add model

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/workspace/Models/Qwen2.5-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: ps_7b_full
+  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. -->
+
+# ps_7b_full
+
+This model is a fine-tuned version of [/mnt/workspace/Models/Qwen2.5-7B](https://huggingface.co//mnt/workspace/Models/Qwen2.5-7B) on the mta_multi_turn_mamrp and the ra_multi_turn_mamrp datasets.
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- 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": 3.0,
+    "total_flos": 3.4614492313052774e+17,
+    "train_loss": 0.32225324711706266,
+    "train_runtime": 433.6826,
+    "train_samples_per_second": 4.545,
+    "train_steps_per_second": 0.574
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/workspace/Models/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": "4.45.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1dcc1bc8c1f2ea52f81764819964cdf1768fee2ee6b4f38b5fa77e21e25718
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5261a5cbb9fc12c5aa2465edfaa6fb1866d23961fc0cead0fdc4bf25dcc0aa5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c37c24574a9b931182b9b996bc252c028aaf13dc624e341b44ad7d214d670f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66517232e5bbd593f7140998d18c7d19bf81adaeedd41b11f1c86a4dd369013e
+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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are 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 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": "<|im_end|>",
+  "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": 3.0,
+    "total_flos": 3.4614492313052774e+17,
+    "train_loss": 0.32225324711706266,
+    "train_runtime": 433.6826,
+    "train_samples_per_second": 4.545,
+    "train_steps_per_second": 0.574
+}

trainer_log.jsonl

@@ -0,0 +1,250 @@
+{"current_steps": 1, "total_steps": 249, "loss": 0.8283, "lr": 9.99960204377842e-06, "epoch": 0.012048192771084338, "percentage": 0.4, "elapsed_time": "0:00:02", "remaining_time": "0:09:38"}
+{"current_steps": 2, "total_steps": 249, "loss": 0.7463, "lr": 9.99840823846134e-06, "epoch": 0.024096385542168676, "percentage": 0.8, "elapsed_time": "0:00:04", "remaining_time": "0:08:17"}
+{"current_steps": 3, "total_steps": 249, "loss": 0.6773, "lr": 9.996418774081658e-06, "epoch": 0.03614457831325301, "percentage": 1.2, "elapsed_time": "0:00:05", "remaining_time": "0:07:49"}
+{"current_steps": 4, "total_steps": 249, "loss": 0.7069, "lr": 9.99363396732727e-06, "epoch": 0.04819277108433735, "percentage": 1.61, "elapsed_time": "0:00:07", "remaining_time": "0:07:35"}
+{"current_steps": 5, "total_steps": 249, "loss": 0.8157, "lr": 9.990054261490643e-06, "epoch": 0.060240963855421686, "percentage": 2.01, "elapsed_time": "0:00:09", "remaining_time": "0:07:26"}
+{"current_steps": 6, "total_steps": 249, "loss": 0.7604, "lr": 9.985680226398261e-06, "epoch": 0.07228915662650602, "percentage": 2.41, "elapsed_time": "0:00:10", "remaining_time": "0:07:19"}
+{"current_steps": 7, "total_steps": 249, "loss": 0.6947, "lr": 9.980512558319915e-06, "epoch": 0.08433734939759036, "percentage": 2.81, "elapsed_time": "0:00:12", "remaining_time": "0:07:13"}
+{"current_steps": 8, "total_steps": 249, "loss": 0.5901, "lr": 9.974552079857873e-06, "epoch": 0.0963855421686747, "percentage": 3.21, "elapsed_time": "0:00:14", "remaining_time": "0:07:09"}
+{"current_steps": 9, "total_steps": 249, "loss": 0.6768, "lr": 9.967799739815925e-06, "epoch": 0.10843373493975904, "percentage": 3.61, "elapsed_time": "0:00:15", "remaining_time": "0:07:05"}
+{"current_steps": 10, "total_steps": 249, "loss": 0.7401, "lr": 9.960256613048367e-06, "epoch": 0.12048192771084337, "percentage": 4.02, "elapsed_time": "0:00:17", "remaining_time": "0:07:02"}
+{"current_steps": 11, "total_steps": 249, "loss": 0.603, "lr": 9.951923900288888e-06, "epoch": 0.13253012048192772, "percentage": 4.42, "elapsed_time": "0:00:19", "remaining_time": "0:06:59"}
+{"current_steps": 12, "total_steps": 249, "loss": 0.5951, "lr": 9.942802927959444e-06, "epoch": 0.14457831325301204, "percentage": 4.82, "elapsed_time": "0:00:21", "remaining_time": "0:06:56"}
+{"current_steps": 13, "total_steps": 249, "loss": 0.6246, "lr": 9.932895147959106e-06, "epoch": 0.1566265060240964, "percentage": 5.22, "elapsed_time": "0:00:22", "remaining_time": "0:06:54"}
+{"current_steps": 14, "total_steps": 249, "loss": 0.8116, "lr": 9.922202137432954e-06, "epoch": 0.1686746987951807, "percentage": 5.62, "elapsed_time": "0:00:24", "remaining_time": "0:06:51"}
+{"current_steps": 15, "total_steps": 249, "loss": 0.5243, "lr": 9.910725598521014e-06, "epoch": 0.18072289156626506, "percentage": 6.02, "elapsed_time": "0:00:26", "remaining_time": "0:06:49"}
+{"current_steps": 16, "total_steps": 249, "loss": 0.5911, "lr": 9.89846735808731e-06, "epoch": 0.1927710843373494, "percentage": 6.43, "elapsed_time": "0:00:27", "remaining_time": "0:06:47"}
+{"current_steps": 17, "total_steps": 249, "loss": 0.5873, "lr": 9.885429367429062e-06, "epoch": 0.20481927710843373, "percentage": 6.83, "elapsed_time": "0:00:29", "remaining_time": "0:06:45"}
+{"current_steps": 18, "total_steps": 249, "loss": 0.58, "lr": 9.871613701966067e-06, "epoch": 0.21686746987951808, "percentage": 7.23, "elapsed_time": "0:00:31", "remaining_time": "0:06:43"}
+{"current_steps": 19, "total_steps": 249, "loss": 0.6884, "lr": 9.857022560910338e-06, "epoch": 0.2289156626506024, "percentage": 7.63, "elapsed_time": "0:00:33", "remaining_time": "0:06:41"}
+{"current_steps": 20, "total_steps": 249, "loss": 0.7507, "lr": 9.84165826691602e-06, "epoch": 0.24096385542168675, "percentage": 8.03, "elapsed_time": "0:00:34", "remaining_time": "0:06:39"}
+{"current_steps": 21, "total_steps": 249, "loss": 0.4539, "lr": 9.825523265709667e-06, "epoch": 0.25301204819277107, "percentage": 8.43, "elapsed_time": "0:00:36", "remaining_time": "0:06:37"}
+{"current_steps": 22, "total_steps": 249, "loss": 0.5744, "lr": 9.808620125700925e-06, "epoch": 0.26506024096385544, "percentage": 8.84, "elapsed_time": "0:00:38", "remaining_time": "0:06:35"}
+{"current_steps": 23, "total_steps": 249, "loss": 0.4361, "lr": 9.790951537573686e-06, "epoch": 0.27710843373493976, "percentage": 9.24, "elapsed_time": "0:00:40", "remaining_time": "0:06:33"}
+{"current_steps": 24, "total_steps": 249, "loss": 0.4565, "lr": 9.772520313857777e-06, "epoch": 0.2891566265060241, "percentage": 9.64, "elapsed_time": "0:00:41", "remaining_time": "0:06:31"}
+{"current_steps": 25, "total_steps": 249, "loss": 0.6564, "lr": 9.753329388481261e-06, "epoch": 0.30120481927710846, "percentage": 10.04, "elapsed_time": "0:00:43", "remaining_time": "0:06:29"}
+{"current_steps": 26, "total_steps": 249, "loss": 0.5905, "lr": 9.733381816303395e-06, "epoch": 0.3132530120481928, "percentage": 10.44, "elapsed_time": "0:00:45", "remaining_time": "0:06:27"}
+{"current_steps": 27, "total_steps": 249, "loss": 0.5458, "lr": 9.712680772628365e-06, "epoch": 0.3253012048192771, "percentage": 10.84, "elapsed_time": "0:00:46", "remaining_time": "0:06:25"}
+{"current_steps": 28, "total_steps": 249, "loss": 0.4196, "lr": 9.691229552699817e-06, "epoch": 0.3373493975903614, "percentage": 11.24, "elapsed_time": "0:00:48", "remaining_time": "0:06:23"}
+{"current_steps": 29, "total_steps": 249, "loss": 0.5939, "lr": 9.669031571176322e-06, "epoch": 0.3493975903614458, "percentage": 11.65, "elapsed_time": "0:00:50", "remaining_time": "0:06:21"}
+{"current_steps": 30, "total_steps": 249, "loss": 0.4942, "lr": 9.646090361587828e-06, "epoch": 0.3614457831325301, "percentage": 12.05, "elapsed_time": "0:00:52", "remaining_time": "0:06:20"}
+{"current_steps": 31, "total_steps": 249, "loss": 0.4447, "lr": 9.622409575773162e-06, "epoch": 0.37349397590361444, "percentage": 12.45, "elapsed_time": "0:00:53", "remaining_time": "0:06:18"}
+{"current_steps": 32, "total_steps": 249, "loss": 0.5443, "lr": 9.597992983298748e-06, "epoch": 0.3855421686746988, "percentage": 12.85, "elapsed_time": "0:00:55", "remaining_time": "0:06:16"}
+{"current_steps": 33, "total_steps": 249, "loss": 0.5228, "lr": 9.572844470858537e-06, "epoch": 0.39759036144578314, "percentage": 13.25, "elapsed_time": "0:00:57", "remaining_time": "0:06:14"}
+{"current_steps": 34, "total_steps": 249, "loss": 0.5745, "lr": 9.546968041655326e-06, "epoch": 0.40963855421686746, "percentage": 13.65, "elapsed_time": "0:00:58", "remaining_time": "0:06:12"}
+{"current_steps": 35, "total_steps": 249, "loss": 0.5249, "lr": 9.520367814763514e-06, "epoch": 0.42168674698795183, "percentage": 14.06, "elapsed_time": "0:01:00", "remaining_time": "0:06:11"}
+{"current_steps": 36, "total_steps": 249, "loss": 0.5533, "lr": 9.493048024473413e-06, "epoch": 0.43373493975903615, "percentage": 14.46, "elapsed_time": "0:01:02", "remaining_time": "0:06:09"}
+{"current_steps": 37, "total_steps": 249, "loss": 0.5707, "lr": 9.46501301961723e-06, "epoch": 0.4457831325301205, "percentage": 14.86, "elapsed_time": "0:01:04", "remaining_time": "0:06:07"}
+{"current_steps": 38, "total_steps": 249, "loss": 0.5537, "lr": 9.436267262876808e-06, "epoch": 0.4578313253012048, "percentage": 15.26, "elapsed_time": "0:01:05", "remaining_time": "0:06:05"}
+{"current_steps": 39, "total_steps": 249, "loss": 0.5072, "lr": 9.406815330073244e-06, "epoch": 0.46987951807228917, "percentage": 15.66, "elapsed_time": "0:01:07", "remaining_time": "0:06:03"}
+{"current_steps": 40, "total_steps": 249, "loss": 0.4088, "lr": 9.376661909438496e-06, "epoch": 0.4819277108433735, "percentage": 16.06, "elapsed_time": "0:01:09", "remaining_time": "0:06:02"}
+{"current_steps": 41, "total_steps": 249, "loss": 0.548, "lr": 9.3458118008691e-06, "epoch": 0.4939759036144578, "percentage": 16.47, "elapsed_time": "0:01:11", "remaining_time": "0:06:00"}
+{"current_steps": 42, "total_steps": 249, "loss": 0.541, "lr": 9.314269915162115e-06, "epoch": 0.5060240963855421, "percentage": 16.87, "elapsed_time": "0:01:12", "remaining_time": "0:05:58"}
+{"current_steps": 43, "total_steps": 249, "loss": 0.5461, "lr": 9.282041273233402e-06, "epoch": 0.5180722891566265, "percentage": 17.27, "elapsed_time": "0:01:14", "remaining_time": "0:05:56"}
+{"current_steps": 44, "total_steps": 249, "loss": 0.6082, "lr": 9.249131005318388e-06, "epoch": 0.5301204819277109, "percentage": 17.67, "elapsed_time": "0:01:16", "remaining_time": "0:05:54"}
+{"current_steps": 45, "total_steps": 249, "loss": 0.6193, "lr": 9.215544350155423e-06, "epoch": 0.5421686746987951, "percentage": 18.07, "elapsed_time": "0:01:17", "remaining_time": "0:05:53"}
+{"current_steps": 46, "total_steps": 249, "loss": 0.4795, "lr": 9.18128665415186e-06, "epoch": 0.5542168674698795, "percentage": 18.47, "elapsed_time": "0:01:19", "remaining_time": "0:05:51"}
+{"current_steps": 47, "total_steps": 249, "loss": 0.5669, "lr": 9.146363370533004e-06, "epoch": 0.5662650602409639, "percentage": 18.88, "elapsed_time": "0:01:21", "remaining_time": "0:05:49"}
+{"current_steps": 48, "total_steps": 249, "loss": 0.4712, "lr": 9.110780058474052e-06, "epoch": 0.5783132530120482, "percentage": 19.28, "elapsed_time": "0:01:23", "remaining_time": "0:05:47"}
+{"current_steps": 49, "total_steps": 249, "loss": 0.4934, "lr": 9.07454238221517e-06, "epoch": 0.5903614457831325, "percentage": 19.68, "elapsed_time": "0:01:24", "remaining_time": "0:05:45"}
+{"current_steps": 50, "total_steps": 249, "loss": 0.5427, "lr": 9.03765611015985e-06, "epoch": 0.6024096385542169, "percentage": 20.08, "elapsed_time": "0:01:26", "remaining_time": "0:05:44"}
+{"current_steps": 51, "total_steps": 249, "loss": 0.4182, "lr": 9.000127113956673e-06, "epoch": 0.6144578313253012, "percentage": 20.48, "elapsed_time": "0:01:28", "remaining_time": "0:05:42"}
+{"current_steps": 52, "total_steps": 249, "loss": 0.5577, "lr": 8.961961367564652e-06, "epoch": 0.6265060240963856, "percentage": 20.88, "elapsed_time": "0:01:29", "remaining_time": "0:05:40"}
+{"current_steps": 53, "total_steps": 249, "loss": 0.5111, "lr": 8.923164946302274e-06, "epoch": 0.6385542168674698, "percentage": 21.29, "elapsed_time": "0:01:31", "remaining_time": "0:05:38"}
+{"current_steps": 54, "total_steps": 249, "loss": 0.5015, "lr": 8.883744025880429e-06, "epoch": 0.6506024096385542, "percentage": 21.69, "elapsed_time": "0:01:33", "remaining_time": "0:05:37"}
+{"current_steps": 55, "total_steps": 249, "loss": 0.3826, "lr": 8.843704881419333e-06, "epoch": 0.6626506024096386, "percentage": 22.09, "elapsed_time": "0:01:35", "remaining_time": "0:05:35"}
+{"current_steps": 56, "total_steps": 249, "loss": 0.4694, "lr": 8.803053886449644e-06, "epoch": 0.6746987951807228, "percentage": 22.49, "elapsed_time": "0:01:36", "remaining_time": "0:05:33"}
+{"current_steps": 57, "total_steps": 249, "loss": 0.5708, "lr": 8.761797511897907e-06, "epoch": 0.6867469879518072, "percentage": 22.89, "elapsed_time": "0:01:38", "remaining_time": "0:05:31"}
+{"current_steps": 58, "total_steps": 249, "loss": 0.5605, "lr": 8.719942325056496e-06, "epoch": 0.6987951807228916, "percentage": 23.29, "elapsed_time": "0:01:40", "remaining_time": "0:05:29"}
+{"current_steps": 59, "total_steps": 249, "loss": 0.5702, "lr": 8.67749498853821e-06, "epoch": 0.7108433734939759, "percentage": 23.69, "elapsed_time": "0:01:41", "remaining_time": "0:05:28"}
+{"current_steps": 60, "total_steps": 249, "loss": 0.5409, "lr": 8.634462259215719e-06, "epoch": 0.7228915662650602, "percentage": 24.1, "elapsed_time": "0:01:43", "remaining_time": "0:05:26"}
+{"current_steps": 61, "total_steps": 249, "loss": 0.4923, "lr": 8.590850987145964e-06, "epoch": 0.7349397590361446, "percentage": 24.5, "elapsed_time": "0:01:45", "remaining_time": "0:05:24"}
+{"current_steps": 62, "total_steps": 249, "loss": 0.6142, "lr": 8.546668114479769e-06, "epoch": 0.7469879518072289, "percentage": 24.9, "elapsed_time": "0:01:47", "remaining_time": "0:05:22"}
+{"current_steps": 63, "total_steps": 249, "loss": 0.4445, "lr": 8.501920674356755e-06, "epoch": 0.7590361445783133, "percentage": 25.3, "elapsed_time": "0:01:48", "remaining_time": "0:05:21"}
+{"current_steps": 64, "total_steps": 249, "loss": 0.491, "lr": 8.456615789785804e-06, "epoch": 0.7710843373493976, "percentage": 25.7, "elapsed_time": "0:01:50", "remaining_time": "0:05:19"}
+{"current_steps": 65, "total_steps": 249, "loss": 0.5563, "lr": 8.410760672511188e-06, "epoch": 0.7831325301204819, "percentage": 26.1, "elapsed_time": "0:01:52", "remaining_time": "0:05:17"}
+{"current_steps": 66, "total_steps": 249, "loss": 0.6574, "lr": 8.364362621864595e-06, "epoch": 0.7951807228915663, "percentage": 26.51, "elapsed_time": "0:01:53", "remaining_time": "0:05:15"}
+{"current_steps": 67, "total_steps": 249, "loss": 0.5063, "lr": 8.31742902360319e-06, "epoch": 0.8072289156626506, "percentage": 26.91, "elapsed_time": "0:01:55", "remaining_time": "0:05:14"}
+{"current_steps": 68, "total_steps": 249, "loss": 0.5504, "lr": 8.269967348733947e-06, "epoch": 0.8192771084337349, "percentage": 27.31, "elapsed_time": "0:01:57", "remaining_time": "0:05:12"}
+{"current_steps": 69, "total_steps": 249, "loss": 0.4678, "lr": 8.221985152324385e-06, "epoch": 0.8313253012048193, "percentage": 27.71, "elapsed_time": "0:01:59", "remaining_time": "0:05:10"}
+{"current_steps": 70, "total_steps": 249, "loss": 0.5589, "lr": 8.17349007229994e-06, "epoch": 0.8433734939759037, "percentage": 28.11, "elapsed_time": "0:02:00", "remaining_time": "0:05:08"}
+{"current_steps": 71, "total_steps": 249, "loss": 0.6464, "lr": 8.124489828228136e-06, "epoch": 0.8554216867469879, "percentage": 28.51, "elapsed_time": "0:02:02", "remaining_time": "0:05:07"}
+{"current_steps": 72, "total_steps": 249, "loss": 0.6037, "lr": 8.07499222008977e-06, "epoch": 0.8674698795180723, "percentage": 28.92, "elapsed_time": "0:02:04", "remaining_time": "0:05:05"}
+{"current_steps": 73, "total_steps": 249, "loss": 0.4077, "lr": 8.025005127037282e-06, "epoch": 0.8795180722891566, "percentage": 29.32, "elapsed_time": "0:02:05", "remaining_time": "0:05:03"}
+{"current_steps": 74, "total_steps": 249, "loss": 0.4523, "lr": 7.974536506140546e-06, "epoch": 0.891566265060241, "percentage": 29.72, "elapsed_time": "0:02:07", "remaining_time": "0:05:01"}
+{"current_steps": 75, "total_steps": 249, "loss": 0.4889, "lr": 7.923594391120237e-06, "epoch": 0.9036144578313253, "percentage": 30.12, "elapsed_time": "0:02:09", "remaining_time": "0:05:00"}
+{"current_steps": 76, "total_steps": 249, "loss": 0.4483, "lr": 7.872186891068997e-06, "epoch": 0.9156626506024096, "percentage": 30.52, "elapsed_time": "0:02:11", "remaining_time": "0:04:58"}
+{"current_steps": 77, "total_steps": 249, "loss": 0.4848, "lr": 7.820322189160618e-06, "epoch": 0.927710843373494, "percentage": 30.92, "elapsed_time": "0:02:12", "remaining_time": "0:04:56"}
+{"current_steps": 78, "total_steps": 249, "loss": 0.4577, "lr": 7.768008541347423e-06, "epoch": 0.9397590361445783, "percentage": 31.33, "elapsed_time": "0:02:14", "remaining_time": "0:04:55"}
+{"current_steps": 79, "total_steps": 249, "loss": 0.6004, "lr": 7.715254275046062e-06, "epoch": 0.9518072289156626, "percentage": 31.73, "elapsed_time": "0:02:16", "remaining_time": "0:04:53"}
+{"current_steps": 80, "total_steps": 249, "loss": 0.5161, "lr": 7.66206778781193e-06, "epoch": 0.963855421686747, "percentage": 32.13, "elapsed_time": "0:02:18", "remaining_time": "0:04:51"}
+{"current_steps": 81, "total_steps": 249, "loss": 0.4645, "lr": 7.608457546002423e-06, "epoch": 0.9759036144578314, "percentage": 32.53, "elapsed_time": "0:02:19", "remaining_time": "0:04:49"}
+{"current_steps": 82, "total_steps": 249, "loss": 0.5267, "lr": 7.554432083429253e-06, "epoch": 0.9879518072289156, "percentage": 32.93, "elapsed_time": "0:02:21", "remaining_time": "0:04:48"}
+{"current_steps": 83, "total_steps": 249, "loss": 0.3909, "lr": 7.500000000000001e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:02:23", "remaining_time": "0:04:46"}
+{"current_steps": 84, "total_steps": 249, "loss": 0.3333, "lr": 7.445169960349167e-06, "epoch": 1.0120481927710843, "percentage": 33.73, "elapsed_time": "0:02:24", "remaining_time": "0:04:44"}
+{"current_steps": 85, "total_steps": 249, "loss": 0.3103, "lr": 7.389950692458916e-06, "epoch": 1.0240963855421688, "percentage": 34.14, "elapsed_time": "0:02:26", "remaining_time": "0:04:42"}
+{"current_steps": 86, "total_steps": 249, "loss": 0.286, "lr": 7.3343509862697295e-06, "epoch": 1.036144578313253, "percentage": 34.54, "elapsed_time": "0:02:28", "remaining_time": "0:04:41"}
+{"current_steps": 87, "total_steps": 249, "loss": 0.2851, "lr": 7.278379692281209e-06, "epoch": 1.0481927710843373, "percentage": 34.94, "elapsed_time": "0:02:30", "remaining_time": "0:04:39"}
+{"current_steps": 88, "total_steps": 249, "loss": 0.3118, "lr": 7.22204572014322e-06, "epoch": 1.0602409638554218, "percentage": 35.34, "elapsed_time": "0:02:31", "remaining_time": "0:04:37"}
+{"current_steps": 89, "total_steps": 249, "loss": 0.3024, "lr": 7.165358037237644e-06, "epoch": 1.072289156626506, "percentage": 35.74, "elapsed_time": "0:02:33", "remaining_time": "0:04:36"}
+{"current_steps": 90, "total_steps": 249, "loss": 0.3262, "lr": 7.10832566725092e-06, "epoch": 1.0843373493975903, "percentage": 36.14, "elapsed_time": "0:02:35", "remaining_time": "0:04:34"}
+{"current_steps": 91, "total_steps": 249, "loss": 0.23, "lr": 7.0509576887376375e-06, "epoch": 1.0963855421686748, "percentage": 36.55, "elapsed_time": "0:02:36", "remaining_time": "0:04:32"}
+{"current_steps": 92, "total_steps": 249, "loss": 0.2511, "lr": 6.99326323367538e-06, "epoch": 1.108433734939759, "percentage": 36.95, "elapsed_time": "0:02:38", "remaining_time": "0:04:30"}
+{"current_steps": 93, "total_steps": 249, "loss": 0.3191, "lr": 6.9352514860110876e-06, "epoch": 1.1204819277108433, "percentage": 37.35, "elapsed_time": "0:02:40", "remaining_time": "0:04:29"}
+{"current_steps": 94, "total_steps": 249, "loss": 0.2792, "lr": 6.876931680199121e-06, "epoch": 1.1325301204819278, "percentage": 37.75, "elapsed_time": "0:02:42", "remaining_time": "0:04:27"}
+{"current_steps": 95, "total_steps": 249, "loss": 0.2653, "lr": 6.818313099731308e-06, "epoch": 1.144578313253012, "percentage": 38.15, "elapsed_time": "0:02:43", "remaining_time": "0:04:25"}
+{"current_steps": 96, "total_steps": 249, "loss": 0.2909, "lr": 6.759405075659165e-06, "epoch": 1.1566265060240963, "percentage": 38.55, "elapsed_time": "0:02:45", "remaining_time": "0:04:23"}
+{"current_steps": 97, "total_steps": 249, "loss": 0.1959, "lr": 6.700216985108568e-06, "epoch": 1.1686746987951806, "percentage": 38.96, "elapsed_time": "0:02:47", "remaining_time": "0:04:22"}
+{"current_steps": 98, "total_steps": 249, "loss": 0.2841, "lr": 6.640758249787067e-06, "epoch": 1.180722891566265, "percentage": 39.36, "elapsed_time": "0:02:49", "remaining_time": "0:04:20"}
+{"current_steps": 99, "total_steps": 249, "loss": 0.2838, "lr": 6.58103833448412e-06, "epoch": 1.1927710843373494, "percentage": 39.76, "elapsed_time": "0:02:50", "remaining_time": "0:04:18"}
+{"current_steps": 100, "total_steps": 249, "loss": 0.2963, "lr": 6.521066745564467e-06, "epoch": 1.2048192771084336, "percentage": 40.16, "elapsed_time": "0:02:52", "remaining_time": "0:04:16"}
+{"current_steps": 101, "total_steps": 249, "loss": 0.2877, "lr": 6.460853029454879e-06, "epoch": 1.216867469879518, "percentage": 40.56, "elapsed_time": "0:02:54", "remaining_time": "0:04:15"}
+{"current_steps": 102, "total_steps": 249, "loss": 0.3066, "lr": 6.4004067711245366e-06, "epoch": 1.2289156626506024, "percentage": 40.96, "elapsed_time": "0:02:55", "remaining_time": "0:04:13"}
+{"current_steps": 103, "total_steps": 249, "loss": 0.3099, "lr": 6.3397375925592675e-06, "epoch": 1.2409638554216866, "percentage": 41.37, "elapsed_time": "0:02:57", "remaining_time": "0:04:11"}
+{"current_steps": 104, "total_steps": 249, "loss": 0.2914, "lr": 6.2788551512299014e-06, "epoch": 1.2530120481927711, "percentage": 41.77, "elapsed_time": "0:02:59", "remaining_time": "0:04:10"}
+{"current_steps": 105, "total_steps": 249, "loss": 0.2931, "lr": 6.2177691385549595e-06, "epoch": 1.2650602409638554, "percentage": 42.17, "elapsed_time": "0:03:01", "remaining_time": "0:04:08"}
+{"current_steps": 106, "total_steps": 249, "loss": 0.2499, "lr": 6.156489278357967e-06, "epoch": 1.2771084337349397, "percentage": 42.57, "elapsed_time": "0:03:02", "remaining_time": "0:04:06"}
+{"current_steps": 107, "total_steps": 249, "loss": 0.3611, "lr": 6.0950253253195656e-06, "epoch": 1.2891566265060241, "percentage": 42.97, "elapsed_time": "0:03:04", "remaining_time": "0:04:04"}
+{"current_steps": 108, "total_steps": 249, "loss": 0.3017, "lr": 6.033387063424765e-06, "epoch": 1.3012048192771084, "percentage": 43.37, "elapsed_time": "0:03:06", "remaining_time": "0:04:03"}
+{"current_steps": 109, "total_steps": 249, "loss": 0.2823, "lr": 5.971584304405489e-06, "epoch": 1.3132530120481927, "percentage": 43.78, "elapsed_time": "0:03:07", "remaining_time": "0:04:01"}
+{"current_steps": 110, "total_steps": 249, "loss": 0.2307, "lr": 5.909626886178721e-06, "epoch": 1.3253012048192772, "percentage": 44.18, "elapsed_time": "0:03:09", "remaining_time": "0:03:59"}
+{"current_steps": 111, "total_steps": 249, "loss": 0.2963, "lr": 5.8475246712804845e-06, "epoch": 1.3373493975903614, "percentage": 44.58, "elapsed_time": "0:03:11", "remaining_time": "0:03:57"}
+{"current_steps": 112, "total_steps": 249, "loss": 0.2874, "lr": 5.785287545295895e-06, "epoch": 1.3493975903614457, "percentage": 44.98, "elapsed_time": "0:03:13", "remaining_time": "0:03:56"}
+{"current_steps": 113, "total_steps": 249, "loss": 0.2454, "lr": 5.722925415285555e-06, "epoch": 1.3614457831325302, "percentage": 45.38, "elapsed_time": "0:03:14", "remaining_time": "0:03:54"}
+{"current_steps": 114, "total_steps": 249, "loss": 0.3654, "lr": 5.660448208208513e-06, "epoch": 1.3734939759036144, "percentage": 45.78, "elapsed_time": "0:03:16", "remaining_time": "0:03:52"}
+{"current_steps": 115, "total_steps": 249, "loss": 0.2931, "lr": 5.597865869342075e-06, "epoch": 1.3855421686746987, "percentage": 46.18, "elapsed_time": "0:03:18", "remaining_time": "0:03:51"}
+{"current_steps": 116, "total_steps": 249, "loss": 0.331, "lr": 5.535188360698687e-06, "epoch": 1.3975903614457832, "percentage": 46.59, "elapsed_time": "0:03:19", "remaining_time": "0:03:49"}
+{"current_steps": 117, "total_steps": 249, "loss": 0.246, "lr": 5.472425659440157e-06, "epoch": 1.4096385542168675, "percentage": 46.99, "elapsed_time": "0:03:21", "remaining_time": "0:03:47"}
+{"current_steps": 118, "total_steps": 249, "loss": 0.2689, "lr": 5.409587756289462e-06, "epoch": 1.4216867469879517, "percentage": 47.39, "elapsed_time": "0:03:23", "remaining_time": "0:03:45"}
+{"current_steps": 119, "total_steps": 249, "loss": 0.2645, "lr": 5.346684653940408e-06, "epoch": 1.4337349397590362, "percentage": 47.79, "elapsed_time": "0:03:25", "remaining_time": "0:03:44"}
+{"current_steps": 120, "total_steps": 249, "loss": 0.3155, "lr": 5.2837263654653715e-06, "epoch": 1.4457831325301205, "percentage": 48.19, "elapsed_time": "0:03:26", "remaining_time": "0:03:42"}
+{"current_steps": 121, "total_steps": 249, "loss": 0.2112, "lr": 5.2207229127213866e-06, "epoch": 1.4578313253012047, "percentage": 48.59, "elapsed_time": "0:03:28", "remaining_time": "0:03:40"}
+{"current_steps": 122, "total_steps": 249, "loss": 0.2441, "lr": 5.157684324754858e-06, "epoch": 1.4698795180722892, "percentage": 49.0, "elapsed_time": "0:03:30", "remaining_time": "0:03:38"}
+{"current_steps": 123, "total_steps": 249, "loss": 0.3087, "lr": 5.094620636205096e-06, "epoch": 1.4819277108433735, "percentage": 49.4, "elapsed_time": "0:03:31", "remaining_time": "0:03:37"}
+{"current_steps": 124, "total_steps": 249, "loss": 0.2499, "lr": 5.031541885706987e-06, "epoch": 1.4939759036144578, "percentage": 49.8, "elapsed_time": "0:03:33", "remaining_time": "0:03:35"}
+{"current_steps": 125, "total_steps": 249, "loss": 0.2413, "lr": 4.9684581142930135e-06, "epoch": 1.5060240963855422, "percentage": 50.2, "elapsed_time": "0:03:35", "remaining_time": "0:03:33"}
+{"current_steps": 126, "total_steps": 249, "loss": 0.3701, "lr": 4.905379363794907e-06, "epoch": 1.5180722891566265, "percentage": 50.6, "elapsed_time": "0:03:37", "remaining_time": "0:03:31"}
+{"current_steps": 127, "total_steps": 249, "loss": 0.2791, "lr": 4.842315675245144e-06, "epoch": 1.5301204819277108, "percentage": 51.0, "elapsed_time": "0:03:38", "remaining_time": "0:03:30"}
+{"current_steps": 128, "total_steps": 249, "loss": 0.3303, "lr": 4.779277087278615e-06, "epoch": 1.5421686746987953, "percentage": 51.41, "elapsed_time": "0:03:40", "remaining_time": "0:03:28"}
+{"current_steps": 129, "total_steps": 249, "loss": 0.2462, "lr": 4.71627363453463e-06, "epoch": 1.5542168674698795, "percentage": 51.81, "elapsed_time": "0:03:42", "remaining_time": "0:03:26"}
+{"current_steps": 130, "total_steps": 249, "loss": 0.3083, "lr": 4.653315346059592e-06, "epoch": 1.5662650602409638, "percentage": 52.21, "elapsed_time": "0:03:44", "remaining_time": "0:03:25"}
+{"current_steps": 131, "total_steps": 249, "loss": 0.2947, "lr": 4.5904122437105384e-06, "epoch": 1.5783132530120483, "percentage": 52.61, "elapsed_time": "0:03:45", "remaining_time": "0:03:23"}
+{"current_steps": 132, "total_steps": 249, "loss": 0.3114, "lr": 4.527574340559844e-06, "epoch": 1.5903614457831325, "percentage": 53.01, "elapsed_time": "0:03:47", "remaining_time": "0:03:21"}
+{"current_steps": 133, "total_steps": 249, "loss": 0.3335, "lr": 4.464811639301314e-06, "epoch": 1.6024096385542168, "percentage": 53.41, "elapsed_time": "0:03:49", "remaining_time": "0:03:19"}
+{"current_steps": 134, "total_steps": 249, "loss": 0.2783, "lr": 4.402134130657925e-06, "epoch": 1.6144578313253013, "percentage": 53.82, "elapsed_time": "0:03:50", "remaining_time": "0:03:18"}
+{"current_steps": 135, "total_steps": 249, "loss": 0.252, "lr": 4.33955179179149e-06, "epoch": 1.6265060240963856, "percentage": 54.22, "elapsed_time": "0:03:52", "remaining_time": "0:03:16"}
+{"current_steps": 136, "total_steps": 249, "loss": 0.2825, "lr": 4.277074584714447e-06, "epoch": 1.6385542168674698, "percentage": 54.62, "elapsed_time": "0:03:54", "remaining_time": "0:03:14"}
+{"current_steps": 137, "total_steps": 249, "loss": 0.2479, "lr": 4.214712454704107e-06, "epoch": 1.6506024096385543, "percentage": 55.02, "elapsed_time": "0:03:56", "remaining_time": "0:03:13"}
+{"current_steps": 138, "total_steps": 249, "loss": 0.2192, "lr": 4.152475328719517e-06, "epoch": 1.6626506024096386, "percentage": 55.42, "elapsed_time": "0:03:57", "remaining_time": "0:03:11"}
+{"current_steps": 139, "total_steps": 249, "loss": 0.2735, "lr": 4.090373113821281e-06, "epoch": 1.6746987951807228, "percentage": 55.82, "elapsed_time": "0:03:59", "remaining_time": "0:03:09"}
+{"current_steps": 140, "total_steps": 249, "loss": 0.2222, "lr": 4.028415695594512e-06, "epoch": 1.6867469879518073, "percentage": 56.22, "elapsed_time": "0:04:01", "remaining_time": "0:03:07"}
+{"current_steps": 141, "total_steps": 249, "loss": 0.2841, "lr": 3.966612936575235e-06, "epoch": 1.6987951807228916, "percentage": 56.63, "elapsed_time": "0:04:02", "remaining_time": "0:03:06"}
+{"current_steps": 142, "total_steps": 249, "loss": 0.281, "lr": 3.904974674680436e-06, "epoch": 1.7108433734939759, "percentage": 57.03, "elapsed_time": "0:04:04", "remaining_time": "0:03:04"}
+{"current_steps": 143, "total_steps": 249, "loss": 0.19, "lr": 3.843510721642036e-06, "epoch": 1.7228915662650603, "percentage": 57.43, "elapsed_time": "0:04:06", "remaining_time": "0:03:02"}
+{"current_steps": 144, "total_steps": 249, "loss": 0.3143, "lr": 3.782230861445041e-06, "epoch": 1.7349397590361446, "percentage": 57.83, "elapsed_time": "0:04:08", "remaining_time": "0:03:00"}
+{"current_steps": 145, "total_steps": 249, "loss": 0.2964, "lr": 3.7211448487701002e-06, "epoch": 1.7469879518072289, "percentage": 58.23, "elapsed_time": "0:04:09", "remaining_time": "0:02:59"}
+{"current_steps": 146, "total_steps": 249, "loss": 0.2749, "lr": 3.6602624074407354e-06, "epoch": 1.7590361445783134, "percentage": 58.63, "elapsed_time": "0:04:11", "remaining_time": "0:02:57"}
+{"current_steps": 147, "total_steps": 249, "loss": 0.2572, "lr": 3.5995932288754655e-06, "epoch": 1.7710843373493976, "percentage": 59.04, "elapsed_time": "0:04:13", "remaining_time": "0:02:55"}
+{"current_steps": 148, "total_steps": 249, "loss": 0.2476, "lr": 3.539146970545124e-06, "epoch": 1.783132530120482, "percentage": 59.44, "elapsed_time": "0:04:14", "remaining_time": "0:02:54"}
+{"current_steps": 149, "total_steps": 249, "loss": 0.2902, "lr": 3.478933254435534e-06, "epoch": 1.7951807228915664, "percentage": 59.84, "elapsed_time": "0:04:16", "remaining_time": "0:02:52"}
+{"current_steps": 150, "total_steps": 249, "loss": 0.3345, "lr": 3.4189616655158803e-06, "epoch": 1.8072289156626506, "percentage": 60.24, "elapsed_time": "0:04:18", "remaining_time": "0:02:50"}
+{"current_steps": 151, "total_steps": 249, "loss": 0.314, "lr": 3.359241750212934e-06, "epoch": 1.819277108433735, "percentage": 60.64, "elapsed_time": "0:04:20", "remaining_time": "0:02:48"}
+{"current_steps": 152, "total_steps": 249, "loss": 0.214, "lr": 3.2997830148914316e-06, "epoch": 1.8313253012048194, "percentage": 61.04, "elapsed_time": "0:04:21", "remaining_time": "0:02:47"}
+{"current_steps": 153, "total_steps": 249, "loss": 0.2988, "lr": 3.240594924340835e-06, "epoch": 1.8433734939759037, "percentage": 61.45, "elapsed_time": "0:04:23", "remaining_time": "0:02:45"}
+{"current_steps": 154, "total_steps": 249, "loss": 0.2481, "lr": 3.181686900268694e-06, "epoch": 1.855421686746988, "percentage": 61.85, "elapsed_time": "0:04:25", "remaining_time": "0:02:43"}
+{"current_steps": 155, "total_steps": 249, "loss": 0.2702, "lr": 3.1230683198008817e-06, "epoch": 1.8674698795180724, "percentage": 62.25, "elapsed_time": "0:04:27", "remaining_time": "0:02:41"}
+{"current_steps": 156, "total_steps": 249, "loss": 0.2957, "lr": 3.0647485139889145e-06, "epoch": 1.8795180722891565, "percentage": 62.65, "elapsed_time": "0:04:28", "remaining_time": "0:02:40"}
+{"current_steps": 157, "total_steps": 249, "loss": 0.2815, "lr": 3.006736766324623e-06, "epoch": 1.891566265060241, "percentage": 63.05, "elapsed_time": "0:04:30", "remaining_time": "0:02:38"}
+{"current_steps": 158, "total_steps": 249, "loss": 0.2791, "lr": 2.9490423112623646e-06, "epoch": 1.9036144578313254, "percentage": 63.45, "elapsed_time": "0:04:32", "remaining_time": "0:02:36"}
+{"current_steps": 159, "total_steps": 249, "loss": 0.3897, "lr": 2.89167433274908e-06, "epoch": 1.9156626506024095, "percentage": 63.86, "elapsed_time": "0:04:33", "remaining_time": "0:02:35"}
+{"current_steps": 160, "total_steps": 249, "loss": 0.2742, "lr": 2.834641962762358e-06, "epoch": 1.927710843373494, "percentage": 64.26, "elapsed_time": "0:04:35", "remaining_time": "0:02:33"}
+{"current_steps": 161, "total_steps": 249, "loss": 0.2678, "lr": 2.7779542798567804e-06, "epoch": 1.9397590361445785, "percentage": 64.66, "elapsed_time": "0:04:37", "remaining_time": "0:02:31"}
+{"current_steps": 162, "total_steps": 249, "loss": 0.3035, "lr": 2.721620307718793e-06, "epoch": 1.9518072289156625, "percentage": 65.06, "elapsed_time": "0:04:39", "remaining_time": "0:02:29"}
+{"current_steps": 163, "total_steps": 249, "loss": 0.3407, "lr": 2.66564901373027e-06, "epoch": 1.963855421686747, "percentage": 65.46, "elapsed_time": "0:04:40", "remaining_time": "0:02:28"}
+{"current_steps": 164, "total_steps": 249, "loss": 0.2533, "lr": 2.610049307541085e-06, "epoch": 1.9759036144578315, "percentage": 65.86, "elapsed_time": "0:04:42", "remaining_time": "0:02:26"}
+{"current_steps": 165, "total_steps": 249, "loss": 0.2369, "lr": 2.554830039650834e-06, "epoch": 1.9879518072289155, "percentage": 66.27, "elapsed_time": "0:04:44", "remaining_time": "0:02:24"}
+{"current_steps": 166, "total_steps": 249, "loss": 0.1612, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:45", "remaining_time": "0:02:22"}
+{"current_steps": 167, "total_steps": 249, "loss": 0.1247, "lr": 2.4455679165707473e-06, "epoch": 2.0120481927710845, "percentage": 67.07, "elapsed_time": "0:04:47", "remaining_time": "0:02:21"}
+{"current_steps": 168, "total_steps": 249, "loss": 0.1618, "lr": 2.391542453997578e-06, "epoch": 2.0240963855421685, "percentage": 67.47, "elapsed_time": "0:04:49", "remaining_time": "0:02:19"}
+{"current_steps": 169, "total_steps": 249, "loss": 0.1427, "lr": 2.337932212188073e-06, "epoch": 2.036144578313253, "percentage": 67.87, "elapsed_time": "0:04:51", "remaining_time": "0:02:17"}
+{"current_steps": 170, "total_steps": 249, "loss": 0.1587, "lr": 2.284745724953939e-06, "epoch": 2.0481927710843375, "percentage": 68.27, "elapsed_time": "0:04:52", "remaining_time": "0:02:16"}
+{"current_steps": 171, "total_steps": 249, "loss": 0.1169, "lr": 2.2319914586525776e-06, "epoch": 2.0602409638554215, "percentage": 68.67, "elapsed_time": "0:04:54", "remaining_time": "0:02:14"}
+{"current_steps": 172, "total_steps": 249, "loss": 0.1232, "lr": 2.1796778108393824e-06, "epoch": 2.072289156626506, "percentage": 69.08, "elapsed_time": "0:04:56", "remaining_time": "0:02:12"}
+{"current_steps": 173, "total_steps": 249, "loss": 0.1646, "lr": 2.127813108931007e-06, "epoch": 2.0843373493975905, "percentage": 69.48, "elapsed_time": "0:04:57", "remaining_time": "0:02:10"}
+{"current_steps": 174, "total_steps": 249, "loss": 0.1058, "lr": 2.0764056088797646e-06, "epoch": 2.0963855421686746, "percentage": 69.88, "elapsed_time": "0:04:59", "remaining_time": "0:02:09"}
+{"current_steps": 175, "total_steps": 249, "loss": 0.1579, "lr": 2.0254634938594555e-06, "epoch": 2.108433734939759, "percentage": 70.28, "elapsed_time": "0:05:01", "remaining_time": "0:02:07"}
+{"current_steps": 176, "total_steps": 249, "loss": 0.138, "lr": 1.9749948729627188e-06, "epoch": 2.1204819277108435, "percentage": 70.68, "elapsed_time": "0:05:03", "remaining_time": "0:02:05"}
+{"current_steps": 177, "total_steps": 249, "loss": 0.1331, "lr": 1.9250077799102323e-06, "epoch": 2.1325301204819276, "percentage": 71.08, "elapsed_time": "0:05:04", "remaining_time": "0:02:04"}
+{"current_steps": 178, "total_steps": 249, "loss": 0.1635, "lr": 1.875510171771865e-06, "epoch": 2.144578313253012, "percentage": 71.49, "elapsed_time": "0:05:06", "remaining_time": "0:02:02"}
+{"current_steps": 179, "total_steps": 249, "loss": 0.1561, "lr": 1.8265099277000614e-06, "epoch": 2.1566265060240966, "percentage": 71.89, "elapsed_time": "0:05:08", "remaining_time": "0:02:00"}
+{"current_steps": 180, "total_steps": 249, "loss": 0.14, "lr": 1.7780148476756148e-06, "epoch": 2.1686746987951806, "percentage": 72.29, "elapsed_time": "0:05:10", "remaining_time": "0:01:58"}
+{"current_steps": 181, "total_steps": 249, "loss": 0.1233, "lr": 1.7300326512660542e-06, "epoch": 2.180722891566265, "percentage": 72.69, "elapsed_time": "0:05:11", "remaining_time": "0:01:57"}
+{"current_steps": 182, "total_steps": 249, "loss": 0.0936, "lr": 1.6825709763968112e-06, "epoch": 2.1927710843373496, "percentage": 73.09, "elapsed_time": "0:05:13", "remaining_time": "0:01:55"}
+{"current_steps": 183, "total_steps": 249, "loss": 0.1648, "lr": 1.6356373781354058e-06, "epoch": 2.2048192771084336, "percentage": 73.49, "elapsed_time": "0:05:15", "remaining_time": "0:01:53"}
+{"current_steps": 184, "total_steps": 249, "loss": 0.126, "lr": 1.589239327488812e-06, "epoch": 2.216867469879518, "percentage": 73.9, "elapsed_time": "0:05:16", "remaining_time": "0:01:51"}
+{"current_steps": 185, "total_steps": 249, "loss": 0.1212, "lr": 1.543384210214196e-06, "epoch": 2.2289156626506026, "percentage": 74.3, "elapsed_time": "0:05:18", "remaining_time": "0:01:50"}
+{"current_steps": 186, "total_steps": 249, "loss": 0.1509, "lr": 1.4980793256432474e-06, "epoch": 2.2409638554216866, "percentage": 74.7, "elapsed_time": "0:05:20", "remaining_time": "0:01:48"}
+{"current_steps": 187, "total_steps": 249, "loss": 0.12, "lr": 1.453331885520234e-06, "epoch": 2.253012048192771, "percentage": 75.1, "elapsed_time": "0:05:22", "remaining_time": "0:01:46"}
+{"current_steps": 188, "total_steps": 249, "loss": 0.1406, "lr": 1.4091490128540374e-06, "epoch": 2.2650602409638556, "percentage": 75.5, "elapsed_time": "0:05:23", "remaining_time": "0:01:45"}
+{"current_steps": 189, "total_steps": 249, "loss": 0.1706, "lr": 1.3655377407842813e-06, "epoch": 2.2771084337349397, "percentage": 75.9, "elapsed_time": "0:05:25", "remaining_time": "0:01:43"}
+{"current_steps": 190, "total_steps": 249, "loss": 0.1243, "lr": 1.32250501146179e-06, "epoch": 2.289156626506024, "percentage": 76.31, "elapsed_time": "0:05:27", "remaining_time": "0:01:41"}
+{"current_steps": 191, "total_steps": 249, "loss": 0.1132, "lr": 1.2800576749435068e-06, "epoch": 2.3012048192771086, "percentage": 76.71, "elapsed_time": "0:05:28", "remaining_time": "0:01:39"}
+{"current_steps": 192, "total_steps": 249, "loss": 0.133, "lr": 1.2382024881020937e-06, "epoch": 2.3132530120481927, "percentage": 77.11, "elapsed_time": "0:05:30", "remaining_time": "0:01:38"}
+{"current_steps": 193, "total_steps": 249, "loss": 0.1153, "lr": 1.1969461135503573e-06, "epoch": 2.325301204819277, "percentage": 77.51, "elapsed_time": "0:05:32", "remaining_time": "0:01:36"}
+{"current_steps": 194, "total_steps": 249, "loss": 0.1068, "lr": 1.1562951185806675e-06, "epoch": 2.337349397590361, "percentage": 77.91, "elapsed_time": "0:05:34", "remaining_time": "0:01:34"}
+{"current_steps": 195, "total_steps": 249, "loss": 0.0926, "lr": 1.1162559741195733e-06, "epoch": 2.3493975903614457, "percentage": 78.31, "elapsed_time": "0:05:35", "remaining_time": "0:01:32"}
+{"current_steps": 196, "total_steps": 249, "loss": 0.1147, "lr": 1.076835053697728e-06, "epoch": 2.36144578313253, "percentage": 78.71, "elapsed_time": "0:05:37", "remaining_time": "0:01:31"}
+{"current_steps": 197, "total_steps": 249, "loss": 0.131, "lr": 1.0380386324353508e-06, "epoch": 2.3734939759036147, "percentage": 79.12, "elapsed_time": "0:05:39", "remaining_time": "0:01:29"}
+{"current_steps": 198, "total_steps": 249, "loss": 0.1377, "lr": 9.998728860433277e-07, "epoch": 2.3855421686746987, "percentage": 79.52, "elapsed_time": "0:05:40", "remaining_time": "0:01:27"}
+{"current_steps": 199, "total_steps": 249, "loss": 0.127, "lr": 9.62343889840151e-07, "epoch": 2.397590361445783, "percentage": 79.92, "elapsed_time": "0:05:42", "remaining_time": "0:01:26"}
+{"current_steps": 200, "total_steps": 249, "loss": 0.1039, "lr": 9.254576177848313e-07, "epoch": 2.4096385542168672, "percentage": 80.32, "elapsed_time": "0:05:44", "remaining_time": "0:01:24"}
+{"current_steps": 201, "total_steps": 249, "loss": 0.1137, "lr": 8.892199415259501e-07, "epoch": 2.4216867469879517, "percentage": 80.72, "elapsed_time": "0:05:46", "remaining_time": "0:01:22"}
+{"current_steps": 202, "total_steps": 249, "loss": 0.1188, "lr": 8.536366294669979e-07, "epoch": 2.433734939759036, "percentage": 81.12, "elapsed_time": "0:05:47", "remaining_time": "0:01:20"}
+{"current_steps": 203, "total_steps": 249, "loss": 0.1393, "lr": 8.187133458481416e-07, "epoch": 2.4457831325301207, "percentage": 81.53, "elapsed_time": "0:05:49", "remaining_time": "0:01:19"}
+{"current_steps": 204, "total_steps": 249, "loss": 0.1088, "lr": 7.844556498445788e-07, "epoch": 2.4578313253012047, "percentage": 81.93, "elapsed_time": "0:05:51", "remaining_time": "0:01:17"}
+{"current_steps": 205, "total_steps": 249, "loss": 0.1012, "lr": 7.508689946816128e-07, "epoch": 2.4698795180722892, "percentage": 82.33, "elapsed_time": "0:05:52", "remaining_time": "0:01:15"}
+{"current_steps": 206, "total_steps": 249, "loss": 0.1283, "lr": 7.179587267665999e-07, "epoch": 2.4819277108433733, "percentage": 82.73, "elapsed_time": "0:05:54", "remaining_time": "0:01:14"}
+{"current_steps": 207, "total_steps": 249, "loss": 0.1773, "lr": 6.857300848378857e-07, "epoch": 2.4939759036144578, "percentage": 83.13, "elapsed_time": "0:05:56", "remaining_time": "0:01:12"}
+{"current_steps": 208, "total_steps": 249, "loss": 0.1003, "lr": 6.541881991309013e-07, "epoch": 2.5060240963855422, "percentage": 83.53, "elapsed_time": "0:05:58", "remaining_time": "0:01:10"}
+{"current_steps": 209, "total_steps": 249, "loss": 0.1059, "lr": 6.233380905615049e-07, "epoch": 2.5180722891566267, "percentage": 83.94, "elapsed_time": "0:05:59", "remaining_time": "0:01:08"}
+{"current_steps": 210, "total_steps": 249, "loss": 0.0997, "lr": 5.931846699267558e-07, "epoch": 2.5301204819277108, "percentage": 84.34, "elapsed_time": "0:06:01", "remaining_time": "0:01:07"}
+{"current_steps": 211, "total_steps": 249, "loss": 0.1074, "lr": 5.637327371231921e-07, "epoch": 2.5421686746987953, "percentage": 84.74, "elapsed_time": "0:06:03", "remaining_time": "0:01:05"}
+{"current_steps": 212, "total_steps": 249, "loss": 0.1635, "lr": 5.349869803827717e-07, "epoch": 2.5542168674698793, "percentage": 85.14, "elapsed_time": "0:06:04", "remaining_time": "0:01:03"}
+{"current_steps": 213, "total_steps": 249, "loss": 0.1394, "lr": 5.0695197552659e-07, "epoch": 2.566265060240964, "percentage": 85.54, "elapsed_time": "0:06:06", "remaining_time": "0:01:01"}
+{"current_steps": 214, "total_steps": 249, "loss": 0.1363, "lr": 4.796321852364877e-07, "epoch": 2.5783132530120483, "percentage": 85.94, "elapsed_time": "0:06:08", "remaining_time": "0:01:00"}
+{"current_steps": 215, "total_steps": 249, "loss": 0.1326, "lr": 4.5303195834467463e-07, "epoch": 2.5903614457831328, "percentage": 86.35, "elapsed_time": "0:06:10", "remaining_time": "0:00:58"}
+{"current_steps": 216, "total_steps": 249, "loss": 0.1222, "lr": 4.271555291414636e-07, "epoch": 2.602409638554217, "percentage": 86.75, "elapsed_time": "0:06:11", "remaining_time": "0:00:56"}
+{"current_steps": 217, "total_steps": 249, "loss": 0.0845, "lr": 4.020070167012541e-07, "epoch": 2.6144578313253013, "percentage": 87.15, "elapsed_time": "0:06:13", "remaining_time": "0:00:55"}
+{"current_steps": 218, "total_steps": 249, "loss": 0.1353, "lr": 3.775904242268391e-07, "epoch": 2.6265060240963853, "percentage": 87.55, "elapsed_time": "0:06:15", "remaining_time": "0:00:53"}
+{"current_steps": 219, "total_steps": 249, "loss": 0.1445, "lr": 3.539096384121743e-07, "epoch": 2.63855421686747, "percentage": 87.95, "elapsed_time": "0:06:17", "remaining_time": "0:00:51"}
+{"current_steps": 220, "total_steps": 249, "loss": 0.1386, "lr": 3.309684288236775e-07, "epoch": 2.6506024096385543, "percentage": 88.35, "elapsed_time": "0:06:18", "remaining_time": "0:00:49"}
+{"current_steps": 221, "total_steps": 249, "loss": 0.1237, "lr": 3.0877044730018515e-07, "epoch": 2.662650602409639, "percentage": 88.76, "elapsed_time": "0:06:20", "remaining_time": "0:00:48"}
+{"current_steps": 222, "total_steps": 249, "loss": 0.153, "lr": 2.873192273716369e-07, "epoch": 2.674698795180723, "percentage": 89.16, "elapsed_time": "0:06:22", "remaining_time": "0:00:46"}
+{"current_steps": 223, "total_steps": 249, "loss": 0.1038, "lr": 2.666181836966053e-07, "epoch": 2.6867469879518073, "percentage": 89.56, "elapsed_time": "0:06:23", "remaining_time": "0:00:44"}
+{"current_steps": 224, "total_steps": 249, "loss": 0.1208, "lr": 2.466706115187406e-07, "epoch": 2.6987951807228914, "percentage": 89.96, "elapsed_time": "0:06:25", "remaining_time": "0:00:43"}
+{"current_steps": 225, "total_steps": 249, "loss": 0.1209, "lr": 2.274796861422246e-07, "epoch": 2.710843373493976, "percentage": 90.36, "elapsed_time": "0:06:27", "remaining_time": "0:00:41"}
+{"current_steps": 226, "total_steps": 249, "loss": 0.1323, "lr": 2.090484624263167e-07, "epoch": 2.7228915662650603, "percentage": 90.76, "elapsed_time": "0:06:29", "remaining_time": "0:00:39"}
+{"current_steps": 227, "total_steps": 249, "loss": 0.1304, "lr": 1.9137987429907635e-07, "epoch": 2.734939759036145, "percentage": 91.16, "elapsed_time": "0:06:30", "remaining_time": "0:00:37"}
+{"current_steps": 228, "total_steps": 249, "loss": 0.1149, "lr": 1.7447673429033361e-07, "epoch": 2.746987951807229, "percentage": 91.57, "elapsed_time": "0:06:32", "remaining_time": "0:00:36"}
+{"current_steps": 229, "total_steps": 249, "loss": 0.1557, "lr": 1.583417330839798e-07, "epoch": 2.7590361445783134, "percentage": 91.97, "elapsed_time": "0:06:34", "remaining_time": "0:00:34"}
+{"current_steps": 230, "total_steps": 249, "loss": 0.1489, "lr": 1.4297743908966212e-07, "epoch": 2.7710843373493974, "percentage": 92.37, "elapsed_time": "0:06:35", "remaining_time": "0:00:32"}
+{"current_steps": 231, "total_steps": 249, "loss": 0.0997, "lr": 1.2838629803393343e-07, "epoch": 2.783132530120482, "percentage": 92.77, "elapsed_time": "0:06:37", "remaining_time": "0:00:30"}
+{"current_steps": 232, "total_steps": 249, "loss": 0.1218, "lr": 1.1457063257093892e-07, "epoch": 2.7951807228915664, "percentage": 93.17, "elapsed_time": "0:06:39", "remaining_time": "0:00:29"}
+{"current_steps": 233, "total_steps": 249, "loss": 0.1135, "lr": 1.0153264191269052e-07, "epoch": 2.807228915662651, "percentage": 93.57, "elapsed_time": "0:06:41", "remaining_time": "0:00:27"}
+{"current_steps": 234, "total_steps": 249, "loss": 0.1065, "lr": 8.927440147898703e-08, "epoch": 2.819277108433735, "percentage": 93.98, "elapsed_time": "0:06:42", "remaining_time": "0:00:25"}
+{"current_steps": 235, "total_steps": 249, "loss": 0.1016, "lr": 7.779786256704669e-08, "epoch": 2.8313253012048194, "percentage": 94.38, "elapsed_time": "0:06:44", "remaining_time": "0:00:24"}
+{"current_steps": 236, "total_steps": 249, "loss": 0.1239, "lr": 6.710485204089456e-08, "epoch": 2.8433734939759034, "percentage": 94.78, "elapsed_time": "0:06:46", "remaining_time": "0:00:22"}
+{"current_steps": 237, "total_steps": 249, "loss": 0.1358, "lr": 5.7197072040557356e-08, "epoch": 2.855421686746988, "percentage": 95.18, "elapsed_time": "0:06:47", "remaining_time": "0:00:20"}
+{"current_steps": 238, "total_steps": 249, "loss": 0.1337, "lr": 4.807609971111238e-08, "epoch": 2.8674698795180724, "percentage": 95.58, "elapsed_time": "0:06:49", "remaining_time": "0:00:18"}
+{"current_steps": 239, "total_steps": 249, "loss": 0.0945, "lr": 3.974338695163393e-08, "epoch": 2.8795180722891565, "percentage": 95.98, "elapsed_time": "0:06:51", "remaining_time": "0:00:17"}
+{"current_steps": 240, "total_steps": 249, "loss": 0.0994, "lr": 3.220026018407541e-08, "epoch": 2.891566265060241, "percentage": 96.39, "elapsed_time": "0:06:53", "remaining_time": "0:00:15"}
+{"current_steps": 241, "total_steps": 249, "loss": 0.1689, "lr": 2.5447920142128712e-08, "epoch": 2.9036144578313254, "percentage": 96.79, "elapsed_time": "0:06:54", "remaining_time": "0:00:13"}
+{"current_steps": 242, "total_steps": 249, "loss": 0.1219, "lr": 1.9487441680084983e-08, "epoch": 2.9156626506024095, "percentage": 97.19, "elapsed_time": "0:06:56", "remaining_time": "0:00:12"}
+{"current_steps": 243, "total_steps": 249, "loss": 0.1137, "lr": 1.431977360173975e-08, "epoch": 2.927710843373494, "percentage": 97.59, "elapsed_time": "0:06:58", "remaining_time": "0:00:10"}
+{"current_steps": 244, "total_steps": 249, "loss": 0.1498, "lr": 9.945738509358205e-09, "epoch": 2.9397590361445785, "percentage": 97.99, "elapsed_time": "0:06:59", "remaining_time": "0:00:08"}
+{"current_steps": 245, "total_steps": 249, "loss": 0.1002, "lr": 6.366032672731059e-09, "epoch": 2.9518072289156625, "percentage": 98.39, "elapsed_time": "0:07:01", "remaining_time": "0:00:06"}
+{"current_steps": 246, "total_steps": 249, "loss": 0.1247, "lr": 3.5812259183426457e-09, "epoch": 2.963855421686747, "percentage": 98.8, "elapsed_time": "0:07:03", "remaining_time": "0:00:05"}
+{"current_steps": 247, "total_steps": 249, "loss": 0.1098, "lr": 1.591761538662362e-09, "epoch": 2.9759036144578315, "percentage": 99.2, "elapsed_time": "0:07:05", "remaining_time": "0:00:03"}
+{"current_steps": 248, "total_steps": 249, "loss": 0.1335, "lr": 3.9795622158111945e-10, "epoch": 2.9879518072289155, "percentage": 99.6, "elapsed_time": "0:07:06", "remaining_time": "0:00:01"}
+{"current_steps": 249, "total_steps": 249, "loss": 0.0612, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:07:08", "remaining_time": "0:00:00"}
+{"current_steps": 249, "total_steps": 249, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:07:08", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1785 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 249,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012048192771084338,
+      "grad_norm": 40.75222396850586,
+      "learning_rate": 9.99960204377842e-06,
+      "loss": 0.8283,
+      "step": 1
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 7.6217546463012695,
+      "learning_rate": 9.99840823846134e-06,
+      "loss": 0.7463,
+      "step": 2
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 4.7737321853637695,
+      "learning_rate": 9.996418774081658e-06,
+      "loss": 0.6773,
+      "step": 3
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 7.380457401275635,
+      "learning_rate": 9.99363396732727e-06,
+      "loss": 0.7069,
+      "step": 4
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 6.07143497467041,
+      "learning_rate": 9.990054261490643e-06,
+      "loss": 0.8157,
+      "step": 5
+    },
+    {
+      "epoch": 0.07228915662650602,
+      "grad_norm": 32.628204345703125,
+      "learning_rate": 9.985680226398261e-06,
+      "loss": 0.7604,
+      "step": 6
+    },
+    {
+      "epoch": 0.08433734939759036,
+      "grad_norm": 7.0896759033203125,
+      "learning_rate": 9.980512558319915e-06,
+      "loss": 0.6947,
+      "step": 7
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 4.166346549987793,
+      "learning_rate": 9.974552079857873e-06,
+      "loss": 0.5901,
+      "step": 8
+    },
+    {
+      "epoch": 0.10843373493975904,
+      "grad_norm": 5.307025909423828,
+      "learning_rate": 9.967799739815925e-06,
+      "loss": 0.6768,
+      "step": 9
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 5.205200672149658,
+      "learning_rate": 9.960256613048367e-06,
+      "loss": 0.7401,
+      "step": 10
+    },
+    {
+      "epoch": 0.13253012048192772,
+      "grad_norm": 4.746809482574463,
+      "learning_rate": 9.951923900288888e-06,
+      "loss": 0.603,
+      "step": 11
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 4.554243087768555,
+      "learning_rate": 9.942802927959444e-06,
+      "loss": 0.5951,
+      "step": 12
+    },
+    {
+      "epoch": 0.1566265060240964,
+      "grad_norm": 4.13496732711792,
+      "learning_rate": 9.932895147959106e-06,
+      "loss": 0.6246,
+      "step": 13
+    },
+    {
+      "epoch": 0.1686746987951807,
+      "grad_norm": 5.653600692749023,
+      "learning_rate": 9.922202137432954e-06,
+      "loss": 0.8116,
+      "step": 14
+    },
+    {
+      "epoch": 0.18072289156626506,
+      "grad_norm": 4.084902286529541,
+      "learning_rate": 9.910725598521014e-06,
+      "loss": 0.5243,
+      "step": 15
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 4.84393835067749,
+      "learning_rate": 9.89846735808731e-06,
+      "loss": 0.5911,
+      "step": 16
+    },
+    {
+      "epoch": 0.20481927710843373,
+      "grad_norm": 3.5985801219940186,
+      "learning_rate": 9.885429367429062e-06,
+      "loss": 0.5873,
+      "step": 17
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 4.133760452270508,
+      "learning_rate": 9.871613701966067e-06,
+      "loss": 0.58,
+      "step": 18
+    },
+    {
+      "epoch": 0.2289156626506024,
+      "grad_norm": 5.736385345458984,
+      "learning_rate": 9.857022560910338e-06,
+      "loss": 0.6884,
+      "step": 19
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 5.400482177734375,
+      "learning_rate": 9.84165826691602e-06,
+      "loss": 0.7507,
+      "step": 20
+    },
+    {
+      "epoch": 0.25301204819277107,
+      "grad_norm": 3.2082321643829346,
+      "learning_rate": 9.825523265709667e-06,
+      "loss": 0.4539,
+      "step": 21
+    },
+    {
+      "epoch": 0.26506024096385544,
+      "grad_norm": 3.9605965614318848,
+      "learning_rate": 9.808620125700925e-06,
+      "loss": 0.5744,
+      "step": 22
+    },
+    {
+      "epoch": 0.27710843373493976,
+      "grad_norm": 3.652902603149414,
+      "learning_rate": 9.790951537573686e-06,
+      "loss": 0.4361,
+      "step": 23
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 3.5659713745117188,
+      "learning_rate": 9.772520313857777e-06,
+      "loss": 0.4565,
+      "step": 24
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "grad_norm": 5.866443157196045,
+      "learning_rate": 9.753329388481261e-06,
+      "loss": 0.6564,
+      "step": 25
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 5.043295383453369,
+      "learning_rate": 9.733381816303395e-06,
+      "loss": 0.5905,
+      "step": 26
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "grad_norm": 4.576389789581299,
+      "learning_rate": 9.712680772628365e-06,
+      "loss": 0.5458,
+      "step": 27
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 2.964594602584839,
+      "learning_rate": 9.691229552699817e-06,
+      "loss": 0.4196,
+      "step": 28
+    },
+    {
+      "epoch": 0.3493975903614458,
+      "grad_norm": 3.668825387954712,
+      "learning_rate": 9.669031571176322e-06,
+      "loss": 0.5939,
+      "step": 29
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 3.4135804176330566,
+      "learning_rate": 9.646090361587828e-06,
+      "loss": 0.4942,
+      "step": 30
+    },
+    {
+      "epoch": 0.37349397590361444,
+      "grad_norm": 3.3271186351776123,
+      "learning_rate": 9.622409575773162e-06,
+      "loss": 0.4447,
+      "step": 31
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 3.8561484813690186,
+      "learning_rate": 9.597992983298748e-06,
+      "loss": 0.5443,
+      "step": 32
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "grad_norm": 3.4959912300109863,
+      "learning_rate": 9.572844470858537e-06,
+      "loss": 0.5228,
+      "step": 33
+    },
+    {
+      "epoch": 0.40963855421686746,
+      "grad_norm": 4.416797637939453,
+      "learning_rate": 9.546968041655326e-06,
+      "loss": 0.5745,
+      "step": 34
+    },
+    {
+      "epoch": 0.42168674698795183,
+      "grad_norm": 3.1685950756073,
+      "learning_rate": 9.520367814763514e-06,
+      "loss": 0.5249,
+      "step": 35
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 3.5792479515075684,
+      "learning_rate": 9.493048024473413e-06,
+      "loss": 0.5533,
+      "step": 36
+    },
+    {
+      "epoch": 0.4457831325301205,
+      "grad_norm": 3.136587619781494,
+      "learning_rate": 9.46501301961723e-06,
+      "loss": 0.5707,
+      "step": 37
+    },
+    {
+      "epoch": 0.4578313253012048,
+      "grad_norm": 6.66333532333374,
+      "learning_rate": 9.436267262876808e-06,
+      "loss": 0.5537,
+      "step": 38
+    },
+    {
+      "epoch": 0.46987951807228917,
+      "grad_norm": 3.710054397583008,
+      "learning_rate": 9.406815330073244e-06,
+      "loss": 0.5072,
+      "step": 39
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 2.439741611480713,
+      "learning_rate": 9.376661909438496e-06,
+      "loss": 0.4088,
+      "step": 40
+    },
+    {
+      "epoch": 0.4939759036144578,
+      "grad_norm": 2.6984646320343018,
+      "learning_rate": 9.3458118008691e-06,
+      "loss": 0.548,
+      "step": 41
+    },
+    {
+      "epoch": 0.5060240963855421,
+      "grad_norm": 2.626049757003784,
+      "learning_rate": 9.314269915162115e-06,
+      "loss": 0.541,
+      "step": 42
+    },
+    {
+      "epoch": 0.5180722891566265,
+      "grad_norm": 31.189899444580078,
+      "learning_rate": 9.282041273233402e-06,
+      "loss": 0.5461,
+      "step": 43
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 4.356227397918701,
+      "learning_rate": 9.249131005318388e-06,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 10.281394958496094,
+      "learning_rate": 9.215544350155423e-06,
+      "loss": 0.6193,
+      "step": 45
+    },
+    {
+      "epoch": 0.5542168674698795,
+      "grad_norm": 81.10453796386719,
+      "learning_rate": 9.18128665415186e-06,
+      "loss": 0.4795,
+      "step": 46
+    },
+    {
+      "epoch": 0.5662650602409639,
+      "grad_norm": 136.2274932861328,
+      "learning_rate": 9.146363370533004e-06,
+      "loss": 0.5669,
+      "step": 47
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 24.73008155822754,
+      "learning_rate": 9.110780058474052e-06,
+      "loss": 0.4712,
+      "step": 48
+    },
+    {
+      "epoch": 0.5903614457831325,
+      "grad_norm": 3.0569868087768555,
+      "learning_rate": 9.07454238221517e-06,
+      "loss": 0.4934,
+      "step": 49
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 3.192237615585327,
+      "learning_rate": 9.03765611015985e-06,
+      "loss": 0.5427,
+      "step": 50
+    },
+    {
+      "epoch": 0.6144578313253012,
+      "grad_norm": 1.920320749282837,
+      "learning_rate": 9.000127113956673e-06,
+      "loss": 0.4182,
+      "step": 51
+    },
+    {
+      "epoch": 0.6265060240963856,
+      "grad_norm": 3.1197104454040527,
+      "learning_rate": 8.961961367564652e-06,
+      "loss": 0.5577,
+      "step": 52
+    },
+    {
+      "epoch": 0.6385542168674698,
+      "grad_norm": 2.1309397220611572,
+      "learning_rate": 8.923164946302274e-06,
+      "loss": 0.5111,
+      "step": 53
+    },
+    {
+      "epoch": 0.6506024096385542,
+      "grad_norm": 2.3042995929718018,
+      "learning_rate": 8.883744025880429e-06,
+      "loss": 0.5015,
+      "step": 54
+    },
+    {
+      "epoch": 0.6626506024096386,
+      "grad_norm": 2.4492433071136475,
+      "learning_rate": 8.843704881419333e-06,
+      "loss": 0.3826,
+      "step": 55
+    },
+    {
+      "epoch": 0.6746987951807228,
+      "grad_norm": 2.3031723499298096,
+      "learning_rate": 8.803053886449644e-06,
+      "loss": 0.4694,
+      "step": 56
+    },
+    {
+      "epoch": 0.6867469879518072,
+      "grad_norm": 3.1464896202087402,
+      "learning_rate": 8.761797511897907e-06,
+      "loss": 0.5708,
+      "step": 57
+    },
+    {
+      "epoch": 0.6987951807228916,
+      "grad_norm": 2.5254249572753906,
+      "learning_rate": 8.719942325056496e-06,
+      "loss": 0.5605,
+      "step": 58
+    },
+    {
+      "epoch": 0.7108433734939759,
+      "grad_norm": 2.614318370819092,
+      "learning_rate": 8.67749498853821e-06,
+      "loss": 0.5702,
+      "step": 59
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 2.1782386302948,
+      "learning_rate": 8.634462259215719e-06,
+      "loss": 0.5409,
+      "step": 60
+    },
+    {
+      "epoch": 0.7349397590361446,
+      "grad_norm": 2.084237813949585,
+      "learning_rate": 8.590850987145964e-06,
+      "loss": 0.4923,
+      "step": 61
+    },
+    {
+      "epoch": 0.7469879518072289,
+      "grad_norm": 2.4142396450042725,
+      "learning_rate": 8.546668114479769e-06,
+      "loss": 0.6142,
+      "step": 62
+    },
+    {
+      "epoch": 0.7590361445783133,
+      "grad_norm": 1.6900039911270142,
+      "learning_rate": 8.501920674356755e-06,
+      "loss": 0.4445,
+      "step": 63
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 1.9757111072540283,
+      "learning_rate": 8.456615789785804e-06,
+      "loss": 0.491,
+      "step": 64
+    },
+    {
+      "epoch": 0.7831325301204819,
+      "grad_norm": 2.328930139541626,
+      "learning_rate": 8.410760672511188e-06,
+      "loss": 0.5563,
+      "step": 65
+    },
+    {
+      "epoch": 0.7951807228915663,
+      "grad_norm": 2.8067822456359863,
+      "learning_rate": 8.364362621864595e-06,
+      "loss": 0.6574,
+      "step": 66
+    },
+    {
+      "epoch": 0.8072289156626506,
+      "grad_norm": 2.0766549110412598,
+      "learning_rate": 8.31742902360319e-06,
+      "loss": 0.5063,
+      "step": 67
+    },
+    {
+      "epoch": 0.8192771084337349,
+      "grad_norm": 2.085911989212036,
+      "learning_rate": 8.269967348733947e-06,
+      "loss": 0.5504,
+      "step": 68
+    },
+    {
+      "epoch": 0.8313253012048193,
+      "grad_norm": 1.8254350423812866,
+      "learning_rate": 8.221985152324385e-06,
+      "loss": 0.4678,
+      "step": 69
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 2.208496332168579,
+      "learning_rate": 8.17349007229994e-06,
+      "loss": 0.5589,
+      "step": 70
+    },
+    {
+      "epoch": 0.8554216867469879,
+      "grad_norm": 2.833843469619751,
+      "learning_rate": 8.124489828228136e-06,
+      "loss": 0.6464,
+      "step": 71
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 2.181140661239624,
+      "learning_rate": 8.07499222008977e-06,
+      "loss": 0.6037,
+      "step": 72
+    },
+    {
+      "epoch": 0.8795180722891566,
+      "grad_norm": 1.5879639387130737,
+      "learning_rate": 8.025005127037282e-06,
+      "loss": 0.4077,
+      "step": 73
+    },
+    {
+      "epoch": 0.891566265060241,
+      "grad_norm": 1.94895601272583,
+      "learning_rate": 7.974536506140546e-06,
+      "loss": 0.4523,
+      "step": 74
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 2.282900810241699,
+      "learning_rate": 7.923594391120237e-06,
+      "loss": 0.4889,
+      "step": 75
+    },
+    {
+      "epoch": 0.9156626506024096,
+      "grad_norm": 1.8225998878479004,
+      "learning_rate": 7.872186891068997e-06,
+      "loss": 0.4483,
+      "step": 76
+    },
+    {
+      "epoch": 0.927710843373494,
+      "grad_norm": 2.1921205520629883,
+      "learning_rate": 7.820322189160618e-06,
+      "loss": 0.4848,
+      "step": 77
+    },
+    {
+      "epoch": 0.9397590361445783,
+      "grad_norm": 1.9695558547973633,
+      "learning_rate": 7.768008541347423e-06,
+      "loss": 0.4577,
+      "step": 78
+    },
+    {
+      "epoch": 0.9518072289156626,
+      "grad_norm": 2.367926836013794,
+      "learning_rate": 7.715254275046062e-06,
+      "loss": 0.6004,
+      "step": 79
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 1.95900297164917,
+      "learning_rate": 7.66206778781193e-06,
+      "loss": 0.5161,
+      "step": 80
+    },
+    {
+      "epoch": 0.9759036144578314,
+      "grad_norm": 4.2675557136535645,
+      "learning_rate": 7.608457546002423e-06,
+      "loss": 0.4645,
+      "step": 81
+    },
+    {
+      "epoch": 0.9879518072289156,
+      "grad_norm": 2.129870891571045,
+      "learning_rate": 7.554432083429253e-06,
+      "loss": 0.5267,
+      "step": 82
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7695404291152954,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3909,
+      "step": 83
+    },
+    {
+      "epoch": 1.0120481927710843,
+      "grad_norm": 2.0876364707946777,
+      "learning_rate": 7.445169960349167e-06,
+      "loss": 0.3333,
+      "step": 84
+    },
+    {
+      "epoch": 1.0240963855421688,
+      "grad_norm": 1.5992554426193237,
+      "learning_rate": 7.389950692458916e-06,
+      "loss": 0.3103,
+      "step": 85
+    },
+    {
+      "epoch": 1.036144578313253,
+      "grad_norm": 2.081721544265747,
+      "learning_rate": 7.3343509862697295e-06,
+      "loss": 0.286,
+      "step": 86
+    },
+    {
+      "epoch": 1.0481927710843373,
+      "grad_norm": 1.5453327894210815,
+      "learning_rate": 7.278379692281209e-06,
+      "loss": 0.2851,
+      "step": 87
+    },
+    {
+      "epoch": 1.0602409638554218,
+      "grad_norm": 1.6960233449935913,
+      "learning_rate": 7.22204572014322e-06,
+      "loss": 0.3118,
+      "step": 88
+    },
+    {
+      "epoch": 1.072289156626506,
+      "grad_norm": 1.6961935758590698,
+      "learning_rate": 7.165358037237644e-06,
+      "loss": 0.3024,
+      "step": 89
+    },
+    {
+      "epoch": 1.0843373493975903,
+      "grad_norm": 1.9473631381988525,
+      "learning_rate": 7.10832566725092e-06,
+      "loss": 0.3262,
+      "step": 90
+    },
+    {
+      "epoch": 1.0963855421686748,
+      "grad_norm": 1.5019605159759521,
+      "learning_rate": 7.0509576887376375e-06,
+      "loss": 0.23,
+      "step": 91
+    },
+    {
+      "epoch": 1.108433734939759,
+      "grad_norm": 1.7088998556137085,
+      "learning_rate": 6.99326323367538e-06,
+      "loss": 0.2511,
+      "step": 92
+    },
+    {
+      "epoch": 1.1204819277108433,
+      "grad_norm": 2.8957417011260986,
+      "learning_rate": 6.9352514860110876e-06,
+      "loss": 0.3191,
+      "step": 93
+    },
+    {
+      "epoch": 1.1325301204819278,
+      "grad_norm": 1.71742844581604,
+      "learning_rate": 6.876931680199121e-06,
+      "loss": 0.2792,
+      "step": 94
+    },
+    {
+      "epoch": 1.144578313253012,
+      "grad_norm": 1.615378975868225,
+      "learning_rate": 6.818313099731308e-06,
+      "loss": 0.2653,
+      "step": 95
+    },
+    {
+      "epoch": 1.1566265060240963,
+      "grad_norm": 1.4427539110183716,
+      "learning_rate": 6.759405075659165e-06,
+      "loss": 0.2909,
+      "step": 96
+    },
+    {
+      "epoch": 1.1686746987951806,
+      "grad_norm": 1.1839165687561035,
+      "learning_rate": 6.700216985108568e-06,
+      "loss": 0.1959,
+      "step": 97
+    },
+    {
+      "epoch": 1.180722891566265,
+      "grad_norm": 1.7143460512161255,
+      "learning_rate": 6.640758249787067e-06,
+      "loss": 0.2841,
+      "step": 98
+    },
+    {
+      "epoch": 1.1927710843373494,
+      "grad_norm": 1.3873624801635742,
+      "learning_rate": 6.58103833448412e-06,
+      "loss": 0.2838,
+      "step": 99
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "grad_norm": 1.8592312335968018,
+      "learning_rate": 6.521066745564467e-06,
+      "loss": 0.2963,
+      "step": 100
+    },
+    {
+      "epoch": 1.216867469879518,
+      "grad_norm": 1.608494758605957,
+      "learning_rate": 6.460853029454879e-06,
+      "loss": 0.2877,
+      "step": 101
+    },
+    {
+      "epoch": 1.2289156626506024,
+      "grad_norm": 1.8831335306167603,
+      "learning_rate": 6.4004067711245366e-06,
+      "loss": 0.3066,
+      "step": 102
+    },
+    {
+      "epoch": 1.2409638554216866,
+      "grad_norm": 1.743905782699585,
+      "learning_rate": 6.3397375925592675e-06,
+      "loss": 0.3099,
+      "step": 103
+    },
+    {
+      "epoch": 1.2530120481927711,
+      "grad_norm": 1.8759677410125732,
+      "learning_rate": 6.2788551512299014e-06,
+      "loss": 0.2914,
+      "step": 104
+    },
+    {
+      "epoch": 1.2650602409638554,
+      "grad_norm": 1.7082366943359375,
+      "learning_rate": 6.2177691385549595e-06,
+      "loss": 0.2931,
+      "step": 105
+    },
+    {
+      "epoch": 1.2771084337349397,
+      "grad_norm": 1.519975185394287,
+      "learning_rate": 6.156489278357967e-06,
+      "loss": 0.2499,
+      "step": 106
+    },
+    {
+      "epoch": 1.2891566265060241,
+      "grad_norm": 1.8293309211730957,
+      "learning_rate": 6.0950253253195656e-06,
+      "loss": 0.3611,
+      "step": 107
+    },
+    {
+      "epoch": 1.3012048192771084,
+      "grad_norm": 1.728571891784668,
+      "learning_rate": 6.033387063424765e-06,
+      "loss": 0.3017,
+      "step": 108
+    },
+    {
+      "epoch": 1.3132530120481927,
+      "grad_norm": 1.6766902208328247,
+      "learning_rate": 5.971584304405489e-06,
+      "loss": 0.2823,
+      "step": 109
+    },
+    {
+      "epoch": 1.3253012048192772,
+      "grad_norm": 1.7143419981002808,
+      "learning_rate": 5.909626886178721e-06,
+      "loss": 0.2307,
+      "step": 110
+    },
+    {
+      "epoch": 1.3373493975903614,
+      "grad_norm": 1.5373152494430542,
+      "learning_rate": 5.8475246712804845e-06,
+      "loss": 0.2963,
+      "step": 111
+    },
+    {
+      "epoch": 1.3493975903614457,
+      "grad_norm": 1.8781455755233765,
+      "learning_rate": 5.785287545295895e-06,
+      "loss": 0.2874,
+      "step": 112
+    },
+    {
+      "epoch": 1.3614457831325302,
+      "grad_norm": 1.824504017829895,
+      "learning_rate": 5.722925415285555e-06,
+      "loss": 0.2454,
+      "step": 113
+    },
+    {
+      "epoch": 1.3734939759036144,
+      "grad_norm": 1.7806376218795776,
+      "learning_rate": 5.660448208208513e-06,
+      "loss": 0.3654,
+      "step": 114
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 1.5633933544158936,
+      "learning_rate": 5.597865869342075e-06,
+      "loss": 0.2931,
+      "step": 115
+    },
+    {
+      "epoch": 1.3975903614457832,
+      "grad_norm": 1.8875840902328491,
+      "learning_rate": 5.535188360698687e-06,
+      "loss": 0.331,
+      "step": 116
+    },
+    {
+      "epoch": 1.4096385542168675,
+      "grad_norm": 1.404435634613037,
+      "learning_rate": 5.472425659440157e-06,
+      "loss": 0.246,
+      "step": 117
+    },
+    {
+      "epoch": 1.4216867469879517,
+      "grad_norm": 1.4050829410552979,
+      "learning_rate": 5.409587756289462e-06,
+      "loss": 0.2689,
+      "step": 118
+    },
+    {
+      "epoch": 1.4337349397590362,
+      "grad_norm": 1.5876859426498413,
+      "learning_rate": 5.346684653940408e-06,
+      "loss": 0.2645,
+      "step": 119
+    },
+    {
+      "epoch": 1.4457831325301205,
+      "grad_norm": 1.6692218780517578,
+      "learning_rate": 5.2837263654653715e-06,
+      "loss": 0.3155,
+      "step": 120
+    },
+    {
+      "epoch": 1.4578313253012047,
+      "grad_norm": 1.2533305883407593,
+      "learning_rate": 5.2207229127213866e-06,
+      "loss": 0.2112,
+      "step": 121
+    },
+    {
+      "epoch": 1.4698795180722892,
+      "grad_norm": 1.5980626344680786,
+      "learning_rate": 5.157684324754858e-06,
+      "loss": 0.2441,
+      "step": 122
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": 1.6085745096206665,
+      "learning_rate": 5.094620636205096e-06,
+      "loss": 0.3087,
+      "step": 123
+    },
+    {
+      "epoch": 1.4939759036144578,
+      "grad_norm": 1.7097792625427246,
+      "learning_rate": 5.031541885706987e-06,
+      "loss": 0.2499,
+      "step": 124
+    },
+    {
+      "epoch": 1.5060240963855422,
+      "grad_norm": 1.4703900814056396,
+      "learning_rate": 4.9684581142930135e-06,
+      "loss": 0.2413,
+      "step": 125
+    },
+    {
+      "epoch": 1.5180722891566265,
+      "grad_norm": 2.3154144287109375,
+      "learning_rate": 4.905379363794907e-06,
+      "loss": 0.3701,
+      "step": 126
+    },
+    {
+      "epoch": 1.5301204819277108,
+      "grad_norm": 1.665852427482605,
+      "learning_rate": 4.842315675245144e-06,
+      "loss": 0.2791,
+      "step": 127
+    },
+    {
+      "epoch": 1.5421686746987953,
+      "grad_norm": 1.7872849702835083,
+      "learning_rate": 4.779277087278615e-06,
+      "loss": 0.3303,
+      "step": 128
+    },
+    {
+      "epoch": 1.5542168674698795,
+      "grad_norm": 1.4255069494247437,
+      "learning_rate": 4.71627363453463e-06,
+      "loss": 0.2462,
+      "step": 129
+    },
+    {
+      "epoch": 1.5662650602409638,
+      "grad_norm": 1.8723397254943848,
+      "learning_rate": 4.653315346059592e-06,
+      "loss": 0.3083,
+      "step": 130
+    },
+    {
+      "epoch": 1.5783132530120483,
+      "grad_norm": 1.6238393783569336,
+      "learning_rate": 4.5904122437105384e-06,
+      "loss": 0.2947,
+      "step": 131
+    },
+    {
+      "epoch": 1.5903614457831325,
+      "grad_norm": 1.5982369184494019,
+      "learning_rate": 4.527574340559844e-06,
+      "loss": 0.3114,
+      "step": 132
+    },
+    {
+      "epoch": 1.6024096385542168,
+      "grad_norm": 1.7584006786346436,
+      "learning_rate": 4.464811639301314e-06,
+      "loss": 0.3335,
+      "step": 133
+    },
+    {
+      "epoch": 1.6144578313253013,
+      "grad_norm": 1.7169082164764404,
+      "learning_rate": 4.402134130657925e-06,
+      "loss": 0.2783,
+      "step": 134
+    },
+    {
+      "epoch": 1.6265060240963856,
+      "grad_norm": 1.6119632720947266,
+      "learning_rate": 4.33955179179149e-06,
+      "loss": 0.252,
+      "step": 135
+    },
+    {
+      "epoch": 1.6385542168674698,
+      "grad_norm": 1.5756961107254028,
+      "learning_rate": 4.277074584714447e-06,
+      "loss": 0.2825,
+      "step": 136
+    },
+    {
+      "epoch": 1.6506024096385543,
+      "grad_norm": 1.511651873588562,
+      "learning_rate": 4.214712454704107e-06,
+      "loss": 0.2479,
+      "step": 137
+    },
+    {
+      "epoch": 1.6626506024096386,
+      "grad_norm": 1.354615330696106,
+      "learning_rate": 4.152475328719517e-06,
+      "loss": 0.2192,
+      "step": 138
+    },
+    {
+      "epoch": 1.6746987951807228,
+      "grad_norm": 1.821956753730774,
+      "learning_rate": 4.090373113821281e-06,
+      "loss": 0.2735,
+      "step": 139
+    },
+    {
+      "epoch": 1.6867469879518073,
+      "grad_norm": 1.4524273872375488,
+      "learning_rate": 4.028415695594512e-06,
+      "loss": 0.2222,
+      "step": 140
+    },
+    {
+      "epoch": 1.6987951807228916,
+      "grad_norm": 1.6997952461242676,
+      "learning_rate": 3.966612936575235e-06,
+      "loss": 0.2841,
+      "step": 141
+    },
+    {
+      "epoch": 1.7108433734939759,
+      "grad_norm": 1.5502634048461914,
+      "learning_rate": 3.904974674680436e-06,
+      "loss": 0.281,
+      "step": 142
+    },
+    {
+      "epoch": 1.7228915662650603,
+      "grad_norm": 1.6944836378097534,
+      "learning_rate": 3.843510721642036e-06,
+      "loss": 0.19,
+      "step": 143
+    },
+    {
+      "epoch": 1.7349397590361446,
+      "grad_norm": 1.958292007446289,
+      "learning_rate": 3.782230861445041e-06,
+      "loss": 0.3143,
+      "step": 144
+    },
+    {
+      "epoch": 1.7469879518072289,
+      "grad_norm": 1.9379884004592896,
+      "learning_rate": 3.7211448487701002e-06,
+      "loss": 0.2964,
+      "step": 145
+    },
+    {
+      "epoch": 1.7590361445783134,
+      "grad_norm": 1.6362128257751465,
+      "learning_rate": 3.6602624074407354e-06,
+      "loss": 0.2749,
+      "step": 146
+    },
+    {
+      "epoch": 1.7710843373493976,
+      "grad_norm": 1.740090250968933,
+      "learning_rate": 3.5995932288754655e-06,
+      "loss": 0.2572,
+      "step": 147
+    },
+    {
+      "epoch": 1.783132530120482,
+      "grad_norm": 1.3941646814346313,
+      "learning_rate": 3.539146970545124e-06,
+      "loss": 0.2476,
+      "step": 148
+    },
+    {
+      "epoch": 1.7951807228915664,
+      "grad_norm": 1.6419267654418945,
+      "learning_rate": 3.478933254435534e-06,
+      "loss": 0.2902,
+      "step": 149
+    },
+    {
+      "epoch": 1.8072289156626506,
+      "grad_norm": 1.825861930847168,
+      "learning_rate": 3.4189616655158803e-06,
+      "loss": 0.3345,
+      "step": 150
+    },
+    {
+      "epoch": 1.819277108433735,
+      "grad_norm": 1.749080777168274,
+      "learning_rate": 3.359241750212934e-06,
+      "loss": 0.314,
+      "step": 151
+    },
+    {
+      "epoch": 1.8313253012048194,
+      "grad_norm": 1.2390449047088623,
+      "learning_rate": 3.2997830148914316e-06,
+      "loss": 0.214,
+      "step": 152
+    },
+    {
+      "epoch": 1.8433734939759037,
+      "grad_norm": 1.6753946542739868,
+      "learning_rate": 3.240594924340835e-06,
+      "loss": 0.2988,
+      "step": 153
+    },
+    {
+      "epoch": 1.855421686746988,
+      "grad_norm": 1.6091383695602417,
+      "learning_rate": 3.181686900268694e-06,
+      "loss": 0.2481,
+      "step": 154
+    },
+    {
+      "epoch": 1.8674698795180724,
+      "grad_norm": 1.438892126083374,
+      "learning_rate": 3.1230683198008817e-06,
+      "loss": 0.2702,
+      "step": 155
+    },
+    {
+      "epoch": 1.8795180722891565,
+      "grad_norm": 1.931443691253662,
+      "learning_rate": 3.0647485139889145e-06,
+      "loss": 0.2957,
+      "step": 156
+    },
+    {
+      "epoch": 1.891566265060241,
+      "grad_norm": 1.5713204145431519,
+      "learning_rate": 3.006736766324623e-06,
+      "loss": 0.2815,
+      "step": 157
+    },
+    {
+      "epoch": 1.9036144578313254,
+      "grad_norm": 1.5962169170379639,
+      "learning_rate": 2.9490423112623646e-06,
+      "loss": 0.2791,
+      "step": 158
+    },
+    {
+      "epoch": 1.9156626506024095,
+      "grad_norm": 2.0020360946655273,
+      "learning_rate": 2.89167433274908e-06,
+      "loss": 0.3897,
+      "step": 159
+    },
+    {
+      "epoch": 1.927710843373494,
+      "grad_norm": 1.6599327325820923,
+      "learning_rate": 2.834641962762358e-06,
+      "loss": 0.2742,
+      "step": 160
+    },
+    {
+      "epoch": 1.9397590361445785,
+      "grad_norm": 1.6006088256835938,
+      "learning_rate": 2.7779542798567804e-06,
+      "loss": 0.2678,
+      "step": 161
+    },
+    {
+      "epoch": 1.9518072289156625,
+      "grad_norm": 1.5215158462524414,
+      "learning_rate": 2.721620307718793e-06,
+      "loss": 0.3035,
+      "step": 162
+    },
+    {
+      "epoch": 1.963855421686747,
+      "grad_norm": 1.8756093978881836,
+      "learning_rate": 2.66564901373027e-06,
+      "loss": 0.3407,
+      "step": 163
+    },
+    {
+      "epoch": 1.9759036144578315,
+      "grad_norm": 1.5014938116073608,
+      "learning_rate": 2.610049307541085e-06,
+      "loss": 0.2533,
+      "step": 164
+    },
+    {
+      "epoch": 1.9879518072289155,
+      "grad_norm": 1.6140003204345703,
+      "learning_rate": 2.554830039650834e-06,
+      "loss": 0.2369,
+      "step": 165
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5059895515441895,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1612,
+      "step": 166
+    },
+    {
+      "epoch": 2.0120481927710845,
+      "grad_norm": 1.2760642766952515,
+      "learning_rate": 2.4455679165707473e-06,
+      "loss": 0.1247,
+      "step": 167
+    },
+    {
+      "epoch": 2.0240963855421685,
+      "grad_norm": 1.3720568418502808,
+      "learning_rate": 2.391542453997578e-06,
+      "loss": 0.1618,
+      "step": 168
+    },
+    {
+      "epoch": 2.036144578313253,
+      "grad_norm": 1.4044466018676758,
+      "learning_rate": 2.337932212188073e-06,
+      "loss": 0.1427,
+      "step": 169
+    },
+    {
+      "epoch": 2.0481927710843375,
+      "grad_norm": 1.2212741374969482,
+      "learning_rate": 2.284745724953939e-06,
+      "loss": 0.1587,
+      "step": 170
+    },
+    {
+      "epoch": 2.0602409638554215,
+      "grad_norm": 1.1166741847991943,
+      "learning_rate": 2.2319914586525776e-06,
+      "loss": 0.1169,
+      "step": 171
+    },
+    {
+      "epoch": 2.072289156626506,
+      "grad_norm": 1.2007352113723755,
+      "learning_rate": 2.1796778108393824e-06,
+      "loss": 0.1232,
+      "step": 172
+    },
+    {
+      "epoch": 2.0843373493975905,
+      "grad_norm": 1.4228880405426025,
+      "learning_rate": 2.127813108931007e-06,
+      "loss": 0.1646,
+      "step": 173
+    },
+    {
+      "epoch": 2.0963855421686746,
+      "grad_norm": 1.2214866876602173,
+      "learning_rate": 2.0764056088797646e-06,
+      "loss": 0.1058,
+      "step": 174
+    },
+    {
+      "epoch": 2.108433734939759,
+      "grad_norm": 1.8072195053100586,
+      "learning_rate": 2.0254634938594555e-06,
+      "loss": 0.1579,
+      "step": 175
+    },
+    {
+      "epoch": 2.1204819277108435,
+      "grad_norm": 1.872309684753418,
+      "learning_rate": 1.9749948729627188e-06,
+      "loss": 0.138,
+      "step": 176
+    },
+    {
+      "epoch": 2.1325301204819276,
+      "grad_norm": 1.8318668603897095,
+      "learning_rate": 1.9250077799102323e-06,
+      "loss": 0.1331,
+      "step": 177
+    },
+    {
+      "epoch": 2.144578313253012,
+      "grad_norm": 2.1385316848754883,
+      "learning_rate": 1.875510171771865e-06,
+      "loss": 0.1635,
+      "step": 178
+    },
+    {
+      "epoch": 2.1566265060240966,
+      "grad_norm": 1.719831943511963,
+      "learning_rate": 1.8265099277000614e-06,
+      "loss": 0.1561,
+      "step": 179
+    },
+    {
+      "epoch": 2.1686746987951806,
+      "grad_norm": 1.7940328121185303,
+      "learning_rate": 1.7780148476756148e-06,
+      "loss": 0.14,
+      "step": 180
+    },
+    {
+      "epoch": 2.180722891566265,
+      "grad_norm": 1.3721911907196045,
+      "learning_rate": 1.7300326512660542e-06,
+      "loss": 0.1233,
+      "step": 181
+    },
+    {
+      "epoch": 2.1927710843373496,
+      "grad_norm": 1.2797173261642456,
+      "learning_rate": 1.6825709763968112e-06,
+      "loss": 0.0936,
+      "step": 182
+    },
+    {
+      "epoch": 2.2048192771084336,
+      "grad_norm": 1.5839323997497559,
+      "learning_rate": 1.6356373781354058e-06,
+      "loss": 0.1648,
+      "step": 183
+    },
+    {
+      "epoch": 2.216867469879518,
+      "grad_norm": 1.3700120449066162,
+      "learning_rate": 1.589239327488812e-06,
+      "loss": 0.126,
+      "step": 184
+    },
+    {
+      "epoch": 2.2289156626506026,
+      "grad_norm": 1.5171151161193848,
+      "learning_rate": 1.543384210214196e-06,
+      "loss": 0.1212,
+      "step": 185
+    },
+    {
+      "epoch": 2.2409638554216866,
+      "grad_norm": 1.6373289823532104,
+      "learning_rate": 1.4980793256432474e-06,
+      "loss": 0.1509,
+      "step": 186
+    },
+    {
+      "epoch": 2.253012048192771,
+      "grad_norm": 1.30360746383667,
+      "learning_rate": 1.453331885520234e-06,
+      "loss": 0.12,
+      "step": 187
+    },
+    {
+      "epoch": 2.2650602409638556,
+      "grad_norm": 1.395431399345398,
+      "learning_rate": 1.4091490128540374e-06,
+      "loss": 0.1406,
+      "step": 188
+    },
+    {
+      "epoch": 2.2771084337349397,
+      "grad_norm": 1.3656375408172607,
+      "learning_rate": 1.3655377407842813e-06,
+      "loss": 0.1706,
+      "step": 189
+    },
+    {
+      "epoch": 2.289156626506024,
+      "grad_norm": 1.189477562904358,
+      "learning_rate": 1.32250501146179e-06,
+      "loss": 0.1243,
+      "step": 190
+    },
+    {
+      "epoch": 2.3012048192771086,
+      "grad_norm": 1.273803949356079,
+      "learning_rate": 1.2800576749435068e-06,
+      "loss": 0.1132,
+      "step": 191
+    },
+    {
+      "epoch": 2.3132530120481927,
+      "grad_norm": 1.249987244606018,
+      "learning_rate": 1.2382024881020937e-06,
+      "loss": 0.133,
+      "step": 192
+    },
+    {
+      "epoch": 2.325301204819277,
+      "grad_norm": 1.2117363214492798,
+      "learning_rate": 1.1969461135503573e-06,
+      "loss": 0.1153,
+      "step": 193
+    },
+    {
+      "epoch": 2.337349397590361,
+      "grad_norm": 1.115524172782898,
+      "learning_rate": 1.1562951185806675e-06,
+      "loss": 0.1068,
+      "step": 194
+    },
+    {
+      "epoch": 2.3493975903614457,
+      "grad_norm": 1.2410939931869507,
+      "learning_rate": 1.1162559741195733e-06,
+      "loss": 0.0926,
+      "step": 195
+    },
+    {
+      "epoch": 2.36144578313253,
+      "grad_norm": 1.0989357233047485,
+      "learning_rate": 1.076835053697728e-06,
+      "loss": 0.1147,
+      "step": 196
+    },
+    {
+      "epoch": 2.3734939759036147,
+      "grad_norm": 1.2773900032043457,
+      "learning_rate": 1.0380386324353508e-06,
+      "loss": 0.131,
+      "step": 197
+    },
+    {
+      "epoch": 2.3855421686746987,
+      "grad_norm": 1.2643158435821533,
+      "learning_rate": 9.998728860433277e-07,
+      "loss": 0.1377,
+      "step": 198
+    },
+    {
+      "epoch": 2.397590361445783,
+      "grad_norm": 1.3157423734664917,
+      "learning_rate": 9.62343889840151e-07,
+      "loss": 0.127,
+      "step": 199
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "grad_norm": 1.1823986768722534,
+      "learning_rate": 9.254576177848313e-07,
+      "loss": 0.1039,
+      "step": 200
+    },
+    {
+      "epoch": 2.4216867469879517,
+      "grad_norm": 1.2062366008758545,
+      "learning_rate": 8.892199415259501e-07,
+      "loss": 0.1137,
+      "step": 201
+    },
+    {
+      "epoch": 2.433734939759036,
+      "grad_norm": 1.358426570892334,
+      "learning_rate": 8.536366294669979e-07,
+      "loss": 0.1188,
+      "step": 202
+    },
+    {
+      "epoch": 2.4457831325301207,
+      "grad_norm": 1.4414290189743042,
+      "learning_rate": 8.187133458481416e-07,
+      "loss": 0.1393,
+      "step": 203
+    },
+    {
+      "epoch": 2.4578313253012047,
+      "grad_norm": 1.2111995220184326,
+      "learning_rate": 7.844556498445788e-07,
+      "loss": 0.1088,
+      "step": 204
+    },
+    {
+      "epoch": 2.4698795180722892,
+      "grad_norm": 1.0797122716903687,
+      "learning_rate": 7.508689946816128e-07,
+      "loss": 0.1012,
+      "step": 205
+    },
+    {
+      "epoch": 2.4819277108433733,
+      "grad_norm": 1.2910206317901611,
+      "learning_rate": 7.179587267665999e-07,
+      "loss": 0.1283,
+      "step": 206
+    },
+    {
+      "epoch": 2.4939759036144578,
+      "grad_norm": 1.76227867603302,
+      "learning_rate": 6.857300848378857e-07,
+      "loss": 0.1773,
+      "step": 207
+    },
+    {
+      "epoch": 2.5060240963855422,
+      "grad_norm": 1.2892178297042847,
+      "learning_rate": 6.541881991309013e-07,
+      "loss": 0.1003,
+      "step": 208
+    },
+    {
+      "epoch": 2.5180722891566267,
+      "grad_norm": 1.2142372131347656,
+      "learning_rate": 6.233380905615049e-07,
+      "loss": 0.1059,
+      "step": 209
+    },
+    {
+      "epoch": 2.5301204819277108,
+      "grad_norm": 1.3028932809829712,
+      "learning_rate": 5.931846699267558e-07,
+      "loss": 0.0997,
+      "step": 210
+    },
+    {
+      "epoch": 2.5421686746987953,
+      "grad_norm": 1.2703701257705688,
+      "learning_rate": 5.637327371231921e-07,
+      "loss": 0.1074,
+      "step": 211
+    },
+    {
+      "epoch": 2.5542168674698793,
+      "grad_norm": 1.6055101156234741,
+      "learning_rate": 5.349869803827717e-07,
+      "loss": 0.1635,
+      "step": 212
+    },
+    {
+      "epoch": 2.566265060240964,
+      "grad_norm": 1.2764710187911987,
+      "learning_rate": 5.0695197552659e-07,
+      "loss": 0.1394,
+      "step": 213
+    },
+    {
+      "epoch": 2.5783132530120483,
+      "grad_norm": 1.3518632650375366,
+      "learning_rate": 4.796321852364877e-07,
+      "loss": 0.1363,
+      "step": 214
+    },
+    {
+      "epoch": 2.5903614457831328,
+      "grad_norm": 1.3571412563323975,
+      "learning_rate": 4.5303195834467463e-07,
+      "loss": 0.1326,
+      "step": 215
+    },
+    {
+      "epoch": 2.602409638554217,
+      "grad_norm": 1.4019449949264526,
+      "learning_rate": 4.271555291414636e-07,
+      "loss": 0.1222,
+      "step": 216
+    },
+    {
+      "epoch": 2.6144578313253013,
+      "grad_norm": 1.184061050415039,
+      "learning_rate": 4.020070167012541e-07,
+      "loss": 0.0845,
+      "step": 217
+    },
+    {
+      "epoch": 2.6265060240963853,
+      "grad_norm": 1.5907222032546997,
+      "learning_rate": 3.775904242268391e-07,
+      "loss": 0.1353,
+      "step": 218
+    },
+    {
+      "epoch": 2.63855421686747,
+      "grad_norm": 1.3479151725769043,
+      "learning_rate": 3.539096384121743e-07,
+      "loss": 0.1445,
+      "step": 219
+    },
+    {
+      "epoch": 2.6506024096385543,
+      "grad_norm": 1.36601722240448,
+      "learning_rate": 3.309684288236775e-07,
+      "loss": 0.1386,
+      "step": 220
+    },
+    {
+      "epoch": 2.662650602409639,
+      "grad_norm": 1.6582006216049194,
+      "learning_rate": 3.0877044730018515e-07,
+      "loss": 0.1237,
+      "step": 221
+    },
+    {
+      "epoch": 2.674698795180723,
+      "grad_norm": 1.505927324295044,
+      "learning_rate": 2.873192273716369e-07,
+      "loss": 0.153,
+      "step": 222
+    },
+    {
+      "epoch": 2.6867469879518073,
+      "grad_norm": 1.2739795446395874,
+      "learning_rate": 2.666181836966053e-07,
+      "loss": 0.1038,
+      "step": 223
+    },
+    {
+      "epoch": 2.6987951807228914,
+      "grad_norm": 1.3373569250106812,
+      "learning_rate": 2.466706115187406e-07,
+      "loss": 0.1208,
+      "step": 224
+    },
+    {
+      "epoch": 2.710843373493976,
+      "grad_norm": 1.3513188362121582,
+      "learning_rate": 2.274796861422246e-07,
+      "loss": 0.1209,
+      "step": 225
+    },
+    {
+      "epoch": 2.7228915662650603,
+      "grad_norm": 1.4020378589630127,
+      "learning_rate": 2.090484624263167e-07,
+      "loss": 0.1323,
+      "step": 226
+    },
+    {
+      "epoch": 2.734939759036145,
+      "grad_norm": 1.4146372079849243,
+      "learning_rate": 1.9137987429907635e-07,
+      "loss": 0.1304,
+      "step": 227
+    },
+    {
+      "epoch": 2.746987951807229,
+      "grad_norm": 1.3225347995758057,
+      "learning_rate": 1.7447673429033361e-07,
+      "loss": 0.1149,
+      "step": 228
+    },
+    {
+      "epoch": 2.7590361445783134,
+      "grad_norm": 1.3890403509140015,
+      "learning_rate": 1.583417330839798e-07,
+      "loss": 0.1557,
+      "step": 229
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 1.466339349746704,
+      "learning_rate": 1.4297743908966212e-07,
+      "loss": 0.1489,
+      "step": 230
+    },
+    {
+      "epoch": 2.783132530120482,
+      "grad_norm": 1.2367849349975586,
+      "learning_rate": 1.2838629803393343e-07,
+      "loss": 0.0997,
+      "step": 231
+    },
+    {
+      "epoch": 2.7951807228915664,
+      "grad_norm": 1.390717625617981,
+      "learning_rate": 1.1457063257093892e-07,
+      "loss": 0.1218,
+      "step": 232
+    },
+    {
+      "epoch": 2.807228915662651,
+      "grad_norm": 1.2239187955856323,
+      "learning_rate": 1.0153264191269052e-07,
+      "loss": 0.1135,
+      "step": 233
+    },
+    {
+      "epoch": 2.819277108433735,
+      "grad_norm": 1.0472311973571777,
+      "learning_rate": 8.927440147898703e-08,
+      "loss": 0.1065,
+      "step": 234
+    },
+    {
+      "epoch": 2.8313253012048194,
+      "grad_norm": 1.2322300672531128,
+      "learning_rate": 7.779786256704669e-08,
+      "loss": 0.1016,
+      "step": 235
+    },
+    {
+      "epoch": 2.8433734939759034,
+      "grad_norm": 1.3203635215759277,
+      "learning_rate": 6.710485204089456e-08,
+      "loss": 0.1239,
+      "step": 236
+    },
+    {
+      "epoch": 2.855421686746988,
+      "grad_norm": 1.2621276378631592,
+      "learning_rate": 5.7197072040557356e-08,
+      "loss": 0.1358,
+      "step": 237
+    },
+    {
+      "epoch": 2.8674698795180724,
+      "grad_norm": 1.3743759393692017,
+      "learning_rate": 4.807609971111238e-08,
+      "loss": 0.1337,
+      "step": 238
+    },
+    {
+      "epoch": 2.8795180722891565,
+      "grad_norm": 1.0450865030288696,
+      "learning_rate": 3.974338695163393e-08,
+      "loss": 0.0945,
+      "step": 239
+    },
+    {
+      "epoch": 2.891566265060241,
+      "grad_norm": 1.5270490646362305,
+      "learning_rate": 3.220026018407541e-08,
+      "loss": 0.0994,
+      "step": 240
+    },
+    {
+      "epoch": 2.9036144578313254,
+      "grad_norm": 1.694990873336792,
+      "learning_rate": 2.5447920142128712e-08,
+      "loss": 0.1689,
+      "step": 241
+    },
+    {
+      "epoch": 2.9156626506024095,
+      "grad_norm": 1.4968199729919434,
+      "learning_rate": 1.9487441680084983e-08,
+      "loss": 0.1219,
+      "step": 242
+    },
+    {
+      "epoch": 2.927710843373494,
+      "grad_norm": 1.332356572151184,
+      "learning_rate": 1.431977360173975e-08,
+      "loss": 0.1137,
+      "step": 243
+    },
+    {
+      "epoch": 2.9397590361445785,
+      "grad_norm": 1.4295134544372559,
+      "learning_rate": 9.945738509358205e-09,
+      "loss": 0.1498,
+      "step": 244
+    },
+    {
+      "epoch": 2.9518072289156625,
+      "grad_norm": 1.1830252408981323,
+      "learning_rate": 6.366032672731059e-09,
+      "loss": 0.1002,
+      "step": 245
+    },
+    {
+      "epoch": 2.963855421686747,
+      "grad_norm": 1.3982295989990234,
+      "learning_rate": 3.5812259183426457e-09,
+      "loss": 0.1247,
+      "step": 246
+    },
+    {
+      "epoch": 2.9759036144578315,
+      "grad_norm": 1.467788577079773,
+      "learning_rate": 1.591761538662362e-09,
+      "loss": 0.1098,
+      "step": 247
+    },
+    {
+      "epoch": 2.9879518072289155,
+      "grad_norm": 1.2710858583450317,
+      "learning_rate": 3.9795622158111945e-10,
+      "loss": 0.1335,
+      "step": 248
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9258020520210266,
+      "learning_rate": 0.0,
+      "loss": 0.0612,
+      "step": 249
+    },
+    {
+      "epoch": 3.0,
+      "step": 249,
+      "total_flos": 3.4614492313052774e+17,
+      "train_loss": 0.32225324711706266,
+      "train_runtime": 433.6826,
+      "train_samples_per_second": 4.545,
+      "train_steps_per_second": 0.574
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 249,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4614492313052774e+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:d23e6c125b24faccdc5404f2f7f53b94d8b311e91f98dbeb1d386e98e44edd9e
+size 7096