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: c1_science_10d_16s_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. -->
+
+# c1_science_10d_16s_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/c1_science_10d_16s_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 2.6.0+cu124
+- Datasets 3.1.0
+- 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": 3.788104761815859e+17,
+    "train_loss": 0.40834243855039987,
+    "train_runtime": 25597.751,
+    "train_samples_per_second": 0.864,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/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:d3cf12b8f116ac681946c0cf06d9c16673a9d97e9a1d03bdfab3de3f0d409a40
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b8fee1051744c06368ab2830f321024ba94d329646dca7c2c1f5239937c551
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c805e3ce64970da7d5112c997760983999e7855c1fc841c8af9399083ed4b8b6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ca59586034b16c55b5ac6c5e5eed318e2f44c24c2948ae2d66026cc2afad86
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-27 03:25:38", "end_time": "2025-04-27 10:34:23"}

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": 3.788104761815859e+17,
+    "train_loss": 0.40834243855039987,
+    "train_runtime": 25597.751,
+    "train_samples_per_second": 0.864,
+    "train_steps_per_second": 0.009
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 1.0468, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:02:08", "remaining_time": "7:59:21"}
+{"current_steps": 2, "total_steps": 224, "loss": 1.0646, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:03:49", "remaining_time": "7:04:31"}
+{"current_steps": 3, "total_steps": 224, "loss": 1.0622, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:05:42", "remaining_time": "7:00:08"}
+{"current_steps": 4, "total_steps": 224, "loss": 1.0444, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:07:41", "remaining_time": "7:02:39"}
+{"current_steps": 5, "total_steps": 224, "loss": 1.0046, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:09:26", "remaining_time": "6:53:39"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.9958, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:11:01", "remaining_time": "6:40:22"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.9489, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:12:49", "remaining_time": "6:37:29"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.931, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:14:30", "remaining_time": "6:31:37"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.9391, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:16:30", "remaining_time": "6:34:20"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.9154, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:18:25", "remaining_time": "6:34:26"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.8921, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:20:18", "remaining_time": "6:33:22"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.8708, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:22:16", "remaining_time": "6:33:36"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.8306, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:24:17", "remaining_time": "6:34:21"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.8636, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:26:06", "remaining_time": "6:31:33"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.8264, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:28:05", "remaining_time": "6:31:28"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.8247, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:29:53", "remaining_time": "6:28:38"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.8329, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:31:47", "remaining_time": "6:27:07"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.8031, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:33:58", "remaining_time": "6:28:52"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.8077, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:35:44", "remaining_time": "6:25:36"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.7619, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:37:19", "remaining_time": "6:20:42"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.7921, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:39:21", "remaining_time": "6:20:24"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.7752, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:41:17", "remaining_time": "6:19:12"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.7474, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:43:16", "remaining_time": "6:18:07"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.7321, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:45:23", "remaining_time": "6:18:14"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.7557, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:47:21", "remaining_time": "6:16:55"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.7621, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:48:54", "remaining_time": "6:12:30"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.7026, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:51:03", "remaining_time": "6:12:31"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.7753, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:52:34", "remaining_time": "6:08:02"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.7075, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:54:25", "remaining_time": "6:05:56"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.727, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:56:08", "remaining_time": "6:03:01"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.7181, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:58:05", "remaining_time": "6:01:40"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.6768, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:00:21", "remaining_time": "6:02:11"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.7094, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:03:13", "remaining_time": "6:05:53"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.6611, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:05:15", "remaining_time": "6:04:42"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.67, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "1:07:09", "remaining_time": "6:02:40"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.6189, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "1:08:55", "remaining_time": "5:59:57"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.5971, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:10:34", "remaining_time": "5:56:42"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.6242, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:12:17", "remaining_time": "5:53:50"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.6202, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:14:08", "remaining_time": "5:51:42"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.6071, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:16:08", "remaining_time": "5:50:15"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.6357, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:18:15", "remaining_time": "5:49:17"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.6197, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:20:02", "remaining_time": "5:46:49"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.6031, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:21:50", "remaining_time": "5:44:29"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.6392, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:23:42", "remaining_time": "5:42:25"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.6182, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:25:30", "remaining_time": "5:40:08"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.6064, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:27:31", "remaining_time": "5:38:41"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.6135, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:29:23", "remaining_time": "5:36:38"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.5892, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:31:15", "remaining_time": "5:34:37"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.5693, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:32:48", "remaining_time": "5:31:26"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.6014, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:34:33", "remaining_time": "5:29:04"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.612, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:36:28", "remaining_time": "5:27:14"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.5901, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:38:28", "remaining_time": "5:25:43"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.5776, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:40:24", "remaining_time": "5:23:56"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.5726, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:42:22", "remaining_time": "5:22:18"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.583, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:44:20", "remaining_time": "5:20:37"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.6398, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:45:54", "remaining_time": "5:17:42"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.6048, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:47:37", "remaining_time": "5:15:19"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.6045, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:49:33", "remaining_time": "5:13:32"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.5815, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:51:20", "remaining_time": "5:11:22"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.5844, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:53:11", "remaining_time": "5:09:24"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.5928, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "1:54:58", "remaining_time": "5:07:13"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.5987, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "1:56:32", "remaining_time": "5:04:31"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.5853, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "1:58:34", "remaining_time": "5:03:00"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.5889, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:00:14", "remaining_time": "5:00:35"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.5823, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:02:16", "remaining_time": "4:59:05"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.5004, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:04:57", "remaining_time": "4:59:09"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.4442, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "2:07:01", "remaining_time": "4:57:39"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.4529, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "2:09:00", "remaining_time": "4:55:58"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.4597, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "2:10:43", "remaining_time": "4:53:40"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.4567, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "2:12:48", "remaining_time": "4:52:10"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.4381, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "2:15:00", "remaining_time": "4:50:56"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.4547, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:17:05", "remaining_time": "4:49:24"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.4592, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:18:57", "remaining_time": "4:47:25"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.4403, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:20:33", "remaining_time": "4:44:55"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.4211, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:22:19", "remaining_time": "4:42:44"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.4218, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:23:44", "remaining_time": "4:39:55"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.4352, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:25:31", "remaining_time": "4:37:48"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.4165, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:27:36", "remaining_time": "4:36:17"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.436, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:29:31", "remaining_time": "4:34:26"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.4277, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:31:45", "remaining_time": "4:33:09"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.4376, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:34:04", "remaining_time": "4:32:00"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.4398, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:35:59", "remaining_time": "4:30:08"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.432, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:38:17", "remaining_time": "4:28:54"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.4718, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:40:06", "remaining_time": "4:26:50"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.444, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:42:06", "remaining_time": "4:25:06"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.4156, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:43:50", "remaining_time": "4:22:54"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.4559, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:45:59", "remaining_time": "4:21:22"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.4472, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:47:54", "remaining_time": "4:19:30"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.4424, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:49:40", "remaining_time": "4:17:22"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.3886, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:51:13", "remaining_time": "4:14:56"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.434, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "2:52:59", "remaining_time": "4:12:50"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.4204, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "2:54:36", "remaining_time": "4:10:31"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.4498, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "2:56:14", "remaining_time": "4:08:15"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.4357, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "2:58:19", "remaining_time": "4:06:37"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.4515, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "3:00:26", "remaining_time": "4:05:01"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.4249, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "3:02:13", "remaining_time": "4:02:58"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.415, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:03:50", "remaining_time": "4:00:42"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.4299, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:05:41", "remaining_time": "3:58:44"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.3223, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:08:29", "remaining_time": "3:57:59"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.3039, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:10:20", "remaining_time": "3:56:01"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.387, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:12:34", "remaining_time": "3:54:31"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.3116, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:14:10", "remaining_time": "3:52:14"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.3444, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:15:52", "remaining_time": "3:50:05"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.3119, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:17:48", "remaining_time": "3:48:14"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.3073, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:19:34", "remaining_time": "3:46:11"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.3276, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:21:18", "remaining_time": "3:44:05"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.3462, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:23:31", "remaining_time": "3:42:32"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.3457, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:25:07", "remaining_time": "3:40:18"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.3107, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:26:55", "remaining_time": "3:38:18"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.3437, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:28:50", "remaining_time": "3:36:26"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.3213, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:30:50", "remaining_time": "3:34:38"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.3114, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:32:57", "remaining_time": "3:32:57"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.3228, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:35:03", "remaining_time": "3:31:15"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.3081, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:36:47", "remaining_time": "3:29:11"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.3042, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:38:32", "remaining_time": "3:27:08"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.3053, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:40:20", "remaining_time": "3:25:08"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.3375, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:42:17", "remaining_time": "3:23:17"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.3163, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:43:59", "remaining_time": "3:21:12"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.2938, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:45:40", "remaining_time": "3:19:07"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.3269, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "3:47:20", "remaining_time": "3:17:01"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.2987, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "3:49:28", "remaining_time": "3:15:20"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.3066, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "3:51:08", "remaining_time": "3:13:15"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.357, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "3:53:15", "remaining_time": "3:11:31"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.3113, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "3:55:02", "remaining_time": "3:09:32"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.3377, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "3:57:09", "remaining_time": "3:07:49"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.3295, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "3:59:11", "remaining_time": "3:06:02"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.3361, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:01:09", "remaining_time": "3:04:11"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.3372, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:03:04", "remaining_time": "3:02:18"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.3051, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:04:34", "remaining_time": "3:00:06"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.3027, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:06:18", "remaining_time": "2:58:05"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.3019, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:09:08", "remaining_time": "2:56:52"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.2514, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:11:02", "remaining_time": "2:54:58"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.2748, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:12:50", "remaining_time": "2:53:00"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.2538, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:14:41", "remaining_time": "2:51:03"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.2544, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:16:36", "remaining_time": "2:49:10"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.2558, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:18:31", "remaining_time": "2:47:17"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.2386, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:19:58", "remaining_time": "2:45:05"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.2229, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:21:39", "remaining_time": "2:43:03"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.2217, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:23:12", "remaining_time": "2:40:57"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.219, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:25:08", "remaining_time": "2:39:05"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.2694, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:27:29", "remaining_time": "2:37:27"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.237, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:29:06", "remaining_time": "2:35:24"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.219, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:30:38", "remaining_time": "2:33:17"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.2681, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:32:44", "remaining_time": "2:31:31"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.2234, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:34:29", "remaining_time": "2:29:32"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.2311, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:36:20", "remaining_time": "2:27:38"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.219, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:38:11", "remaining_time": "2:25:43"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.2596, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:40:09", "remaining_time": "2:23:51"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.2196, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "4:41:58", "remaining_time": "2:21:55"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.2243, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "4:43:53", "remaining_time": "2:20:03"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.27, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "4:46:07", "remaining_time": "2:18:19"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.2326, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "4:47:47", "remaining_time": "2:16:19"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.2515, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "4:49:50", "remaining_time": "2:14:30"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.2568, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "4:51:50", "remaining_time": "2:12:39"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.2254, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "4:53:54", "remaining_time": "2:10:50"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.2251, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "4:55:39", "remaining_time": "2:08:52"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.2606, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "4:57:34", "remaining_time": "2:06:59"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.2372, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "4:59:34", "remaining_time": "2:05:08"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.2486, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:01:33", "remaining_time": "2:03:16"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.2237, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:03:35", "remaining_time": "2:01:26"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.2456, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:05:18", "remaining_time": "1:59:28"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.2122, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:07:17", "remaining_time": "1:57:36"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.2381, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:09:07", "remaining_time": "1:55:41"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.2435, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:12:02", "remaining_time": "1:54:09"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.211, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:14:00", "remaining_time": "1:52:16"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.2125, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:15:50", "remaining_time": "1:50:21"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.2237, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:18:03", "remaining_time": "1:48:33"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.1855, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:19:50", "remaining_time": "1:46:36"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.2202, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:21:42", "remaining_time": "1:44:41"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.1671, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:23:29", "remaining_time": "1:42:45"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.1951, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:25:14", "remaining_time": "1:40:48"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.2149, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:27:19", "remaining_time": "1:38:57"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.1779, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:28:59", "remaining_time": "1:36:59"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.1839, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:30:53", "remaining_time": "1:35:05"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.2051, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:32:53", "remaining_time": "1:33:12"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.185, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "5:34:34", "remaining_time": "1:31:14"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.2011, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "5:36:30", "remaining_time": "1:29:21"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.1991, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "5:38:40", "remaining_time": "1:27:31"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.1772, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "5:40:15", "remaining_time": "1:25:32"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.2011, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "5:42:01", "remaining_time": "1:23:36"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.2106, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "5:44:00", "remaining_time": "1:21:43"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.1798, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "5:45:45", "remaining_time": "1:19:47"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.215, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "5:47:58", "remaining_time": "1:17:57"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.1856, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "5:49:36", "remaining_time": "1:16:00"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.2213, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "5:51:44", "remaining_time": "1:14:09"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.2019, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "5:53:43", "remaining_time": "1:12:16"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.1541, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "5:55:15", "remaining_time": "1:10:17"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.1714, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "5:57:01", "remaining_time": "1:08:21"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.1575, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "5:58:30", "remaining_time": "1:06:23"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.1565, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "5:59:59", "remaining_time": "1:04:25"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.1609, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "6:01:53", "remaining_time": "1:02:31"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.2001, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "6:03:49", "remaining_time": "1:00:38"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.2026, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "6:05:43", "remaining_time": "0:58:44"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.2137, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "6:07:43", "remaining_time": "0:56:51"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.1824, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "6:09:28", "remaining_time": "0:54:56"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.2031, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "6:11:11", "remaining_time": "0:53:01"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.1966, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "6:14:12", "remaining_time": "0:51:17"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.1619, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "6:16:25", "remaining_time": "0:49:25"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.1907, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "6:18:29", "remaining_time": "0:47:33"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.1711, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "6:20:12", "remaining_time": "0:45:37"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.2338, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "6:22:24", "remaining_time": "0:43:45"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.1467, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "6:24:04", "remaining_time": "0:41:49"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.1907, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "6:26:00", "remaining_time": "0:39:55"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.1429, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "6:27:29", "remaining_time": "0:37:59"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.1648, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "6:29:04", "remaining_time": "0:36:03"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.169, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "6:30:47", "remaining_time": "0:34:08"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.1797, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "6:32:48", "remaining_time": "0:32:15"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.1497, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "6:34:18", "remaining_time": "0:30:19"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.1658, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "6:36:01", "remaining_time": "0:28:25"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.1859, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "6:38:02", "remaining_time": "0:26:32"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.1688, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "6:39:50", "remaining_time": "0:24:38"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.1891, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "6:41:38", "remaining_time": "0:22:44"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.1711, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "6:43:18", "remaining_time": "0:20:49"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.1777, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "6:45:18", "remaining_time": "0:18:56"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.1825, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "6:47:01", "remaining_time": "0:17:02"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.1685, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "6:48:38", "remaining_time": "0:15:08"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.1835, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "6:50:35", "remaining_time": "0:13:14"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.1633, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "6:52:18", "remaining_time": "0:11:20"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.18, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "6:54:08", "remaining_time": "0:09:27"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.1688, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "6:55:53", "remaining_time": "0:07:33"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.2004, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "6:58:01", "remaining_time": "0:05:40"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.1789, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "6:59:53", "remaining_time": "0:03:46"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.1866, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "7:02:05", "remaining_time": "0:01:53"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.2146, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "7:04:13", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "7:06:19", "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": 6.571710244916427,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.0468,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.584888261901075,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.0646,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.5829190846891965,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.0622,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 5.986274057023929,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.0444,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.916943092294921,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.0046,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.5806009746099323,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.9958,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.1381745868721245,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.9489,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 4.409782277140252,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.931,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 4.700716606778443,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.9391,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 4.563103880723426,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.9154,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 4.356293158183602,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.8921,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.8837074690270024,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.8708,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 3.131081058420418,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.8306,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 2.692877292452746,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.8636,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.660046552948952,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.8264,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.6247949320839616,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.8247,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 2.6097971785450556,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.8329,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.986529333432244,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.8031,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.6970915565643376,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.8077,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 1.47944010935288,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.7619,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 1.600785511063542,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.7921,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 1.2463876261791966,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.7752,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 1.2765022654214535,
+      "learning_rate": 2e-05,
+      "loss": 0.7474,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 1.0820472673303314,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.7321,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 1.033830390932466,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.7557,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 1.15093605459584,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.7621,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.90808619471091,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.7026,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 1.1592780803576461,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.7753,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 1.0881166841141052,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.7075,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.8885254561219318,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.727,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 1.2824703578093604,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.7181,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.9825576866386416,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.6768,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 1.2158455805572395,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.7094,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.9923158660662204,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.6611,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.9089019186870102,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.67,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.7627833742076737,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.6189,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.6939967503990835,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.5971,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.8217387241250471,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.6242,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.6853136969708522,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.6202,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.8162936323626641,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.6071,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.8521213485064775,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.6357,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.8708493902686254,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.6197,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.7759754507613245,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.6031,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.8598689433498667,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.6392,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.7842680485348008,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.6182,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.8512495674609817,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.6064,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 1.0399579537207244,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.6135,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.7785410527633699,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.5892,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.781085354056731,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.5693,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.9638349374413304,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.6014,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.7248911543227423,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.612,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.7185899614179934,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.5901,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.9403225382334981,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.5776,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.7277422223823456,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.5726,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.8484567601014534,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.583,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.7273805263769564,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.6398,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.8112017793403115,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.6048,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.7447221693680904,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.6045,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.7800809256719868,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.5815,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.7070384208924317,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.5844,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.8534386134810288,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.5928,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.7991713227608602,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.5987,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.7835569930011058,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.5853,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.8306022048153217,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.5889,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.6860569907741538,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.5823,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.7989377323443457,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.5004,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.6932589763968676,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.4442,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 1.261951551373665,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.4529,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.7827963460304641,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.4597,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 1.1352669012355001,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.4567,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.9247863155500291,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.4381,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.6924916493077918,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.4547,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.8120055923792734,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.4592,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.6823279393839417,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.4403,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 1.2690156570062068,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.4211,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.6298587598480608,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.4218,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.6815787062968733,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.4352,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.6009356136430085,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.4165,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.6637178455182509,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.436,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.6317392617042757,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.4277,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.7088088197088229,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.4376,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.5919345378484626,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.4398,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.5849589547319439,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.432,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.820570546030797,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.4718,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.5942270512761931,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.444,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.5877349622542494,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.4156,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.7074455538437789,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.4559,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.6009228668998818,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.4472,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.6237321719245432,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.4424,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.6038850128760376,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3886,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.6094845356241455,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.434,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.664655172703334,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.4204,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.64365610583345,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.4498,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.558508872697568,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.4357,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.6412349883744713,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.4515,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.6052921897084557,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.4249,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.6475401662226178,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.415,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.6213067810425908,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.4299,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.9293603871494556,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.3223,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.5899335803856,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.3039,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 1.2809540789102956,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.387,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.8986933927044485,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.3116,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.7102894310919661,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.3444,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.8953531613474207,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.3119,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.7036215868342826,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.3073,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.6781709170943677,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.3276,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.6929725261564401,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.3462,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.7112868072324559,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.3457,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.6257867773500337,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.3107,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.5957828232725987,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.3437,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.578906684628111,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.3213,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.6323367600589211,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.3114,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.6765034084565158,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.3228,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5928815732690462,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.3081,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.553573258993955,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.3042,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.5848194295079728,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.3053,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.5772365456657795,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.3375,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.5381449788350662,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.3163,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.5216562838814953,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.2938,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.536579118947148,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.3269,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.5341080183973637,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.2987,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.5248291012635133,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.3066,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.4993469436246074,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.357,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.5318884508564896,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.3113,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.5643495474864679,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.3377,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.5261524951831621,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.3295,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.5347883974392824,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.3361,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.515343390787002,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.3372,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.5596963864172609,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.3051,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.4734596843335074,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.3027,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.49200411877665867,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.3019,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.5695776585815239,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.2514,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.4357481693196861,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.2748,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.5509843753267881,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.2538,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.6348670712782296,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.2544,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.4524695786647717,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.2558,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.47506577387319127,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.2386,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.5155716168871031,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.2229,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.4585368837376427,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.2217,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.41330785361461114,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.219,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.4830241066548344,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.2694,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.5111579283891808,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.237,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.4501333280070922,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.219,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.4677430262051855,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.2681,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.453358547318383,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.2234,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.5155045393434438,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.2311,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.46182713500382666,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.219,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.42303706778202704,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.2596,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.432662674573151,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.2196,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.4234332930723555,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.2243,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.42460055403171637,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.27,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.42506826817752974,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.2326,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.39979191016820853,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.2515,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.4008425062621252,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.2568,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.42723429229383986,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.2254,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.42260474316931795,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.2251,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.4067240585220915,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.2606,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.38823072250163293,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.2372,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.4191822779374117,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.2486,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.4461708890820075,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.2237,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.4174090508507243,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.2456,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.3874314184390399,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.2122,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.42666677238256934,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.2381,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.46547502767623333,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.2435,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.5162266310966511,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.211,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.4134007391032785,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.2125,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.3473501092708669,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.2237,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.3696619109171167,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.1855,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.5069681270754923,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.2202,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.4762521157436079,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.1671,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.47960208578525826,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.1951,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.35924733837405015,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.2149,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.348448947623233,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.1779,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.404257135957341,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.1839,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.40593422037271537,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.2051,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.3521219402602394,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.185,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.32273379765564403,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.2011,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.32490098676443463,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.1991,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.3544739337877738,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.1772,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.3577236527157084,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.2011,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.3506390551925719,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.2106,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.34715119704574837,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.1798,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.3651223054017652,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.215,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.33377854019749137,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.1856,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.351922253411728,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.2213,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.35104562168350345,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.2019,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.31701739152330494,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.1541,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.34192159832257357,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.1714,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.3200613805323288,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.1575,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.3553716020021964,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.1565,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.3176563059889475,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.1609,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.3236672089672163,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.2001,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.3540755256144387,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.2026,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.33591079192847045,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.2137,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.3268029265342323,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.1824,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.3343098338067192,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.2031,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.3588586366271071,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.1966,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.2713228166680348,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.1619,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.3500882262386705,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.1907,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.335448550594209,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.1711,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.31632384454067425,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.2338,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.30598375246696663,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.1467,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.3001671556277259,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.1907,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.28456378192655113,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.1429,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.2908463467436283,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.1648,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.3047163062035505,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.169,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.2925779697765088,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.1797,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.2874622808103571,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.1497,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.2903038716340111,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.1658,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.29311481243284,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.1859,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.29807460647131795,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.1688,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.31717937043968736,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.1891,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.29155618807746464,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.1711,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.2934592403237966,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.1777,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.3033189007155214,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.1825,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.28465506705550975,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.1685,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.28494872266415744,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.1835,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.28501659601138096,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.1633,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.2913187231660811,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.18,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.2898243561952896,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.1688,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.30141955235920126,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.2004,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.2967842814028097,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.1789,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.28235982181228925,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.1866,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.30226486624869175,
+      "learning_rate": 0.0,
+      "loss": 0.2146,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 3.788104761815859e+17,
+      "train_loss": 0.40834243855039987,
+      "train_runtime": 25597.751,
+      "train_samples_per_second": 0.864,
+      "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": 3.788104761815859e+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 sha256:0391cf007d5336865e9e81b4a89681e577b1242ce26a347eeb0eb088b07cbffa
+size 7352