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": 2.9904153354632586,
+    "total_flos": 4.367681917432627e+17,
+    "train_loss": 0.6496183709838451,
+    "train_runtime": 9740.0942,
+    "train_samples_per_second": 3.08,
+    "train_steps_per_second": 0.032
+}

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:ce47c03904dba8be8bf6a6e3c44caee426ef1b12adef7529700b929fb5125a09
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52007a9b0f101748aa3ef6c11c3d1547d55e602d30f2a3afc65603159d7b827c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e8b356869d634d930772f89955a3dbde39f5bcc41e4ed06ab19e7a09c6a21b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e31bd89d53f99053d5d1f3406d3bdb14472d08e8f03a0a55410c83ba72ce83
+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": 2.9904153354632586,
+    "total_flos": 4.367681917432627e+17,
+    "train_loss": 0.6496183709838451,
+    "train_runtime": 9740.0942,
+    "train_samples_per_second": 3.08,
+    "train_steps_per_second": 0.032
+}

trainer_log.jsonl

@@ -0,0 +1,313 @@
+{"current_steps": 1, "total_steps": 312, "loss": 1.1107, "lr": 3.125e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:38", "remaining_time": "3:17:30"}
+{"current_steps": 2, "total_steps": 312, "loss": 1.1177, "lr": 6.25e-07, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:10", "remaining_time": "3:02:09"}
+{"current_steps": 3, "total_steps": 312, "loss": 1.1165, "lr": 9.375000000000001e-07, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:41", "remaining_time": "2:54:36"}
+{"current_steps": 4, "total_steps": 312, "loss": 1.1067, "lr": 1.25e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:11", "remaining_time": "2:48:58"}
+{"current_steps": 5, "total_steps": 312, "loss": 1.0499, "lr": 1.5625e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:44", "remaining_time": "2:48:10"}
+{"current_steps": 6, "total_steps": 312, "loss": 1.0371, "lr": 1.8750000000000003e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:16", "remaining_time": "2:46:38"}
+{"current_steps": 7, "total_steps": 312, "loss": 1.0494, "lr": 2.1875000000000002e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:46", "remaining_time": "2:44:21"}
+{"current_steps": 8, "total_steps": 312, "loss": 1.0762, "lr": 2.5e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:18", "remaining_time": "2:43:54"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.9586, "lr": 2.8125e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:04:50", "remaining_time": "2:43:10"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.9199, "lr": 3.125e-06, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:05:25", "remaining_time": "2:43:45"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.9448, "lr": 3.4375e-06, "epoch": 0.10543130990415335, "percentage": 3.53, "elapsed_time": "0:05:54", "remaining_time": "2:41:44"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.932, "lr": 3.7500000000000005e-06, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:06:25", "remaining_time": "2:40:26"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.9471, "lr": 4.0625000000000005e-06, "epoch": 0.12460063897763578, "percentage": 4.17, "elapsed_time": "0:06:59", "remaining_time": "2:40:49"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.9282, "lr": 4.3750000000000005e-06, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:07:30", "remaining_time": "2:39:46"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.9321, "lr": 4.6875000000000004e-06, "epoch": 0.14376996805111822, "percentage": 4.81, "elapsed_time": "0:08:01", "remaining_time": "2:38:53"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.8831, "lr": 5e-06, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:08:33", "remaining_time": "2:38:18"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.865, "lr": 5.3125e-06, "epoch": 0.16293929712460065, "percentage": 5.45, "elapsed_time": "0:08:59", "remaining_time": "2:35:57"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.8637, "lr": 5.625e-06, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:09:32", "remaining_time": "2:35:57"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.8407, "lr": 5.9375e-06, "epoch": 0.18210862619808307, "percentage": 6.09, "elapsed_time": "0:10:05", "remaining_time": "2:35:34"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.8496, "lr": 6.25e-06, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:10:36", "remaining_time": "2:34:59"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.7852, "lr": 6.5625e-06, "epoch": 0.2012779552715655, "percentage": 6.73, "elapsed_time": "0:11:07", "remaining_time": "2:34:03"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.8268, "lr": 6.875e-06, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:11:36", "remaining_time": "2:32:58"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.87, "lr": 7.1875e-06, "epoch": 0.22044728434504793, "percentage": 7.37, "elapsed_time": "0:12:08", "remaining_time": "2:32:31"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.8051, "lr": 7.500000000000001e-06, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:12:38", "remaining_time": "2:31:45"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.7869, "lr": 7.8125e-06, "epoch": 0.23961661341853036, "percentage": 8.01, "elapsed_time": "0:13:14", "remaining_time": "2:31:55"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.7946, "lr": 8.125000000000001e-06, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:13:46", "remaining_time": "2:31:32"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.8175, "lr": 8.4375e-06, "epoch": 0.25878594249201275, "percentage": 8.65, "elapsed_time": "0:14:19", "remaining_time": "2:31:10"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.8078, "lr": 8.750000000000001e-06, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:14:49", "remaining_time": "2:30:22"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.7935, "lr": 9.0625e-06, "epoch": 0.2779552715654952, "percentage": 9.29, "elapsed_time": "0:15:20", "remaining_time": "2:29:46"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.7915, "lr": 9.375000000000001e-06, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:15:53", "remaining_time": "2:29:20"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.771, "lr": 9.6875e-06, "epoch": 0.2971246006389776, "percentage": 9.94, "elapsed_time": "0:16:25", "remaining_time": "2:28:53"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.735, "lr": 1e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:16:55", "remaining_time": "2:28:06"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.7474, "lr": 9.999685283773504e-06, "epoch": 0.31629392971246006, "percentage": 10.58, "elapsed_time": "0:17:27", "remaining_time": "2:27:32"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.7496, "lr": 9.998741174712534e-06, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:17:57", "remaining_time": "2:26:49"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.78, "lr": 9.997167791667668e-06, "epoch": 0.3354632587859425, "percentage": 11.22, "elapsed_time": "0:18:29", "remaining_time": "2:26:24"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.7421, "lr": 9.994965332706574e-06, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:19:00", "remaining_time": "2:25:46"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.7473, "lr": 9.992134075089085e-06, "epoch": 0.3546325878594249, "percentage": 11.86, "elapsed_time": "0:19:34", "remaining_time": "2:25:32"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.7495, "lr": 9.98867437523228e-06, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:20:03", "remaining_time": "2:24:39"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.7489, "lr": 9.984586668665641e-06, "epoch": 0.3738019169329074, "percentage": 12.5, "elapsed_time": "0:20:32", "remaining_time": "2:23:48"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.7466, "lr": 9.979871469976197e-06, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:21:00", "remaining_time": "2:22:51"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.7061, "lr": 9.974529372743762e-06, "epoch": 0.3929712460063898, "percentage": 13.14, "elapsed_time": "0:21:28", "remaining_time": "2:21:59"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.7475, "lr": 9.968561049466214e-06, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:21:55", "remaining_time": "2:20:55"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.7191, "lr": 9.961967251474823e-06, "epoch": 0.41214057507987223, "percentage": 13.78, "elapsed_time": "0:22:24", "remaining_time": "2:20:08"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.7258, "lr": 9.954748808839675e-06, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:22:58", "remaining_time": "2:19:56"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.7387, "lr": 9.946906630265184e-06, "epoch": 0.43130990415335463, "percentage": 14.42, "elapsed_time": "0:23:32", "remaining_time": "2:19:40"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.7654, "lr": 9.938441702975689e-06, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:24:04", "remaining_time": "2:19:15"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.7222, "lr": 9.92935509259118e-06, "epoch": 0.4504792332268371, "percentage": 15.06, "elapsed_time": "0:24:36", "remaining_time": "2:18:42"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.7348, "lr": 9.91964794299315e-06, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:25:07", "remaining_time": "2:18:08"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.7483, "lr": 9.909321476180594e-06, "epoch": 0.4696485623003195, "percentage": 15.71, "elapsed_time": "0:25:36", "remaining_time": "2:17:26"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.7098, "lr": 9.898376992116179e-06, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:26:07", "remaining_time": "2:16:56"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.7285, "lr": 9.886815868562596e-06, "epoch": 0.48881789137380194, "percentage": 16.35, "elapsed_time": "0:26:39", "remaining_time": "2:16:28"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.6991, "lr": 9.874639560909118e-06, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:27:13", "remaining_time": "2:16:07"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.7529, "lr": 9.861849601988384e-06, "epoch": 0.5079872204472844, "percentage": 16.99, "elapsed_time": "0:27:40", "remaining_time": "2:15:16"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.7609, "lr": 9.848447601883436e-06, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:28:09", "remaining_time": "2:14:29"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.7336, "lr": 9.834435247725032e-06, "epoch": 0.5271565495207667, "percentage": 17.63, "elapsed_time": "0:28:40", "remaining_time": "2:13:58"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.7087, "lr": 9.819814303479268e-06, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:29:05", "remaining_time": "2:13:01"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.777, "lr": 9.804586609725499e-06, "epoch": 0.5463258785942492, "percentage": 18.27, "elapsed_time": "0:29:36", "remaining_time": "2:12:27"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.7518, "lr": 9.788754083424654e-06, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:30:02", "remaining_time": "2:11:34"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.7085, "lr": 9.772318717677905e-06, "epoch": 0.5654952076677316, "percentage": 18.91, "elapsed_time": "0:30:36", "remaining_time": "2:11:13"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.75, "lr": 9.755282581475769e-06, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:31:10", "remaining_time": "2:10:56"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.7344, "lr": 9.737647819437645e-06, "epoch": 0.5846645367412141, "percentage": 19.55, "elapsed_time": "0:31:39", "remaining_time": "2:10:16"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.7143, "lr": 9.719416651541839e-06, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:32:11", "remaining_time": "2:09:49"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.7163, "lr": 9.700591372846096e-06, "epoch": 0.6038338658146964, "percentage": 20.19, "elapsed_time": "0:32:44", "remaining_time": "2:09:25"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.7334, "lr": 9.681174353198687e-06, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:33:17", "remaining_time": "2:08:59"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.6995, "lr": 9.661168036940071e-06, "epoch": 0.6230031948881789, "percentage": 20.83, "elapsed_time": "0:33:51", "remaining_time": "2:08:38"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.7297, "lr": 9.640574942595195e-06, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:34:22", "remaining_time": "2:08:08"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.7042, "lr": 9.619397662556434e-06, "epoch": 0.6421725239616614, "percentage": 21.47, "elapsed_time": "0:34:48", "remaining_time": "2:07:17"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.7509, "lr": 9.597638862757255e-06, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:35:17", "remaining_time": "2:06:36"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.7036, "lr": 9.5753012823366e-06, "epoch": 0.6613418530351438, "percentage": 22.12, "elapsed_time": "0:35:49", "remaining_time": "2:06:08"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.7685, "lr": 9.552387733294081e-06, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:36:23", "remaining_time": "2:05:47"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.7108, "lr": 9.528901100135971e-06, "epoch": 0.6805111821086262, "percentage": 22.76, "elapsed_time": "0:36:49", "remaining_time": "2:05:01"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.7254, "lr": 9.504844339512096e-06, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:37:16", "remaining_time": "2:04:15"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.6991, "lr": 9.480220479843627e-06, "epoch": 0.6996805111821086, "percentage": 23.4, "elapsed_time": "0:37:48", "remaining_time": "2:03:46"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.718, "lr": 9.45503262094184e-06, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:38:15", "remaining_time": "2:03:03"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.6881, "lr": 9.4292839336179e-06, "epoch": 0.7188498402555911, "percentage": 24.04, "elapsed_time": "0:38:47", "remaining_time": "2:02:34"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.7312, "lr": 9.40297765928369e-06, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:39:17", "remaining_time": "2:02:02"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.7122, "lr": 9.376117109543769e-06, "epoch": 0.7380191693290735, "percentage": 24.68, "elapsed_time": "0:39:48", "remaining_time": "2:01:30"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.7109, "lr": 9.348705665778479e-06, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:40:19", "remaining_time": "2:00:58"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.7056, "lr": 9.320746778718274e-06, "epoch": 0.7571884984025559, "percentage": 25.32, "elapsed_time": "0:40:45", "remaining_time": "2:00:13"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.696, "lr": 9.292243968009332e-06, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:41:15", "remaining_time": "1:59:38"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.7332, "lr": 9.263200821770462e-06, "epoch": 0.7763578274760383, "percentage": 25.96, "elapsed_time": "0:41:42", "remaining_time": "1:58:58"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.6944, "lr": 9.233620996141421e-06, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:42:16", "remaining_time": "1:58:33"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.7478, "lr": 9.203508214822652e-06, "epoch": 0.7955271565495208, "percentage": 26.6, "elapsed_time": "0:42:49", "remaining_time": "1:58:08"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.7252, "lr": 9.172866268606514e-06, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:43:19", "remaining_time": "1:57:36"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.7, "lr": 9.141699014900084e-06, "epoch": 0.8146964856230032, "percentage": 27.24, "elapsed_time": "0:43:52", "remaining_time": "1:57:10"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.6773, "lr": 9.110010377239552e-06, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:44:24", "remaining_time": "1:56:42"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.7296, "lr": 9.077804344796302e-06, "epoch": 0.8338658146964856, "percentage": 27.88, "elapsed_time": "0:44:57", "remaining_time": "1:56:17"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.7017, "lr": 9.045084971874738e-06, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:45:29", "remaining_time": "1:55:48"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.7441, "lr": 9.011856377401891e-06, "epoch": 0.853035143769968, "percentage": 28.53, "elapsed_time": "0:45:59", "remaining_time": "1:55:14"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.7361, "lr": 8.978122744408905e-06, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:46:29", "remaining_time": "1:54:40"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.6952, "lr": 8.943888319504456e-06, "epoch": 0.8722044728434505, "percentage": 29.17, "elapsed_time": "0:47:02", "remaining_time": "1:54:13"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.6944, "lr": 8.90915741234015e-06, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:47:35", "remaining_time": "1:53:49"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.6945, "lr": 8.873934395068006e-06, "epoch": 0.8913738019169329, "percentage": 29.81, "elapsed_time": "0:48:08", "remaining_time": "1:53:22"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.6825, "lr": 8.838223701790057e-06, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:48:40", "remaining_time": "1:52:53"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.7075, "lr": 8.802029828000157e-06, "epoch": 0.9105431309904153, "percentage": 30.45, "elapsed_time": "0:49:09", "remaining_time": "1:52:16"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.7157, "lr": 8.765357330018056e-06, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:49:39", "remaining_time": "1:51:43"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.7014, "lr": 8.728210824415829e-06, "epoch": 0.9297124600638977, "percentage": 31.09, "elapsed_time": "0:50:09", "remaining_time": "1:51:10"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.7267, "lr": 8.690594987436705e-06, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:50:42", "remaining_time": "1:50:43"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.706, "lr": 8.652514554406388e-06, "epoch": 0.9488817891373802, "percentage": 31.73, "elapsed_time": "0:51:17", "remaining_time": "1:50:21"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.6619, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:51:50", "remaining_time": "1:49:54"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.7069, "lr": 8.574979133323378e-06, "epoch": 0.9680511182108626, "percentage": 32.37, "elapsed_time": "0:52:18", "remaining_time": "1:49:16"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.7253, "lr": 8.535533905932739e-06, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:52:49", "remaining_time": "1:48:44"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.678, "lr": 8.495643602586287e-06, "epoch": 0.987220447284345, "percentage": 33.01, "elapsed_time": "0:53:19", "remaining_time": "1:48:13"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.7143, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:53:52", "remaining_time": "1:47:44"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.6676, "lr": 8.414547910024035e-06, "epoch": 1.0063897763578276, "percentage": 33.65, "elapsed_time": "0:54:51", "remaining_time": "1:48:09"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.6234, "lr": 8.373352729660373e-06, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:55:23", "remaining_time": "1:47:38"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.6192, "lr": 8.331732889760021e-06, "epoch": 1.0255591054313098, "percentage": 34.29, "elapsed_time": "0:55:49", "remaining_time": "1:46:57"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.6335, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:56:18", "remaining_time": "1:46:21"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.6148, "lr": 8.247240241650918e-06, "epoch": 1.0447284345047922, "percentage": 34.94, "elapsed_time": "0:56:52", "remaining_time": "1:45:56"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.6204, "lr": 8.204378069925121e-06, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:57:24", "remaining_time": "1:45:24"}
+{"current_steps": 111, "total_steps": 312, "loss": 0.6116, "lr": 8.16111251028955e-06, "epoch": 1.0638977635782747, "percentage": 35.58, "elapsed_time": "0:57:58", "remaining_time": "1:44:58"}
+{"current_steps": 112, "total_steps": 312, "loss": 0.6457, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:58:27", "remaining_time": "1:44:23"}
+{"current_steps": 113, "total_steps": 312, "loss": 0.6246, "lr": 8.073393063582386e-06, "epoch": 1.0830670926517572, "percentage": 36.22, "elapsed_time": "0:58:57", "remaining_time": "1:43:49"}
+{"current_steps": 114, "total_steps": 312, "loss": 0.6342, "lr": 8.0289502192041e-06, "epoch": 1.0926517571884984, "percentage": 36.54, "elapsed_time": "0:59:29", "remaining_time": "1:43:19"}
+{"current_steps": 115, "total_steps": 312, "loss": 0.6439, "lr": 7.984126070912519e-06, "epoch": 1.1022364217252396, "percentage": 36.86, "elapsed_time": "1:00:00", "remaining_time": "1:42:47"}
+{"current_steps": 116, "total_steps": 312, "loss": 0.6205, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "1:00:29", "remaining_time": "1:42:13"}
+{"current_steps": 117, "total_steps": 312, "loss": 0.6241, "lr": 7.89335648089903e-06, "epoch": 1.121405750798722, "percentage": 37.5, "elapsed_time": "1:00:55", "remaining_time": "1:41:32"}
+{"current_steps": 118, "total_steps": 312, "loss": 0.6483, "lr": 7.84742246584226e-06, "epoch": 1.1309904153354633, "percentage": 37.82, "elapsed_time": "1:01:22", "remaining_time": "1:40:54"}
+{"current_steps": 119, "total_steps": 312, "loss": 0.6231, "lr": 7.801129998764014e-06, "epoch": 1.1405750798722045, "percentage": 38.14, "elapsed_time": "1:01:56", "remaining_time": "1:40:27"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.5994, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "1:02:25", "remaining_time": "1:39:53"}
+{"current_steps": 121, "total_steps": 312, "loss": 0.6296, "lr": 7.70749306331863e-06, "epoch": 1.159744408945687, "percentage": 38.78, "elapsed_time": "1:02:56", "remaining_time": "1:39:21"}
+{"current_steps": 122, "total_steps": 312, "loss": 0.6182, "lr": 7.660160382576683e-06, "epoch": 1.1693290734824282, "percentage": 39.1, "elapsed_time": "1:03:30", "remaining_time": "1:38:54"}
+{"current_steps": 123, "total_steps": 312, "loss": 0.6507, "lr": 7.612492823579744e-06, "epoch": 1.1789137380191694, "percentage": 39.42, "elapsed_time": "1:04:02", "remaining_time": "1:38:24"}
+{"current_steps": 124, "total_steps": 312, "loss": 0.63, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "1:04:30", "remaining_time": "1:37:48"}
+{"current_steps": 125, "total_steps": 312, "loss": 0.6101, "lr": 7.516177115029002e-06, "epoch": 1.1980830670926517, "percentage": 40.06, "elapsed_time": "1:04:58", "remaining_time": "1:37:12"}
+{"current_steps": 126, "total_steps": 312, "loss": 0.6097, "lr": 7.467541090321735e-06, "epoch": 1.207667731629393, "percentage": 40.38, "elapsed_time": "1:05:28", "remaining_time": "1:36:39"}
+{"current_steps": 127, "total_steps": 312, "loss": 0.6323, "lr": 7.4185944355261996e-06, "epoch": 1.2172523961661341, "percentage": 40.71, "elapsed_time": "1:06:00", "remaining_time": "1:36:09"}
+{"current_steps": 128, "total_steps": 312, "loss": 0.6205, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "1:06:33", "remaining_time": "1:35:40"}
+{"current_steps": 129, "total_steps": 312, "loss": 0.5997, "lr": 7.319793920889171e-06, "epoch": 1.2364217252396166, "percentage": 41.35, "elapsed_time": "1:07:05", "remaining_time": "1:35:10"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.6221, "lr": 7.269952498697734e-06, "epoch": 1.2460063897763578, "percentage": 41.67, "elapsed_time": "1:07:36", "remaining_time": "1:34:38"}
+{"current_steps": 131, "total_steps": 312, "loss": 0.6302, "lr": 7.219825320152411e-06, "epoch": 1.255591054313099, "percentage": 41.99, "elapsed_time": "1:08:03", "remaining_time": "1:34:01"}
+{"current_steps": 132, "total_steps": 312, "loss": 0.6076, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "1:08:35", "remaining_time": "1:33:32"}
+{"current_steps": 133, "total_steps": 312, "loss": 0.619, "lr": 7.118738970516944e-06, "epoch": 1.2747603833865815, "percentage": 42.63, "elapsed_time": "1:09:08", "remaining_time": "1:33:03"}
+{"current_steps": 134, "total_steps": 312, "loss": 0.6104, "lr": 7.067792524832604e-06, "epoch": 1.2843450479233227, "percentage": 42.95, "elapsed_time": "1:09:40", "remaining_time": "1:32:33"}
+{"current_steps": 135, "total_steps": 312, "loss": 0.6119, "lr": 7.016585772004026e-06, "epoch": 1.293929712460064, "percentage": 43.27, "elapsed_time": "1:10:05", "remaining_time": "1:31:53"}
+{"current_steps": 136, "total_steps": 312, "loss": 0.6136, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "1:10:34", "remaining_time": "1:31:20"}
+{"current_steps": 137, "total_steps": 312, "loss": 0.6245, "lr": 6.913417161825449e-06, "epoch": 1.3130990415335464, "percentage": 43.91, "elapsed_time": "1:11:05", "remaining_time": "1:30:49"}
+{"current_steps": 138, "total_steps": 312, "loss": 0.6218, "lr": 6.8614682920097265e-06, "epoch": 1.3226837060702876, "percentage": 44.23, "elapsed_time": "1:11:38", "remaining_time": "1:30:20"}
+{"current_steps": 139, "total_steps": 312, "loss": 0.6018, "lr": 6.809285088483361e-06, "epoch": 1.3322683706070286, "percentage": 44.55, "elapsed_time": "1:12:12", "remaining_time": "1:29:52"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.6105, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "1:12:37", "remaining_time": "1:29:13"}
+{"current_steps": 141, "total_steps": 312, "loss": 0.6114, "lr": 6.704241985612625e-06, "epoch": 1.351437699680511, "percentage": 45.19, "elapsed_time": "1:13:07", "remaining_time": "1:28:40"}
+{"current_steps": 142, "total_steps": 312, "loss": 0.5887, "lr": 6.651395309775837e-06, "epoch": 1.3610223642172525, "percentage": 45.51, "elapsed_time": "1:13:39", "remaining_time": "1:28:10"}
+{"current_steps": 143, "total_steps": 312, "loss": 0.6531, "lr": 6.598340745578908e-06, "epoch": 1.3706070287539935, "percentage": 45.83, "elapsed_time": "1:14:09", "remaining_time": "1:27:38"}
+{"current_steps": 144, "total_steps": 312, "loss": 0.6384, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "1:14:36", "remaining_time": "1:27:02"}
+{"current_steps": 145, "total_steps": 312, "loss": 0.6243, "lr": 6.491634692845781e-06, "epoch": 1.389776357827476, "percentage": 46.47, "elapsed_time": "1:15:02", "remaining_time": "1:26:26"}
+{"current_steps": 146, "total_steps": 312, "loss": 0.6022, "lr": 6.437996637160086e-06, "epoch": 1.3993610223642172, "percentage": 46.79, "elapsed_time": "1:15:33", "remaining_time": "1:25:54"}
+{"current_steps": 147, "total_steps": 312, "loss": 0.6286, "lr": 6.384177557124247e-06, "epoch": 1.4089456869009584, "percentage": 47.12, "elapsed_time": "1:16:05", "remaining_time": "1:25:24"}
+{"current_steps": 148, "total_steps": 312, "loss": 0.6325, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "1:16:38", "remaining_time": "1:24:56"}
+{"current_steps": 149, "total_steps": 312, "loss": 0.6116, "lr": 6.276023446318214e-06, "epoch": 1.428115015974441, "percentage": 47.76, "elapsed_time": "1:17:06", "remaining_time": "1:24:21"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.613, "lr": 6.2217020306894705e-06, "epoch": 1.4376996805111821, "percentage": 48.08, "elapsed_time": "1:17:37", "remaining_time": "1:23:49"}
+{"current_steps": 151, "total_steps": 312, "loss": 0.6349, "lr": 6.1672268192795285e-06, "epoch": 1.4472843450479234, "percentage": 48.4, "elapsed_time": "1:18:07", "remaining_time": "1:23:17"}
+{"current_steps": 152, "total_steps": 312, "loss": 0.6382, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:18:37", "remaining_time": "1:22:45"}
+{"current_steps": 153, "total_steps": 312, "loss": 0.6132, "lr": 6.057842458386315e-06, "epoch": 1.4664536741214058, "percentage": 49.04, "elapsed_time": "1:19:10", "remaining_time": "1:22:16"}
+{"current_steps": 154, "total_steps": 312, "loss": 0.6323, "lr": 6.002947078916365e-06, "epoch": 1.476038338658147, "percentage": 49.36, "elapsed_time": "1:19:40", "remaining_time": "1:21:44"}
+{"current_steps": 155, "total_steps": 312, "loss": 0.6107, "lr": 5.947925441958393e-06, "epoch": 1.4856230031948883, "percentage": 49.68, "elapsed_time": "1:20:07", "remaining_time": "1:21:09"}
+{"current_steps": 156, "total_steps": 312, "loss": 0.6227, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:20:37", "remaining_time": "1:20:37"}
+{"current_steps": 157, "total_steps": 312, "loss": 0.6237, "lr": 5.837531116523683e-06, "epoch": 1.5047923322683707, "percentage": 50.32, "elapsed_time": "1:21:10", "remaining_time": "1:20:08"}
+{"current_steps": 158, "total_steps": 312, "loss": 0.6297, "lr": 5.782172325201155e-06, "epoch": 1.5143769968051117, "percentage": 50.64, "elapsed_time": "1:21:39", "remaining_time": "1:19:35"}
+{"current_steps": 159, "total_steps": 312, "loss": 0.6197, "lr": 5.726715068949564e-06, "epoch": 1.5239616613418532, "percentage": 50.96, "elapsed_time": "1:22:08", "remaining_time": "1:19:02"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.6154, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:22:42", "remaining_time": "1:18:34"}
+{"current_steps": 161, "total_steps": 312, "loss": 0.624, "lr": 5.615533098453215e-06, "epoch": 1.5431309904153354, "percentage": 51.6, "elapsed_time": "1:23:13", "remaining_time": "1:18:03"}
+{"current_steps": 162, "total_steps": 312, "loss": 0.6079, "lr": 5.559822380516539e-06, "epoch": 1.5527156549520766, "percentage": 51.92, "elapsed_time": "1:23:40", "remaining_time": "1:17:28"}
+{"current_steps": 163, "total_steps": 312, "loss": 0.6326, "lr": 5.504041188505022e-06, "epoch": 1.5623003194888179, "percentage": 52.24, "elapsed_time": "1:24:11", "remaining_time": "1:16:57"}
+{"current_steps": 164, "total_steps": 312, "loss": 0.6246, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:24:46", "remaining_time": "1:16:30"}
+{"current_steps": 165, "total_steps": 312, "loss": 0.6181, "lr": 5.392295478639226e-06, "epoch": 1.5814696485623003, "percentage": 52.88, "elapsed_time": "1:25:18", "remaining_time": "1:16:00"}
+{"current_steps": 166, "total_steps": 312, "loss": 0.5863, "lr": 5.336345028060199e-06, "epoch": 1.5910543130990416, "percentage": 53.21, "elapsed_time": "1:25:51", "remaining_time": "1:15:30"}
+{"current_steps": 167, "total_steps": 312, "loss": 0.6022, "lr": 5.2803522361859596e-06, "epoch": 1.6006389776357828, "percentage": 53.53, "elapsed_time": "1:26:22", "remaining_time": "1:14:59"}
+{"current_steps": 168, "total_steps": 312, "loss": 0.5895, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:26:52", "remaining_time": "1:14:28"}
+{"current_steps": 169, "total_steps": 312, "loss": 0.5819, "lr": 5.168267827938971e-06, "epoch": 1.619808306709265, "percentage": 54.17, "elapsed_time": "1:27:24", "remaining_time": "1:13:58"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.6221, "lr": 5.112190321479026e-06, "epoch": 1.6293929712460065, "percentage": 54.49, "elapsed_time": "1:27:51", "remaining_time": "1:13:23"}
+{"current_steps": 171, "total_steps": 312, "loss": 0.6216, "lr": 5.05609869177323e-06, "epoch": 1.6389776357827475, "percentage": 54.81, "elapsed_time": "1:28:20", "remaining_time": "1:12:50"}
+{"current_steps": 172, "total_steps": 312, "loss": 0.6331, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:28:53", "remaining_time": "1:12:20"}
+{"current_steps": 173, "total_steps": 312, "loss": 0.6208, "lr": 4.943901308226771e-06, "epoch": 1.65814696485623, "percentage": 55.45, "elapsed_time": "1:29:22", "remaining_time": "1:11:48"}
+{"current_steps": 174, "total_steps": 312, "loss": 0.6244, "lr": 4.887809678520976e-06, "epoch": 1.6677316293929714, "percentage": 55.77, "elapsed_time": "1:29:52", "remaining_time": "1:11:16"}
+{"current_steps": 175, "total_steps": 312, "loss": 0.6057, "lr": 4.831732172061032e-06, "epoch": 1.6773162939297124, "percentage": 56.09, "elapsed_time": "1:30:22", "remaining_time": "1:10:45"}
+{"current_steps": 176, "total_steps": 312, "loss": 0.6224, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:30:56", "remaining_time": "1:10:16"}
+{"current_steps": 177, "total_steps": 312, "loss": 0.6295, "lr": 4.719647763814041e-06, "epoch": 1.6964856230031948, "percentage": 56.73, "elapsed_time": "1:31:26", "remaining_time": "1:09:44"}
+{"current_steps": 178, "total_steps": 312, "loss": 0.6178, "lr": 4.663654971939802e-06, "epoch": 1.706070287539936, "percentage": 57.05, "elapsed_time": "1:32:00", "remaining_time": "1:09:15"}
+{"current_steps": 179, "total_steps": 312, "loss": 0.6038, "lr": 4.6077045213607765e-06, "epoch": 1.7156549520766773, "percentage": 57.37, "elapsed_time": "1:32:31", "remaining_time": "1:08:44"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.6119, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:33:02", "remaining_time": "1:08:13"}
+{"current_steps": 181, "total_steps": 312, "loss": 0.6036, "lr": 4.4959588114949785e-06, "epoch": 1.7348242811501597, "percentage": 58.01, "elapsed_time": "1:33:33", "remaining_time": "1:07:42"}
+{"current_steps": 182, "total_steps": 312, "loss": 0.6035, "lr": 4.4401776194834615e-06, "epoch": 1.744408945686901, "percentage": 58.33, "elapsed_time": "1:34:06", "remaining_time": "1:07:12"}
+{"current_steps": 183, "total_steps": 312, "loss": 0.6128, "lr": 4.384466901546786e-06, "epoch": 1.7539936102236422, "percentage": 58.65, "elapsed_time": "1:34:36", "remaining_time": "1:06:41"}
+{"current_steps": 184, "total_steps": 312, "loss": 0.5901, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:35:02", "remaining_time": "1:06:07"}
+{"current_steps": 185, "total_steps": 312, "loss": 0.6313, "lr": 4.273284931050438e-06, "epoch": 1.7731629392971247, "percentage": 59.29, "elapsed_time": "1:35:26", "remaining_time": "1:05:31"}
+{"current_steps": 186, "total_steps": 312, "loss": 0.6166, "lr": 4.217827674798845e-06, "epoch": 1.7827476038338657, "percentage": 59.62, "elapsed_time": "1:36:01", "remaining_time": "1:05:02"}
+{"current_steps": 187, "total_steps": 312, "loss": 0.628, "lr": 4.162468883476319e-06, "epoch": 1.792332268370607, "percentage": 59.94, "elapsed_time": "1:36:35", "remaining_time": "1:04:34"}
+{"current_steps": 188, "total_steps": 312, "loss": 0.6344, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:37:03", "remaining_time": "1:04:00"}
+{"current_steps": 189, "total_steps": 312, "loss": 0.6376, "lr": 4.052074558041608e-06, "epoch": 1.8115015974440896, "percentage": 60.58, "elapsed_time": "1:37:29", "remaining_time": "1:03:27"}
+{"current_steps": 190, "total_steps": 312, "loss": 0.5847, "lr": 3.997052921083637e-06, "epoch": 1.8210862619808306, "percentage": 60.9, "elapsed_time": "1:38:02", "remaining_time": "1:02:57"}
+{"current_steps": 191, "total_steps": 312, "loss": 0.6211, "lr": 3.9421575416136866e-06, "epoch": 1.830670926517572, "percentage": 61.22, "elapsed_time": "1:38:34", "remaining_time": "1:02:27"}
+{"current_steps": 192, "total_steps": 312, "loss": 0.6119, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:39:03", "remaining_time": "1:01:54"}
+{"current_steps": 193, "total_steps": 312, "loss": 0.6265, "lr": 3.832773180720475e-06, "epoch": 1.8498402555910545, "percentage": 61.86, "elapsed_time": "1:39:34", "remaining_time": "1:01:23"}
+{"current_steps": 194, "total_steps": 312, "loss": 0.6256, "lr": 3.778297969310529e-06, "epoch": 1.8594249201277955, "percentage": 62.18, "elapsed_time": "1:40:04", "remaining_time": "1:00:52"}
+{"current_steps": 195, "total_steps": 312, "loss": 0.5961, "lr": 3.723976553681787e-06, "epoch": 1.8690095846645367, "percentage": 62.5, "elapsed_time": "1:40:32", "remaining_time": "1:00:19"}
+{"current_steps": 196, "total_steps": 312, "loss": 0.5961, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:41:05", "remaining_time": "0:59:49"}
+{"current_steps": 197, "total_steps": 312, "loss": 0.6051, "lr": 3.6158224428757538e-06, "epoch": 1.8881789137380192, "percentage": 63.14, "elapsed_time": "1:41:33", "remaining_time": "0:59:16"}
+{"current_steps": 198, "total_steps": 312, "loss": 0.6515, "lr": 3.562003362839914e-06, "epoch": 1.8977635782747604, "percentage": 63.46, "elapsed_time": "1:42:04", "remaining_time": "0:58:46"}
+{"current_steps": 199, "total_steps": 312, "loss": 0.6192, "lr": 3.50836530715422e-06, "epoch": 1.9073482428115016, "percentage": 63.78, "elapsed_time": "1:42:38", "remaining_time": "0:58:17"}
+{"current_steps": 200, "total_steps": 312, "loss": 0.6012, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:43:04", "remaining_time": "0:57:43"}
+{"current_steps": 201, "total_steps": 312, "loss": 0.6247, "lr": 3.4016592544210937e-06, "epoch": 1.926517571884984, "percentage": 64.42, "elapsed_time": "1:43:36", "remaining_time": "0:57:12"}
+{"current_steps": 202, "total_steps": 312, "loss": 0.6207, "lr": 3.3486046902241663e-06, "epoch": 1.9361022364217253, "percentage": 64.74, "elapsed_time": "1:44:10", "remaining_time": "0:56:43"}
+{"current_steps": 203, "total_steps": 312, "loss": 0.6113, "lr": 3.295758014387375e-06, "epoch": 1.9456869009584663, "percentage": 65.06, "elapsed_time": "1:44:42", "remaining_time": "0:56:13"}
+{"current_steps": 204, "total_steps": 312, "loss": 0.6131, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:45:16", "remaining_time": "0:55:43"}
+{"current_steps": 205, "total_steps": 312, "loss": 0.6146, "lr": 3.1907149115166403e-06, "epoch": 1.9648562300319488, "percentage": 65.71, "elapsed_time": "1:45:41", "remaining_time": "0:55:09"}
+{"current_steps": 206, "total_steps": 312, "loss": 0.6028, "lr": 3.1385317079902743e-06, "epoch": 1.9744408945686902, "percentage": 66.03, "elapsed_time": "1:46:12", "remaining_time": "0:54:39"}
+{"current_steps": 207, "total_steps": 312, "loss": 0.5971, "lr": 3.0865828381745515e-06, "epoch": 1.9840255591054312, "percentage": 66.35, "elapsed_time": "1:46:44", "remaining_time": "0:54:08"}
+{"current_steps": 208, "total_steps": 312, "loss": 0.6448, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:47:16", "remaining_time": "0:53:38"}
+{"current_steps": 209, "total_steps": 312, "loss": 0.5869, "lr": 2.9834142279959754e-06, "epoch": 2.0031948881789137, "percentage": 66.99, "elapsed_time": "1:48:15", "remaining_time": "0:53:21"}
+{"current_steps": 210, "total_steps": 312, "loss": 0.5447, "lr": 2.932207475167398e-06, "epoch": 2.012779552715655, "percentage": 67.31, "elapsed_time": "1:48:48", "remaining_time": "0:52:51"}
+{"current_steps": 211, "total_steps": 312, "loss": 0.5638, "lr": 2.8812610294830568e-06, "epoch": 2.022364217252396, "percentage": 67.63, "elapsed_time": "1:49:18", "remaining_time": "0:52:19"}
+{"current_steps": 212, "total_steps": 312, "loss": 0.5758, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:49:47", "remaining_time": "0:51:47"}
+{"current_steps": 213, "total_steps": 312, "loss": 0.5618, "lr": 2.7801746798475905e-06, "epoch": 2.0415335463258786, "percentage": 68.27, "elapsed_time": "1:50:18", "remaining_time": "0:51:16"}
+{"current_steps": 214, "total_steps": 312, "loss": 0.5669, "lr": 2.7300475013022666e-06, "epoch": 2.0511182108626196, "percentage": 68.59, "elapsed_time": "1:50:49", "remaining_time": "0:50:44"}
+{"current_steps": 215, "total_steps": 312, "loss": 0.5495, "lr": 2.6802060791108304e-06, "epoch": 2.060702875399361, "percentage": 68.91, "elapsed_time": "1:51:21", "remaining_time": "0:50:14"}
+{"current_steps": 216, "total_steps": 312, "loss": 0.5421, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "1:51:50", "remaining_time": "0:49:42"}
+{"current_steps": 217, "total_steps": 312, "loss": 0.5708, "lr": 2.5814055644738013e-06, "epoch": 2.0798722044728435, "percentage": 69.55, "elapsed_time": "1:52:20", "remaining_time": "0:49:11"}
+{"current_steps": 218, "total_steps": 312, "loss": 0.5391, "lr": 2.532458909678266e-06, "epoch": 2.0894568690095845, "percentage": 69.87, "elapsed_time": "1:52:46", "remaining_time": "0:48:37"}
+{"current_steps": 219, "total_steps": 312, "loss": 0.5425, "lr": 2.483822884971e-06, "epoch": 2.099041533546326, "percentage": 70.19, "elapsed_time": "1:53:14", "remaining_time": "0:48:05"}
+{"current_steps": 220, "total_steps": 312, "loss": 0.5674, "lr": 2.43550361297047e-06, "epoch": 2.108626198083067, "percentage": 70.51, "elapsed_time": "1:53:46", "remaining_time": "0:47:34"}
+{"current_steps": 221, "total_steps": 312, "loss": 0.5401, "lr": 2.387507176420256e-06, "epoch": 2.1182108626198084, "percentage": 70.83, "elapsed_time": "1:54:17", "remaining_time": "0:47:03"}
+{"current_steps": 222, "total_steps": 312, "loss": 0.529, "lr": 2.339839617423318e-06, "epoch": 2.1277955271565494, "percentage": 71.15, "elapsed_time": "1:54:49", "remaining_time": "0:46:33"}
+{"current_steps": 223, "total_steps": 312, "loss": 0.5653, "lr": 2.2925069366813718e-06, "epoch": 2.137380191693291, "percentage": 71.47, "elapsed_time": "1:55:19", "remaining_time": "0:46:01"}
+{"current_steps": 224, "total_steps": 312, "loss": 0.566, "lr": 2.245515092739488e-06, "epoch": 2.146964856230032, "percentage": 71.79, "elapsed_time": "1:55:52", "remaining_time": "0:45:31"}
+{"current_steps": 225, "total_steps": 312, "loss": 0.5317, "lr": 2.1988700012359865e-06, "epoch": 2.1565495207667733, "percentage": 72.12, "elapsed_time": "1:56:24", "remaining_time": "0:45:00"}
+{"current_steps": 226, "total_steps": 312, "loss": 0.5708, "lr": 2.1525775341577404e-06, "epoch": 2.1661341853035143, "percentage": 72.44, "elapsed_time": "1:56:53", "remaining_time": "0:44:28"}
+{"current_steps": 227, "total_steps": 312, "loss": 0.5208, "lr": 2.1066435191009717e-06, "epoch": 2.1757188498402558, "percentage": 72.76, "elapsed_time": "1:57:24", "remaining_time": "0:43:57"}
+{"current_steps": 228, "total_steps": 312, "loss": 0.541, "lr": 2.061073738537635e-06, "epoch": 2.1853035143769968, "percentage": 73.08, "elapsed_time": "1:57:45", "remaining_time": "0:43:23"}
+{"current_steps": 229, "total_steps": 312, "loss": 0.5416, "lr": 2.0158739290874822e-06, "epoch": 2.194888178913738, "percentage": 73.4, "elapsed_time": "1:58:12", "remaining_time": "0:42:50"}
+{"current_steps": 230, "total_steps": 312, "loss": 0.5375, "lr": 1.971049780795901e-06, "epoch": 2.2044728434504792, "percentage": 73.72, "elapsed_time": "1:58:43", "remaining_time": "0:42:19"}
+{"current_steps": 231, "total_steps": 312, "loss": 0.5798, "lr": 1.9266069364176144e-06, "epoch": 2.2140575079872207, "percentage": 74.04, "elapsed_time": "1:59:14", "remaining_time": "0:41:48"}
+{"current_steps": 232, "total_steps": 312, "loss": 0.54, "lr": 1.8825509907063328e-06, "epoch": 2.2236421725239617, "percentage": 74.36, "elapsed_time": "1:59:46", "remaining_time": "0:41:18"}
+{"current_steps": 233, "total_steps": 312, "loss": 0.5242, "lr": 1.838887489710452e-06, "epoch": 2.2332268370607027, "percentage": 74.68, "elapsed_time": "2:00:12", "remaining_time": "0:40:45"}
+{"current_steps": 234, "total_steps": 312, "loss": 0.5511, "lr": 1.7956219300748796e-06, "epoch": 2.242811501597444, "percentage": 75.0, "elapsed_time": "2:00:41", "remaining_time": "0:40:13"}
+{"current_steps": 235, "total_steps": 312, "loss": 0.5785, "lr": 1.7527597583490825e-06, "epoch": 2.252396166134185, "percentage": 75.32, "elapsed_time": "2:01:14", "remaining_time": "0:39:43"}
+{"current_steps": 236, "total_steps": 312, "loss": 0.5382, "lr": 1.7103063703014372e-06, "epoch": 2.2619808306709266, "percentage": 75.64, "elapsed_time": "2:01:46", "remaining_time": "0:39:13"}
+{"current_steps": 237, "total_steps": 312, "loss": 0.5375, "lr": 1.6682671102399806e-06, "epoch": 2.2715654952076676, "percentage": 75.96, "elapsed_time": "2:02:14", "remaining_time": "0:38:41"}
+{"current_steps": 238, "total_steps": 312, "loss": 0.5652, "lr": 1.6266472703396286e-06, "epoch": 2.281150159744409, "percentage": 76.28, "elapsed_time": "2:02:45", "remaining_time": "0:38:10"}
+{"current_steps": 239, "total_steps": 312, "loss": 0.5606, "lr": 1.5854520899759656e-06, "epoch": 2.29073482428115, "percentage": 76.6, "elapsed_time": "2:03:20", "remaining_time": "0:37:40"}
+{"current_steps": 240, "total_steps": 312, "loss": 0.5495, "lr": 1.544686755065677e-06, "epoch": 2.3003194888178915, "percentage": 76.92, "elapsed_time": "2:03:48", "remaining_time": "0:37:08"}
+{"current_steps": 241, "total_steps": 312, "loss": 0.5273, "lr": 1.5043563974137132e-06, "epoch": 2.3099041533546325, "percentage": 77.24, "elapsed_time": "2:04:18", "remaining_time": "0:36:37"}
+{"current_steps": 242, "total_steps": 312, "loss": 0.5451, "lr": 1.4644660940672628e-06, "epoch": 2.319488817891374, "percentage": 77.56, "elapsed_time": "2:04:49", "remaining_time": "0:36:06"}
+{"current_steps": 243, "total_steps": 312, "loss": 0.5572, "lr": 1.4250208666766235e-06, "epoch": 2.329073482428115, "percentage": 77.88, "elapsed_time": "2:05:16", "remaining_time": "0:35:34"}
+{"current_steps": 244, "total_steps": 312, "loss": 0.561, "lr": 1.3860256808630429e-06, "epoch": 2.3386581469648564, "percentage": 78.21, "elapsed_time": "2:05:48", "remaining_time": "0:35:03"}
+{"current_steps": 245, "total_steps": 312, "loss": 0.5511, "lr": 1.3474854455936126e-06, "epoch": 2.3482428115015974, "percentage": 78.53, "elapsed_time": "2:06:17", "remaining_time": "0:34:32"}
+{"current_steps": 246, "total_steps": 312, "loss": 0.5806, "lr": 1.3094050125632973e-06, "epoch": 2.357827476038339, "percentage": 78.85, "elapsed_time": "2:06:49", "remaining_time": "0:34:01"}
+{"current_steps": 247, "total_steps": 312, "loss": 0.5497, "lr": 1.2717891755841722e-06, "epoch": 2.36741214057508, "percentage": 79.17, "elapsed_time": "2:07:21", "remaining_time": "0:33:30"}
+{"current_steps": 248, "total_steps": 312, "loss": 0.5724, "lr": 1.234642669981946e-06, "epoch": 2.376996805111821, "percentage": 79.49, "elapsed_time": "2:07:51", "remaining_time": "0:32:59"}
+{"current_steps": 249, "total_steps": 312, "loss": 0.5336, "lr": 1.1979701719998454e-06, "epoch": 2.3865814696485623, "percentage": 79.81, "elapsed_time": "2:08:22", "remaining_time": "0:32:28"}
+{"current_steps": 250, "total_steps": 312, "loss": 0.5318, "lr": 1.1617762982099446e-06, "epoch": 2.3961661341853033, "percentage": 80.13, "elapsed_time": "2:08:52", "remaining_time": "0:31:57"}
+{"current_steps": 251, "total_steps": 312, "loss": 0.5577, "lr": 1.1260656049319957e-06, "epoch": 2.405750798722045, "percentage": 80.45, "elapsed_time": "2:09:24", "remaining_time": "0:31:26"}
+{"current_steps": 252, "total_steps": 312, "loss": 0.5367, "lr": 1.0908425876598512e-06, "epoch": 2.415335463258786, "percentage": 80.77, "elapsed_time": "2:09:54", "remaining_time": "0:30:55"}
+{"current_steps": 253, "total_steps": 312, "loss": 0.5605, "lr": 1.0561116804955451e-06, "epoch": 2.4249201277955272, "percentage": 81.09, "elapsed_time": "2:10:23", "remaining_time": "0:30:24"}
+{"current_steps": 254, "total_steps": 312, "loss": 0.5436, "lr": 1.0218772555910955e-06, "epoch": 2.4345047923322682, "percentage": 81.41, "elapsed_time": "2:10:53", "remaining_time": "0:29:53"}
+{"current_steps": 255, "total_steps": 312, "loss": 0.5533, "lr": 9.881436225981107e-07, "epoch": 2.4440894568690097, "percentage": 81.73, "elapsed_time": "2:11:26", "remaining_time": "0:29:22"}
+{"current_steps": 256, "total_steps": 312, "loss": 0.5358, "lr": 9.549150281252633e-07, "epoch": 2.4536741214057507, "percentage": 82.05, "elapsed_time": "2:11:58", "remaining_time": "0:28:52"}
+{"current_steps": 257, "total_steps": 312, "loss": 0.5475, "lr": 9.221956552036992e-07, "epoch": 2.463258785942492, "percentage": 82.37, "elapsed_time": "2:12:32", "remaining_time": "0:28:21"}
+{"current_steps": 258, "total_steps": 312, "loss": 0.5291, "lr": 8.899896227604509e-07, "epoch": 2.472843450479233, "percentage": 82.69, "elapsed_time": "2:13:07", "remaining_time": "0:27:51"}
+{"current_steps": 259, "total_steps": 312, "loss": 0.5522, "lr": 8.58300985099918e-07, "epoch": 2.4824281150159746, "percentage": 83.01, "elapsed_time": "2:13:39", "remaining_time": "0:27:20"}
+{"current_steps": 260, "total_steps": 312, "loss": 0.5428, "lr": 8.271337313934869e-07, "epoch": 2.4920127795527156, "percentage": 83.33, "elapsed_time": "2:14:11", "remaining_time": "0:26:50"}
+{"current_steps": 261, "total_steps": 312, "loss": 0.5438, "lr": 7.964917851773496e-07, "epoch": 2.501597444089457, "percentage": 83.65, "elapsed_time": "2:14:44", "remaining_time": "0:26:19"}
+{"current_steps": 262, "total_steps": 312, "loss": 0.5412, "lr": 7.663790038585794e-07, "epoch": 2.511182108626198, "percentage": 83.97, "elapsed_time": "2:15:15", "remaining_time": "0:25:48"}
+{"current_steps": 263, "total_steps": 312, "loss": 0.5393, "lr": 7.367991782295392e-07, "epoch": 2.520766773162939, "percentage": 84.29, "elapsed_time": "2:15:46", "remaining_time": "0:25:17"}
+{"current_steps": 264, "total_steps": 312, "loss": 0.5659, "lr": 7.077560319906696e-07, "epoch": 2.5303514376996805, "percentage": 84.62, "elapsed_time": "2:16:20", "remaining_time": "0:24:47"}
+{"current_steps": 265, "total_steps": 312, "loss": 0.5345, "lr": 6.792532212817271e-07, "epoch": 2.539936102236422, "percentage": 84.94, "elapsed_time": "2:16:52", "remaining_time": "0:24:16"}
+{"current_steps": 266, "total_steps": 312, "loss": 0.5222, "lr": 6.512943342215234e-07, "epoch": 2.549520766773163, "percentage": 85.26, "elapsed_time": "2:17:22", "remaining_time": "0:23:45"}
+{"current_steps": 267, "total_steps": 312, "loss": 0.5617, "lr": 6.238828904562316e-07, "epoch": 2.559105431309904, "percentage": 85.58, "elapsed_time": "2:17:54", "remaining_time": "0:23:14"}
+{"current_steps": 268, "total_steps": 312, "loss": 0.5715, "lr": 5.9702234071631e-07, "epoch": 2.5686900958466454, "percentage": 85.9, "elapsed_time": "2:18:26", "remaining_time": "0:22:43"}
+{"current_steps": 269, "total_steps": 312, "loss": 0.5746, "lr": 5.707160663821009e-07, "epoch": 2.5782747603833864, "percentage": 86.22, "elapsed_time": "2:18:57", "remaining_time": "0:22:12"}
+{"current_steps": 270, "total_steps": 312, "loss": 0.5655, "lr": 5.449673790581611e-07, "epoch": 2.587859424920128, "percentage": 86.54, "elapsed_time": "2:19:30", "remaining_time": "0:21:42"}
+{"current_steps": 271, "total_steps": 312, "loss": 0.543, "lr": 5.197795201563744e-07, "epoch": 2.597444089456869, "percentage": 86.86, "elapsed_time": "2:19:59", "remaining_time": "0:21:10"}
+{"current_steps": 272, "total_steps": 312, "loss": 0.5313, "lr": 4.951556604879049e-07, "epoch": 2.6070287539936103, "percentage": 87.18, "elapsed_time": "2:20:34", "remaining_time": "0:20:40"}
+{"current_steps": 273, "total_steps": 312, "loss": 0.582, "lr": 4.710988998640298e-07, "epoch": 2.6166134185303513, "percentage": 87.5, "elapsed_time": "2:21:03", "remaining_time": "0:20:09"}
+{"current_steps": 274, "total_steps": 312, "loss": 0.5743, "lr": 4.4761226670592074e-07, "epoch": 2.626198083067093, "percentage": 87.82, "elapsed_time": "2:21:31", "remaining_time": "0:19:37"}
+{"current_steps": 275, "total_steps": 312, "loss": 0.548, "lr": 4.2469871766340096e-07, "epoch": 2.635782747603834, "percentage": 88.14, "elapsed_time": "2:22:02", "remaining_time": "0:19:06"}
+{"current_steps": 276, "total_steps": 312, "loss": 0.5453, "lr": 4.0236113724274716e-07, "epoch": 2.6453674121405752, "percentage": 88.46, "elapsed_time": "2:22:31", "remaining_time": "0:18:35"}
+{"current_steps": 277, "total_steps": 312, "loss": 0.5498, "lr": 3.8060233744356634e-07, "epoch": 2.6549520766773163, "percentage": 88.78, "elapsed_time": "2:23:03", "remaining_time": "0:18:04"}
+{"current_steps": 278, "total_steps": 312, "loss": 0.5508, "lr": 3.5942505740480583e-07, "epoch": 2.6645367412140573, "percentage": 89.1, "elapsed_time": "2:23:32", "remaining_time": "0:17:33"}
+{"current_steps": 279, "total_steps": 312, "loss": 0.54, "lr": 3.3883196305992906e-07, "epoch": 2.6741214057507987, "percentage": 89.42, "elapsed_time": "2:24:05", "remaining_time": "0:17:02"}
+{"current_steps": 280, "total_steps": 312, "loss": 0.525, "lr": 3.18825646801314e-07, "epoch": 2.68370607028754, "percentage": 89.74, "elapsed_time": "2:24:34", "remaining_time": "0:16:31"}
+{"current_steps": 281, "total_steps": 312, "loss": 0.5509, "lr": 2.9940862715390483e-07, "epoch": 2.693290734824281, "percentage": 90.06, "elapsed_time": "2:25:04", "remaining_time": "0:16:00"}
+{"current_steps": 282, "total_steps": 312, "loss": 0.5394, "lr": 2.8058334845816214e-07, "epoch": 2.702875399361022, "percentage": 90.38, "elapsed_time": "2:25:37", "remaining_time": "0:15:29"}
+{"current_steps": 283, "total_steps": 312, "loss": 0.4987, "lr": 2.6235218056235633e-07, "epoch": 2.7124600638977636, "percentage": 90.71, "elapsed_time": "2:26:05", "remaining_time": "0:14:58"}
+{"current_steps": 284, "total_steps": 312, "loss": 0.5417, "lr": 2.447174185242324e-07, "epoch": 2.722044728434505, "percentage": 91.03, "elapsed_time": "2:26:34", "remaining_time": "0:14:27"}
+{"current_steps": 285, "total_steps": 312, "loss": 0.5531, "lr": 2.276812823220964e-07, "epoch": 2.731629392971246, "percentage": 91.35, "elapsed_time": "2:27:05", "remaining_time": "0:13:56"}
+{"current_steps": 286, "total_steps": 312, "loss": 0.5725, "lr": 2.1124591657534776e-07, "epoch": 2.741214057507987, "percentage": 91.67, "elapsed_time": "2:27:39", "remaining_time": "0:13:25"}
+{"current_steps": 287, "total_steps": 312, "loss": 0.5432, "lr": 1.9541339027450256e-07, "epoch": 2.7507987220447285, "percentage": 91.99, "elapsed_time": "2:28:10", "remaining_time": "0:12:54"}
+{"current_steps": 288, "total_steps": 312, "loss": 0.5235, "lr": 1.801856965207338e-07, "epoch": 2.7603833865814695, "percentage": 92.31, "elapsed_time": "2:28:43", "remaining_time": "0:12:23"}
+{"current_steps": 289, "total_steps": 312, "loss": 0.5529, "lr": 1.6556475227496816e-07, "epoch": 2.769968051118211, "percentage": 92.63, "elapsed_time": "2:29:16", "remaining_time": "0:11:52"}
+{"current_steps": 290, "total_steps": 312, "loss": 0.5339, "lr": 1.5155239811656562e-07, "epoch": 2.779552715654952, "percentage": 92.95, "elapsed_time": "2:29:48", "remaining_time": "0:11:21"}
+{"current_steps": 291, "total_steps": 312, "loss": 0.5502, "lr": 1.3815039801161723e-07, "epoch": 2.7891373801916934, "percentage": 93.27, "elapsed_time": "2:30:20", "remaining_time": "0:10:50"}
+{"current_steps": 292, "total_steps": 312, "loss": 0.5275, "lr": 1.253604390908819e-07, "epoch": 2.7987220447284344, "percentage": 93.59, "elapsed_time": "2:30:50", "remaining_time": "0:10:19"}
+{"current_steps": 293, "total_steps": 312, "loss": 0.5326, "lr": 1.1318413143740436e-07, "epoch": 2.8083067092651754, "percentage": 93.91, "elapsed_time": "2:31:17", "remaining_time": "0:09:48"}
+{"current_steps": 294, "total_steps": 312, "loss": 0.5481, "lr": 1.0162300788382263e-07, "epoch": 2.817891373801917, "percentage": 94.23, "elapsed_time": "2:31:48", "remaining_time": "0:09:17"}
+{"current_steps": 295, "total_steps": 312, "loss": 0.5222, "lr": 9.0678523819408e-08, "epoch": 2.8274760383386583, "percentage": 94.55, "elapsed_time": "2:32:17", "remaining_time": "0:08:46"}
+{"current_steps": 296, "total_steps": 312, "loss": 0.5522, "lr": 8.035205700685167e-08, "epoch": 2.8370607028753994, "percentage": 94.87, "elapsed_time": "2:32:48", "remaining_time": "0:08:15"}
+{"current_steps": 297, "total_steps": 312, "loss": 0.546, "lr": 7.064490740882057e-08, "epoch": 2.8466453674121404, "percentage": 95.19, "elapsed_time": "2:33:14", "remaining_time": "0:07:44"}
+{"current_steps": 298, "total_steps": 312, "loss": 0.5542, "lr": 6.15582970243117e-08, "epoch": 2.856230031948882, "percentage": 95.51, "elapsed_time": "2:33:49", "remaining_time": "0:07:13"}
+{"current_steps": 299, "total_steps": 312, "loss": 0.5663, "lr": 5.3093369734816824e-08, "epoch": 2.8658146964856233, "percentage": 95.83, "elapsed_time": "2:34:18", "remaining_time": "0:06:42"}
+{"current_steps": 300, "total_steps": 312, "loss": 0.5595, "lr": 4.52511911603265e-08, "epoch": 2.8753993610223643, "percentage": 96.15, "elapsed_time": "2:34:49", "remaining_time": "0:06:11"}
+{"current_steps": 301, "total_steps": 312, "loss": 0.5338, "lr": 3.8032748525179684e-08, "epoch": 2.8849840255591053, "percentage": 96.47, "elapsed_time": "2:35:19", "remaining_time": "0:05:40"}
+{"current_steps": 302, "total_steps": 312, "loss": 0.5481, "lr": 3.143895053378698e-08, "epoch": 2.8945686900958467, "percentage": 96.79, "elapsed_time": "2:35:47", "remaining_time": "0:05:09"}
+{"current_steps": 303, "total_steps": 312, "loss": 0.531, "lr": 2.547062725623828e-08, "epoch": 2.9041533546325877, "percentage": 97.12, "elapsed_time": "2:36:20", "remaining_time": "0:04:38"}
+{"current_steps": 304, "total_steps": 312, "loss": 0.5522, "lr": 2.012853002380466e-08, "epoch": 2.913738019169329, "percentage": 97.44, "elapsed_time": "2:36:54", "remaining_time": "0:04:07"}
+{"current_steps": 305, "total_steps": 312, "loss": 0.5487, "lr": 1.541333133436018e-08, "epoch": 2.92332268370607, "percentage": 97.76, "elapsed_time": "2:37:26", "remaining_time": "0:03:36"}
+{"current_steps": 306, "total_steps": 312, "loss": 0.5437, "lr": 1.132562476771959e-08, "epoch": 2.9329073482428116, "percentage": 98.08, "elapsed_time": "2:37:56", "remaining_time": "0:03:05"}
+{"current_steps": 307, "total_steps": 312, "loss": 0.5611, "lr": 7.865924910916977e-09, "epoch": 2.9424920127795526, "percentage": 98.4, "elapsed_time": "2:38:29", "remaining_time": "0:02:34"}
+{"current_steps": 308, "total_steps": 312, "loss": 0.5626, "lr": 5.034667293427053e-09, "epoch": 2.952076677316294, "percentage": 98.72, "elapsed_time": "2:39:01", "remaining_time": "0:02:03"}
+{"current_steps": 309, "total_steps": 312, "loss": 0.5644, "lr": 2.8322083323334417e-09, "epoch": 2.961661341853035, "percentage": 99.04, "elapsed_time": "2:39:37", "remaining_time": "0:01:32"}
+{"current_steps": 310, "total_steps": 312, "loss": 0.5432, "lr": 1.2588252874673469e-09, "epoch": 2.9712460063897765, "percentage": 99.36, "elapsed_time": "2:40:10", "remaining_time": "0:01:02"}
+{"current_steps": 311, "total_steps": 312, "loss": 0.5563, "lr": 3.147162264971471e-10, "epoch": 2.9808306709265175, "percentage": 99.68, "elapsed_time": "2:40:42", "remaining_time": "0:00:31"}
+{"current_steps": 312, "total_steps": 312, "loss": 0.5641, "lr": 0.0, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:41:15", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:42:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2226 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9904153354632586,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009584664536741214,
+      "grad_norm": 6.971998691558838,
+      "learning_rate": 3.125e-07,
+      "loss": 1.1107,
+      "step": 1
+    },
+    {
+      "epoch": 0.019169329073482427,
+      "grad_norm": 7.050237655639648,
+      "learning_rate": 6.25e-07,
+      "loss": 1.1177,
+      "step": 2
+    },
+    {
+      "epoch": 0.02875399361022364,
+      "grad_norm": 7.03878927230835,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.1165,
+      "step": 3
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 6.786710262298584,
+      "learning_rate": 1.25e-06,
+      "loss": 1.1067,
+      "step": 4
+    },
+    {
+      "epoch": 0.04792332268370607,
+      "grad_norm": 6.495321750640869,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.0499,
+      "step": 5
+    },
+    {
+      "epoch": 0.05750798722044728,
+      "grad_norm": 6.044283390045166,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.0371,
+      "step": 6
+    },
+    {
+      "epoch": 0.0670926517571885,
+      "grad_norm": 5.145187854766846,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 1.0494,
+      "step": 7
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 4.828237533569336,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0762,
+      "step": 8
+    },
+    {
+      "epoch": 0.08626198083067092,
+      "grad_norm": 2.552110195159912,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.9586,
+      "step": 9
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 2.331293821334839,
+      "learning_rate": 3.125e-06,
+      "loss": 0.9199,
+      "step": 10
+    },
+    {
+      "epoch": 0.10543130990415335,
+      "grad_norm": 2.1774399280548096,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.9448,
+      "step": 11
+    },
+    {
+      "epoch": 0.11501597444089456,
+      "grad_norm": 3.9896745681762695,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.932,
+      "step": 12
+    },
+    {
+      "epoch": 0.12460063897763578,
+      "grad_norm": 4.284629821777344,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.9471,
+      "step": 13
+    },
+    {
+      "epoch": 0.134185303514377,
+      "grad_norm": 4.1393818855285645,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.9282,
+      "step": 14
+    },
+    {
+      "epoch": 0.14376996805111822,
+      "grad_norm": 3.974306106567383,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.9321,
+      "step": 15
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 2.983408212661743,
+      "learning_rate": 5e-06,
+      "loss": 0.8831,
+      "step": 16
+    },
+    {
+      "epoch": 0.16293929712460065,
+      "grad_norm": 2.5403692722320557,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.865,
+      "step": 17
+    },
+    {
+      "epoch": 0.17252396166134185,
+      "grad_norm": 2.273620128631592,
+      "learning_rate": 5.625e-06,
+      "loss": 0.8637,
+      "step": 18
+    },
+    {
+      "epoch": 0.18210862619808307,
+      "grad_norm": 1.9839009046554565,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.8407,
+      "step": 19
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 1.8639857769012451,
+      "learning_rate": 6.25e-06,
+      "loss": 0.8496,
+      "step": 20
+    },
+    {
+      "epoch": 0.2012779552715655,
+      "grad_norm": 1.6055963039398193,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.7852,
+      "step": 21
+    },
+    {
+      "epoch": 0.2108626198083067,
+      "grad_norm": 1.4574110507965088,
+      "learning_rate": 6.875e-06,
+      "loss": 0.8268,
+      "step": 22
+    },
+    {
+      "epoch": 0.22044728434504793,
+      "grad_norm": 1.5689210891723633,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.87,
+      "step": 23
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 1.4550209045410156,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8051,
+      "step": 24
+    },
+    {
+      "epoch": 0.23961661341853036,
+      "grad_norm": 1.18101966381073,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.7869,
+      "step": 25
+    },
+    {
+      "epoch": 0.24920127795527156,
+      "grad_norm": 1.2257055044174194,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.7946,
+      "step": 26
+    },
+    {
+      "epoch": 0.25878594249201275,
+      "grad_norm": 1.1306984424591064,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.8175,
+      "step": 27
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 1.247745156288147,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.8078,
+      "step": 28
+    },
+    {
+      "epoch": 0.2779552715654952,
+      "grad_norm": 2.521697998046875,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.7935,
+      "step": 29
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.3057435750961304,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.7915,
+      "step": 30
+    },
+    {
+      "epoch": 0.2971246006389776,
+      "grad_norm": 0.9969050288200378,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.771,
+      "step": 31
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.9421972632408142,
+      "learning_rate": 1e-05,
+      "loss": 0.735,
+      "step": 32
+    },
+    {
+      "epoch": 0.31629392971246006,
+      "grad_norm": 1.0489099025726318,
+      "learning_rate": 9.999685283773504e-06,
+      "loss": 0.7474,
+      "step": 33
+    },
+    {
+      "epoch": 0.3258785942492013,
+      "grad_norm": 0.8595058917999268,
+      "learning_rate": 9.998741174712534e-06,
+      "loss": 0.7496,
+      "step": 34
+    },
+    {
+      "epoch": 0.3354632587859425,
+      "grad_norm": 0.8780394792556763,
+      "learning_rate": 9.997167791667668e-06,
+      "loss": 0.78,
+      "step": 35
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 0.8949142694473267,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.7421,
+      "step": 36
+    },
+    {
+      "epoch": 0.3546325878594249,
+      "grad_norm": 0.7785873413085938,
+      "learning_rate": 9.992134075089085e-06,
+      "loss": 0.7473,
+      "step": 37
+    },
+    {
+      "epoch": 0.36421725239616615,
+      "grad_norm": 0.8248518109321594,
+      "learning_rate": 9.98867437523228e-06,
+      "loss": 0.7495,
+      "step": 38
+    },
+    {
+      "epoch": 0.3738019169329074,
+      "grad_norm": 0.7783116102218628,
+      "learning_rate": 9.984586668665641e-06,
+      "loss": 0.7489,
+      "step": 39
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.7744529843330383,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.7466,
+      "step": 40
+    },
+    {
+      "epoch": 0.3929712460063898,
+      "grad_norm": 0.7752032279968262,
+      "learning_rate": 9.974529372743762e-06,
+      "loss": 0.7061,
+      "step": 41
+    },
+    {
+      "epoch": 0.402555910543131,
+      "grad_norm": 0.7973994016647339,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.7475,
+      "step": 42
+    },
+    {
+      "epoch": 0.41214057507987223,
+      "grad_norm": 0.7251701354980469,
+      "learning_rate": 9.961967251474823e-06,
+      "loss": 0.7191,
+      "step": 43
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 0.8239709734916687,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.7258,
+      "step": 44
+    },
+    {
+      "epoch": 0.43130990415335463,
+      "grad_norm": 0.7722738981246948,
+      "learning_rate": 9.946906630265184e-06,
+      "loss": 0.7387,
+      "step": 45
+    },
+    {
+      "epoch": 0.44089456869009586,
+      "grad_norm": 0.8330404758453369,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.7654,
+      "step": 46
+    },
+    {
+      "epoch": 0.4504792332268371,
+      "grad_norm": 0.7460812330245972,
+      "learning_rate": 9.92935509259118e-06,
+      "loss": 0.7222,
+      "step": 47
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.7764353156089783,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.7348,
+      "step": 48
+    },
+    {
+      "epoch": 0.4696485623003195,
+      "grad_norm": 0.7835634350776672,
+      "learning_rate": 9.909321476180594e-06,
+      "loss": 0.7483,
+      "step": 49
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.6525381207466125,
+      "learning_rate": 9.898376992116179e-06,
+      "loss": 0.7098,
+      "step": 50
+    },
+    {
+      "epoch": 0.48881789137380194,
+      "grad_norm": 0.7374613881111145,
+      "learning_rate": 9.886815868562596e-06,
+      "loss": 0.7285,
+      "step": 51
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 0.6773239374160767,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.6991,
+      "step": 52
+    },
+    {
+      "epoch": 0.5079872204472844,
+      "grad_norm": 0.6954315304756165,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 0.7529,
+      "step": 53
+    },
+    {
+      "epoch": 0.5175718849840255,
+      "grad_norm": 0.6873759031295776,
+      "learning_rate": 9.848447601883436e-06,
+      "loss": 0.7609,
+      "step": 54
+    },
+    {
+      "epoch": 0.5271565495207667,
+      "grad_norm": 0.7804772257804871,
+      "learning_rate": 9.834435247725032e-06,
+      "loss": 0.7336,
+      "step": 55
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 0.7185588479042053,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.7087,
+      "step": 56
+    },
+    {
+      "epoch": 0.5463258785942492,
+      "grad_norm": 0.7161798477172852,
+      "learning_rate": 9.804586609725499e-06,
+      "loss": 0.777,
+      "step": 57
+    },
+    {
+      "epoch": 0.5559105431309904,
+      "grad_norm": 0.7221360802650452,
+      "learning_rate": 9.788754083424654e-06,
+      "loss": 0.7518,
+      "step": 58
+    },
+    {
+      "epoch": 0.5654952076677316,
+      "grad_norm": 0.7326431274414062,
+      "learning_rate": 9.772318717677905e-06,
+      "loss": 0.7085,
+      "step": 59
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.6565002202987671,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.75,
+      "step": 60
+    },
+    {
+      "epoch": 0.5846645367412141,
+      "grad_norm": 0.7010030150413513,
+      "learning_rate": 9.737647819437645e-06,
+      "loss": 0.7344,
+      "step": 61
+    },
+    {
+      "epoch": 0.5942492012779552,
+      "grad_norm": 0.7021656036376953,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.7143,
+      "step": 62
+    },
+    {
+      "epoch": 0.6038338658146964,
+      "grad_norm": 0.7053258419036865,
+      "learning_rate": 9.700591372846096e-06,
+      "loss": 0.7163,
+      "step": 63
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.6960455179214478,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.7334,
+      "step": 64
+    },
+    {
+      "epoch": 0.6230031948881789,
+      "grad_norm": 0.5773729681968689,
+      "learning_rate": 9.661168036940071e-06,
+      "loss": 0.6995,
+      "step": 65
+    },
+    {
+      "epoch": 0.6325878594249201,
+      "grad_norm": 0.6698278784751892,
+      "learning_rate": 9.640574942595195e-06,
+      "loss": 0.7297,
+      "step": 66
+    },
+    {
+      "epoch": 0.6421725239616614,
+      "grad_norm": 0.6030433773994446,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.7042,
+      "step": 67
+    },
+    {
+      "epoch": 0.6517571884984026,
+      "grad_norm": 0.7778566479682922,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.7509,
+      "step": 68
+    },
+    {
+      "epoch": 0.6613418530351438,
+      "grad_norm": 0.6630182266235352,
+      "learning_rate": 9.5753012823366e-06,
+      "loss": 0.7036,
+      "step": 69
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 0.866037130355835,
+      "learning_rate": 9.552387733294081e-06,
+      "loss": 0.7685,
+      "step": 70
+    },
+    {
+      "epoch": 0.6805111821086262,
+      "grad_norm": 0.8120040893554688,
+      "learning_rate": 9.528901100135971e-06,
+      "loss": 0.7108,
+      "step": 71
+    },
+    {
+      "epoch": 0.6900958466453674,
+      "grad_norm": 0.729915201663971,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.7254,
+      "step": 72
+    },
+    {
+      "epoch": 0.6996805111821086,
+      "grad_norm": 0.7347356677055359,
+      "learning_rate": 9.480220479843627e-06,
+      "loss": 0.6991,
+      "step": 73
+    },
+    {
+      "epoch": 0.7092651757188498,
+      "grad_norm": 0.810127854347229,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.718,
+      "step": 74
+    },
+    {
+      "epoch": 0.7188498402555911,
+      "grad_norm": 0.6601433157920837,
+      "learning_rate": 9.4292839336179e-06,
+      "loss": 0.6881,
+      "step": 75
+    },
+    {
+      "epoch": 0.7284345047923323,
+      "grad_norm": 0.7950295209884644,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.7312,
+      "step": 76
+    },
+    {
+      "epoch": 0.7380191693290735,
+      "grad_norm": 0.6458447575569153,
+      "learning_rate": 9.376117109543769e-06,
+      "loss": 0.7122,
+      "step": 77
+    },
+    {
+      "epoch": 0.7476038338658147,
+      "grad_norm": 0.7140399813652039,
+      "learning_rate": 9.348705665778479e-06,
+      "loss": 0.7109,
+      "step": 78
+    },
+    {
+      "epoch": 0.7571884984025559,
+      "grad_norm": 0.605841875076294,
+      "learning_rate": 9.320746778718274e-06,
+      "loss": 0.7056,
+      "step": 79
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.6923595070838928,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.696,
+      "step": 80
+    },
+    {
+      "epoch": 0.7763578274760383,
+      "grad_norm": 0.6835519671440125,
+      "learning_rate": 9.263200821770462e-06,
+      "loss": 0.7332,
+      "step": 81
+    },
+    {
+      "epoch": 0.7859424920127795,
+      "grad_norm": 0.6267021894454956,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.6944,
+      "step": 82
+    },
+    {
+      "epoch": 0.7955271565495208,
+      "grad_norm": 0.8507176637649536,
+      "learning_rate": 9.203508214822652e-06,
+      "loss": 0.7478,
+      "step": 83
+    },
+    {
+      "epoch": 0.805111821086262,
+      "grad_norm": 0.732303261756897,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.7252,
+      "step": 84
+    },
+    {
+      "epoch": 0.8146964856230032,
+      "grad_norm": 0.6333317160606384,
+      "learning_rate": 9.141699014900084e-06,
+      "loss": 0.7,
+      "step": 85
+    },
+    {
+      "epoch": 0.8242811501597445,
+      "grad_norm": 0.6137699484825134,
+      "learning_rate": 9.110010377239552e-06,
+      "loss": 0.6773,
+      "step": 86
+    },
+    {
+      "epoch": 0.8338658146964856,
+      "grad_norm": 0.6669235825538635,
+      "learning_rate": 9.077804344796302e-06,
+      "loss": 0.7296,
+      "step": 87
+    },
+    {
+      "epoch": 0.8434504792332268,
+      "grad_norm": 0.7705378532409668,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7017,
+      "step": 88
+    },
+    {
+      "epoch": 0.853035143769968,
+      "grad_norm": 0.7653799653053284,
+      "learning_rate": 9.011856377401891e-06,
+      "loss": 0.7441,
+      "step": 89
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 0.6707456707954407,
+      "learning_rate": 8.978122744408905e-06,
+      "loss": 0.7361,
+      "step": 90
+    },
+    {
+      "epoch": 0.8722044728434505,
+      "grad_norm": 0.7691360712051392,
+      "learning_rate": 8.943888319504456e-06,
+      "loss": 0.6952,
+      "step": 91
+    },
+    {
+      "epoch": 0.8817891373801917,
+      "grad_norm": 0.7389594912528992,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.6944,
+      "step": 92
+    },
+    {
+      "epoch": 0.8913738019169329,
+      "grad_norm": 0.7065908908843994,
+      "learning_rate": 8.873934395068006e-06,
+      "loss": 0.6945,
+      "step": 93
+    },
+    {
+      "epoch": 0.9009584664536742,
+      "grad_norm": 0.6882407069206238,
+      "learning_rate": 8.838223701790057e-06,
+      "loss": 0.6825,
+      "step": 94
+    },
+    {
+      "epoch": 0.9105431309904153,
+      "grad_norm": 0.6808512210845947,
+      "learning_rate": 8.802029828000157e-06,
+      "loss": 0.7075,
+      "step": 95
+    },
+    {
+      "epoch": 0.9201277955271565,
+      "grad_norm": 0.6349908709526062,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.7157,
+      "step": 96
+    },
+    {
+      "epoch": 0.9297124600638977,
+      "grad_norm": 0.6814895272254944,
+      "learning_rate": 8.728210824415829e-06,
+      "loss": 0.7014,
+      "step": 97
+    },
+    {
+      "epoch": 0.939297124600639,
+      "grad_norm": 0.6316925287246704,
+      "learning_rate": 8.690594987436705e-06,
+      "loss": 0.7267,
+      "step": 98
+    },
+    {
+      "epoch": 0.9488817891373802,
+      "grad_norm": 0.6401665806770325,
+      "learning_rate": 8.652514554406388e-06,
+      "loss": 0.706,
+      "step": 99
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 0.5566475987434387,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.6619,
+      "step": 100
+    },
+    {
+      "epoch": 0.9680511182108626,
+      "grad_norm": 0.632225513458252,
+      "learning_rate": 8.574979133323378e-06,
+      "loss": 0.7069,
+      "step": 101
+    },
+    {
+      "epoch": 0.9776357827476039,
+      "grad_norm": 0.5987431406974792,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.7253,
+      "step": 102
+    },
+    {
+      "epoch": 0.987220447284345,
+      "grad_norm": 0.604228675365448,
+      "learning_rate": 8.495643602586287e-06,
+      "loss": 0.678,
+      "step": 103
+    },
+    {
+      "epoch": 0.9968051118210862,
+      "grad_norm": 0.6816259622573853,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.7143,
+      "step": 104
+    },
+    {
+      "epoch": 1.0063897763578276,
+      "grad_norm": 0.5808905363082886,
+      "learning_rate": 8.414547910024035e-06,
+      "loss": 0.6676,
+      "step": 105
+    },
+    {
+      "epoch": 1.0159744408945688,
+      "grad_norm": 0.6644414067268372,
+      "learning_rate": 8.373352729660373e-06,
+      "loss": 0.6234,
+      "step": 106
+    },
+    {
+      "epoch": 1.0255591054313098,
+      "grad_norm": 0.7519953846931458,
+      "learning_rate": 8.331732889760021e-06,
+      "loss": 0.6192,
+      "step": 107
+    },
+    {
+      "epoch": 1.035143769968051,
+      "grad_norm": 0.5884900689125061,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.6335,
+      "step": 108
+    },
+    {
+      "epoch": 1.0447284345047922,
+      "grad_norm": 0.5819219946861267,
+      "learning_rate": 8.247240241650918e-06,
+      "loss": 0.6148,
+      "step": 109
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.6081036925315857,
+      "learning_rate": 8.204378069925121e-06,
+      "loss": 0.6204,
+      "step": 110
+    },
+    {
+      "epoch": 1.0638977635782747,
+      "grad_norm": 0.7000735998153687,
+      "learning_rate": 8.16111251028955e-06,
+      "loss": 0.6116,
+      "step": 111
+    },
+    {
+      "epoch": 1.073482428115016,
+      "grad_norm": 0.6014118790626526,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.6457,
+      "step": 112
+    },
+    {
+      "epoch": 1.0830670926517572,
+      "grad_norm": 0.6278773546218872,
+      "learning_rate": 8.073393063582386e-06,
+      "loss": 0.6246,
+      "step": 113
+    },
+    {
+      "epoch": 1.0926517571884984,
+      "grad_norm": 0.6522474884986877,
+      "learning_rate": 8.0289502192041e-06,
+      "loss": 0.6342,
+      "step": 114
+    },
+    {
+      "epoch": 1.1022364217252396,
+      "grad_norm": 0.6242803931236267,
+      "learning_rate": 7.984126070912519e-06,
+      "loss": 0.6439,
+      "step": 115
+    },
+    {
+      "epoch": 1.1118210862619808,
+      "grad_norm": 0.5995987057685852,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.6205,
+      "step": 116
+    },
+    {
+      "epoch": 1.121405750798722,
+      "grad_norm": 0.6373648047447205,
+      "learning_rate": 7.89335648089903e-06,
+      "loss": 0.6241,
+      "step": 117
+    },
+    {
+      "epoch": 1.1309904153354633,
+      "grad_norm": 0.6015115976333618,
+      "learning_rate": 7.84742246584226e-06,
+      "loss": 0.6483,
+      "step": 118
+    },
+    {
+      "epoch": 1.1405750798722045,
+      "grad_norm": 0.663524866104126,
+      "learning_rate": 7.801129998764014e-06,
+      "loss": 0.6231,
+      "step": 119
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.49973756074905396,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.5994,
+      "step": 120
+    },
+    {
+      "epoch": 1.159744408945687,
+      "grad_norm": 0.6662487983703613,
+      "learning_rate": 7.70749306331863e-06,
+      "loss": 0.6296,
+      "step": 121
+    },
+    {
+      "epoch": 1.1693290734824282,
+      "grad_norm": 0.6271225810050964,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.6182,
+      "step": 122
+    },
+    {
+      "epoch": 1.1789137380191694,
+      "grad_norm": 0.5760684609413147,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.6507,
+      "step": 123
+    },
+    {
+      "epoch": 1.1884984025559104,
+      "grad_norm": 0.6523165702819824,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.63,
+      "step": 124
+    },
+    {
+      "epoch": 1.1980830670926517,
+      "grad_norm": 0.5384656190872192,
+      "learning_rate": 7.516177115029002e-06,
+      "loss": 0.6101,
+      "step": 125
+    },
+    {
+      "epoch": 1.207667731629393,
+      "grad_norm": 0.6138818264007568,
+      "learning_rate": 7.467541090321735e-06,
+      "loss": 0.6097,
+      "step": 126
+    },
+    {
+      "epoch": 1.2172523961661341,
+      "grad_norm": 0.6557722091674805,
+      "learning_rate": 7.4185944355261996e-06,
+      "loss": 0.6323,
+      "step": 127
+    },
+    {
+      "epoch": 1.2268370607028753,
+      "grad_norm": 0.6197437047958374,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.6205,
+      "step": 128
+    },
+    {
+      "epoch": 1.2364217252396166,
+      "grad_norm": 0.573975145816803,
+      "learning_rate": 7.319793920889171e-06,
+      "loss": 0.5997,
+      "step": 129
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.6613350510597229,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.6221,
+      "step": 130
+    },
+    {
+      "epoch": 1.255591054313099,
+      "grad_norm": 0.6064529418945312,
+      "learning_rate": 7.219825320152411e-06,
+      "loss": 0.6302,
+      "step": 131
+    },
+    {
+      "epoch": 1.2651757188498403,
+      "grad_norm": 0.5708147883415222,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.6076,
+      "step": 132
+    },
+    {
+      "epoch": 1.2747603833865815,
+      "grad_norm": 0.6603698134422302,
+      "learning_rate": 7.118738970516944e-06,
+      "loss": 0.619,
+      "step": 133
+    },
+    {
+      "epoch": 1.2843450479233227,
+      "grad_norm": 0.5752602219581604,
+      "learning_rate": 7.067792524832604e-06,
+      "loss": 0.6104,
+      "step": 134
+    },
+    {
+      "epoch": 1.293929712460064,
+      "grad_norm": 0.5691383481025696,
+      "learning_rate": 7.016585772004026e-06,
+      "loss": 0.6119,
+      "step": 135
+    },
+    {
+      "epoch": 1.3035143769968052,
+      "grad_norm": 0.6326082944869995,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.6136,
+      "step": 136
+    },
+    {
+      "epoch": 1.3130990415335464,
+      "grad_norm": 0.6783974766731262,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.6245,
+      "step": 137
+    },
+    {
+      "epoch": 1.3226837060702876,
+      "grad_norm": 0.5575075149536133,
+      "learning_rate": 6.8614682920097265e-06,
+      "loss": 0.6218,
+      "step": 138
+    },
+    {
+      "epoch": 1.3322683706070286,
+      "grad_norm": 0.5773029327392578,
+      "learning_rate": 6.809285088483361e-06,
+      "loss": 0.6018,
+      "step": 139
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.7214598655700684,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.6105,
+      "step": 140
+    },
+    {
+      "epoch": 1.351437699680511,
+      "grad_norm": 0.5614567399024963,
+      "learning_rate": 6.704241985612625e-06,
+      "loss": 0.6114,
+      "step": 141
+    },
+    {
+      "epoch": 1.3610223642172525,
+      "grad_norm": 0.5857440233230591,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.5887,
+      "step": 142
+    },
+    {
+      "epoch": 1.3706070287539935,
+      "grad_norm": 0.6536932587623596,
+      "learning_rate": 6.598340745578908e-06,
+      "loss": 0.6531,
+      "step": 143
+    },
+    {
+      "epoch": 1.3801916932907348,
+      "grad_norm": 0.5684155225753784,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.6384,
+      "step": 144
+    },
+    {
+      "epoch": 1.389776357827476,
+      "grad_norm": 0.5640861988067627,
+      "learning_rate": 6.491634692845781e-06,
+      "loss": 0.6243,
+      "step": 145
+    },
+    {
+      "epoch": 1.3993610223642172,
+      "grad_norm": 0.48580506443977356,
+      "learning_rate": 6.437996637160086e-06,
+      "loss": 0.6022,
+      "step": 146
+    },
+    {
+      "epoch": 1.4089456869009584,
+      "grad_norm": 0.5101671814918518,
+      "learning_rate": 6.384177557124247e-06,
+      "loss": 0.6286,
+      "step": 147
+    },
+    {
+      "epoch": 1.4185303514376997,
+      "grad_norm": 0.5692585706710815,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.6325,
+      "step": 148
+    },
+    {
+      "epoch": 1.428115015974441,
+      "grad_norm": 0.6159618496894836,
+      "learning_rate": 6.276023446318214e-06,
+      "loss": 0.6116,
+      "step": 149
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 0.5336474776268005,
+      "learning_rate": 6.2217020306894705e-06,
+      "loss": 0.613,
+      "step": 150
+    },
+    {
+      "epoch": 1.4472843450479234,
+      "grad_norm": 0.5104553699493408,
+      "learning_rate": 6.1672268192795285e-06,
+      "loss": 0.6349,
+      "step": 151
+    },
+    {
+      "epoch": 1.4568690095846646,
+      "grad_norm": 0.5543062090873718,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.6382,
+      "step": 152
+    },
+    {
+      "epoch": 1.4664536741214058,
+      "grad_norm": 0.5532480478286743,
+      "learning_rate": 6.057842458386315e-06,
+      "loss": 0.6132,
+      "step": 153
+    },
+    {
+      "epoch": 1.476038338658147,
+      "grad_norm": 0.6132843494415283,
+      "learning_rate": 6.002947078916365e-06,
+      "loss": 0.6323,
+      "step": 154
+    },
+    {
+      "epoch": 1.4856230031948883,
+      "grad_norm": 0.510259747505188,
+      "learning_rate": 5.947925441958393e-06,
+      "loss": 0.6107,
+      "step": 155
+    },
+    {
+      "epoch": 1.4952076677316293,
+      "grad_norm": 0.6006035804748535,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.6227,
+      "step": 156
+    },
+    {
+      "epoch": 1.5047923322683707,
+      "grad_norm": 0.5839741230010986,
+      "learning_rate": 5.837531116523683e-06,
+      "loss": 0.6237,
+      "step": 157
+    },
+    {
+      "epoch": 1.5143769968051117,
+      "grad_norm": 0.5134792923927307,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.6297,
+      "step": 158
+    },
+    {
+      "epoch": 1.5239616613418532,
+      "grad_norm": 0.5354273319244385,
+      "learning_rate": 5.726715068949564e-06,
+      "loss": 0.6197,
+      "step": 159
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 0.5770488977432251,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.6154,
+      "step": 160
+    },
+    {
+      "epoch": 1.5431309904153354,
+      "grad_norm": 0.5453071594238281,
+      "learning_rate": 5.615533098453215e-06,
+      "loss": 0.624,
+      "step": 161
+    },
+    {
+      "epoch": 1.5527156549520766,
+      "grad_norm": 0.5175986886024475,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.6079,
+      "step": 162
+    },
+    {
+      "epoch": 1.5623003194888179,
+      "grad_norm": 0.6262847781181335,
+      "learning_rate": 5.504041188505022e-06,
+      "loss": 0.6326,
+      "step": 163
+    },
+    {
+      "epoch": 1.571884984025559,
+      "grad_norm": 0.5686348080635071,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.6246,
+      "step": 164
+    },
+    {
+      "epoch": 1.5814696485623003,
+      "grad_norm": 0.560458779335022,
+      "learning_rate": 5.392295478639226e-06,
+      "loss": 0.6181,
+      "step": 165
+    },
+    {
+      "epoch": 1.5910543130990416,
+      "grad_norm": 0.5434932112693787,
+      "learning_rate": 5.336345028060199e-06,
+      "loss": 0.5863,
+      "step": 166
+    },
+    {
+      "epoch": 1.6006389776357828,
+      "grad_norm": 0.5670589804649353,
+      "learning_rate": 5.2803522361859596e-06,
+      "loss": 0.6022,
+      "step": 167
+    },
+    {
+      "epoch": 1.610223642172524,
+      "grad_norm": 0.5307400226593018,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.5895,
+      "step": 168
+    },
+    {
+      "epoch": 1.619808306709265,
+      "grad_norm": 0.6883311867713928,
+      "learning_rate": 5.168267827938971e-06,
+      "loss": 0.5819,
+      "step": 169
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6043215990066528,
+      "learning_rate": 5.112190321479026e-06,
+      "loss": 0.6221,
+      "step": 170
+    },
+    {
+      "epoch": 1.6389776357827475,
+      "grad_norm": 0.5461068153381348,
+      "learning_rate": 5.05609869177323e-06,
+      "loss": 0.6216,
+      "step": 171
+    },
+    {
+      "epoch": 1.648562300319489,
+      "grad_norm": 0.5376251339912415,
+      "learning_rate": 5e-06,
+      "loss": 0.6331,
+      "step": 172
+    },
+    {
+      "epoch": 1.65814696485623,
+      "grad_norm": 0.5725062489509583,
+      "learning_rate": 4.943901308226771e-06,
+      "loss": 0.6208,
+      "step": 173
+    },
+    {
+      "epoch": 1.6677316293929714,
+      "grad_norm": 0.5605234503746033,
+      "learning_rate": 4.887809678520976e-06,
+      "loss": 0.6244,
+      "step": 174
+    },
+    {
+      "epoch": 1.6773162939297124,
+      "grad_norm": 0.6107360124588013,
+      "learning_rate": 4.831732172061032e-06,
+      "loss": 0.6057,
+      "step": 175
+    },
+    {
+      "epoch": 1.6869009584664538,
+      "grad_norm": 0.5460118651390076,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.6224,
+      "step": 176
+    },
+    {
+      "epoch": 1.6964856230031948,
+      "grad_norm": 0.5322807431221008,
+      "learning_rate": 4.719647763814041e-06,
+      "loss": 0.6295,
+      "step": 177
+    },
+    {
+      "epoch": 1.706070287539936,
+      "grad_norm": 0.5447019338607788,
+      "learning_rate": 4.663654971939802e-06,
+      "loss": 0.6178,
+      "step": 178
+    },
+    {
+      "epoch": 1.7156549520766773,
+      "grad_norm": 0.5457282066345215,
+      "learning_rate": 4.6077045213607765e-06,
+      "loss": 0.6038,
+      "step": 179
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 0.5212422609329224,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.6119,
+      "step": 180
+    },
+    {
+      "epoch": 1.7348242811501597,
+      "grad_norm": 0.49170607328414917,
+      "learning_rate": 4.4959588114949785e-06,
+      "loss": 0.6036,
+      "step": 181
+    },
+    {
+      "epoch": 1.744408945686901,
+      "grad_norm": 0.536220371723175,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.6035,
+      "step": 182
+    },
+    {
+      "epoch": 1.7539936102236422,
+      "grad_norm": 0.5448375344276428,
+      "learning_rate": 4.384466901546786e-06,
+      "loss": 0.6128,
+      "step": 183
+    },
+    {
+      "epoch": 1.7635782747603834,
+      "grad_norm": 0.5462779998779297,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.5901,
+      "step": 184
+    },
+    {
+      "epoch": 1.7731629392971247,
+      "grad_norm": 0.5666403770446777,
+      "learning_rate": 4.273284931050438e-06,
+      "loss": 0.6313,
+      "step": 185
+    },
+    {
+      "epoch": 1.7827476038338657,
+      "grad_norm": 0.5086902379989624,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.6166,
+      "step": 186
+    },
+    {
+      "epoch": 1.792332268370607,
+      "grad_norm": 0.5493374466896057,
+      "learning_rate": 4.162468883476319e-06,
+      "loss": 0.628,
+      "step": 187
+    },
+    {
+      "epoch": 1.8019169329073481,
+      "grad_norm": 0.5654379725456238,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.6344,
+      "step": 188
+    },
+    {
+      "epoch": 1.8115015974440896,
+      "grad_norm": 0.57657790184021,
+      "learning_rate": 4.052074558041608e-06,
+      "loss": 0.6376,
+      "step": 189
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 0.5371982455253601,
+      "learning_rate": 3.997052921083637e-06,
+      "loss": 0.5847,
+      "step": 190
+    },
+    {
+      "epoch": 1.830670926517572,
+      "grad_norm": 0.541728138923645,
+      "learning_rate": 3.9421575416136866e-06,
+      "loss": 0.6211,
+      "step": 191
+    },
+    {
+      "epoch": 1.840255591054313,
+      "grad_norm": 0.5112797021865845,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.6119,
+      "step": 192
+    },
+    {
+      "epoch": 1.8498402555910545,
+      "grad_norm": 0.5171915888786316,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.6265,
+      "step": 193
+    },
+    {
+      "epoch": 1.8594249201277955,
+      "grad_norm": 0.46963581442832947,
+      "learning_rate": 3.778297969310529e-06,
+      "loss": 0.6256,
+      "step": 194
+    },
+    {
+      "epoch": 1.8690095846645367,
+      "grad_norm": 0.47522279620170593,
+      "learning_rate": 3.723976553681787e-06,
+      "loss": 0.5961,
+      "step": 195
+    },
+    {
+      "epoch": 1.878594249201278,
+      "grad_norm": 0.4703618884086609,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.5961,
+      "step": 196
+    },
+    {
+      "epoch": 1.8881789137380192,
+      "grad_norm": 0.5094874501228333,
+      "learning_rate": 3.6158224428757538e-06,
+      "loss": 0.6051,
+      "step": 197
+    },
+    {
+      "epoch": 1.8977635782747604,
+      "grad_norm": 0.49340417981147766,
+      "learning_rate": 3.562003362839914e-06,
+      "loss": 0.6515,
+      "step": 198
+    },
+    {
+      "epoch": 1.9073482428115016,
+      "grad_norm": 0.5253342390060425,
+      "learning_rate": 3.50836530715422e-06,
+      "loss": 0.6192,
+      "step": 199
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.47582119703292847,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6012,
+      "step": 200
+    },
+    {
+      "epoch": 1.926517571884984,
+      "grad_norm": 0.5417906045913696,
+      "learning_rate": 3.4016592544210937e-06,
+      "loss": 0.6247,
+      "step": 201
+    },
+    {
+      "epoch": 1.9361022364217253,
+      "grad_norm": 0.4653812050819397,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.6207,
+      "step": 202
+    },
+    {
+      "epoch": 1.9456869009584663,
+      "grad_norm": 0.5107676386833191,
+      "learning_rate": 3.295758014387375e-06,
+      "loss": 0.6113,
+      "step": 203
+    },
+    {
+      "epoch": 1.9552715654952078,
+      "grad_norm": 0.48281431198120117,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.6131,
+      "step": 204
+    },
+    {
+      "epoch": 1.9648562300319488,
+      "grad_norm": 0.4904637634754181,
+      "learning_rate": 3.1907149115166403e-06,
+      "loss": 0.6146,
+      "step": 205
+    },
+    {
+      "epoch": 1.9744408945686902,
+      "grad_norm": 0.5293906331062317,
+      "learning_rate": 3.1385317079902743e-06,
+      "loss": 0.6028,
+      "step": 206
+    },
+    {
+      "epoch": 1.9840255591054312,
+      "grad_norm": 0.48737844824790955,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.5971,
+      "step": 207
+    },
+    {
+      "epoch": 1.9936102236421727,
+      "grad_norm": 0.5447724461555481,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.6448,
+      "step": 208
+    },
+    {
+      "epoch": 2.0031948881789137,
+      "grad_norm": 0.48444610834121704,
+      "learning_rate": 2.9834142279959754e-06,
+      "loss": 0.5869,
+      "step": 209
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.675361156463623,
+      "learning_rate": 2.932207475167398e-06,
+      "loss": 0.5447,
+      "step": 210
+    },
+    {
+      "epoch": 2.022364217252396,
+      "grad_norm": 0.625113844871521,
+      "learning_rate": 2.8812610294830568e-06,
+      "loss": 0.5638,
+      "step": 211
+    },
+    {
+      "epoch": 2.0319488817891376,
+      "grad_norm": 0.528229296207428,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.5758,
+      "step": 212
+    },
+    {
+      "epoch": 2.0415335463258786,
+      "grad_norm": 0.5284104347229004,
+      "learning_rate": 2.7801746798475905e-06,
+      "loss": 0.5618,
+      "step": 213
+    },
+    {
+      "epoch": 2.0511182108626196,
+      "grad_norm": 0.6477755308151245,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.5669,
+      "step": 214
+    },
+    {
+      "epoch": 2.060702875399361,
+      "grad_norm": 0.6743851900100708,
+      "learning_rate": 2.6802060791108304e-06,
+      "loss": 0.5495,
+      "step": 215
+    },
+    {
+      "epoch": 2.070287539936102,
+      "grad_norm": 0.5009170174598694,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.5421,
+      "step": 216
+    },
+    {
+      "epoch": 2.0798722044728435,
+      "grad_norm": 0.5411891937255859,
+      "learning_rate": 2.5814055644738013e-06,
+      "loss": 0.5708,
+      "step": 217
+    },
+    {
+      "epoch": 2.0894568690095845,
+      "grad_norm": 0.523042619228363,
+      "learning_rate": 2.532458909678266e-06,
+      "loss": 0.5391,
+      "step": 218
+    },
+    {
+      "epoch": 2.099041533546326,
+      "grad_norm": 0.6371281743049622,
+      "learning_rate": 2.483822884971e-06,
+      "loss": 0.5425,
+      "step": 219
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.47539764642715454,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.5674,
+      "step": 220
+    },
+    {
+      "epoch": 2.1182108626198084,
+      "grad_norm": 0.5385382175445557,
+      "learning_rate": 2.387507176420256e-06,
+      "loss": 0.5401,
+      "step": 221
+    },
+    {
+      "epoch": 2.1277955271565494,
+      "grad_norm": 0.5269696116447449,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.529,
+      "step": 222
+    },
+    {
+      "epoch": 2.137380191693291,
+      "grad_norm": 0.5272794365882874,
+      "learning_rate": 2.2925069366813718e-06,
+      "loss": 0.5653,
+      "step": 223
+    },
+    {
+      "epoch": 2.146964856230032,
+      "grad_norm": 0.5422731041908264,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.566,
+      "step": 224
+    },
+    {
+      "epoch": 2.1565495207667733,
+      "grad_norm": 0.5046980977058411,
+      "learning_rate": 2.1988700012359865e-06,
+      "loss": 0.5317,
+      "step": 225
+    },
+    {
+      "epoch": 2.1661341853035143,
+      "grad_norm": 0.4797118306159973,
+      "learning_rate": 2.1525775341577404e-06,
+      "loss": 0.5708,
+      "step": 226
+    },
+    {
+      "epoch": 2.1757188498402558,
+      "grad_norm": 0.475576251745224,
+      "learning_rate": 2.1066435191009717e-06,
+      "loss": 0.5208,
+      "step": 227
+    },
+    {
+      "epoch": 2.1853035143769968,
+      "grad_norm": 0.5215170979499817,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.541,
+      "step": 228
+    },
+    {
+      "epoch": 2.194888178913738,
+      "grad_norm": 0.5315196514129639,
+      "learning_rate": 2.0158739290874822e-06,
+      "loss": 0.5416,
+      "step": 229
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 0.5296704769134521,
+      "learning_rate": 1.971049780795901e-06,
+      "loss": 0.5375,
+      "step": 230
+    },
+    {
+      "epoch": 2.2140575079872207,
+      "grad_norm": 0.4825049340724945,
+      "learning_rate": 1.9266069364176144e-06,
+      "loss": 0.5798,
+      "step": 231
+    },
+    {
+      "epoch": 2.2236421725239617,
+      "grad_norm": 0.47409123182296753,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.54,
+      "step": 232
+    },
+    {
+      "epoch": 2.2332268370607027,
+      "grad_norm": 0.5220174789428711,
+      "learning_rate": 1.838887489710452e-06,
+      "loss": 0.5242,
+      "step": 233
+    },
+    {
+      "epoch": 2.242811501597444,
+      "grad_norm": 0.5206701159477234,
+      "learning_rate": 1.7956219300748796e-06,
+      "loss": 0.5511,
+      "step": 234
+    },
+    {
+      "epoch": 2.252396166134185,
+      "grad_norm": 0.4608929455280304,
+      "learning_rate": 1.7527597583490825e-06,
+      "loss": 0.5785,
+      "step": 235
+    },
+    {
+      "epoch": 2.2619808306709266,
+      "grad_norm": 0.4998515844345093,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.5382,
+      "step": 236
+    },
+    {
+      "epoch": 2.2715654952076676,
+      "grad_norm": 0.4545069634914398,
+      "learning_rate": 1.6682671102399806e-06,
+      "loss": 0.5375,
+      "step": 237
+    },
+    {
+      "epoch": 2.281150159744409,
+      "grad_norm": 0.4538171887397766,
+      "learning_rate": 1.6266472703396286e-06,
+      "loss": 0.5652,
+      "step": 238
+    },
+    {
+      "epoch": 2.29073482428115,
+      "grad_norm": 0.4549846053123474,
+      "learning_rate": 1.5854520899759656e-06,
+      "loss": 0.5606,
+      "step": 239
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 0.45981788635253906,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.5495,
+      "step": 240
+    },
+    {
+      "epoch": 2.3099041533546325,
+      "grad_norm": 0.509513795375824,
+      "learning_rate": 1.5043563974137132e-06,
+      "loss": 0.5273,
+      "step": 241
+    },
+    {
+      "epoch": 2.319488817891374,
+      "grad_norm": 0.4437123239040375,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5451,
+      "step": 242
+    },
+    {
+      "epoch": 2.329073482428115,
+      "grad_norm": 0.4303329586982727,
+      "learning_rate": 1.4250208666766235e-06,
+      "loss": 0.5572,
+      "step": 243
+    },
+    {
+      "epoch": 2.3386581469648564,
+      "grad_norm": 0.4266361892223358,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.561,
+      "step": 244
+    },
+    {
+      "epoch": 2.3482428115015974,
+      "grad_norm": 0.47618621587753296,
+      "learning_rate": 1.3474854455936126e-06,
+      "loss": 0.5511,
+      "step": 245
+    },
+    {
+      "epoch": 2.357827476038339,
+      "grad_norm": 0.480275422334671,
+      "learning_rate": 1.3094050125632973e-06,
+      "loss": 0.5806,
+      "step": 246
+    },
+    {
+      "epoch": 2.36741214057508,
+      "grad_norm": 0.4448004961013794,
+      "learning_rate": 1.2717891755841722e-06,
+      "loss": 0.5497,
+      "step": 247
+    },
+    {
+      "epoch": 2.376996805111821,
+      "grad_norm": 0.4528818726539612,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.5724,
+      "step": 248
+    },
+    {
+      "epoch": 2.3865814696485623,
+      "grad_norm": 0.5146142840385437,
+      "learning_rate": 1.1979701719998454e-06,
+      "loss": 0.5336,
+      "step": 249
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.4516039192676544,
+      "learning_rate": 1.1617762982099446e-06,
+      "loss": 0.5318,
+      "step": 250
+    },
+    {
+      "epoch": 2.405750798722045,
+      "grad_norm": 0.48698943853378296,
+      "learning_rate": 1.1260656049319957e-06,
+      "loss": 0.5577,
+      "step": 251
+    },
+    {
+      "epoch": 2.415335463258786,
+      "grad_norm": 0.4867784380912781,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5367,
+      "step": 252
+    },
+    {
+      "epoch": 2.4249201277955272,
+      "grad_norm": 0.49107033014297485,
+      "learning_rate": 1.0561116804955451e-06,
+      "loss": 0.5605,
+      "step": 253
+    },
+    {
+      "epoch": 2.4345047923322682,
+      "grad_norm": 0.4654329717159271,
+      "learning_rate": 1.0218772555910955e-06,
+      "loss": 0.5436,
+      "step": 254
+    },
+    {
+      "epoch": 2.4440894568690097,
+      "grad_norm": 0.4349857270717621,
+      "learning_rate": 9.881436225981107e-07,
+      "loss": 0.5533,
+      "step": 255
+    },
+    {
+      "epoch": 2.4536741214057507,
+      "grad_norm": 0.43953022360801697,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5358,
+      "step": 256
+    },
+    {
+      "epoch": 2.463258785942492,
+      "grad_norm": 0.425687313079834,
+      "learning_rate": 9.221956552036992e-07,
+      "loss": 0.5475,
+      "step": 257
+    },
+    {
+      "epoch": 2.472843450479233,
+      "grad_norm": 0.4697389304637909,
+      "learning_rate": 8.899896227604509e-07,
+      "loss": 0.5291,
+      "step": 258
+    },
+    {
+      "epoch": 2.4824281150159746,
+      "grad_norm": 0.4302732050418854,
+      "learning_rate": 8.58300985099918e-07,
+      "loss": 0.5522,
+      "step": 259
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 0.44490545988082886,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.5428,
+      "step": 260
+    },
+    {
+      "epoch": 2.501597444089457,
+      "grad_norm": 0.457554429769516,
+      "learning_rate": 7.964917851773496e-07,
+      "loss": 0.5438,
+      "step": 261
+    },
+    {
+      "epoch": 2.511182108626198,
+      "grad_norm": 0.48835253715515137,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.5412,
+      "step": 262
+    },
+    {
+      "epoch": 2.520766773162939,
+      "grad_norm": 0.4150005280971527,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 2.5303514376996805,
+      "grad_norm": 0.44234219193458557,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.5659,
+      "step": 264
+    },
+    {
+      "epoch": 2.539936102236422,
+      "grad_norm": 0.43340200185775757,
+      "learning_rate": 6.792532212817271e-07,
+      "loss": 0.5345,
+      "step": 265
+    },
+    {
+      "epoch": 2.549520766773163,
+      "grad_norm": 0.4623399078845978,
+      "learning_rate": 6.512943342215234e-07,
+      "loss": 0.5222,
+      "step": 266
+    },
+    {
+      "epoch": 2.559105431309904,
+      "grad_norm": 0.44783130288124084,
+      "learning_rate": 6.238828904562316e-07,
+      "loss": 0.5617,
+      "step": 267
+    },
+    {
+      "epoch": 2.5686900958466454,
+      "grad_norm": 0.45720329880714417,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.5715,
+      "step": 268
+    },
+    {
+      "epoch": 2.5782747603833864,
+      "grad_norm": 0.460199236869812,
+      "learning_rate": 5.707160663821009e-07,
+      "loss": 0.5746,
+      "step": 269
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 0.4227401614189148,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.5655,
+      "step": 270
+    },
+    {
+      "epoch": 2.597444089456869,
+      "grad_norm": 0.4950794577598572,
+      "learning_rate": 5.197795201563744e-07,
+      "loss": 0.543,
+      "step": 271
+    },
+    {
+      "epoch": 2.6070287539936103,
+      "grad_norm": 0.42022472620010376,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.5313,
+      "step": 272
+    },
+    {
+      "epoch": 2.6166134185303513,
+      "grad_norm": 0.4263933002948761,
+      "learning_rate": 4.710988998640298e-07,
+      "loss": 0.582,
+      "step": 273
+    },
+    {
+      "epoch": 2.626198083067093,
+      "grad_norm": 0.456779807806015,
+      "learning_rate": 4.4761226670592074e-07,
+      "loss": 0.5743,
+      "step": 274
+    },
+    {
+      "epoch": 2.635782747603834,
+      "grad_norm": 0.46589067578315735,
+      "learning_rate": 4.2469871766340096e-07,
+      "loss": 0.548,
+      "step": 275
+    },
+    {
+      "epoch": 2.6453674121405752,
+      "grad_norm": 0.45368775725364685,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.5453,
+      "step": 276
+    },
+    {
+      "epoch": 2.6549520766773163,
+      "grad_norm": 0.45604661107063293,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.5498,
+      "step": 277
+    },
+    {
+      "epoch": 2.6645367412140573,
+      "grad_norm": 0.46903011202812195,
+      "learning_rate": 3.5942505740480583e-07,
+      "loss": 0.5508,
+      "step": 278
+    },
+    {
+      "epoch": 2.6741214057507987,
+      "grad_norm": 0.431189626455307,
+      "learning_rate": 3.3883196305992906e-07,
+      "loss": 0.54,
+      "step": 279
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 0.4565132260322571,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.525,
+      "step": 280
+    },
+    {
+      "epoch": 2.693290734824281,
+      "grad_norm": 0.46803998947143555,
+      "learning_rate": 2.9940862715390483e-07,
+      "loss": 0.5509,
+      "step": 281
+    },
+    {
+      "epoch": 2.702875399361022,
+      "grad_norm": 0.44332244992256165,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.5394,
+      "step": 282
+    },
+    {
+      "epoch": 2.7124600638977636,
+      "grad_norm": 0.46024301648139954,
+      "learning_rate": 2.6235218056235633e-07,
+      "loss": 0.4987,
+      "step": 283
+    },
+    {
+      "epoch": 2.722044728434505,
+      "grad_norm": 0.4184441566467285,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5417,
+      "step": 284
+    },
+    {
+      "epoch": 2.731629392971246,
+      "grad_norm": 0.4836418628692627,
+      "learning_rate": 2.276812823220964e-07,
+      "loss": 0.5531,
+      "step": 285
+    },
+    {
+      "epoch": 2.741214057507987,
+      "grad_norm": 0.44165509939193726,
+      "learning_rate": 2.1124591657534776e-07,
+      "loss": 0.5725,
+      "step": 286
+    },
+    {
+      "epoch": 2.7507987220447285,
+      "grad_norm": 0.44304710626602173,
+      "learning_rate": 1.9541339027450256e-07,
+      "loss": 0.5432,
+      "step": 287
+    },
+    {
+      "epoch": 2.7603833865814695,
+      "grad_norm": 0.4602050185203552,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.5235,
+      "step": 288
+    },
+    {
+      "epoch": 2.769968051118211,
+      "grad_norm": 0.4554177224636078,
+      "learning_rate": 1.6556475227496816e-07,
+      "loss": 0.5529,
+      "step": 289
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 0.4562681019306183,
+      "learning_rate": 1.5155239811656562e-07,
+      "loss": 0.5339,
+      "step": 290
+    },
+    {
+      "epoch": 2.7891373801916934,
+      "grad_norm": 0.4614582061767578,
+      "learning_rate": 1.3815039801161723e-07,
+      "loss": 0.5502,
+      "step": 291
+    },
+    {
+      "epoch": 2.7987220447284344,
+      "grad_norm": 0.4560908079147339,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.5275,
+      "step": 292
+    },
+    {
+      "epoch": 2.8083067092651754,
+      "grad_norm": 0.4341632127761841,
+      "learning_rate": 1.1318413143740436e-07,
+      "loss": 0.5326,
+      "step": 293
+    },
+    {
+      "epoch": 2.817891373801917,
+      "grad_norm": 0.4644143879413605,
+      "learning_rate": 1.0162300788382263e-07,
+      "loss": 0.5481,
+      "step": 294
+    },
+    {
+      "epoch": 2.8274760383386583,
+      "grad_norm": 0.4713132381439209,
+      "learning_rate": 9.0678523819408e-08,
+      "loss": 0.5222,
+      "step": 295
+    },
+    {
+      "epoch": 2.8370607028753994,
+      "grad_norm": 0.450314462184906,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.5522,
+      "step": 296
+    },
+    {
+      "epoch": 2.8466453674121404,
+      "grad_norm": 0.46823227405548096,
+      "learning_rate": 7.064490740882057e-08,
+      "loss": 0.546,
+      "step": 297
+    },
+    {
+      "epoch": 2.856230031948882,
+      "grad_norm": 0.43032318353652954,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.5542,
+      "step": 298
+    },
+    {
+      "epoch": 2.8658146964856233,
+      "grad_norm": 0.40848687291145325,
+      "learning_rate": 5.3093369734816824e-08,
+      "loss": 0.5663,
+      "step": 299
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 0.4318215250968933,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.5595,
+      "step": 300
+    },
+    {
+      "epoch": 2.8849840255591053,
+      "grad_norm": 0.4364784359931946,
+      "learning_rate": 3.8032748525179684e-08,
+      "loss": 0.5338,
+      "step": 301
+    },
+    {
+      "epoch": 2.8945686900958467,
+      "grad_norm": 0.4324475824832916,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.5481,
+      "step": 302
+    },
+    {
+      "epoch": 2.9041533546325877,
+      "grad_norm": 0.4409596920013428,
+      "learning_rate": 2.547062725623828e-08,
+      "loss": 0.531,
+      "step": 303
+    },
+    {
+      "epoch": 2.913738019169329,
+      "grad_norm": 0.4079962968826294,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.5522,
+      "step": 304
+    },
+    {
+      "epoch": 2.92332268370607,
+      "grad_norm": 0.43923890590667725,
+      "learning_rate": 1.541333133436018e-08,
+      "loss": 0.5487,
+      "step": 305
+    },
+    {
+      "epoch": 2.9329073482428116,
+      "grad_norm": 0.3935544490814209,
+      "learning_rate": 1.132562476771959e-08,
+      "loss": 0.5437,
+      "step": 306
+    },
+    {
+      "epoch": 2.9424920127795526,
+      "grad_norm": 0.4257122874259949,
+      "learning_rate": 7.865924910916977e-09,
+      "loss": 0.5611,
+      "step": 307
+    },
+    {
+      "epoch": 2.952076677316294,
+      "grad_norm": 0.49820852279663086,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.5626,
+      "step": 308
+    },
+    {
+      "epoch": 2.961661341853035,
+      "grad_norm": 0.43063557147979736,
+      "learning_rate": 2.8322083323334417e-09,
+      "loss": 0.5644,
+      "step": 309
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 0.4651414453983307,
+      "learning_rate": 1.2588252874673469e-09,
+      "loss": 0.5432,
+      "step": 310
+    },
+    {
+      "epoch": 2.9808306709265175,
+      "grad_norm": 0.4408637583255768,
+      "learning_rate": 3.147162264971471e-10,
+      "loss": 0.5563,
+      "step": 311
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "grad_norm": 0.40899205207824707,
+      "learning_rate": 0.0,
+      "loss": 0.5641,
+      "step": 312
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "step": 312,
+      "total_flos": 4.367681917432627e+17,
+      "train_loss": 0.6496183709838451,
+      "train_runtime": 9740.0942,
+      "train_samples_per_second": 3.08,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 312,
+  "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": 4.367681917432627e+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 sha256:311794ef5dc91fa2cd7acec8345828d31e736efa554d59b163320c6f30ee9ed3
+size 7608