Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9867256637168142,
+    "total_flos": 7.721927725170033e+17,
+    "train_loss": 0.7663452034526401,
+    "train_runtime": 7882.5173,
+    "train_samples_per_second": 2.745,
+    "train_steps_per_second": 0.029
+}

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fd3fe061ac6f1a27efe547a5d39af69c88b5c99ffc46c038057034b20a48d6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e0b924807decedb30818e097901859ca1a14ccfba9e000e006c8f720711417
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce1041378a4518f22afe541b9da3df2799433a0ea8c1a54385ad5fc8e7d7356
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099ef09a5c3410266b3dae1bb57a4d61ab40c04860908c65b603e19bd6a4036c
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9867256637168142,
+    "total_flos": 7.721927725170033e+17,
+    "train_loss": 0.7663452034526401,
+    "train_runtime": 7882.5173,
+    "train_samples_per_second": 2.745,
+    "train_steps_per_second": 0.029
+}

trainer_log.jsonl

@@ -0,0 +1,226 @@
+{"current_steps": 1, "total_steps": 225, "loss": 1.2083, "lr": 4.347826086956522e-07, "epoch": 0.01327433628318584, "percentage": 0.44, "elapsed_time": "0:00:58", "remaining_time": "3:38:17"}
+{"current_steps": 2, "total_steps": 225, "loss": 1.2329, "lr": 8.695652173913044e-07, "epoch": 0.02654867256637168, "percentage": 0.89, "elapsed_time": "0:01:32", "remaining_time": "2:52:06"}
+{"current_steps": 3, "total_steps": 225, "loss": 1.2323, "lr": 1.3043478260869566e-06, "epoch": 0.03982300884955752, "percentage": 1.33, "elapsed_time": "0:02:06", "remaining_time": "2:36:17"}
+{"current_steps": 4, "total_steps": 225, "loss": 1.1988, "lr": 1.7391304347826088e-06, "epoch": 0.05309734513274336, "percentage": 1.78, "elapsed_time": "0:02:40", "remaining_time": "2:28:11"}
+{"current_steps": 5, "total_steps": 225, "loss": 1.2046, "lr": 2.173913043478261e-06, "epoch": 0.06637168141592921, "percentage": 2.22, "elapsed_time": "0:03:15", "remaining_time": "2:23:06"}
+{"current_steps": 6, "total_steps": 225, "loss": 1.1353, "lr": 2.6086956521739132e-06, "epoch": 0.07964601769911504, "percentage": 2.67, "elapsed_time": "0:03:49", "remaining_time": "2:19:29"}
+{"current_steps": 7, "total_steps": 225, "loss": 1.1348, "lr": 3.043478260869566e-06, "epoch": 0.09292035398230089, "percentage": 3.11, "elapsed_time": "0:04:23", "remaining_time": "2:16:45"}
+{"current_steps": 8, "total_steps": 225, "loss": 1.0683, "lr": 3.4782608695652175e-06, "epoch": 0.10619469026548672, "percentage": 3.56, "elapsed_time": "0:04:57", "remaining_time": "2:14:38"}
+{"current_steps": 9, "total_steps": 225, "loss": 1.0536, "lr": 3.91304347826087e-06, "epoch": 0.11946902654867257, "percentage": 4.0, "elapsed_time": "0:05:32", "remaining_time": "2:12:48"}
+{"current_steps": 10, "total_steps": 225, "loss": 1.0506, "lr": 4.347826086956522e-06, "epoch": 0.13274336283185842, "percentage": 4.44, "elapsed_time": "0:06:06", "remaining_time": "2:11:13"}
+{"current_steps": 11, "total_steps": 225, "loss": 1.0238, "lr": 4.782608695652174e-06, "epoch": 0.14601769911504425, "percentage": 4.89, "elapsed_time": "0:06:40", "remaining_time": "2:09:48"}
+{"current_steps": 12, "total_steps": 225, "loss": 1.0412, "lr": 5.2173913043478265e-06, "epoch": 0.1592920353982301, "percentage": 5.33, "elapsed_time": "0:07:14", "remaining_time": "2:08:32"}
+{"current_steps": 13, "total_steps": 225, "loss": 1.0377, "lr": 5.652173913043479e-06, "epoch": 0.17256637168141592, "percentage": 5.78, "elapsed_time": "0:07:48", "remaining_time": "2:07:23"}
+{"current_steps": 14, "total_steps": 225, "loss": 0.9789, "lr": 6.086956521739132e-06, "epoch": 0.18584070796460178, "percentage": 6.22, "elapsed_time": "0:08:22", "remaining_time": "2:06:18"}
+{"current_steps": 15, "total_steps": 225, "loss": 0.9534, "lr": 6.521739130434783e-06, "epoch": 0.19911504424778761, "percentage": 6.67, "elapsed_time": "0:08:56", "remaining_time": "2:05:17"}
+{"current_steps": 16, "total_steps": 225, "loss": 0.9418, "lr": 6.956521739130435e-06, "epoch": 0.21238938053097345, "percentage": 7.11, "elapsed_time": "0:09:31", "remaining_time": "2:04:20"}
+{"current_steps": 17, "total_steps": 225, "loss": 0.951, "lr": 7.391304347826087e-06, "epoch": 0.22566371681415928, "percentage": 7.56, "elapsed_time": "0:10:05", "remaining_time": "2:03:26"}
+{"current_steps": 18, "total_steps": 225, "loss": 0.9296, "lr": 7.82608695652174e-06, "epoch": 0.23893805309734514, "percentage": 8.0, "elapsed_time": "0:10:39", "remaining_time": "2:02:33"}
+{"current_steps": 19, "total_steps": 225, "loss": 0.9174, "lr": 8.260869565217392e-06, "epoch": 0.252212389380531, "percentage": 8.44, "elapsed_time": "0:11:13", "remaining_time": "2:01:43"}
+{"current_steps": 20, "total_steps": 225, "loss": 0.8893, "lr": 8.695652173913044e-06, "epoch": 0.26548672566371684, "percentage": 8.89, "elapsed_time": "0:11:47", "remaining_time": "2:00:54"}
+{"current_steps": 21, "total_steps": 225, "loss": 0.8833, "lr": 9.130434782608697e-06, "epoch": 0.27876106194690264, "percentage": 9.33, "elapsed_time": "0:12:21", "remaining_time": "2:00:06"}
+{"current_steps": 22, "total_steps": 225, "loss": 0.8773, "lr": 9.565217391304349e-06, "epoch": 0.2920353982300885, "percentage": 9.78, "elapsed_time": "0:12:56", "remaining_time": "1:59:21"}
+{"current_steps": 23, "total_steps": 225, "loss": 0.8674, "lr": 1e-05, "epoch": 0.3053097345132743, "percentage": 10.22, "elapsed_time": "0:13:30", "remaining_time": "1:58:36"}
+{"current_steps": 24, "total_steps": 225, "loss": 0.8848, "lr": 9.999395316300748e-06, "epoch": 0.3185840707964602, "percentage": 10.67, "elapsed_time": "0:14:04", "remaining_time": "1:57:52"}
+{"current_steps": 25, "total_steps": 225, "loss": 0.8717, "lr": 9.99758141145994e-06, "epoch": 0.33185840707964603, "percentage": 11.11, "elapsed_time": "0:14:38", "remaining_time": "1:57:09"}
+{"current_steps": 26, "total_steps": 225, "loss": 0.8578, "lr": 9.994558724213056e-06, "epoch": 0.34513274336283184, "percentage": 11.56, "elapsed_time": "0:15:12", "remaining_time": "1:56:27"}
+{"current_steps": 27, "total_steps": 225, "loss": 0.8576, "lr": 9.990327985667972e-06, "epoch": 0.3584070796460177, "percentage": 12.0, "elapsed_time": "0:15:47", "remaining_time": "1:55:45"}
+{"current_steps": 28, "total_steps": 225, "loss": 0.861, "lr": 9.984890219128148e-06, "epoch": 0.37168141592920356, "percentage": 12.44, "elapsed_time": "0:16:21", "remaining_time": "1:55:04"}
+{"current_steps": 29, "total_steps": 225, "loss": 0.8376, "lr": 9.978246739845095e-06, "epoch": 0.38495575221238937, "percentage": 12.89, "elapsed_time": "0:16:55", "remaining_time": "1:54:23"}
+{"current_steps": 30, "total_steps": 225, "loss": 0.8358, "lr": 9.970399154700264e-06, "epoch": 0.39823008849557523, "percentage": 13.33, "elapsed_time": "0:17:29", "remaining_time": "1:53:42"}
+{"current_steps": 31, "total_steps": 225, "loss": 0.8266, "lr": 9.961349361816384e-06, "epoch": 0.41150442477876104, "percentage": 13.78, "elapsed_time": "0:18:03", "remaining_time": "1:53:02"}
+{"current_steps": 32, "total_steps": 225, "loss": 0.8271, "lr": 9.951099550098349e-06, "epoch": 0.4247787610619469, "percentage": 14.22, "elapsed_time": "0:18:38", "remaining_time": "1:52:23"}
+{"current_steps": 33, "total_steps": 225, "loss": 0.8212, "lr": 9.939652198703785e-06, "epoch": 0.43805309734513276, "percentage": 14.67, "elapsed_time": "0:19:12", "remaining_time": "1:51:43"}
+{"current_steps": 34, "total_steps": 225, "loss": 0.8088, "lr": 9.927010076443408e-06, "epoch": 0.45132743362831856, "percentage": 15.11, "elapsed_time": "0:19:46", "remaining_time": "1:51:03"}
+{"current_steps": 35, "total_steps": 225, "loss": 0.8248, "lr": 9.91317624111132e-06, "epoch": 0.4646017699115044, "percentage": 15.56, "elapsed_time": "0:20:20", "remaining_time": "1:50:24"}
+{"current_steps": 36, "total_steps": 225, "loss": 0.8227, "lr": 9.898154038745408e-06, "epoch": 0.4778761061946903, "percentage": 16.0, "elapsed_time": "0:20:54", "remaining_time": "1:49:46"}
+{"current_steps": 37, "total_steps": 225, "loss": 0.8136, "lr": 9.881947102818036e-06, "epoch": 0.4911504424778761, "percentage": 16.44, "elapsed_time": "0:21:28", "remaining_time": "1:49:08"}
+{"current_steps": 38, "total_steps": 225, "loss": 0.8219, "lr": 9.864559353357189e-06, "epoch": 0.504424778761062, "percentage": 16.89, "elapsed_time": "0:22:02", "remaining_time": "1:48:30"}
+{"current_steps": 39, "total_steps": 225, "loss": 0.8121, "lr": 9.845994995998332e-06, "epoch": 0.5176991150442478, "percentage": 17.33, "elapsed_time": "0:22:37", "remaining_time": "1:47:52"}
+{"current_steps": 40, "total_steps": 225, "loss": 0.8064, "lr": 9.826258520967178e-06, "epoch": 0.5309734513274337, "percentage": 17.78, "elapsed_time": "0:23:11", "remaining_time": "1:47:15"}
+{"current_steps": 41, "total_steps": 225, "loss": 0.7947, "lr": 9.805354701993624e-06, "epoch": 0.5442477876106194, "percentage": 18.22, "elapsed_time": "0:23:45", "remaining_time": "1:46:37"}
+{"current_steps": 42, "total_steps": 225, "loss": 0.7997, "lr": 9.7832885951571e-06, "epoch": 0.5575221238938053, "percentage": 18.67, "elapsed_time": "0:24:19", "remaining_time": "1:45:59"}
+{"current_steps": 43, "total_steps": 225, "loss": 0.8128, "lr": 9.76006553766365e-06, "epoch": 0.5707964601769911, "percentage": 19.11, "elapsed_time": "0:24:53", "remaining_time": "1:45:22"}
+{"current_steps": 44, "total_steps": 225, "loss": 0.7987, "lr": 9.735691146555002e-06, "epoch": 0.584070796460177, "percentage": 19.56, "elapsed_time": "0:25:28", "remaining_time": "1:44:45"}
+{"current_steps": 45, "total_steps": 225, "loss": 0.7982, "lr": 9.710171317349946e-06, "epoch": 0.5973451327433629, "percentage": 20.0, "elapsed_time": "0:26:02", "remaining_time": "1:44:08"}
+{"current_steps": 46, "total_steps": 225, "loss": 0.8022, "lr": 9.683512222618376e-06, "epoch": 0.6106194690265486, "percentage": 20.44, "elapsed_time": "0:26:36", "remaining_time": "1:43:32"}
+{"current_steps": 47, "total_steps": 225, "loss": 0.7927, "lr": 9.655720310488298e-06, "epoch": 0.6238938053097345, "percentage": 20.89, "elapsed_time": "0:27:10", "remaining_time": "1:42:55"}
+{"current_steps": 48, "total_steps": 225, "loss": 0.7833, "lr": 9.62680230308621e-06, "epoch": 0.6371681415929203, "percentage": 21.33, "elapsed_time": "0:27:44", "remaining_time": "1:42:18"}
+{"current_steps": 49, "total_steps": 225, "loss": 0.7759, "lr": 9.596765194911182e-06, "epoch": 0.6504424778761062, "percentage": 21.78, "elapsed_time": "0:28:19", "remaining_time": "1:41:42"}
+{"current_steps": 50, "total_steps": 225, "loss": 0.7904, "lr": 9.565616251143094e-06, "epoch": 0.6637168141592921, "percentage": 22.22, "elapsed_time": "0:28:53", "remaining_time": "1:41:06"}
+{"current_steps": 51, "total_steps": 225, "loss": 0.7966, "lr": 9.533363005885362e-06, "epoch": 0.6769911504424779, "percentage": 22.67, "elapsed_time": "0:29:27", "remaining_time": "1:40:29"}
+{"current_steps": 52, "total_steps": 225, "loss": 0.7831, "lr": 9.50001326034265e-06, "epoch": 0.6902654867256637, "percentage": 23.11, "elapsed_time": "0:30:01", "remaining_time": "1:39:53"}
+{"current_steps": 53, "total_steps": 225, "loss": 0.7822, "lr": 9.465575080933959e-06, "epoch": 0.7035398230088495, "percentage": 23.56, "elapsed_time": "0:30:35", "remaining_time": "1:39:17"}
+{"current_steps": 54, "total_steps": 225, "loss": 0.766, "lr": 9.430056797341574e-06, "epoch": 0.7168141592920354, "percentage": 24.0, "elapsed_time": "0:31:09", "remaining_time": "1:38:40"}
+{"current_steps": 55, "total_steps": 225, "loss": 0.8123, "lr": 9.393467000496345e-06, "epoch": 0.7300884955752213, "percentage": 24.44, "elapsed_time": "0:31:43", "remaining_time": "1:38:05"}
+{"current_steps": 56, "total_steps": 225, "loss": 0.792, "lr": 9.355814540499753e-06, "epoch": 0.7433628318584071, "percentage": 24.89, "elapsed_time": "0:32:18", "remaining_time": "1:37:28"}
+{"current_steps": 57, "total_steps": 225, "loss": 0.7808, "lr": 9.317108524483319e-06, "epoch": 0.7566371681415929, "percentage": 25.33, "elapsed_time": "0:32:52", "remaining_time": "1:36:52"}
+{"current_steps": 58, "total_steps": 225, "loss": 0.775, "lr": 9.27735831440582e-06, "epoch": 0.7699115044247787, "percentage": 25.78, "elapsed_time": "0:33:26", "remaining_time": "1:36:16"}
+{"current_steps": 59, "total_steps": 225, "loss": 0.8022, "lr": 9.236573524788888e-06, "epoch": 0.7831858407079646, "percentage": 26.22, "elapsed_time": "0:34:00", "remaining_time": "1:35:41"}
+{"current_steps": 60, "total_steps": 225, "loss": 0.7881, "lr": 9.194764020391507e-06, "epoch": 0.7964601769911505, "percentage": 26.67, "elapsed_time": "0:34:34", "remaining_time": "1:35:05"}
+{"current_steps": 61, "total_steps": 225, "loss": 0.7865, "lr": 9.151939913823988e-06, "epoch": 0.8097345132743363, "percentage": 27.11, "elapsed_time": "0:35:08", "remaining_time": "1:34:29"}
+{"current_steps": 62, "total_steps": 225, "loss": 0.7636, "lr": 9.108111563102005e-06, "epoch": 0.8230088495575221, "percentage": 27.56, "elapsed_time": "0:35:42", "remaining_time": "1:33:53"}
+{"current_steps": 63, "total_steps": 225, "loss": 0.8098, "lr": 9.063289569141251e-06, "epoch": 0.8362831858407079, "percentage": 28.0, "elapsed_time": "0:36:17", "remaining_time": "1:33:18"}
+{"current_steps": 64, "total_steps": 225, "loss": 0.7983, "lr": 9.01748477319338e-06, "epoch": 0.8495575221238938, "percentage": 28.44, "elapsed_time": "0:36:51", "remaining_time": "1:32:42"}
+{"current_steps": 65, "total_steps": 225, "loss": 0.7809, "lr": 8.970708254223768e-06, "epoch": 0.8628318584070797, "percentage": 28.89, "elapsed_time": "0:37:25", "remaining_time": "1:32:06"}
+{"current_steps": 66, "total_steps": 225, "loss": 0.771, "lr": 8.92297132623183e-06, "epoch": 0.8761061946902655, "percentage": 29.33, "elapsed_time": "0:37:59", "remaining_time": "1:31:32"}
+{"current_steps": 67, "total_steps": 225, "loss": 0.7774, "lr": 8.87428553551445e-06, "epoch": 0.8893805309734514, "percentage": 29.78, "elapsed_time": "0:38:34", "remaining_time": "1:30:56"}
+{"current_steps": 68, "total_steps": 225, "loss": 0.7715, "lr": 8.82466265787324e-06, "epoch": 0.9026548672566371, "percentage": 30.22, "elapsed_time": "0:39:08", "remaining_time": "1:30:21"}
+{"current_steps": 69, "total_steps": 225, "loss": 0.7601, "lr": 8.774114695766286e-06, "epoch": 0.915929203539823, "percentage": 30.67, "elapsed_time": "0:39:42", "remaining_time": "1:29:45"}
+{"current_steps": 70, "total_steps": 225, "loss": 0.7808, "lr": 8.722653875405077e-06, "epoch": 0.9292035398230089, "percentage": 31.11, "elapsed_time": "0:40:16", "remaining_time": "1:29:10"}
+{"current_steps": 71, "total_steps": 225, "loss": 0.771, "lr": 8.670292643797302e-06, "epoch": 0.9424778761061947, "percentage": 31.56, "elapsed_time": "0:40:50", "remaining_time": "1:28:35"}
+{"current_steps": 72, "total_steps": 225, "loss": 0.7665, "lr": 8.61704366573625e-06, "epoch": 0.9557522123893806, "percentage": 32.0, "elapsed_time": "0:41:24", "remaining_time": "1:28:00"}
+{"current_steps": 73, "total_steps": 225, "loss": 0.7489, "lr": 8.562919820737537e-06, "epoch": 0.9690265486725663, "percentage": 32.44, "elapsed_time": "0:41:58", "remaining_time": "1:27:24"}
+{"current_steps": 74, "total_steps": 225, "loss": 0.7959, "lr": 8.507934199923884e-06, "epoch": 0.9823008849557522, "percentage": 32.89, "elapsed_time": "0:42:32", "remaining_time": "1:26:49"}
+{"current_steps": 75, "total_steps": 225, "loss": 0.7848, "lr": 8.452100102858734e-06, "epoch": 0.995575221238938, "percentage": 33.33, "elapsed_time": "0:43:07", "remaining_time": "1:26:14"}
+{"current_steps": 76, "total_steps": 225, "loss": 0.7542, "lr": 8.395431034329431e-06, "epoch": 1.008849557522124, "percentage": 33.78, "elapsed_time": "0:44:26", "remaining_time": "1:27:07"}
+{"current_steps": 77, "total_steps": 225, "loss": 0.7461, "lr": 8.33794070108077e-06, "epoch": 1.0221238938053097, "percentage": 34.22, "elapsed_time": "0:45:00", "remaining_time": "1:26:30"}
+{"current_steps": 78, "total_steps": 225, "loss": 0.7213, "lr": 8.2796430084997e-06, "epoch": 1.0353982300884956, "percentage": 34.67, "elapsed_time": "0:45:34", "remaining_time": "1:25:53"}
+{"current_steps": 79, "total_steps": 225, "loss": 0.7324, "lr": 8.22055205725199e-06, "epoch": 1.0486725663716814, "percentage": 35.11, "elapsed_time": "0:46:08", "remaining_time": "1:25:16"}
+{"current_steps": 80, "total_steps": 225, "loss": 0.7468, "lr": 8.160682139871634e-06, "epoch": 1.0619469026548674, "percentage": 35.56, "elapsed_time": "0:46:42", "remaining_time": "1:24:40"}
+{"current_steps": 81, "total_steps": 225, "loss": 0.7501, "lr": 8.100047737303877e-06, "epoch": 1.075221238938053, "percentage": 36.0, "elapsed_time": "0:47:17", "remaining_time": "1:24:03"}
+{"current_steps": 82, "total_steps": 225, "loss": 0.7252, "lr": 8.038663515402659e-06, "epoch": 1.0884955752212389, "percentage": 36.44, "elapsed_time": "0:47:51", "remaining_time": "1:23:27"}
+{"current_steps": 83, "total_steps": 225, "loss": 0.7435, "lr": 7.97654432138333e-06, "epoch": 1.1017699115044248, "percentage": 36.89, "elapsed_time": "0:48:25", "remaining_time": "1:22:50"}
+{"current_steps": 84, "total_steps": 225, "loss": 0.7416, "lr": 7.913705180231505e-06, "epoch": 1.1150442477876106, "percentage": 37.33, "elapsed_time": "0:48:59", "remaining_time": "1:22:14"}
+{"current_steps": 85, "total_steps": 225, "loss": 0.7328, "lr": 7.850161291068915e-06, "epoch": 1.1283185840707965, "percentage": 37.78, "elapsed_time": "0:49:33", "remaining_time": "1:21:37"}
+{"current_steps": 86, "total_steps": 225, "loss": 0.7482, "lr": 7.785928023477142e-06, "epoch": 1.1415929203539823, "percentage": 38.22, "elapsed_time": "0:50:07", "remaining_time": "1:21:01"}
+{"current_steps": 87, "total_steps": 225, "loss": 0.7496, "lr": 7.721020913780137e-06, "epoch": 1.154867256637168, "percentage": 38.67, "elapsed_time": "0:50:41", "remaining_time": "1:20:25"}
+{"current_steps": 88, "total_steps": 225, "loss": 0.7355, "lr": 7.655455661286376e-06, "epoch": 1.168141592920354, "percentage": 39.11, "elapsed_time": "0:51:16", "remaining_time": "1:19:48"}
+{"current_steps": 89, "total_steps": 225, "loss": 0.772, "lr": 7.589248124491627e-06, "epoch": 1.1814159292035398, "percentage": 39.56, "elapsed_time": "0:51:50", "remaining_time": "1:19:12"}
+{"current_steps": 90, "total_steps": 225, "loss": 0.7308, "lr": 7.5224143172432e-06, "epoch": 1.1946902654867257, "percentage": 40.0, "elapsed_time": "0:52:24", "remaining_time": "1:18:36"}
+{"current_steps": 91, "total_steps": 225, "loss": 0.7281, "lr": 7.454970404866612e-06, "epoch": 1.2079646017699115, "percentage": 40.44, "elapsed_time": "0:52:59", "remaining_time": "1:18:02"}
+{"current_steps": 92, "total_steps": 225, "loss": 0.754, "lr": 7.386932700255635e-06, "epoch": 1.2212389380530975, "percentage": 40.89, "elapsed_time": "0:53:34", "remaining_time": "1:17:27"}
+{"current_steps": 93, "total_steps": 225, "loss": 0.7459, "lr": 7.318317659926637e-06, "epoch": 1.2345132743362832, "percentage": 41.33, "elapsed_time": "0:54:08", "remaining_time": "1:16:51"}
+{"current_steps": 94, "total_steps": 225, "loss": 0.7298, "lr": 7.249141880038181e-06, "epoch": 1.247787610619469, "percentage": 41.78, "elapsed_time": "0:54:43", "remaining_time": "1:16:15"}
+{"current_steps": 95, "total_steps": 225, "loss": 0.7205, "lr": 7.179422092376856e-06, "epoch": 1.261061946902655, "percentage": 42.22, "elapsed_time": "0:55:17", "remaining_time": "1:15:39"}
+{"current_steps": 96, "total_steps": 225, "loss": 0.7237, "lr": 7.109175160310312e-06, "epoch": 1.2743362831858407, "percentage": 42.67, "elapsed_time": "0:55:51", "remaining_time": "1:15:03"}
+{"current_steps": 97, "total_steps": 225, "loss": 0.7165, "lr": 7.038418074708444e-06, "epoch": 1.2876106194690267, "percentage": 43.11, "elapsed_time": "0:56:25", "remaining_time": "1:14:27"}
+{"current_steps": 98, "total_steps": 225, "loss": 0.7205, "lr": 6.967167949833763e-06, "epoch": 1.3008849557522124, "percentage": 43.56, "elapsed_time": "0:56:59", "remaining_time": "1:13:51"}
+{"current_steps": 99, "total_steps": 225, "loss": 0.7401, "lr": 6.895442019201898e-06, "epoch": 1.3141592920353982, "percentage": 44.0, "elapsed_time": "0:57:33", "remaining_time": "1:13:15"}
+{"current_steps": 100, "total_steps": 225, "loss": 0.7521, "lr": 6.8232576314132755e-06, "epoch": 1.3274336283185841, "percentage": 44.44, "elapsed_time": "0:58:08", "remaining_time": "1:12:40"}
+{"current_steps": 101, "total_steps": 225, "loss": 0.7267, "lr": 6.750632245956954e-06, "epoch": 1.3407079646017699, "percentage": 44.89, "elapsed_time": "0:58:42", "remaining_time": "1:12:04"}
+{"current_steps": 102, "total_steps": 225, "loss": 0.7391, "lr": 6.677583428987625e-06, "epoch": 1.3539823008849559, "percentage": 45.33, "elapsed_time": "0:59:16", "remaining_time": "1:11:28"}
+{"current_steps": 103, "total_steps": 225, "loss": 0.7501, "lr": 6.6041288490768385e-06, "epoch": 1.3672566371681416, "percentage": 45.78, "elapsed_time": "0:59:50", "remaining_time": "1:10:52"}
+{"current_steps": 104, "total_steps": 225, "loss": 0.7364, "lr": 6.530286272939438e-06, "epoch": 1.3805309734513274, "percentage": 46.22, "elapsed_time": "1:00:24", "remaining_time": "1:10:17"}
+{"current_steps": 105, "total_steps": 225, "loss": 0.7439, "lr": 6.456073561136261e-06, "epoch": 1.3938053097345133, "percentage": 46.67, "elapsed_time": "1:00:58", "remaining_time": "1:09:41"}
+{"current_steps": 106, "total_steps": 225, "loss": 0.7294, "lr": 6.381508663754152e-06, "epoch": 1.407079646017699, "percentage": 47.11, "elapsed_time": "1:01:32", "remaining_time": "1:09:05"}
+{"current_steps": 107, "total_steps": 225, "loss": 0.7363, "lr": 6.306609616064304e-06, "epoch": 1.420353982300885, "percentage": 47.56, "elapsed_time": "1:02:07", "remaining_time": "1:08:30"}
+{"current_steps": 108, "total_steps": 225, "loss": 0.7383, "lr": 6.231394534160008e-06, "epoch": 1.4336283185840708, "percentage": 48.0, "elapsed_time": "1:02:41", "remaining_time": "1:07:54"}
+{"current_steps": 109, "total_steps": 225, "loss": 0.7411, "lr": 6.15588161057485e-06, "epoch": 1.4469026548672566, "percentage": 48.44, "elapsed_time": "1:03:15", "remaining_time": "1:07:19"}
+{"current_steps": 110, "total_steps": 225, "loss": 0.7259, "lr": 6.080089109882419e-06, "epoch": 1.4601769911504425, "percentage": 48.89, "elapsed_time": "1:03:49", "remaining_time": "1:06:43"}
+{"current_steps": 111, "total_steps": 225, "loss": 0.7374, "lr": 6.004035364278593e-06, "epoch": 1.4734513274336283, "percentage": 49.33, "elapsed_time": "1:04:23", "remaining_time": "1:06:07"}
+{"current_steps": 112, "total_steps": 225, "loss": 0.7325, "lr": 5.927738769147467e-06, "epoch": 1.4867256637168142, "percentage": 49.78, "elapsed_time": "1:04:57", "remaining_time": "1:05:32"}
+{"current_steps": 113, "total_steps": 225, "loss": 0.7345, "lr": 5.851217778611994e-06, "epoch": 1.5, "percentage": 50.22, "elapsed_time": "1:05:31", "remaining_time": "1:04:56"}
+{"current_steps": 114, "total_steps": 225, "loss": 0.737, "lr": 5.774490901070424e-06, "epoch": 1.5132743362831858, "percentage": 50.67, "elapsed_time": "1:06:05", "remaining_time": "1:04:21"}
+{"current_steps": 115, "total_steps": 225, "loss": 0.7272, "lr": 5.697576694719616e-06, "epoch": 1.5265486725663717, "percentage": 51.11, "elapsed_time": "1:06:39", "remaining_time": "1:03:46"}
+{"current_steps": 116, "total_steps": 225, "loss": 0.734, "lr": 5.6204937630662974e-06, "epoch": 1.5398230088495575, "percentage": 51.56, "elapsed_time": "1:07:14", "remaining_time": "1:03:10"}
+{"current_steps": 117, "total_steps": 225, "loss": 0.7466, "lr": 5.543260750427373e-06, "epoch": 1.5530973451327434, "percentage": 52.0, "elapsed_time": "1:07:48", "remaining_time": "1:02:35"}
+{"current_steps": 118, "total_steps": 225, "loss": 0.7141, "lr": 5.465896337420359e-06, "epoch": 1.5663716814159292, "percentage": 52.44, "elapsed_time": "1:08:22", "remaining_time": "1:02:00"}
+{"current_steps": 119, "total_steps": 225, "loss": 0.7285, "lr": 5.388419236445033e-06, "epoch": 1.579646017699115, "percentage": 52.89, "elapsed_time": "1:08:56", "remaining_time": "1:01:24"}
+{"current_steps": 120, "total_steps": 225, "loss": 0.7185, "lr": 5.310848187157404e-06, "epoch": 1.592920353982301, "percentage": 53.33, "elapsed_time": "1:09:30", "remaining_time": "1:00:49"}
+{"current_steps": 121, "total_steps": 225, "loss": 0.7189, "lr": 5.233201951937088e-06, "epoch": 1.606194690265487, "percentage": 53.78, "elapsed_time": "1:10:04", "remaining_time": "1:00:14"}
+{"current_steps": 122, "total_steps": 225, "loss": 0.7169, "lr": 5.155499311349185e-06, "epoch": 1.6194690265486726, "percentage": 54.22, "elapsed_time": "1:10:39", "remaining_time": "0:59:38"}
+{"current_steps": 123, "total_steps": 225, "loss": 0.7265, "lr": 5.077759059601756e-06, "epoch": 1.6327433628318584, "percentage": 54.67, "elapsed_time": "1:11:13", "remaining_time": "0:59:03"}
+{"current_steps": 124, "total_steps": 225, "loss": 0.7227, "lr": 5e-06, "epoch": 1.6460176991150441, "percentage": 55.11, "elapsed_time": "1:11:47", "remaining_time": "0:58:28"}
+{"current_steps": 125, "total_steps": 225, "loss": 0.7129, "lr": 4.922240940398246e-06, "epoch": 1.6592920353982301, "percentage": 55.56, "elapsed_time": "1:12:21", "remaining_time": "0:57:53"}
+{"current_steps": 126, "total_steps": 225, "loss": 0.7199, "lr": 4.844500688650817e-06, "epoch": 1.672566371681416, "percentage": 56.0, "elapsed_time": "1:12:55", "remaining_time": "0:57:17"}
+{"current_steps": 127, "total_steps": 225, "loss": 0.7251, "lr": 4.766798048062913e-06, "epoch": 1.6858407079646018, "percentage": 56.44, "elapsed_time": "1:13:29", "remaining_time": "0:56:42"}
+{"current_steps": 128, "total_steps": 225, "loss": 0.746, "lr": 4.689151812842598e-06, "epoch": 1.6991150442477876, "percentage": 56.89, "elapsed_time": "1:14:07", "remaining_time": "0:56:10"}
+{"current_steps": 129, "total_steps": 225, "loss": 0.7166, "lr": 4.611580763554969e-06, "epoch": 1.7123893805309733, "percentage": 57.33, "elapsed_time": "1:14:41", "remaining_time": "0:55:35"}
+{"current_steps": 130, "total_steps": 225, "loss": 0.7078, "lr": 4.534103662579643e-06, "epoch": 1.7256637168141593, "percentage": 57.78, "elapsed_time": "1:15:15", "remaining_time": "0:55:00"}
+{"current_steps": 131, "total_steps": 225, "loss": 0.7192, "lr": 4.456739249572628e-06, "epoch": 1.7389380530973453, "percentage": 58.22, "elapsed_time": "1:15:50", "remaining_time": "0:54:24"}
+{"current_steps": 132, "total_steps": 225, "loss": 0.7186, "lr": 4.379506236933703e-06, "epoch": 1.752212389380531, "percentage": 58.67, "elapsed_time": "1:16:24", "remaining_time": "0:53:49"}
+{"current_steps": 133, "total_steps": 225, "loss": 0.7214, "lr": 4.3024233052803855e-06, "epoch": 1.7654867256637168, "percentage": 59.11, "elapsed_time": "1:16:58", "remaining_time": "0:53:14"}
+{"current_steps": 134, "total_steps": 225, "loss": 0.7155, "lr": 4.2255090989295765e-06, "epoch": 1.7787610619469025, "percentage": 59.56, "elapsed_time": "1:17:32", "remaining_time": "0:52:39"}
+{"current_steps": 135, "total_steps": 225, "loss": 0.709, "lr": 4.148782221388007e-06, "epoch": 1.7920353982300885, "percentage": 60.0, "elapsed_time": "1:18:06", "remaining_time": "0:52:04"}
+{"current_steps": 136, "total_steps": 225, "loss": 0.7042, "lr": 4.072261230852534e-06, "epoch": 1.8053097345132745, "percentage": 60.44, "elapsed_time": "1:18:40", "remaining_time": "0:51:29"}
+{"current_steps": 137, "total_steps": 225, "loss": 0.7182, "lr": 3.995964635721409e-06, "epoch": 1.8185840707964602, "percentage": 60.89, "elapsed_time": "1:19:14", "remaining_time": "0:50:54"}
+{"current_steps": 138, "total_steps": 225, "loss": 0.7082, "lr": 3.919910890117584e-06, "epoch": 1.831858407079646, "percentage": 61.33, "elapsed_time": "1:19:49", "remaining_time": "0:50:19"}
+{"current_steps": 139, "total_steps": 225, "loss": 0.7329, "lr": 3.844118389425154e-06, "epoch": 1.8451327433628317, "percentage": 61.78, "elapsed_time": "1:20:23", "remaining_time": "0:49:44"}
+{"current_steps": 140, "total_steps": 225, "loss": 0.7173, "lr": 3.768605465839994e-06, "epoch": 1.8584070796460177, "percentage": 62.22, "elapsed_time": "1:20:57", "remaining_time": "0:49:09"}
+{"current_steps": 141, "total_steps": 225, "loss": 0.7221, "lr": 3.6933903839356983e-06, "epoch": 1.8716814159292037, "percentage": 62.67, "elapsed_time": "1:21:31", "remaining_time": "0:48:34"}
+{"current_steps": 142, "total_steps": 225, "loss": 0.7315, "lr": 3.6184913362458497e-06, "epoch": 1.8849557522123894, "percentage": 63.11, "elapsed_time": "1:22:05", "remaining_time": "0:47:58"}
+{"current_steps": 143, "total_steps": 225, "loss": 0.7154, "lr": 3.5439264388637407e-06, "epoch": 1.8982300884955752, "percentage": 63.56, "elapsed_time": "1:22:39", "remaining_time": "0:47:23"}
+{"current_steps": 144, "total_steps": 225, "loss": 0.7221, "lr": 3.469713727060564e-06, "epoch": 1.911504424778761, "percentage": 64.0, "elapsed_time": "1:23:13", "remaining_time": "0:46:48"}
+{"current_steps": 145, "total_steps": 225, "loss": 0.7675, "lr": 3.3958711509231627e-06, "epoch": 1.924778761061947, "percentage": 64.44, "elapsed_time": "1:23:47", "remaining_time": "0:46:13"}
+{"current_steps": 146, "total_steps": 225, "loss": 0.7343, "lr": 3.322416571012376e-06, "epoch": 1.9380530973451329, "percentage": 64.89, "elapsed_time": "1:24:21", "remaining_time": "0:45:39"}
+{"current_steps": 147, "total_steps": 225, "loss": 0.7341, "lr": 3.249367754043047e-06, "epoch": 1.9513274336283186, "percentage": 65.33, "elapsed_time": "1:24:56", "remaining_time": "0:45:04"}
+{"current_steps": 148, "total_steps": 225, "loss": 0.7222, "lr": 3.176742368586725e-06, "epoch": 1.9646017699115044, "percentage": 65.78, "elapsed_time": "1:25:30", "remaining_time": "0:44:29"}
+{"current_steps": 149, "total_steps": 225, "loss": 0.7172, "lr": 3.104557980798104e-06, "epoch": 1.9778761061946901, "percentage": 66.22, "elapsed_time": "1:26:04", "remaining_time": "0:43:54"}
+{"current_steps": 150, "total_steps": 225, "loss": 0.7224, "lr": 3.032832050166239e-06, "epoch": 1.991150442477876, "percentage": 66.67, "elapsed_time": "1:26:38", "remaining_time": "0:43:19"}
+{"current_steps": 151, "total_steps": 225, "loss": 0.7017, "lr": 2.961581925291557e-06, "epoch": 2.004424778761062, "percentage": 67.11, "elapsed_time": "1:27:57", "remaining_time": "0:43:06"}
+{"current_steps": 152, "total_steps": 225, "loss": 0.7, "lr": 2.8908248396896893e-06, "epoch": 2.017699115044248, "percentage": 67.56, "elapsed_time": "1:28:31", "remaining_time": "0:42:30"}
+{"current_steps": 153, "total_steps": 225, "loss": 0.7034, "lr": 2.820577907623145e-06, "epoch": 2.0309734513274336, "percentage": 68.0, "elapsed_time": "1:29:05", "remaining_time": "0:41:55"}
+{"current_steps": 154, "total_steps": 225, "loss": 0.7078, "lr": 2.750858119961821e-06, "epoch": 2.0442477876106193, "percentage": 68.44, "elapsed_time": "1:29:39", "remaining_time": "0:41:20"}
+{"current_steps": 155, "total_steps": 225, "loss": 0.6995, "lr": 2.6816823400733628e-06, "epoch": 2.0575221238938055, "percentage": 68.89, "elapsed_time": "1:30:13", "remaining_time": "0:40:44"}
+{"current_steps": 156, "total_steps": 225, "loss": 0.7055, "lr": 2.613067299744364e-06, "epoch": 2.0707964601769913, "percentage": 69.33, "elapsed_time": "1:30:47", "remaining_time": "0:40:09"}
+{"current_steps": 157, "total_steps": 225, "loss": 0.6959, "lr": 2.5450295951333896e-06, "epoch": 2.084070796460177, "percentage": 69.78, "elapsed_time": "1:31:22", "remaining_time": "0:39:34"}
+{"current_steps": 158, "total_steps": 225, "loss": 0.6883, "lr": 2.4775856827568016e-06, "epoch": 2.0973451327433628, "percentage": 70.22, "elapsed_time": "1:31:56", "remaining_time": "0:38:59"}
+{"current_steps": 159, "total_steps": 225, "loss": 0.6695, "lr": 2.410751875508373e-06, "epoch": 2.1106194690265485, "percentage": 70.67, "elapsed_time": "1:32:30", "remaining_time": "0:38:23"}
+{"current_steps": 160, "total_steps": 225, "loss": 0.6957, "lr": 2.3445443387136247e-06, "epoch": 2.1238938053097347, "percentage": 71.11, "elapsed_time": "1:33:04", "remaining_time": "0:37:48"}
+{"current_steps": 161, "total_steps": 225, "loss": 0.6828, "lr": 2.278979086219863e-06, "epoch": 2.1371681415929205, "percentage": 71.56, "elapsed_time": "1:33:38", "remaining_time": "0:37:13"}
+{"current_steps": 162, "total_steps": 225, "loss": 0.7153, "lr": 2.2140719765228587e-06, "epoch": 2.150442477876106, "percentage": 72.0, "elapsed_time": "1:34:12", "remaining_time": "0:36:38"}
+{"current_steps": 163, "total_steps": 225, "loss": 0.703, "lr": 2.149838708931087e-06, "epoch": 2.163716814159292, "percentage": 72.44, "elapsed_time": "1:34:51", "remaining_time": "0:36:04"}
+{"current_steps": 164, "total_steps": 225, "loss": 0.6879, "lr": 2.086294819768496e-06, "epoch": 2.1769911504424777, "percentage": 72.89, "elapsed_time": "1:35:25", "remaining_time": "0:35:29"}
+{"current_steps": 165, "total_steps": 225, "loss": 0.6988, "lr": 2.0234556786166715e-06, "epoch": 2.190265486725664, "percentage": 73.33, "elapsed_time": "1:35:59", "remaining_time": "0:34:54"}
+{"current_steps": 166, "total_steps": 225, "loss": 0.7004, "lr": 1.9613364845973433e-06, "epoch": 2.2035398230088497, "percentage": 73.78, "elapsed_time": "1:36:33", "remaining_time": "0:34:19"}
+{"current_steps": 167, "total_steps": 225, "loss": 0.6835, "lr": 1.8999522626961254e-06, "epoch": 2.2168141592920354, "percentage": 74.22, "elapsed_time": "1:37:07", "remaining_time": "0:33:44"}
+{"current_steps": 168, "total_steps": 225, "loss": 0.6954, "lr": 1.8393178601283684e-06, "epoch": 2.230088495575221, "percentage": 74.67, "elapsed_time": "1:37:41", "remaining_time": "0:33:08"}
+{"current_steps": 169, "total_steps": 225, "loss": 0.7103, "lr": 1.7794479427480115e-06, "epoch": 2.243362831858407, "percentage": 75.11, "elapsed_time": "1:38:16", "remaining_time": "0:32:33"}
+{"current_steps": 170, "total_steps": 225, "loss": 0.7001, "lr": 1.7203569915003005e-06, "epoch": 2.256637168141593, "percentage": 75.56, "elapsed_time": "1:38:50", "remaining_time": "0:31:58"}
+{"current_steps": 171, "total_steps": 225, "loss": 0.7123, "lr": 1.6620592989192318e-06, "epoch": 2.269911504424779, "percentage": 76.0, "elapsed_time": "1:39:24", "remaining_time": "0:31:23"}
+{"current_steps": 172, "total_steps": 225, "loss": 0.6823, "lr": 1.6045689656705715e-06, "epoch": 2.2831858407079646, "percentage": 76.44, "elapsed_time": "1:39:58", "remaining_time": "0:30:48"}
+{"current_steps": 173, "total_steps": 225, "loss": 0.6891, "lr": 1.5478998971412669e-06, "epoch": 2.2964601769911503, "percentage": 76.89, "elapsed_time": "1:40:32", "remaining_time": "0:30:13"}
+{"current_steps": 174, "total_steps": 225, "loss": 0.683, "lr": 1.4920658000761172e-06, "epoch": 2.309734513274336, "percentage": 77.33, "elapsed_time": "1:41:07", "remaining_time": "0:29:38"}
+{"current_steps": 175, "total_steps": 225, "loss": 0.7062, "lr": 1.4370801792624656e-06, "epoch": 2.3230088495575223, "percentage": 77.78, "elapsed_time": "1:41:44", "remaining_time": "0:29:04"}
+{"current_steps": 176, "total_steps": 225, "loss": 0.6941, "lr": 1.3829563342637514e-06, "epoch": 2.336283185840708, "percentage": 78.22, "elapsed_time": "1:42:18", "remaining_time": "0:28:28"}
+{"current_steps": 177, "total_steps": 225, "loss": 0.696, "lr": 1.3297073562026992e-06, "epoch": 2.349557522123894, "percentage": 78.67, "elapsed_time": "1:42:52", "remaining_time": "0:27:53"}
+{"current_steps": 178, "total_steps": 225, "loss": 0.6904, "lr": 1.2773461245949249e-06, "epoch": 2.3628318584070795, "percentage": 79.11, "elapsed_time": "1:43:26", "remaining_time": "0:27:18"}
+{"current_steps": 179, "total_steps": 225, "loss": 0.6939, "lr": 1.225885304233716e-06, "epoch": 2.3761061946902653, "percentage": 79.56, "elapsed_time": "1:44:00", "remaining_time": "0:26:43"}
+{"current_steps": 180, "total_steps": 225, "loss": 0.6797, "lr": 1.1753373421267622e-06, "epoch": 2.3893805309734515, "percentage": 80.0, "elapsed_time": "1:44:34", "remaining_time": "0:26:08"}
+{"current_steps": 181, "total_steps": 225, "loss": 0.6966, "lr": 1.125714464485551e-06, "epoch": 2.4026548672566372, "percentage": 80.44, "elapsed_time": "1:45:08", "remaining_time": "0:25:33"}
+{"current_steps": 182, "total_steps": 225, "loss": 0.6885, "lr": 1.0770286737681701e-06, "epoch": 2.415929203539823, "percentage": 80.89, "elapsed_time": "1:45:42", "remaining_time": "0:24:58"}
+{"current_steps": 183, "total_steps": 225, "loss": 0.7007, "lr": 1.0292917457762325e-06, "epoch": 2.4292035398230087, "percentage": 81.33, "elapsed_time": "1:46:17", "remaining_time": "0:24:23"}
+{"current_steps": 184, "total_steps": 225, "loss": 0.6807, "lr": 9.825152268066213e-07, "epoch": 2.442477876106195, "percentage": 81.78, "elapsed_time": "1:46:51", "remaining_time": "0:23:48"}
+{"current_steps": 185, "total_steps": 225, "loss": 0.6987, "lr": 9.367104308587493e-07, "epoch": 2.4557522123893807, "percentage": 82.22, "elapsed_time": "1:47:25", "remaining_time": "0:23:13"}
+{"current_steps": 186, "total_steps": 225, "loss": 0.6749, "lr": 8.918884368979969e-07, "epoch": 2.4690265486725664, "percentage": 82.67, "elapsed_time": "1:47:59", "remaining_time": "0:22:38"}
+{"current_steps": 187, "total_steps": 225, "loss": 0.7019, "lr": 8.480600861760124e-07, "epoch": 2.482300884955752, "percentage": 83.11, "elapsed_time": "1:48:33", "remaining_time": "0:22:03"}
+{"current_steps": 188, "total_steps": 225, "loss": 0.6816, "lr": 8.052359796084952e-07, "epoch": 2.495575221238938, "percentage": 83.56, "elapsed_time": "1:49:07", "remaining_time": "0:21:28"}
+{"current_steps": 189, "total_steps": 225, "loss": 0.68, "lr": 7.634264752111131e-07, "epoch": 2.508849557522124, "percentage": 84.0, "elapsed_time": "1:49:42", "remaining_time": "0:20:53"}
+{"current_steps": 190, "total_steps": 225, "loss": 0.7033, "lr": 7.226416855941814e-07, "epoch": 2.52212389380531, "percentage": 84.44, "elapsed_time": "1:50:16", "remaining_time": "0:20:18"}
+{"current_steps": 191, "total_steps": 225, "loss": 0.6979, "lr": 6.828914755166826e-07, "epoch": 2.5353982300884956, "percentage": 84.89, "elapsed_time": "1:50:50", "remaining_time": "0:19:43"}
+{"current_steps": 192, "total_steps": 225, "loss": 0.6809, "lr": 6.441854595002478e-07, "epoch": 2.5486725663716814, "percentage": 85.33, "elapsed_time": "1:51:24", "remaining_time": "0:19:08"}
+{"current_steps": 193, "total_steps": 225, "loss": 0.7131, "lr": 6.065329995036573e-07, "epoch": 2.561946902654867, "percentage": 85.78, "elapsed_time": "1:51:58", "remaining_time": "0:18:33"}
+{"current_steps": 194, "total_steps": 225, "loss": 0.6959, "lr": 5.699432026584267e-07, "epoch": 2.5752212389380533, "percentage": 86.22, "elapsed_time": "1:52:32", "remaining_time": "0:17:59"}
+{"current_steps": 195, "total_steps": 225, "loss": 0.7001, "lr": 5.344249190660427e-07, "epoch": 2.588495575221239, "percentage": 86.67, "elapsed_time": "1:53:07", "remaining_time": "0:17:24"}
+{"current_steps": 196, "total_steps": 225, "loss": 0.6893, "lr": 4.999867396573499e-07, "epoch": 2.601769911504425, "percentage": 87.11, "elapsed_time": "1:53:41", "remaining_time": "0:16:49"}
+{"current_steps": 197, "total_steps": 225, "loss": 0.6937, "lr": 4.666369941146376e-07, "epoch": 2.6150442477876106, "percentage": 87.56, "elapsed_time": "1:54:15", "remaining_time": "0:16:14"}
+{"current_steps": 198, "total_steps": 225, "loss": 0.6943, "lr": 4.343837488569058e-07, "epoch": 2.6283185840707963, "percentage": 88.0, "elapsed_time": "1:54:49", "remaining_time": "0:15:39"}
+{"current_steps": 199, "total_steps": 225, "loss": 0.7204, "lr": 4.03234805088818e-07, "epoch": 2.6415929203539825, "percentage": 88.44, "elapsed_time": "1:55:23", "remaining_time": "0:15:04"}
+{"current_steps": 200, "total_steps": 225, "loss": 0.6887, "lr": 3.7319769691379295e-07, "epoch": 2.6548672566371683, "percentage": 88.89, "elapsed_time": "1:55:57", "remaining_time": "0:14:29"}
+{"current_steps": 201, "total_steps": 225, "loss": 0.7037, "lr": 3.4427968951170287e-07, "epoch": 2.668141592920354, "percentage": 89.33, "elapsed_time": "1:56:31", "remaining_time": "0:13:54"}
+{"current_steps": 202, "total_steps": 225, "loss": 0.702, "lr": 3.1648777738162496e-07, "epoch": 2.6814159292035398, "percentage": 89.78, "elapsed_time": "1:57:06", "remaining_time": "0:13:20"}
+{"current_steps": 203, "total_steps": 225, "loss": 0.684, "lr": 2.8982868265005457e-07, "epoch": 2.6946902654867255, "percentage": 90.22, "elapsed_time": "1:57:40", "remaining_time": "0:12:45"}
+{"current_steps": 204, "total_steps": 225, "loss": 0.7095, "lr": 2.6430885344499944e-07, "epoch": 2.7079646017699117, "percentage": 90.67, "elapsed_time": "1:58:14", "remaining_time": "0:12:10"}
+{"current_steps": 205, "total_steps": 225, "loss": 0.6892, "lr": 2.399344623363503e-07, "epoch": 2.7212389380530975, "percentage": 91.11, "elapsed_time": "1:58:48", "remaining_time": "0:11:35"}
+{"current_steps": 206, "total_steps": 225, "loss": 0.6904, "lr": 2.1671140484290144e-07, "epoch": 2.734513274336283, "percentage": 91.56, "elapsed_time": "1:59:22", "remaining_time": "0:11:00"}
+{"current_steps": 207, "total_steps": 225, "loss": 0.6816, "lr": 1.9464529800637731e-07, "epoch": 2.747787610619469, "percentage": 92.0, "elapsed_time": "1:59:56", "remaining_time": "0:10:25"}
+{"current_steps": 208, "total_steps": 225, "loss": 0.7106, "lr": 1.737414790328218e-07, "epoch": 2.7610619469026547, "percentage": 92.44, "elapsed_time": "2:00:31", "remaining_time": "0:09:51"}
+{"current_steps": 209, "total_steps": 225, "loss": 0.6838, "lr": 1.540050040016694e-07, "epoch": 2.774336283185841, "percentage": 92.89, "elapsed_time": "2:01:05", "remaining_time": "0:09:16"}
+{"current_steps": 210, "total_steps": 225, "loss": 0.6835, "lr": 1.3544064664281266e-07, "epoch": 2.7876106194690267, "percentage": 93.33, "elapsed_time": "2:01:39", "remaining_time": "0:08:41"}
+{"current_steps": 211, "total_steps": 225, "loss": 0.7034, "lr": 1.1805289718196499e-07, "epoch": 2.8008849557522124, "percentage": 93.78, "elapsed_time": "2:02:13", "remaining_time": "0:08:06"}
+{"current_steps": 212, "total_steps": 225, "loss": 0.6882, "lr": 1.0184596125459134e-07, "epoch": 2.814159292035398, "percentage": 94.22, "elapsed_time": "2:02:47", "remaining_time": "0:07:31"}
+{"current_steps": 213, "total_steps": 225, "loss": 0.6952, "lr": 8.682375888868167e-08, "epoch": 2.827433628318584, "percentage": 94.67, "elapsed_time": "2:03:21", "remaining_time": "0:06:57"}
+{"current_steps": 214, "total_steps": 225, "loss": 0.6998, "lr": 7.29899235565934e-08, "epoch": 2.84070796460177, "percentage": 95.11, "elapsed_time": "2:03:56", "remaining_time": "0:06:22"}
+{"current_steps": 215, "total_steps": 225, "loss": 0.6918, "lr": 6.034780129621664e-08, "epoch": 2.853982300884956, "percentage": 95.56, "elapsed_time": "2:04:30", "remaining_time": "0:05:47"}
+{"current_steps": 216, "total_steps": 225, "loss": 0.6887, "lr": 4.8900449901653214e-08, "epoch": 2.8672566371681416, "percentage": 96.0, "elapsed_time": "2:05:04", "remaining_time": "0:05:12"}
+{"current_steps": 217, "total_steps": 225, "loss": 0.6984, "lr": 3.8650638183617695e-08, "epoch": 2.8805309734513274, "percentage": 96.44, "elapsed_time": "2:05:38", "remaining_time": "0:04:37"}
+{"current_steps": 218, "total_steps": 225, "loss": 0.6982, "lr": 2.960084529973706e-08, "epoch": 2.893805309734513, "percentage": 96.89, "elapsed_time": "2:06:12", "remaining_time": "0:04:03"}
+{"current_steps": 219, "total_steps": 225, "loss": 0.6907, "lr": 2.1753260154906973e-08, "epoch": 2.9070796460176993, "percentage": 97.33, "elapsed_time": "2:06:46", "remaining_time": "0:03:28"}
+{"current_steps": 220, "total_steps": 225, "loss": 0.6966, "lr": 1.5109780871853663e-08, "epoch": 2.920353982300885, "percentage": 97.78, "elapsed_time": "2:07:21", "remaining_time": "0:02:53"}
+{"current_steps": 221, "total_steps": 225, "loss": 0.6937, "lr": 9.672014332028357e-09, "epoch": 2.933628318584071, "percentage": 98.22, "elapsed_time": "2:07:55", "remaining_time": "0:02:18"}
+{"current_steps": 222, "total_steps": 225, "loss": 0.7024, "lr": 5.4412757869459765e-09, "epoch": 2.9469026548672566, "percentage": 98.67, "elapsed_time": "2:08:29", "remaining_time": "0:01:44"}
+{"current_steps": 223, "total_steps": 225, "loss": 0.686, "lr": 2.4185885400596076e-09, "epoch": 2.9601769911504423, "percentage": 99.11, "elapsed_time": "2:09:03", "remaining_time": "0:01:09"}
+{"current_steps": 224, "total_steps": 225, "loss": 0.7013, "lr": 6.04683699252373e-10, "epoch": 2.9734513274336285, "percentage": 99.56, "elapsed_time": "2:09:37", "remaining_time": "0:00:34"}
+{"current_steps": 225, "total_steps": 225, "loss": 0.7003, "lr": 0.0, "epoch": 2.9867256637168142, "percentage": 100.0, "elapsed_time": "2:10:11", "remaining_time": "0:00:00"}
+{"current_steps": 225, "total_steps": 225, "epoch": 2.9867256637168142, "percentage": 100.0, "elapsed_time": "2:11:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1617 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9867256637168142,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01327433628318584,
+      "grad_norm": 7.501493793577306,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 1.2083,
+      "step": 1
+    },
+    {
+      "epoch": 0.02654867256637168,
+      "grad_norm": 7.69893637940224,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.2329,
+      "step": 2
+    },
+    {
+      "epoch": 0.03982300884955752,
+      "grad_norm": 7.606118479356691,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 1.2323,
+      "step": 3
+    },
+    {
+      "epoch": 0.05309734513274336,
+      "grad_norm": 7.175916361320481,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.1988,
+      "step": 4
+    },
+    {
+      "epoch": 0.06637168141592921,
+      "grad_norm": 6.935826297903381,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 1.2046,
+      "step": 5
+    },
+    {
+      "epoch": 0.07964601769911504,
+      "grad_norm": 5.549054007536664,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.1353,
+      "step": 6
+    },
+    {
+      "epoch": 0.09292035398230089,
+      "grad_norm": 5.031745386989603,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 1.1348,
+      "step": 7
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "grad_norm": 2.737042220164658,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.0683,
+      "step": 8
+    },
+    {
+      "epoch": 0.11946902654867257,
+      "grad_norm": 2.3132871718286463,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 1.0536,
+      "step": 9
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "grad_norm": 2.7666200466111754,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.0506,
+      "step": 10
+    },
+    {
+      "epoch": 0.14601769911504425,
+      "grad_norm": 4.090979262135771,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 1.0238,
+      "step": 11
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "grad_norm": 4.142166776364045,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.0412,
+      "step": 12
+    },
+    {
+      "epoch": 0.17256637168141592,
+      "grad_norm": 3.79529965630404,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 1.0377,
+      "step": 13
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "grad_norm": 2.6054414904303718,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.9789,
+      "step": 14
+    },
+    {
+      "epoch": 0.19911504424778761,
+      "grad_norm": 2.627668862856322,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.9534,
+      "step": 15
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "grad_norm": 2.1366957452962083,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.9418,
+      "step": 16
+    },
+    {
+      "epoch": 0.22566371681415928,
+      "grad_norm": 1.6354470043380167,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 0.951,
+      "step": 17
+    },
+    {
+      "epoch": 0.23893805309734514,
+      "grad_norm": 1.4598328197110417,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.9296,
+      "step": 18
+    },
+    {
+      "epoch": 0.252212389380531,
+      "grad_norm": 1.5519981091962836,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.9174,
+      "step": 19
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 1.4414501159063233,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.8893,
+      "step": 20
+    },
+    {
+      "epoch": 0.27876106194690264,
+      "grad_norm": 1.2559447173533318,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.8833,
+      "step": 21
+    },
+    {
+      "epoch": 0.2920353982300885,
+      "grad_norm": 1.202388398042244,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.8773,
+      "step": 22
+    },
+    {
+      "epoch": 0.3053097345132743,
+      "grad_norm": 1.0994174756781598,
+      "learning_rate": 1e-05,
+      "loss": 0.8674,
+      "step": 23
+    },
+    {
+      "epoch": 0.3185840707964602,
+      "grad_norm": 0.9262699978897617,
+      "learning_rate": 9.999395316300748e-06,
+      "loss": 0.8848,
+      "step": 24
+    },
+    {
+      "epoch": 0.33185840707964603,
+      "grad_norm": 1.0063568356700823,
+      "learning_rate": 9.99758141145994e-06,
+      "loss": 0.8717,
+      "step": 25
+    },
+    {
+      "epoch": 0.34513274336283184,
+      "grad_norm": 0.7838127318380594,
+      "learning_rate": 9.994558724213056e-06,
+      "loss": 0.8578,
+      "step": 26
+    },
+    {
+      "epoch": 0.3584070796460177,
+      "grad_norm": 0.7604334069843581,
+      "learning_rate": 9.990327985667972e-06,
+      "loss": 0.8576,
+      "step": 27
+    },
+    {
+      "epoch": 0.37168141592920356,
+      "grad_norm": 0.7392944593702723,
+      "learning_rate": 9.984890219128148e-06,
+      "loss": 0.861,
+      "step": 28
+    },
+    {
+      "epoch": 0.38495575221238937,
+      "grad_norm": 0.6180669571411701,
+      "learning_rate": 9.978246739845095e-06,
+      "loss": 0.8376,
+      "step": 29
+    },
+    {
+      "epoch": 0.39823008849557523,
+      "grad_norm": 0.5653293908697061,
+      "learning_rate": 9.970399154700264e-06,
+      "loss": 0.8358,
+      "step": 30
+    },
+    {
+      "epoch": 0.41150442477876104,
+      "grad_norm": 0.6253879615255548,
+      "learning_rate": 9.961349361816384e-06,
+      "loss": 0.8266,
+      "step": 31
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "grad_norm": 0.6311146270349652,
+      "learning_rate": 9.951099550098349e-06,
+      "loss": 0.8271,
+      "step": 32
+    },
+    {
+      "epoch": 0.43805309734513276,
+      "grad_norm": 0.4522340368594046,
+      "learning_rate": 9.939652198703785e-06,
+      "loss": 0.8212,
+      "step": 33
+    },
+    {
+      "epoch": 0.45132743362831856,
+      "grad_norm": 0.46944490857782306,
+      "learning_rate": 9.927010076443408e-06,
+      "loss": 0.8088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4646017699115044,
+      "grad_norm": 0.6619178624223411,
+      "learning_rate": 9.91317624111132e-06,
+      "loss": 0.8248,
+      "step": 35
+    },
+    {
+      "epoch": 0.4778761061946903,
+      "grad_norm": 0.4793421273100569,
+      "learning_rate": 9.898154038745408e-06,
+      "loss": 0.8227,
+      "step": 36
+    },
+    {
+      "epoch": 0.4911504424778761,
+      "grad_norm": 0.5048716018168768,
+      "learning_rate": 9.881947102818036e-06,
+      "loss": 0.8136,
+      "step": 37
+    },
+    {
+      "epoch": 0.504424778761062,
+      "grad_norm": 0.5310568438628753,
+      "learning_rate": 9.864559353357189e-06,
+      "loss": 0.8219,
+      "step": 38
+    },
+    {
+      "epoch": 0.5176991150442478,
+      "grad_norm": 0.4039868493135018,
+      "learning_rate": 9.845994995998332e-06,
+      "loss": 0.8121,
+      "step": 39
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.40613975716581396,
+      "learning_rate": 9.826258520967178e-06,
+      "loss": 0.8064,
+      "step": 40
+    },
+    {
+      "epoch": 0.5442477876106194,
+      "grad_norm": 0.4243798130279049,
+      "learning_rate": 9.805354701993624e-06,
+      "loss": 0.7947,
+      "step": 41
+    },
+    {
+      "epoch": 0.5575221238938053,
+      "grad_norm": 0.3937395008126602,
+      "learning_rate": 9.7832885951571e-06,
+      "loss": 0.7997,
+      "step": 42
+    },
+    {
+      "epoch": 0.5707964601769911,
+      "grad_norm": 0.35927664574355933,
+      "learning_rate": 9.76006553766365e-06,
+      "loss": 0.8128,
+      "step": 43
+    },
+    {
+      "epoch": 0.584070796460177,
+      "grad_norm": 0.41494094102543927,
+      "learning_rate": 9.735691146555002e-06,
+      "loss": 0.7987,
+      "step": 44
+    },
+    {
+      "epoch": 0.5973451327433629,
+      "grad_norm": 0.39159423176658326,
+      "learning_rate": 9.710171317349946e-06,
+      "loss": 0.7982,
+      "step": 45
+    },
+    {
+      "epoch": 0.6106194690265486,
+      "grad_norm": 0.3546396421266,
+      "learning_rate": 9.683512222618376e-06,
+      "loss": 0.8022,
+      "step": 46
+    },
+    {
+      "epoch": 0.6238938053097345,
+      "grad_norm": 0.4031443445409564,
+      "learning_rate": 9.655720310488298e-06,
+      "loss": 0.7927,
+      "step": 47
+    },
+    {
+      "epoch": 0.6371681415929203,
+      "grad_norm": 0.3739479458029583,
+      "learning_rate": 9.62680230308621e-06,
+      "loss": 0.7833,
+      "step": 48
+    },
+    {
+      "epoch": 0.6504424778761062,
+      "grad_norm": 0.36631551044391514,
+      "learning_rate": 9.596765194911182e-06,
+      "loss": 0.7759,
+      "step": 49
+    },
+    {
+      "epoch": 0.6637168141592921,
+      "grad_norm": 0.422089187866885,
+      "learning_rate": 9.565616251143094e-06,
+      "loss": 0.7904,
+      "step": 50
+    },
+    {
+      "epoch": 0.6769911504424779,
+      "grad_norm": 0.38001471063547193,
+      "learning_rate": 9.533363005885362e-06,
+      "loss": 0.7966,
+      "step": 51
+    },
+    {
+      "epoch": 0.6902654867256637,
+      "grad_norm": 0.34994815094524784,
+      "learning_rate": 9.50001326034265e-06,
+      "loss": 0.7831,
+      "step": 52
+    },
+    {
+      "epoch": 0.7035398230088495,
+      "grad_norm": 0.4021483166751257,
+      "learning_rate": 9.465575080933959e-06,
+      "loss": 0.7822,
+      "step": 53
+    },
+    {
+      "epoch": 0.7168141592920354,
+      "grad_norm": 0.37951200554127446,
+      "learning_rate": 9.430056797341574e-06,
+      "loss": 0.766,
+      "step": 54
+    },
+    {
+      "epoch": 0.7300884955752213,
+      "grad_norm": 0.3885651067994481,
+      "learning_rate": 9.393467000496345e-06,
+      "loss": 0.8123,
+      "step": 55
+    },
+    {
+      "epoch": 0.7433628318584071,
+      "grad_norm": 0.33788656471657824,
+      "learning_rate": 9.355814540499753e-06,
+      "loss": 0.792,
+      "step": 56
+    },
+    {
+      "epoch": 0.7566371681415929,
+      "grad_norm": 0.35257733343859254,
+      "learning_rate": 9.317108524483319e-06,
+      "loss": 0.7808,
+      "step": 57
+    },
+    {
+      "epoch": 0.7699115044247787,
+      "grad_norm": 0.4493980702652022,
+      "learning_rate": 9.27735831440582e-06,
+      "loss": 0.775,
+      "step": 58
+    },
+    {
+      "epoch": 0.7831858407079646,
+      "grad_norm": 0.31327763449691237,
+      "learning_rate": 9.236573524788888e-06,
+      "loss": 0.8022,
+      "step": 59
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.3539933006466989,
+      "learning_rate": 9.194764020391507e-06,
+      "loss": 0.7881,
+      "step": 60
+    },
+    {
+      "epoch": 0.8097345132743363,
+      "grad_norm": 0.33723712804528594,
+      "learning_rate": 9.151939913823988e-06,
+      "loss": 0.7865,
+      "step": 61
+    },
+    {
+      "epoch": 0.8230088495575221,
+      "grad_norm": 0.32722331239315644,
+      "learning_rate": 9.108111563102005e-06,
+      "loss": 0.7636,
+      "step": 62
+    },
+    {
+      "epoch": 0.8362831858407079,
+      "grad_norm": 0.29895062665359806,
+      "learning_rate": 9.063289569141251e-06,
+      "loss": 0.8098,
+      "step": 63
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "grad_norm": 0.33490720312849226,
+      "learning_rate": 9.01748477319338e-06,
+      "loss": 0.7983,
+      "step": 64
+    },
+    {
+      "epoch": 0.8628318584070797,
+      "grad_norm": 0.3138722396258816,
+      "learning_rate": 8.970708254223768e-06,
+      "loss": 0.7809,
+      "step": 65
+    },
+    {
+      "epoch": 0.8761061946902655,
+      "grad_norm": 0.3503834090081562,
+      "learning_rate": 8.92297132623183e-06,
+      "loss": 0.771,
+      "step": 66
+    },
+    {
+      "epoch": 0.8893805309734514,
+      "grad_norm": 0.3200718203542079,
+      "learning_rate": 8.87428553551445e-06,
+      "loss": 0.7774,
+      "step": 67
+    },
+    {
+      "epoch": 0.9026548672566371,
+      "grad_norm": 0.3076356619481548,
+      "learning_rate": 8.82466265787324e-06,
+      "loss": 0.7715,
+      "step": 68
+    },
+    {
+      "epoch": 0.915929203539823,
+      "grad_norm": 0.38503832854879466,
+      "learning_rate": 8.774114695766286e-06,
+      "loss": 0.7601,
+      "step": 69
+    },
+    {
+      "epoch": 0.9292035398230089,
+      "grad_norm": 0.3446207105255993,
+      "learning_rate": 8.722653875405077e-06,
+      "loss": 0.7808,
+      "step": 70
+    },
+    {
+      "epoch": 0.9424778761061947,
+      "grad_norm": 0.40538454765257886,
+      "learning_rate": 8.670292643797302e-06,
+      "loss": 0.771,
+      "step": 71
+    },
+    {
+      "epoch": 0.9557522123893806,
+      "grad_norm": 0.36973676733332295,
+      "learning_rate": 8.61704366573625e-06,
+      "loss": 0.7665,
+      "step": 72
+    },
+    {
+      "epoch": 0.9690265486725663,
+      "grad_norm": 0.3591470148947773,
+      "learning_rate": 8.562919820737537e-06,
+      "loss": 0.7489,
+      "step": 73
+    },
+    {
+      "epoch": 0.9823008849557522,
+      "grad_norm": 0.40505318586997696,
+      "learning_rate": 8.507934199923884e-06,
+      "loss": 0.7959,
+      "step": 74
+    },
+    {
+      "epoch": 0.995575221238938,
+      "grad_norm": 0.43745974627838796,
+      "learning_rate": 8.452100102858734e-06,
+      "loss": 0.7848,
+      "step": 75
+    },
+    {
+      "epoch": 1.008849557522124,
+      "grad_norm": 0.34126147919255617,
+      "learning_rate": 8.395431034329431e-06,
+      "loss": 0.7542,
+      "step": 76
+    },
+    {
+      "epoch": 1.0221238938053097,
+      "grad_norm": 0.4316984815289514,
+      "learning_rate": 8.33794070108077e-06,
+      "loss": 0.7461,
+      "step": 77
+    },
+    {
+      "epoch": 1.0353982300884956,
+      "grad_norm": 0.3615278805808863,
+      "learning_rate": 8.2796430084997e-06,
+      "loss": 0.7213,
+      "step": 78
+    },
+    {
+      "epoch": 1.0486725663716814,
+      "grad_norm": 0.35254356847110446,
+      "learning_rate": 8.22055205725199e-06,
+      "loss": 0.7324,
+      "step": 79
+    },
+    {
+      "epoch": 1.0619469026548674,
+      "grad_norm": 0.3963258413649147,
+      "learning_rate": 8.160682139871634e-06,
+      "loss": 0.7468,
+      "step": 80
+    },
+    {
+      "epoch": 1.075221238938053,
+      "grad_norm": 0.35741415329062726,
+      "learning_rate": 8.100047737303877e-06,
+      "loss": 0.7501,
+      "step": 81
+    },
+    {
+      "epoch": 1.0884955752212389,
+      "grad_norm": 0.3471322354436462,
+      "learning_rate": 8.038663515402659e-06,
+      "loss": 0.7252,
+      "step": 82
+    },
+    {
+      "epoch": 1.1017699115044248,
+      "grad_norm": 0.42484254049532516,
+      "learning_rate": 7.97654432138333e-06,
+      "loss": 0.7435,
+      "step": 83
+    },
+    {
+      "epoch": 1.1150442477876106,
+      "grad_norm": 0.3394032976998188,
+      "learning_rate": 7.913705180231505e-06,
+      "loss": 0.7416,
+      "step": 84
+    },
+    {
+      "epoch": 1.1283185840707965,
+      "grad_norm": 0.3419038953247492,
+      "learning_rate": 7.850161291068915e-06,
+      "loss": 0.7328,
+      "step": 85
+    },
+    {
+      "epoch": 1.1415929203539823,
+      "grad_norm": 0.3897771775281859,
+      "learning_rate": 7.785928023477142e-06,
+      "loss": 0.7482,
+      "step": 86
+    },
+    {
+      "epoch": 1.154867256637168,
+      "grad_norm": 0.3573777190290809,
+      "learning_rate": 7.721020913780137e-06,
+      "loss": 0.7496,
+      "step": 87
+    },
+    {
+      "epoch": 1.168141592920354,
+      "grad_norm": 0.3259149835142648,
+      "learning_rate": 7.655455661286376e-06,
+      "loss": 0.7355,
+      "step": 88
+    },
+    {
+      "epoch": 1.1814159292035398,
+      "grad_norm": 0.3482317049523075,
+      "learning_rate": 7.589248124491627e-06,
+      "loss": 0.772,
+      "step": 89
+    },
+    {
+      "epoch": 1.1946902654867257,
+      "grad_norm": 0.35536003531689786,
+      "learning_rate": 7.5224143172432e-06,
+      "loss": 0.7308,
+      "step": 90
+    },
+    {
+      "epoch": 1.2079646017699115,
+      "grad_norm": 0.3512034399410828,
+      "learning_rate": 7.454970404866612e-06,
+      "loss": 0.7281,
+      "step": 91
+    },
+    {
+      "epoch": 1.2212389380530975,
+      "grad_norm": 0.3443490381255487,
+      "learning_rate": 7.386932700255635e-06,
+      "loss": 0.754,
+      "step": 92
+    },
+    {
+      "epoch": 1.2345132743362832,
+      "grad_norm": 0.3321105735622909,
+      "learning_rate": 7.318317659926637e-06,
+      "loss": 0.7459,
+      "step": 93
+    },
+    {
+      "epoch": 1.247787610619469,
+      "grad_norm": 0.30533172570444717,
+      "learning_rate": 7.249141880038181e-06,
+      "loss": 0.7298,
+      "step": 94
+    },
+    {
+      "epoch": 1.261061946902655,
+      "grad_norm": 0.3420069157117049,
+      "learning_rate": 7.179422092376856e-06,
+      "loss": 0.7205,
+      "step": 95
+    },
+    {
+      "epoch": 1.2743362831858407,
+      "grad_norm": 0.2974664185360883,
+      "learning_rate": 7.109175160310312e-06,
+      "loss": 0.7237,
+      "step": 96
+    },
+    {
+      "epoch": 1.2876106194690267,
+      "grad_norm": 0.3354261539877681,
+      "learning_rate": 7.038418074708444e-06,
+      "loss": 0.7165,
+      "step": 97
+    },
+    {
+      "epoch": 1.3008849557522124,
+      "grad_norm": 0.30569893584802527,
+      "learning_rate": 6.967167949833763e-06,
+      "loss": 0.7205,
+      "step": 98
+    },
+    {
+      "epoch": 1.3141592920353982,
+      "grad_norm": 0.331228561765267,
+      "learning_rate": 6.895442019201898e-06,
+      "loss": 0.7401,
+      "step": 99
+    },
+    {
+      "epoch": 1.3274336283185841,
+      "grad_norm": 0.31319049040987623,
+      "learning_rate": 6.8232576314132755e-06,
+      "loss": 0.7521,
+      "step": 100
+    },
+    {
+      "epoch": 1.3407079646017699,
+      "grad_norm": 0.3221250361865119,
+      "learning_rate": 6.750632245956954e-06,
+      "loss": 0.7267,
+      "step": 101
+    },
+    {
+      "epoch": 1.3539823008849559,
+      "grad_norm": 0.29427759113072766,
+      "learning_rate": 6.677583428987625e-06,
+      "loss": 0.7391,
+      "step": 102
+    },
+    {
+      "epoch": 1.3672566371681416,
+      "grad_norm": 0.31137760374687096,
+      "learning_rate": 6.6041288490768385e-06,
+      "loss": 0.7501,
+      "step": 103
+    },
+    {
+      "epoch": 1.3805309734513274,
+      "grad_norm": 0.34160988744926724,
+      "learning_rate": 6.530286272939438e-06,
+      "loss": 0.7364,
+      "step": 104
+    },
+    {
+      "epoch": 1.3938053097345133,
+      "grad_norm": 0.28973977407554946,
+      "learning_rate": 6.456073561136261e-06,
+      "loss": 0.7439,
+      "step": 105
+    },
+    {
+      "epoch": 1.407079646017699,
+      "grad_norm": 0.3568614786870276,
+      "learning_rate": 6.381508663754152e-06,
+      "loss": 0.7294,
+      "step": 106
+    },
+    {
+      "epoch": 1.420353982300885,
+      "grad_norm": 0.3029840332798554,
+      "learning_rate": 6.306609616064304e-06,
+      "loss": 0.7363,
+      "step": 107
+    },
+    {
+      "epoch": 1.4336283185840708,
+      "grad_norm": 0.3861113557071875,
+      "learning_rate": 6.231394534160008e-06,
+      "loss": 0.7383,
+      "step": 108
+    },
+    {
+      "epoch": 1.4469026548672566,
+      "grad_norm": 0.28409536861891677,
+      "learning_rate": 6.15588161057485e-06,
+      "loss": 0.7411,
+      "step": 109
+    },
+    {
+      "epoch": 1.4601769911504425,
+      "grad_norm": 0.3530117611821851,
+      "learning_rate": 6.080089109882419e-06,
+      "loss": 0.7259,
+      "step": 110
+    },
+    {
+      "epoch": 1.4734513274336283,
+      "grad_norm": 0.33355378626358784,
+      "learning_rate": 6.004035364278593e-06,
+      "loss": 0.7374,
+      "step": 111
+    },
+    {
+      "epoch": 1.4867256637168142,
+      "grad_norm": 0.30357771727319294,
+      "learning_rate": 5.927738769147467e-06,
+      "loss": 0.7325,
+      "step": 112
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.3362838667459555,
+      "learning_rate": 5.851217778611994e-06,
+      "loss": 0.7345,
+      "step": 113
+    },
+    {
+      "epoch": 1.5132743362831858,
+      "grad_norm": 0.32474587984909936,
+      "learning_rate": 5.774490901070424e-06,
+      "loss": 0.737,
+      "step": 114
+    },
+    {
+      "epoch": 1.5265486725663717,
+      "grad_norm": 0.3014879597724264,
+      "learning_rate": 5.697576694719616e-06,
+      "loss": 0.7272,
+      "step": 115
+    },
+    {
+      "epoch": 1.5398230088495575,
+      "grad_norm": 0.3040467458628167,
+      "learning_rate": 5.6204937630662974e-06,
+      "loss": 0.734,
+      "step": 116
+    },
+    {
+      "epoch": 1.5530973451327434,
+      "grad_norm": 0.31350706920507393,
+      "learning_rate": 5.543260750427373e-06,
+      "loss": 0.7466,
+      "step": 117
+    },
+    {
+      "epoch": 1.5663716814159292,
+      "grad_norm": 0.3229512522338443,
+      "learning_rate": 5.465896337420359e-06,
+      "loss": 0.7141,
+      "step": 118
+    },
+    {
+      "epoch": 1.579646017699115,
+      "grad_norm": 0.28121228903323864,
+      "learning_rate": 5.388419236445033e-06,
+      "loss": 0.7285,
+      "step": 119
+    },
+    {
+      "epoch": 1.592920353982301,
+      "grad_norm": 0.338272529289003,
+      "learning_rate": 5.310848187157404e-06,
+      "loss": 0.7185,
+      "step": 120
+    },
+    {
+      "epoch": 1.606194690265487,
+      "grad_norm": 0.29341122571043904,
+      "learning_rate": 5.233201951937088e-06,
+      "loss": 0.7189,
+      "step": 121
+    },
+    {
+      "epoch": 1.6194690265486726,
+      "grad_norm": 0.3376683438075859,
+      "learning_rate": 5.155499311349185e-06,
+      "loss": 0.7169,
+      "step": 122
+    },
+    {
+      "epoch": 1.6327433628318584,
+      "grad_norm": 0.3007152432888567,
+      "learning_rate": 5.077759059601756e-06,
+      "loss": 0.7265,
+      "step": 123
+    },
+    {
+      "epoch": 1.6460176991150441,
+      "grad_norm": 0.26177776789824847,
+      "learning_rate": 5e-06,
+      "loss": 0.7227,
+      "step": 124
+    },
+    {
+      "epoch": 1.6592920353982301,
+      "grad_norm": 0.3554074144730279,
+      "learning_rate": 4.922240940398246e-06,
+      "loss": 0.7129,
+      "step": 125
+    },
+    {
+      "epoch": 1.672566371681416,
+      "grad_norm": 0.29604443076936837,
+      "learning_rate": 4.844500688650817e-06,
+      "loss": 0.7199,
+      "step": 126
+    },
+    {
+      "epoch": 1.6858407079646018,
+      "grad_norm": 0.3045326626118736,
+      "learning_rate": 4.766798048062913e-06,
+      "loss": 0.7251,
+      "step": 127
+    },
+    {
+      "epoch": 1.6991150442477876,
+      "grad_norm": 0.2994924584025303,
+      "learning_rate": 4.689151812842598e-06,
+      "loss": 0.746,
+      "step": 128
+    },
+    {
+      "epoch": 1.7123893805309733,
+      "grad_norm": 0.26667687455270667,
+      "learning_rate": 4.611580763554969e-06,
+      "loss": 0.7166,
+      "step": 129
+    },
+    {
+      "epoch": 1.7256637168141593,
+      "grad_norm": 0.2954822813324762,
+      "learning_rate": 4.534103662579643e-06,
+      "loss": 0.7078,
+      "step": 130
+    },
+    {
+      "epoch": 1.7389380530973453,
+      "grad_norm": 0.26995487436514215,
+      "learning_rate": 4.456739249572628e-06,
+      "loss": 0.7192,
+      "step": 131
+    },
+    {
+      "epoch": 1.752212389380531,
+      "grad_norm": 0.26773767932102494,
+      "learning_rate": 4.379506236933703e-06,
+      "loss": 0.7186,
+      "step": 132
+    },
+    {
+      "epoch": 1.7654867256637168,
+      "grad_norm": 0.257637247498496,
+      "learning_rate": 4.3024233052803855e-06,
+      "loss": 0.7214,
+      "step": 133
+    },
+    {
+      "epoch": 1.7787610619469025,
+      "grad_norm": 0.2875621691724459,
+      "learning_rate": 4.2255090989295765e-06,
+      "loss": 0.7155,
+      "step": 134
+    },
+    {
+      "epoch": 1.7920353982300885,
+      "grad_norm": 0.29010788059474596,
+      "learning_rate": 4.148782221388007e-06,
+      "loss": 0.709,
+      "step": 135
+    },
+    {
+      "epoch": 1.8053097345132745,
+      "grad_norm": 0.2588099571871009,
+      "learning_rate": 4.072261230852534e-06,
+      "loss": 0.7042,
+      "step": 136
+    },
+    {
+      "epoch": 1.8185840707964602,
+      "grad_norm": 0.2664579826688701,
+      "learning_rate": 3.995964635721409e-06,
+      "loss": 0.7182,
+      "step": 137
+    },
+    {
+      "epoch": 1.831858407079646,
+      "grad_norm": 0.27721920237328196,
+      "learning_rate": 3.919910890117584e-06,
+      "loss": 0.7082,
+      "step": 138
+    },
+    {
+      "epoch": 1.8451327433628317,
+      "grad_norm": 0.27627030502639816,
+      "learning_rate": 3.844118389425154e-06,
+      "loss": 0.7329,
+      "step": 139
+    },
+    {
+      "epoch": 1.8584070796460177,
+      "grad_norm": 0.2913739464055808,
+      "learning_rate": 3.768605465839994e-06,
+      "loss": 0.7173,
+      "step": 140
+    },
+    {
+      "epoch": 1.8716814159292037,
+      "grad_norm": 0.2850484954797806,
+      "learning_rate": 3.6933903839356983e-06,
+      "loss": 0.7221,
+      "step": 141
+    },
+    {
+      "epoch": 1.8849557522123894,
+      "grad_norm": 0.25821886946143024,
+      "learning_rate": 3.6184913362458497e-06,
+      "loss": 0.7315,
+      "step": 142
+    },
+    {
+      "epoch": 1.8982300884955752,
+      "grad_norm": 0.2569518339216896,
+      "learning_rate": 3.5439264388637407e-06,
+      "loss": 0.7154,
+      "step": 143
+    },
+    {
+      "epoch": 1.911504424778761,
+      "grad_norm": 0.2648943046537424,
+      "learning_rate": 3.469713727060564e-06,
+      "loss": 0.7221,
+      "step": 144
+    },
+    {
+      "epoch": 1.924778761061947,
+      "grad_norm": 0.32763318064063895,
+      "learning_rate": 3.3958711509231627e-06,
+      "loss": 0.7675,
+      "step": 145
+    },
+    {
+      "epoch": 1.9380530973451329,
+      "grad_norm": 0.2653495628703862,
+      "learning_rate": 3.322416571012376e-06,
+      "loss": 0.7343,
+      "step": 146
+    },
+    {
+      "epoch": 1.9513274336283186,
+      "grad_norm": 0.2702072967100288,
+      "learning_rate": 3.249367754043047e-06,
+      "loss": 0.7341,
+      "step": 147
+    },
+    {
+      "epoch": 1.9646017699115044,
+      "grad_norm": 0.2803919016892307,
+      "learning_rate": 3.176742368586725e-06,
+      "loss": 0.7222,
+      "step": 148
+    },
+    {
+      "epoch": 1.9778761061946901,
+      "grad_norm": 0.25493487382341745,
+      "learning_rate": 3.104557980798104e-06,
+      "loss": 0.7172,
+      "step": 149
+    },
+    {
+      "epoch": 1.991150442477876,
+      "grad_norm": 0.2570628171188845,
+      "learning_rate": 3.032832050166239e-06,
+      "loss": 0.7224,
+      "step": 150
+    },
+    {
+      "epoch": 2.004424778761062,
+      "grad_norm": 0.267565604708211,
+      "learning_rate": 2.961581925291557e-06,
+      "loss": 0.7017,
+      "step": 151
+    },
+    {
+      "epoch": 2.017699115044248,
+      "grad_norm": 0.26815503106911354,
+      "learning_rate": 2.8908248396896893e-06,
+      "loss": 0.7,
+      "step": 152
+    },
+    {
+      "epoch": 2.0309734513274336,
+      "grad_norm": 0.26249885130766193,
+      "learning_rate": 2.820577907623145e-06,
+      "loss": 0.7034,
+      "step": 153
+    },
+    {
+      "epoch": 2.0442477876106193,
+      "grad_norm": 0.2549779907951391,
+      "learning_rate": 2.750858119961821e-06,
+      "loss": 0.7078,
+      "step": 154
+    },
+    {
+      "epoch": 2.0575221238938055,
+      "grad_norm": 0.2525346837688464,
+      "learning_rate": 2.6816823400733628e-06,
+      "loss": 0.6995,
+      "step": 155
+    },
+    {
+      "epoch": 2.0707964601769913,
+      "grad_norm": 0.2679663133077141,
+      "learning_rate": 2.613067299744364e-06,
+      "loss": 0.7055,
+      "step": 156
+    },
+    {
+      "epoch": 2.084070796460177,
+      "grad_norm": 0.2586016464525557,
+      "learning_rate": 2.5450295951333896e-06,
+      "loss": 0.6959,
+      "step": 157
+    },
+    {
+      "epoch": 2.0973451327433628,
+      "grad_norm": 0.30308624026957554,
+      "learning_rate": 2.4775856827568016e-06,
+      "loss": 0.6883,
+      "step": 158
+    },
+    {
+      "epoch": 2.1106194690265485,
+      "grad_norm": 0.27265295782990395,
+      "learning_rate": 2.410751875508373e-06,
+      "loss": 0.6695,
+      "step": 159
+    },
+    {
+      "epoch": 2.1238938053097347,
+      "grad_norm": 0.2700979984703012,
+      "learning_rate": 2.3445443387136247e-06,
+      "loss": 0.6957,
+      "step": 160
+    },
+    {
+      "epoch": 2.1371681415929205,
+      "grad_norm": 0.30092750399401313,
+      "learning_rate": 2.278979086219863e-06,
+      "loss": 0.6828,
+      "step": 161
+    },
+    {
+      "epoch": 2.150442477876106,
+      "grad_norm": 0.29172927343524324,
+      "learning_rate": 2.2140719765228587e-06,
+      "loss": 0.7153,
+      "step": 162
+    },
+    {
+      "epoch": 2.163716814159292,
+      "grad_norm": 0.26968822161138883,
+      "learning_rate": 2.149838708931087e-06,
+      "loss": 0.703,
+      "step": 163
+    },
+    {
+      "epoch": 2.1769911504424777,
+      "grad_norm": 0.2572024987696099,
+      "learning_rate": 2.086294819768496e-06,
+      "loss": 0.6879,
+      "step": 164
+    },
+    {
+      "epoch": 2.190265486725664,
+      "grad_norm": 0.26928155454929387,
+      "learning_rate": 2.0234556786166715e-06,
+      "loss": 0.6988,
+      "step": 165
+    },
+    {
+      "epoch": 2.2035398230088497,
+      "grad_norm": 0.27668720512764094,
+      "learning_rate": 1.9613364845973433e-06,
+      "loss": 0.7004,
+      "step": 166
+    },
+    {
+      "epoch": 2.2168141592920354,
+      "grad_norm": 0.2618962828624147,
+      "learning_rate": 1.8999522626961254e-06,
+      "loss": 0.6835,
+      "step": 167
+    },
+    {
+      "epoch": 2.230088495575221,
+      "grad_norm": 0.2559019455661947,
+      "learning_rate": 1.8393178601283684e-06,
+      "loss": 0.6954,
+      "step": 168
+    },
+    {
+      "epoch": 2.243362831858407,
+      "grad_norm": 0.2586893846210169,
+      "learning_rate": 1.7794479427480115e-06,
+      "loss": 0.7103,
+      "step": 169
+    },
+    {
+      "epoch": 2.256637168141593,
+      "grad_norm": 0.27637512548980897,
+      "learning_rate": 1.7203569915003005e-06,
+      "loss": 0.7001,
+      "step": 170
+    },
+    {
+      "epoch": 2.269911504424779,
+      "grad_norm": 0.25343974808714076,
+      "learning_rate": 1.6620592989192318e-06,
+      "loss": 0.7123,
+      "step": 171
+    },
+    {
+      "epoch": 2.2831858407079646,
+      "grad_norm": 0.24237088389234168,
+      "learning_rate": 1.6045689656705715e-06,
+      "loss": 0.6823,
+      "step": 172
+    },
+    {
+      "epoch": 2.2964601769911503,
+      "grad_norm": 0.2711005680287586,
+      "learning_rate": 1.5478998971412669e-06,
+      "loss": 0.6891,
+      "step": 173
+    },
+    {
+      "epoch": 2.309734513274336,
+      "grad_norm": 0.27026911575300705,
+      "learning_rate": 1.4920658000761172e-06,
+      "loss": 0.683,
+      "step": 174
+    },
+    {
+      "epoch": 2.3230088495575223,
+      "grad_norm": 0.2675921091939595,
+      "learning_rate": 1.4370801792624656e-06,
+      "loss": 0.7062,
+      "step": 175
+    },
+    {
+      "epoch": 2.336283185840708,
+      "grad_norm": 0.250664626986251,
+      "learning_rate": 1.3829563342637514e-06,
+      "loss": 0.6941,
+      "step": 176
+    },
+    {
+      "epoch": 2.349557522123894,
+      "grad_norm": 0.2318767325573604,
+      "learning_rate": 1.3297073562026992e-06,
+      "loss": 0.696,
+      "step": 177
+    },
+    {
+      "epoch": 2.3628318584070795,
+      "grad_norm": 0.24483698072857207,
+      "learning_rate": 1.2773461245949249e-06,
+      "loss": 0.6904,
+      "step": 178
+    },
+    {
+      "epoch": 2.3761061946902653,
+      "grad_norm": 0.24702478932419128,
+      "learning_rate": 1.225885304233716e-06,
+      "loss": 0.6939,
+      "step": 179
+    },
+    {
+      "epoch": 2.3893805309734515,
+      "grad_norm": 0.24194451250650229,
+      "learning_rate": 1.1753373421267622e-06,
+      "loss": 0.6797,
+      "step": 180
+    },
+    {
+      "epoch": 2.4026548672566372,
+      "grad_norm": 0.2645341332285249,
+      "learning_rate": 1.125714464485551e-06,
+      "loss": 0.6966,
+      "step": 181
+    },
+    {
+      "epoch": 2.415929203539823,
+      "grad_norm": 0.2534238881143905,
+      "learning_rate": 1.0770286737681701e-06,
+      "loss": 0.6885,
+      "step": 182
+    },
+    {
+      "epoch": 2.4292035398230087,
+      "grad_norm": 0.25437197528124134,
+      "learning_rate": 1.0292917457762325e-06,
+      "loss": 0.7007,
+      "step": 183
+    },
+    {
+      "epoch": 2.442477876106195,
+      "grad_norm": 0.24736717833800334,
+      "learning_rate": 9.825152268066213e-07,
+      "loss": 0.6807,
+      "step": 184
+    },
+    {
+      "epoch": 2.4557522123893807,
+      "grad_norm": 0.22872199162900433,
+      "learning_rate": 9.367104308587493e-07,
+      "loss": 0.6987,
+      "step": 185
+    },
+    {
+      "epoch": 2.4690265486725664,
+      "grad_norm": 0.24419690309952968,
+      "learning_rate": 8.918884368979969e-07,
+      "loss": 0.6749,
+      "step": 186
+    },
+    {
+      "epoch": 2.482300884955752,
+      "grad_norm": 0.2512421685702932,
+      "learning_rate": 8.480600861760124e-07,
+      "loss": 0.7019,
+      "step": 187
+    },
+    {
+      "epoch": 2.495575221238938,
+      "grad_norm": 0.2282816625905513,
+      "learning_rate": 8.052359796084952e-07,
+      "loss": 0.6816,
+      "step": 188
+    },
+    {
+      "epoch": 2.508849557522124,
+      "grad_norm": 0.23523586566320434,
+      "learning_rate": 7.634264752111131e-07,
+      "loss": 0.68,
+      "step": 189
+    },
+    {
+      "epoch": 2.52212389380531,
+      "grad_norm": 0.2363793146961199,
+      "learning_rate": 7.226416855941814e-07,
+      "loss": 0.7033,
+      "step": 190
+    },
+    {
+      "epoch": 2.5353982300884956,
+      "grad_norm": 0.24298969213909608,
+      "learning_rate": 6.828914755166826e-07,
+      "loss": 0.6979,
+      "step": 191
+    },
+    {
+      "epoch": 2.5486725663716814,
+      "grad_norm": 0.251085353078741,
+      "learning_rate": 6.441854595002478e-07,
+      "loss": 0.6809,
+      "step": 192
+    },
+    {
+      "epoch": 2.561946902654867,
+      "grad_norm": 0.2448680893471181,
+      "learning_rate": 6.065329995036573e-07,
+      "loss": 0.7131,
+      "step": 193
+    },
+    {
+      "epoch": 2.5752212389380533,
+      "grad_norm": 0.23725089777367897,
+      "learning_rate": 5.699432026584267e-07,
+      "loss": 0.6959,
+      "step": 194
+    },
+    {
+      "epoch": 2.588495575221239,
+      "grad_norm": 0.23157485314336165,
+      "learning_rate": 5.344249190660427e-07,
+      "loss": 0.7001,
+      "step": 195
+    },
+    {
+      "epoch": 2.601769911504425,
+      "grad_norm": 0.23391962016161583,
+      "learning_rate": 4.999867396573499e-07,
+      "loss": 0.6893,
+      "step": 196
+    },
+    {
+      "epoch": 2.6150442477876106,
+      "grad_norm": 0.236263144354454,
+      "learning_rate": 4.666369941146376e-07,
+      "loss": 0.6937,
+      "step": 197
+    },
+    {
+      "epoch": 2.6283185840707963,
+      "grad_norm": 0.23366739049943105,
+      "learning_rate": 4.343837488569058e-07,
+      "loss": 0.6943,
+      "step": 198
+    },
+    {
+      "epoch": 2.6415929203539825,
+      "grad_norm": 0.2362436163336678,
+      "learning_rate": 4.03234805088818e-07,
+      "loss": 0.7204,
+      "step": 199
+    },
+    {
+      "epoch": 2.6548672566371683,
+      "grad_norm": 0.23416015494584175,
+      "learning_rate": 3.7319769691379295e-07,
+      "loss": 0.6887,
+      "step": 200
+    },
+    {
+      "epoch": 2.668141592920354,
+      "grad_norm": 0.23617669670661126,
+      "learning_rate": 3.4427968951170287e-07,
+      "loss": 0.7037,
+      "step": 201
+    },
+    {
+      "epoch": 2.6814159292035398,
+      "grad_norm": 0.24035284150274663,
+      "learning_rate": 3.1648777738162496e-07,
+      "loss": 0.702,
+      "step": 202
+    },
+    {
+      "epoch": 2.6946902654867255,
+      "grad_norm": 0.22345558795205156,
+      "learning_rate": 2.8982868265005457e-07,
+      "loss": 0.684,
+      "step": 203
+    },
+    {
+      "epoch": 2.7079646017699117,
+      "grad_norm": 0.22664491638297707,
+      "learning_rate": 2.6430885344499944e-07,
+      "loss": 0.7095,
+      "step": 204
+    },
+    {
+      "epoch": 2.7212389380530975,
+      "grad_norm": 0.23480608139334605,
+      "learning_rate": 2.399344623363503e-07,
+      "loss": 0.6892,
+      "step": 205
+    },
+    {
+      "epoch": 2.734513274336283,
+      "grad_norm": 0.2286804361911203,
+      "learning_rate": 2.1671140484290144e-07,
+      "loss": 0.6904,
+      "step": 206
+    },
+    {
+      "epoch": 2.747787610619469,
+      "grad_norm": 0.2368767359746762,
+      "learning_rate": 1.9464529800637731e-07,
+      "loss": 0.6816,
+      "step": 207
+    },
+    {
+      "epoch": 2.7610619469026547,
+      "grad_norm": 0.22986090669280276,
+      "learning_rate": 1.737414790328218e-07,
+      "loss": 0.7106,
+      "step": 208
+    },
+    {
+      "epoch": 2.774336283185841,
+      "grad_norm": 0.22856046175085815,
+      "learning_rate": 1.540050040016694e-07,
+      "loss": 0.6838,
+      "step": 209
+    },
+    {
+      "epoch": 2.7876106194690267,
+      "grad_norm": 0.23620045893690103,
+      "learning_rate": 1.3544064664281266e-07,
+      "loss": 0.6835,
+      "step": 210
+    },
+    {
+      "epoch": 2.8008849557522124,
+      "grad_norm": 0.22791291798965643,
+      "learning_rate": 1.1805289718196499e-07,
+      "loss": 0.7034,
+      "step": 211
+    },
+    {
+      "epoch": 2.814159292035398,
+      "grad_norm": 0.2369430962945639,
+      "learning_rate": 1.0184596125459134e-07,
+      "loss": 0.6882,
+      "step": 212
+    },
+    {
+      "epoch": 2.827433628318584,
+      "grad_norm": 0.22918753871731054,
+      "learning_rate": 8.682375888868167e-08,
+      "loss": 0.6952,
+      "step": 213
+    },
+    {
+      "epoch": 2.84070796460177,
+      "grad_norm": 0.2370616166930934,
+      "learning_rate": 7.29899235565934e-08,
+      "loss": 0.6998,
+      "step": 214
+    },
+    {
+      "epoch": 2.853982300884956,
+      "grad_norm": 0.22596145625094352,
+      "learning_rate": 6.034780129621664e-08,
+      "loss": 0.6918,
+      "step": 215
+    },
+    {
+      "epoch": 2.8672566371681416,
+      "grad_norm": 0.23262221148740786,
+      "learning_rate": 4.8900449901653214e-08,
+      "loss": 0.6887,
+      "step": 216
+    },
+    {
+      "epoch": 2.8805309734513274,
+      "grad_norm": 0.24233993030152726,
+      "learning_rate": 3.8650638183617695e-08,
+      "loss": 0.6984,
+      "step": 217
+    },
+    {
+      "epoch": 2.893805309734513,
+      "grad_norm": 0.22180097024671025,
+      "learning_rate": 2.960084529973706e-08,
+      "loss": 0.6982,
+      "step": 218
+    },
+    {
+      "epoch": 2.9070796460176993,
+      "grad_norm": 0.2299320357668445,
+      "learning_rate": 2.1753260154906973e-08,
+      "loss": 0.6907,
+      "step": 219
+    },
+    {
+      "epoch": 2.920353982300885,
+      "grad_norm": 0.24963653707358402,
+      "learning_rate": 1.5109780871853663e-08,
+      "loss": 0.6966,
+      "step": 220
+    },
+    {
+      "epoch": 2.933628318584071,
+      "grad_norm": 0.23346145464997622,
+      "learning_rate": 9.672014332028357e-09,
+      "loss": 0.6937,
+      "step": 221
+    },
+    {
+      "epoch": 2.9469026548672566,
+      "grad_norm": 0.2293849764149983,
+      "learning_rate": 5.4412757869459765e-09,
+      "loss": 0.7024,
+      "step": 222
+    },
+    {
+      "epoch": 2.9601769911504423,
+      "grad_norm": 0.23761192295842704,
+      "learning_rate": 2.4185885400596076e-09,
+      "loss": 0.686,
+      "step": 223
+    },
+    {
+      "epoch": 2.9734513274336285,
+      "grad_norm": 0.234006094580547,
+      "learning_rate": 6.04683699252373e-10,
+      "loss": 0.7013,
+      "step": 224
+    },
+    {
+      "epoch": 2.9867256637168142,
+      "grad_norm": 0.2434351223584646,
+      "learning_rate": 0.0,
+      "loss": 0.7003,
+      "step": 225
+    },
+    {
+      "epoch": 2.9867256637168142,
+      "step": 225,
+      "total_flos": 7.721927725170033e+17,
+      "train_loss": 0.7663452034526401,
+      "train_runtime": 7882.5173,
+      "train_samples_per_second": 2.745,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.721927725170033e+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 sha256:7abb361235cd827bf99c162d2b5925bf25634ae167580933db6755031cf48135
+size 7416