7581,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.1898964303901207,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.7633,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 1.035618164716581,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.7508,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 1.2588535581836704,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.756,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 1.1617604276047977,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.7484,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 0.9841377574007387,
+      "learning_rate": 2e-05,
+      "loss": 0.7437,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 1.2440118406941543,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.7342,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 1.0300660603430258,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.7267,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 0.7994354421344978,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.7148,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.9547887154481206,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.7305,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 0.8419282983446993,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.7112,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 0.8172700043560845,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.7131,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.9765213342565793,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.7068,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 0.8037906708063665,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.7023,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.7867836114885146,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.7089,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 0.9452960916004703,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.9312,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.7612295632163256,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.6469,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.8790900939266659,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.6854,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.6722911813478583,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.6264,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.8284270125532621,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.6853,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.5923231874699565,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.6191,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.677938105073477,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.6562,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.6445750513490396,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.6591,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.6591398559850276,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.6612,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.6785355561827732,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.6241,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.6640277076291504,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.6607,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.5723424852123583,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.5973,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.6129280945530802,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.6609,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.6123091193951057,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.6566,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 0.563780665966425,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.5956,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.6745099171218181,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.6094,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.6182295743556719,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.6534,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.6871798376763909,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.6472,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.7931097277491445,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.6351,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.7237136732899917,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.6369,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.6778553571142459,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.6105,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.833449444590497,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.6305,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.6151138014005336,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.6107,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.7431336710612528,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.6388,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.596509290604107,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.5825,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.7103672796228194,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.6686,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6569967513611935,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.6024,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.7545111659846401,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.6166,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.7915012712287626,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.6062,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.7255250890449719,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.6111,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.644262805662098,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.6015,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.7171018109103273,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.6214,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.8148776134831176,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.7401,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.6222837355511308,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.6623,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.639255387373808,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.5927,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 0.5593358910252636,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.5582,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.6197086381920219,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.5404,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 0.5802149367130685,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.6123,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.538474276913493,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.5055,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.5199149831200351,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.5698,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.4857710491511767,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.4924,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.5948737890772205,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.5793,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 0.6721221764728632,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.5658,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.5488349407810451,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.5228,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.6313108503170125,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.5833,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.8000920793639112,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.5486,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.7119338711789602,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.5026,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.7164819120687533,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.5361,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.7685277648765818,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.5752,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.5671292352052345,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.5008,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.6500481756936068,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.5641,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.6072746509141675,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.5247,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.5576438241361014,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.5518,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.7536130329548041,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.5802,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.6249046196175972,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.4849,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.5897098153304258,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.53,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.7724460281117684,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.577,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.5415458791892559,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5144,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.6243505252839292,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.504,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.5829233737143158,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.5807,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.6610733522406311,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.5403,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.6314309911410616,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.5283,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.5996596372228271,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.5485,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.6560318990398022,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.5511,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.47042230492960135,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.5387,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.7105360844787569,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.7318,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.6414075588950308,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.4751,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.5253463695637456,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.482,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 0.774967432159217,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.4803,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.5868652627563569,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.4788,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.820794326242705,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.4749,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.6077241504221031,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.4676,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.594783508239959,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.4607,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.6533478854426843,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.4734,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.5723197211508168,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.4784,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.5519310549231674,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.4598,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.6227249058550656,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.4547,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.5651010498903033,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.4659,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.5822811679193834,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.4647,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.5819816802343004,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.4707,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.5660083107300502,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.4654,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5185498875411866,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.4663,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.5116411329423655,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.4712,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.5209997436098156,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.4743,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.4871230760841342,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.4617,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.457102675321537,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.4745,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.5127974866098665,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.4527,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.42245001835461105,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.4708,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.49188080220386793,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.4584,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.44167618457063434,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.4712,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.5039688673027475,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.4615,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.4205361183926625,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.4625,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.43233021008075545,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.4751,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.487910224415194,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.476,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.4030581513496535,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.4764,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.4393249352179175,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.4693,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.44104563278521997,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.4707,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.4002212987011352,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.4651,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.648026859841576,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.6193,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.561221316671484,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.4262,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.45269085949811677,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.3715,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.6779101453871519,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.4212,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.5497678034724917,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.398,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.5003797530147505,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.3865,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.5580549407868024,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.407,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.5172188041194234,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.38,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.48915210633040296,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.4108,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.558908230314928,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.4117,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.49602986574082164,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.3829,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.4609800715774028,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.4057,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.46096456188788704,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.3917,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.4585718750789489,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.4182,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.41614902867794823,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.3778,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.4297531850892571,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.372,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.4404023195294183,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.408,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.45167223263998,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.3948,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.41539136420911377,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.3861,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.42074220510910704,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.4038,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.4141695669267265,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.3865,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.41079371804642845,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.4039,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.3884188627873057,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.3861,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.37953254241519824,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.4395,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.39987415094795503,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.4035,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.3877759370729739,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.3661,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.389059575644023,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4107,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.345400783073805,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.3779,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.39166180661464217,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.4036,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.38343303718359834,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.4067,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.3880946514795974,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.4307,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.34848503794352365,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.3579,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.45449586177166873,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.5092,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.5062638334113145,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.3992,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.5312794593990976,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.3741,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.3549986667359863,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.3439,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.42625586846437513,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.3518,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.6145040463567123,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.3535,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.5190472940259413,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.3497,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.4037654231868124,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.3744,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.39010492521577306,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.3417,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.43621092475439815,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.3453,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.45622542720212206,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.3755,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.3808402384317074,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.3329,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.37053760936822366,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.3386,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.4073764552671374,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.3327,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.4290701109825632,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.3602,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.40941863501824033,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.3285,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.4139293691174814,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.3701,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.3777113984274894,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.3447,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.36629086304895164,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.3332,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.35730174201686227,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.3255,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.33898170898210067,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.3236,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.35556052455015685,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.3343,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.3628091740313485,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.3671,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.3528887633239016,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.3627,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.35540816712948214,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.3452,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.35604246573404463,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.3251,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.3322343669563559,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.3543,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.34493178170408967,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.3578,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.3593545359875567,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.336,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.359523898968028,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.3468,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.35103113454869783,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.335,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.35416910936066975,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.3708,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.34424571317134517,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.3713,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.45934808464555765,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.4364,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.44962762325821687,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.3312,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.4478929520440433,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.3133,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.38955085059958916,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.3235,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.34255835552872055,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.3187,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.3181615279992102,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.3285,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.3563527291119814,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.3165,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.3401868281682868,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.3267,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.35960005423937524,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.3341,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.3763544106961004,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.3216,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.40579998510222787,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.3374,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.3686629640169421,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.3172,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.3799925645700284,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.3332,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.33580814479557997,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.3177,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.3583375161475769,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.3235,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.33920282172817046,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.3299,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.33097595841372207,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.3187,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.32482371977032953,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.3283,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.3166975241806231,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.3212,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.30366787288195024,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.327,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.33313199684156974,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.3241,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.3186026476638579,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.3321,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.3453794528323902,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.3053,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.3205422906400857,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.325,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.3132049065793132,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.3388,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.3185655590073017,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.329,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.3054909895467588,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.3282,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.3155921368834683,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.32,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.33481857262300907,
+      "learning_rate": 0.0,
+      "loss": 0.3219,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 5.742441502835999e+17,
+      "train_loss": 0.5152867310015219,
+      "train_runtime": 24342.4741,
+      "train_samples_per_second": 0.909,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 224,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 5.742441502835999e+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 sha256:1574b6244a0656171c94b9de1b403e0a24974f2d01a523d7ae16185470a83d2a
+size 7288