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": 2.995131507754271e+17,
+    "train_loss": 0.6095600314438343,
+    "train_runtime": 8590.5636,
+    "train_samples_per_second": 3.492,
+    "train_steps_per_second": 0.036
+}

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 sha256:1fdc320bb1aac64df09968de57fa42cacd76b74ab117bdf09631dc63bcdb1ca1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c88e9b0f94fb95f13713365df417453c23bf91701850e671c106199924f298e
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7340d3871737d0218efbe1b3068c8c1c9cc55845f685972d4e959f0f285dc80d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e1a51718d993a9bb718fda62610b1a9e2f8f0b008160634fae717c4aadd2f0
+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": 2.995131507754271e+17,
+    "train_loss": 0.6095600314438343,
+    "train_runtime": 8590.5636,
+    "train_samples_per_second": 3.492,
+    "train_steps_per_second": 0.036
+}

trainer_log.jsonl

@@ -0,0 +1,313 @@
+{"current_steps": 1, "total_steps": 312, "loss": 1.1437, "lr": 3.125e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:28:05"}
+{"current_steps": 2, "total_steps": 312, "loss": 1.0804, "lr": 6.25e-07, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:09", "remaining_time": "2:58:23"}
+{"current_steps": 3, "total_steps": 312, "loss": 1.155, "lr": 9.375000000000001e-07, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:37", "remaining_time": "2:48:09"}
+{"current_steps": 4, "total_steps": 312, "loss": 1.0944, "lr": 1.25e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:05", "remaining_time": "2:40:43"}
+{"current_steps": 5, "total_steps": 312, "loss": 1.1085, "lr": 1.5625e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:31", "remaining_time": "2:35:16"}
+{"current_steps": 6, "total_steps": 312, "loss": 1.099, "lr": 1.8750000000000003e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:01", "remaining_time": "2:34:25"}
+{"current_steps": 7, "total_steps": 312, "loss": 1.0407, "lr": 2.1875000000000002e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:32", "remaining_time": "2:34:33"}
+{"current_steps": 8, "total_steps": 312, "loss": 1.0256, "lr": 2.5e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:00", "remaining_time": "2:32:25"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.9822, "lr": 2.8125e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:04:31", "remaining_time": "2:32:03"}
+{"current_steps": 10, "total_steps": 312, "loss": 1.0148, "lr": 3.125e-06, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:04:58", "remaining_time": "2:30:01"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.9717, "lr": 3.4375e-06, "epoch": 0.10543130990415335, "percentage": 3.53, "elapsed_time": "0:05:23", "remaining_time": "2:27:24"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.9585, "lr": 3.7500000000000005e-06, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:05:47", "remaining_time": "2:24:58"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.9466, "lr": 4.0625000000000005e-06, "epoch": 0.12460063897763578, "percentage": 4.17, "elapsed_time": "0:06:14", "remaining_time": "2:23:43"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.9149, "lr": 4.3750000000000005e-06, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:06:41", "remaining_time": "2:22:34"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.9003, "lr": 4.6875000000000004e-06, "epoch": 0.14376996805111822, "percentage": 4.81, "elapsed_time": "0:07:07", "remaining_time": "2:21:07"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.8858, "lr": 5e-06, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:07:34", "remaining_time": "2:20:11"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.8923, "lr": 5.3125e-06, "epoch": 0.16293929712460065, "percentage": 5.45, "elapsed_time": "0:07:59", "remaining_time": "2:18:39"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.8444, "lr": 5.625e-06, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:08:26", "remaining_time": "2:17:52"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.846, "lr": 5.9375e-06, "epoch": 0.18210862619808307, "percentage": 6.09, "elapsed_time": "0:08:55", "remaining_time": "2:17:40"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.8413, "lr": 6.25e-06, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:09:24", "remaining_time": "2:17:15"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.7976, "lr": 6.5625e-06, "epoch": 0.2012779552715655, "percentage": 6.73, "elapsed_time": "0:09:50", "remaining_time": "2:16:15"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.7873, "lr": 6.875e-06, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:10:18", "remaining_time": "2:15:47"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.7909, "lr": 7.1875e-06, "epoch": 0.22044728434504793, "percentage": 7.37, "elapsed_time": "0:10:42", "remaining_time": "2:14:30"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.789, "lr": 7.500000000000001e-06, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:11:14", "remaining_time": "2:14:55"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.7688, "lr": 7.8125e-06, "epoch": 0.23961661341853036, "percentage": 8.01, "elapsed_time": "0:11:43", "remaining_time": "2:14:33"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.7509, "lr": 8.125000000000001e-06, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:12:11", "remaining_time": "2:14:11"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.7451, "lr": 8.4375e-06, "epoch": 0.25878594249201275, "percentage": 8.65, "elapsed_time": "0:12:42", "remaining_time": "2:14:11"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.7739, "lr": 8.750000000000001e-06, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:13:07", "remaining_time": "2:13:11"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.7406, "lr": 9.0625e-06, "epoch": 0.2779552715654952, "percentage": 9.29, "elapsed_time": "0:13:34", "remaining_time": "2:12:27"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.7302, "lr": 9.375000000000001e-06, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:14:02", "remaining_time": "2:11:58"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.7396, "lr": 9.6875e-06, "epoch": 0.2971246006389776, "percentage": 9.94, "elapsed_time": "0:14:30", "remaining_time": "2:11:30"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.7593, "lr": 1e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:14:55", "remaining_time": "2:10:34"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.7255, "lr": 9.999685283773504e-06, "epoch": 0.31629392971246006, "percentage": 10.58, "elapsed_time": "0:15:18", "remaining_time": "2:09:22"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.7172, "lr": 9.998741174712534e-06, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:15:44", "remaining_time": "2:08:43"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.7309, "lr": 9.997167791667668e-06, "epoch": 0.3354632587859425, "percentage": 11.22, "elapsed_time": "0:16:12", "remaining_time": "2:08:15"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.7316, "lr": 9.994965332706574e-06, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:16:35", "remaining_time": "2:07:10"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.7276, "lr": 9.992134075089085e-06, "epoch": 0.3546325878594249, "percentage": 11.86, "elapsed_time": "0:17:02", "remaining_time": "2:06:37"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.7029, "lr": 9.98867437523228e-06, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:17:33", "remaining_time": "2:06:33"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.7111, "lr": 9.984586668665641e-06, "epoch": 0.3738019169329074, "percentage": 12.5, "elapsed_time": "0:17:56", "remaining_time": "2:05:37"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.733, "lr": 9.979871469976197e-06, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:18:29", "remaining_time": "2:05:41"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.7054, "lr": 9.974529372743762e-06, "epoch": 0.3929712460063898, "percentage": 13.14, "elapsed_time": "0:18:58", "remaining_time": "2:05:23"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.6961, "lr": 9.968561049466214e-06, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:19:20", "remaining_time": "2:04:23"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.7093, "lr": 9.961967251474823e-06, "epoch": 0.41214057507987223, "percentage": 13.78, "elapsed_time": "0:19:47", "remaining_time": "2:03:49"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.6822, "lr": 9.954748808839675e-06, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:20:15", "remaining_time": "2:03:22"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.693, "lr": 9.946906630265184e-06, "epoch": 0.43130990415335463, "percentage": 14.42, "elapsed_time": "0:20:43", "remaining_time": "2:02:58"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.7289, "lr": 9.938441702975689e-06, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:21:12", "remaining_time": "2:02:37"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.6953, "lr": 9.92935509259118e-06, "epoch": 0.4504792332268371, "percentage": 15.06, "elapsed_time": "0:21:42", "remaining_time": "2:02:25"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.6735, "lr": 9.91964794299315e-06, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:22:17", "remaining_time": "2:02:35"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.6932, "lr": 9.909321476180594e-06, "epoch": 0.4696485623003195, "percentage": 15.71, "elapsed_time": "0:22:44", "remaining_time": "2:02:05"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.6902, "lr": 9.898376992116179e-06, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:23:11", "remaining_time": "2:01:29"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.6869, "lr": 9.886815868562596e-06, "epoch": 0.48881789137380194, "percentage": 16.35, "elapsed_time": "0:23:30", "remaining_time": "2:00:17"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.6825, "lr": 9.874639560909118e-06, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:24:02", "remaining_time": "2:00:13"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.6854, "lr": 9.861849601988384e-06, "epoch": 0.5079872204472844, "percentage": 16.99, "elapsed_time": "0:24:31", "remaining_time": "1:59:49"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.6904, "lr": 9.848447601883436e-06, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:24:55", "remaining_time": "1:59:07"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.684, "lr": 9.834435247725032e-06, "epoch": 0.5271565495207667, "percentage": 17.63, "elapsed_time": "0:25:25", "remaining_time": "1:58:48"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.6821, "lr": 9.819814303479268e-06, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:25:44", "remaining_time": "1:57:39"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.7041, "lr": 9.804586609725499e-06, "epoch": 0.5463258785942492, "percentage": 18.27, "elapsed_time": "0:26:11", "remaining_time": "1:57:10"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.6591, "lr": 9.788754083424654e-06, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:26:39", "remaining_time": "1:56:46"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.668, "lr": 9.772318717677905e-06, "epoch": 0.5654952076677316, "percentage": 18.91, "elapsed_time": "0:27:02", "remaining_time": "1:55:58"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.6889, "lr": 9.755282581475769e-06, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:27:29", "remaining_time": "1:55:29"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.6824, "lr": 9.737647819437645e-06, "epoch": 0.5846645367412141, "percentage": 19.55, "elapsed_time": "0:28:00", "remaining_time": "1:55:16"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.6652, "lr": 9.719416651541839e-06, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:28:27", "remaining_time": "1:54:44"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.6681, "lr": 9.700591372846096e-06, "epoch": 0.6038338658146964, "percentage": 20.19, "elapsed_time": "0:28:53", "remaining_time": "1:54:09"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.6741, "lr": 9.681174353198687e-06, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:29:22", "remaining_time": "1:53:50"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.6763, "lr": 9.661168036940071e-06, "epoch": 0.6230031948881789, "percentage": 20.83, "elapsed_time": "0:29:48", "remaining_time": "1:53:15"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.6863, "lr": 9.640574942595195e-06, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:30:17", "remaining_time": "1:52:54"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.6772, "lr": 9.619397662556434e-06, "epoch": 0.6421725239616614, "percentage": 21.47, "elapsed_time": "0:30:41", "remaining_time": "1:52:13"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.6726, "lr": 9.597638862757255e-06, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:31:09", "remaining_time": "1:51:48"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.6603, "lr": 9.5753012823366e-06, "epoch": 0.6613418530351438, "percentage": 22.12, "elapsed_time": "0:31:29", "remaining_time": "1:50:54"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.6855, "lr": 9.552387733294081e-06, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:31:56", "remaining_time": "1:50:25"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.6717, "lr": 9.528901100135971e-06, "epoch": 0.6805111821086262, "percentage": 22.76, "elapsed_time": "0:32:27", "remaining_time": "1:50:08"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.6842, "lr": 9.504844339512096e-06, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:32:50", "remaining_time": "1:49:29"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.666, "lr": 9.480220479843627e-06, "epoch": 0.6996805111821086, "percentage": 23.4, "elapsed_time": "0:33:18", "remaining_time": "1:49:04"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.6856, "lr": 9.45503262094184e-06, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:33:43", "remaining_time": "1:48:27"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.6581, "lr": 9.4292839336179e-06, "epoch": 0.7188498402555911, "percentage": 24.04, "elapsed_time": "0:34:12", "remaining_time": "1:48:05"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.6734, "lr": 9.40297765928369e-06, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:34:32", "remaining_time": "1:47:15"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.6694, "lr": 9.376117109543769e-06, "epoch": 0.7380191693290735, "percentage": 24.68, "elapsed_time": "0:34:53", "remaining_time": "1:46:30"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.6755, "lr": 9.348705665778479e-06, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:35:17", "remaining_time": "1:45:51"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.6469, "lr": 9.320746778718274e-06, "epoch": 0.7571884984025559, "percentage": 25.32, "elapsed_time": "0:35:35", "remaining_time": "1:44:58"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.6723, "lr": 9.292243968009332e-06, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:36:03", "remaining_time": "1:44:33"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.6757, "lr": 9.263200821770462e-06, "epoch": 0.7763578274760383, "percentage": 25.96, "elapsed_time": "0:36:32", "remaining_time": "1:44:13"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.6727, "lr": 9.233620996141421e-06, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:37:02", "remaining_time": "1:43:54"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.6635, "lr": 9.203508214822652e-06, "epoch": 0.7955271565495208, "percentage": 26.6, "elapsed_time": "0:37:33", "remaining_time": "1:43:36"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.6389, "lr": 9.172866268606514e-06, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:38:00", "remaining_time": "1:43:09"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.6848, "lr": 9.141699014900084e-06, "epoch": 0.8146964856230032, "percentage": 27.24, "elapsed_time": "0:38:22", "remaining_time": "1:42:28"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.6687, "lr": 9.110010377239552e-06, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:38:54", "remaining_time": "1:42:15"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.6772, "lr": 9.077804344796302e-06, "epoch": 0.8338658146964856, "percentage": 27.88, "elapsed_time": "0:39:20", "remaining_time": "1:41:44"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.649, "lr": 9.045084971874738e-06, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:39:45", "remaining_time": "1:41:12"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.6667, "lr": 9.011856377401891e-06, "epoch": 0.853035143769968, "percentage": 28.53, "elapsed_time": "0:40:12", "remaining_time": "1:40:44"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.6846, "lr": 8.978122744408905e-06, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:40:35", "remaining_time": "1:40:08"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.6694, "lr": 8.943888319504456e-06, "epoch": 0.8722044728434505, "percentage": 29.17, "elapsed_time": "0:41:03", "remaining_time": "1:39:43"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.6731, "lr": 8.90915741234015e-06, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:41:26", "remaining_time": "1:39:06"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.6445, "lr": 8.873934395068006e-06, "epoch": 0.8913738019169329, "percentage": 29.81, "elapsed_time": "0:41:56", "remaining_time": "1:38:46"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.6833, "lr": 8.838223701790057e-06, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:42:27", "remaining_time": "1:38:27"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.6291, "lr": 8.802029828000157e-06, "epoch": 0.9105431309904153, "percentage": 30.45, "elapsed_time": "0:42:53", "remaining_time": "1:37:57"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.6729, "lr": 8.765357330018056e-06, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:43:19", "remaining_time": "1:37:28"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.6617, "lr": 8.728210824415829e-06, "epoch": 0.9297124600638977, "percentage": 31.09, "elapsed_time": "0:43:43", "remaining_time": "1:36:54"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.6557, "lr": 8.690594987436705e-06, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:44:08", "remaining_time": "1:36:23"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.6525, "lr": 8.652514554406388e-06, "epoch": 0.9488817891373802, "percentage": 31.73, "elapsed_time": "0:44:40", "remaining_time": "1:36:06"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.6618, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:45:05", "remaining_time": "1:35:36"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.6403, "lr": 8.574979133323378e-06, "epoch": 0.9680511182108626, "percentage": 32.37, "elapsed_time": "0:45:32", "remaining_time": "1:35:09"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.6523, "lr": 8.535533905932739e-06, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:46:02", "remaining_time": "1:34:46"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.6454, "lr": 8.495643602586287e-06, "epoch": 0.987220447284345, "percentage": 33.01, "elapsed_time": "0:46:29", "remaining_time": "1:34:19"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.6529, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:47:00", "remaining_time": "1:34:01"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.6219, "lr": 8.414547910024035e-06, "epoch": 1.0063897763578276, "percentage": 33.65, "elapsed_time": "0:47:56", "remaining_time": "1:34:30"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.5887, "lr": 8.373352729660373e-06, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:48:18", "remaining_time": "1:33:53"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.5787, "lr": 8.331732889760021e-06, "epoch": 1.0255591054313098, "percentage": 34.29, "elapsed_time": "0:48:43", "remaining_time": "1:33:21"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.5986, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:49:10", "remaining_time": "1:32:52"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.5626, "lr": 8.247240241650918e-06, "epoch": 1.0447284345047922, "percentage": 34.94, "elapsed_time": "0:49:34", "remaining_time": "1:32:20"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.5935, "lr": 8.204378069925121e-06, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:49:58", "remaining_time": "1:31:46"}
+{"current_steps": 111, "total_steps": 312, "loss": 0.5891, "lr": 8.16111251028955e-06, "epoch": 1.0638977635782747, "percentage": 35.58, "elapsed_time": "0:50:26", "remaining_time": "1:31:20"}
+{"current_steps": 112, "total_steps": 312, "loss": 0.5729, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:50:52", "remaining_time": "1:30:50"}
+{"current_steps": 113, "total_steps": 312, "loss": 0.5781, "lr": 8.073393063582386e-06, "epoch": 1.0830670926517572, "percentage": 36.22, "elapsed_time": "0:51:21", "remaining_time": "1:30:26"}
+{"current_steps": 114, "total_steps": 312, "loss": 0.5843, "lr": 8.0289502192041e-06, "epoch": 1.0926517571884984, "percentage": 36.54, "elapsed_time": "0:51:51", "remaining_time": "1:30:04"}
+{"current_steps": 115, "total_steps": 312, "loss": 0.5648, "lr": 7.984126070912519e-06, "epoch": 1.1022364217252396, "percentage": 36.86, "elapsed_time": "0:52:13", "remaining_time": "1:29:27"}
+{"current_steps": 116, "total_steps": 312, "loss": 0.5617, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:52:36", "remaining_time": "1:28:53"}
+{"current_steps": 117, "total_steps": 312, "loss": 0.5983, "lr": 7.89335648089903e-06, "epoch": 1.121405750798722, "percentage": 37.5, "elapsed_time": "0:53:04", "remaining_time": "1:28:28"}
+{"current_steps": 118, "total_steps": 312, "loss": 0.6143, "lr": 7.84742246584226e-06, "epoch": 1.1309904153354633, "percentage": 37.82, "elapsed_time": "0:53:30", "remaining_time": "1:27:58"}
+{"current_steps": 119, "total_steps": 312, "loss": 0.5664, "lr": 7.801129998764014e-06, "epoch": 1.1405750798722045, "percentage": 38.14, "elapsed_time": "0:54:01", "remaining_time": "1:27:36"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.5801, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:54:26", "remaining_time": "1:27:05"}
+{"current_steps": 121, "total_steps": 312, "loss": 0.5573, "lr": 7.70749306331863e-06, "epoch": 1.159744408945687, "percentage": 38.78, "elapsed_time": "0:54:51", "remaining_time": "1:26:36"}
+{"current_steps": 122, "total_steps": 312, "loss": 0.575, "lr": 7.660160382576683e-06, "epoch": 1.1693290734824282, "percentage": 39.1, "elapsed_time": "0:55:25", "remaining_time": "1:26:19"}
+{"current_steps": 123, "total_steps": 312, "loss": 0.5878, "lr": 7.612492823579744e-06, "epoch": 1.1789137380191694, "percentage": 39.42, "elapsed_time": "0:55:55", "remaining_time": "1:25:55"}
+{"current_steps": 124, "total_steps": 312, "loss": 0.5486, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:56:19", "remaining_time": "1:25:23"}
+{"current_steps": 125, "total_steps": 312, "loss": 0.5884, "lr": 7.516177115029002e-06, "epoch": 1.1980830670926517, "percentage": 40.06, "elapsed_time": "0:56:51", "remaining_time": "1:25:04"}
+{"current_steps": 126, "total_steps": 312, "loss": 0.5565, "lr": 7.467541090321735e-06, "epoch": 1.207667731629393, "percentage": 40.38, "elapsed_time": "0:57:15", "remaining_time": "1:24:31"}
+{"current_steps": 127, "total_steps": 312, "loss": 0.5943, "lr": 7.4185944355261996e-06, "epoch": 1.2172523961661341, "percentage": 40.71, "elapsed_time": "0:57:41", "remaining_time": "1:24:02"}
+{"current_steps": 128, "total_steps": 312, "loss": 0.5965, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:58:08", "remaining_time": "1:23:34"}
+{"current_steps": 129, "total_steps": 312, "loss": 0.5895, "lr": 7.319793920889171e-06, "epoch": 1.2364217252396166, "percentage": 41.35, "elapsed_time": "0:58:40", "remaining_time": "1:23:14"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.5785, "lr": 7.269952498697734e-06, "epoch": 1.2460063897763578, "percentage": 41.67, "elapsed_time": "0:59:07", "remaining_time": "1:22:46"}
+{"current_steps": 131, "total_steps": 312, "loss": 0.5873, "lr": 7.219825320152411e-06, "epoch": 1.255591054313099, "percentage": 41.99, "elapsed_time": "0:59:34", "remaining_time": "1:22:18"}
+{"current_steps": 132, "total_steps": 312, "loss": 0.5811, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "1:00:02", "remaining_time": "1:21:53"}
+{"current_steps": 133, "total_steps": 312, "loss": 0.5854, "lr": 7.118738970516944e-06, "epoch": 1.2747603833865815, "percentage": 42.63, "elapsed_time": "1:00:31", "remaining_time": "1:21:27"}
+{"current_steps": 134, "total_steps": 312, "loss": 0.5859, "lr": 7.067792524832604e-06, "epoch": 1.2843450479233227, "percentage": 42.95, "elapsed_time": "1:00:57", "remaining_time": "1:20:58"}
+{"current_steps": 135, "total_steps": 312, "loss": 0.5812, "lr": 7.016585772004026e-06, "epoch": 1.293929712460064, "percentage": 43.27, "elapsed_time": "1:01:21", "remaining_time": "1:20:26"}
+{"current_steps": 136, "total_steps": 312, "loss": 0.5712, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "1:01:49", "remaining_time": "1:20:00"}
+{"current_steps": 137, "total_steps": 312, "loss": 0.5692, "lr": 6.913417161825449e-06, "epoch": 1.3130990415335464, "percentage": 43.91, "elapsed_time": "1:02:16", "remaining_time": "1:19:33"}
+{"current_steps": 138, "total_steps": 312, "loss": 0.5681, "lr": 6.8614682920097265e-06, "epoch": 1.3226837060702876, "percentage": 44.23, "elapsed_time": "1:02:45", "remaining_time": "1:19:08"}
+{"current_steps": 139, "total_steps": 312, "loss": 0.576, "lr": 6.809285088483361e-06, "epoch": 1.3322683706070286, "percentage": 44.55, "elapsed_time": "1:03:12", "remaining_time": "1:18:40"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.5779, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "1:03:35", "remaining_time": "1:18:07"}
+{"current_steps": 141, "total_steps": 312, "loss": 0.5499, "lr": 6.704241985612625e-06, "epoch": 1.351437699680511, "percentage": 45.19, "elapsed_time": "1:04:04", "remaining_time": "1:17:42"}
+{"current_steps": 142, "total_steps": 312, "loss": 0.5603, "lr": 6.651395309775837e-06, "epoch": 1.3610223642172525, "percentage": 45.51, "elapsed_time": "1:04:23", "remaining_time": "1:17:05"}
+{"current_steps": 143, "total_steps": 312, "loss": 0.5949, "lr": 6.598340745578908e-06, "epoch": 1.3706070287539935, "percentage": 45.83, "elapsed_time": "1:04:52", "remaining_time": "1:16:40"}
+{"current_steps": 144, "total_steps": 312, "loss": 0.5864, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "1:05:19", "remaining_time": "1:16:12"}
+{"current_steps": 145, "total_steps": 312, "loss": 0.5977, "lr": 6.491634692845781e-06, "epoch": 1.389776357827476, "percentage": 46.47, "elapsed_time": "1:05:40", "remaining_time": "1:15:38"}
+{"current_steps": 146, "total_steps": 312, "loss": 0.5824, "lr": 6.437996637160086e-06, "epoch": 1.3993610223642172, "percentage": 46.79, "elapsed_time": "1:06:11", "remaining_time": "1:15:15"}
+{"current_steps": 147, "total_steps": 312, "loss": 0.5648, "lr": 6.384177557124247e-06, "epoch": 1.4089456869009584, "percentage": 47.12, "elapsed_time": "1:06:39", "remaining_time": "1:14:48"}
+{"current_steps": 148, "total_steps": 312, "loss": 0.5641, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "1:07:00", "remaining_time": "1:14:15"}
+{"current_steps": 149, "total_steps": 312, "loss": 0.5642, "lr": 6.276023446318214e-06, "epoch": 1.428115015974441, "percentage": 47.76, "elapsed_time": "1:07:29", "remaining_time": "1:13:49"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.5672, "lr": 6.2217020306894705e-06, "epoch": 1.4376996805111821, "percentage": 48.08, "elapsed_time": "1:07:56", "remaining_time": "1:13:22"}
+{"current_steps": 151, "total_steps": 312, "loss": 0.5738, "lr": 6.1672268192795285e-06, "epoch": 1.4472843450479234, "percentage": 48.4, "elapsed_time": "1:08:15", "remaining_time": "1:12:46"}
+{"current_steps": 152, "total_steps": 312, "loss": 0.574, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:08:44", "remaining_time": "1:12:21"}
+{"current_steps": 153, "total_steps": 312, "loss": 0.5747, "lr": 6.057842458386315e-06, "epoch": 1.4664536741214058, "percentage": 49.04, "elapsed_time": "1:09:14", "remaining_time": "1:11:57"}
+{"current_steps": 154, "total_steps": 312, "loss": 0.5653, "lr": 6.002947078916365e-06, "epoch": 1.476038338658147, "percentage": 49.36, "elapsed_time": "1:09:38", "remaining_time": "1:11:26"}
+{"current_steps": 155, "total_steps": 312, "loss": 0.5493, "lr": 5.947925441958393e-06, "epoch": 1.4856230031948883, "percentage": 49.68, "elapsed_time": "1:10:05", "remaining_time": "1:11:00"}
+{"current_steps": 156, "total_steps": 312, "loss": 0.5723, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:10:33", "remaining_time": "1:10:33"}
+{"current_steps": 157, "total_steps": 312, "loss": 0.5914, "lr": 5.837531116523683e-06, "epoch": 1.5047923322683707, "percentage": 50.32, "elapsed_time": "1:10:59", "remaining_time": "1:10:04"}
+{"current_steps": 158, "total_steps": 312, "loss": 0.5577, "lr": 5.782172325201155e-06, "epoch": 1.5143769968051117, "percentage": 50.64, "elapsed_time": "1:11:22", "remaining_time": "1:09:33"}
+{"current_steps": 159, "total_steps": 312, "loss": 0.5672, "lr": 5.726715068949564e-06, "epoch": 1.5239616613418532, "percentage": 50.96, "elapsed_time": "1:11:49", "remaining_time": "1:09:06"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.5853, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:12:16", "remaining_time": "1:08:39"}
+{"current_steps": 161, "total_steps": 312, "loss": 0.5599, "lr": 5.615533098453215e-06, "epoch": 1.5431309904153354, "percentage": 51.6, "elapsed_time": "1:12:47", "remaining_time": "1:08:16"}
+{"current_steps": 162, "total_steps": 312, "loss": 0.5578, "lr": 5.559822380516539e-06, "epoch": 1.5527156549520766, "percentage": 51.92, "elapsed_time": "1:13:14", "remaining_time": "1:07:48"}
+{"current_steps": 163, "total_steps": 312, "loss": 0.5634, "lr": 5.504041188505022e-06, "epoch": 1.5623003194888179, "percentage": 52.24, "elapsed_time": "1:13:41", "remaining_time": "1:07:21"}
+{"current_steps": 164, "total_steps": 312, "loss": 0.5677, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:14:05", "remaining_time": "1:06:51"}
+{"current_steps": 165, "total_steps": 312, "loss": 0.5647, "lr": 5.392295478639226e-06, "epoch": 1.5814696485623003, "percentage": 52.88, "elapsed_time": "1:14:31", "remaining_time": "1:06:23"}
+{"current_steps": 166, "total_steps": 312, "loss": 0.5792, "lr": 5.336345028060199e-06, "epoch": 1.5910543130990416, "percentage": 53.21, "elapsed_time": "1:15:02", "remaining_time": "1:06:00"}
+{"current_steps": 167, "total_steps": 312, "loss": 0.5477, "lr": 5.2803522361859596e-06, "epoch": 1.6006389776357828, "percentage": 53.53, "elapsed_time": "1:15:29", "remaining_time": "1:05:33"}
+{"current_steps": 168, "total_steps": 312, "loss": 0.583, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:15:57", "remaining_time": "1:05:06"}
+{"current_steps": 169, "total_steps": 312, "loss": 0.5439, "lr": 5.168267827938971e-06, "epoch": 1.619808306709265, "percentage": 54.17, "elapsed_time": "1:16:20", "remaining_time": "1:04:35"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.5671, "lr": 5.112190321479026e-06, "epoch": 1.6293929712460065, "percentage": 54.49, "elapsed_time": "1:16:52", "remaining_time": "1:04:13"}
+{"current_steps": 171, "total_steps": 312, "loss": 0.5886, "lr": 5.05609869177323e-06, "epoch": 1.6389776357827475, "percentage": 54.81, "elapsed_time": "1:17:15", "remaining_time": "1:03:42"}
+{"current_steps": 172, "total_steps": 312, "loss": 0.5653, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:17:40", "remaining_time": "1:03:13"}
+{"current_steps": 173, "total_steps": 312, "loss": 0.5602, "lr": 4.943901308226771e-06, "epoch": 1.65814696485623, "percentage": 55.45, "elapsed_time": "1:18:07", "remaining_time": "1:02:46"}
+{"current_steps": 174, "total_steps": 312, "loss": 0.5801, "lr": 4.887809678520976e-06, "epoch": 1.6677316293929714, "percentage": 55.77, "elapsed_time": "1:18:29", "remaining_time": "1:02:15"}
+{"current_steps": 175, "total_steps": 312, "loss": 0.5842, "lr": 4.831732172061032e-06, "epoch": 1.6773162939297124, "percentage": 56.09, "elapsed_time": "1:18:58", "remaining_time": "1:01:49"}
+{"current_steps": 176, "total_steps": 312, "loss": 0.5595, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:19:30", "remaining_time": "1:01:25"}
+{"current_steps": 177, "total_steps": 312, "loss": 0.5727, "lr": 4.719647763814041e-06, "epoch": 1.6964856230031948, "percentage": 56.73, "elapsed_time": "1:20:00", "remaining_time": "1:01:01"}
+{"current_steps": 178, "total_steps": 312, "loss": 0.5575, "lr": 4.663654971939802e-06, "epoch": 1.706070287539936, "percentage": 57.05, "elapsed_time": "1:20:25", "remaining_time": "1:00:32"}
+{"current_steps": 179, "total_steps": 312, "loss": 0.5706, "lr": 4.6077045213607765e-06, "epoch": 1.7156549520766773, "percentage": 57.37, "elapsed_time": "1:20:57", "remaining_time": "1:00:09"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.6007, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:21:24", "remaining_time": "0:59:42"}
+{"current_steps": 181, "total_steps": 312, "loss": 0.5686, "lr": 4.4959588114949785e-06, "epoch": 1.7348242811501597, "percentage": 58.01, "elapsed_time": "1:21:53", "remaining_time": "0:59:15"}
+{"current_steps": 182, "total_steps": 312, "loss": 0.5829, "lr": 4.4401776194834615e-06, "epoch": 1.744408945686901, "percentage": 58.33, "elapsed_time": "1:22:20", "remaining_time": "0:58:49"}
+{"current_steps": 183, "total_steps": 312, "loss": 0.5745, "lr": 4.384466901546786e-06, "epoch": 1.7539936102236422, "percentage": 58.65, "elapsed_time": "1:22:50", "remaining_time": "0:58:23"}
+{"current_steps": 184, "total_steps": 312, "loss": 0.5708, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:23:17", "remaining_time": "0:57:56"}
+{"current_steps": 185, "total_steps": 312, "loss": 0.5532, "lr": 4.273284931050438e-06, "epoch": 1.7731629392971247, "percentage": 59.29, "elapsed_time": "1:23:35", "remaining_time": "0:57:23"}
+{"current_steps": 186, "total_steps": 312, "loss": 0.5676, "lr": 4.217827674798845e-06, "epoch": 1.7827476038338657, "percentage": 59.62, "elapsed_time": "1:23:58", "remaining_time": "0:56:53"}
+{"current_steps": 187, "total_steps": 312, "loss": 0.5656, "lr": 4.162468883476319e-06, "epoch": 1.792332268370607, "percentage": 59.94, "elapsed_time": "1:24:25", "remaining_time": "0:56:25"}
+{"current_steps": 188, "total_steps": 312, "loss": 0.5734, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:24:56", "remaining_time": "0:56:01"}
+{"current_steps": 189, "total_steps": 312, "loss": 0.5891, "lr": 4.052074558041608e-06, "epoch": 1.8115015974440896, "percentage": 60.58, "elapsed_time": "1:25:23", "remaining_time": "0:55:34"}
+{"current_steps": 190, "total_steps": 312, "loss": 0.5838, "lr": 3.997052921083637e-06, "epoch": 1.8210862619808306, "percentage": 60.9, "elapsed_time": "1:25:49", "remaining_time": "0:55:06"}
+{"current_steps": 191, "total_steps": 312, "loss": 0.5682, "lr": 3.9421575416136866e-06, "epoch": 1.830670926517572, "percentage": 61.22, "elapsed_time": "1:26:18", "remaining_time": "0:54:40"}
+{"current_steps": 192, "total_steps": 312, "loss": 0.5774, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:26:43", "remaining_time": "0:54:12"}
+{"current_steps": 193, "total_steps": 312, "loss": 0.5755, "lr": 3.832773180720475e-06, "epoch": 1.8498402555910545, "percentage": 61.86, "elapsed_time": "1:27:06", "remaining_time": "0:53:42"}
+{"current_steps": 194, "total_steps": 312, "loss": 0.5894, "lr": 3.778297969310529e-06, "epoch": 1.8594249201277955, "percentage": 62.18, "elapsed_time": "1:27:31", "remaining_time": "0:53:14"}
+{"current_steps": 195, "total_steps": 312, "loss": 0.5881, "lr": 3.723976553681787e-06, "epoch": 1.8690095846645367, "percentage": 62.5, "elapsed_time": "1:27:58", "remaining_time": "0:52:46"}
+{"current_steps": 196, "total_steps": 312, "loss": 0.5699, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:28:31", "remaining_time": "0:52:23"}
+{"current_steps": 197, "total_steps": 312, "loss": 0.5747, "lr": 3.6158224428757538e-06, "epoch": 1.8881789137380192, "percentage": 63.14, "elapsed_time": "1:29:02", "remaining_time": "0:51:58"}
+{"current_steps": 198, "total_steps": 312, "loss": 0.5596, "lr": 3.562003362839914e-06, "epoch": 1.8977635782747604, "percentage": 63.46, "elapsed_time": "1:29:32", "remaining_time": "0:51:33"}
+{"current_steps": 199, "total_steps": 312, "loss": 0.5709, "lr": 3.50836530715422e-06, "epoch": 1.9073482428115016, "percentage": 63.78, "elapsed_time": "1:29:59", "remaining_time": "0:51:06"}
+{"current_steps": 200, "total_steps": 312, "loss": 0.5771, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:30:24", "remaining_time": "0:50:37"}
+{"current_steps": 201, "total_steps": 312, "loss": 0.5763, "lr": 3.4016592544210937e-06, "epoch": 1.926517571884984, "percentage": 64.42, "elapsed_time": "1:30:53", "remaining_time": "0:50:11"}
+{"current_steps": 202, "total_steps": 312, "loss": 0.5495, "lr": 3.3486046902241663e-06, "epoch": 1.9361022364217253, "percentage": 64.74, "elapsed_time": "1:31:25", "remaining_time": "0:49:46"}
+{"current_steps": 203, "total_steps": 312, "loss": 0.5836, "lr": 3.295758014387375e-06, "epoch": 1.9456869009584663, "percentage": 65.06, "elapsed_time": "1:31:51", "remaining_time": "0:49:19"}
+{"current_steps": 204, "total_steps": 312, "loss": 0.5865, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:32:24", "remaining_time": "0:48:55"}
+{"current_steps": 205, "total_steps": 312, "loss": 0.5638, "lr": 3.1907149115166403e-06, "epoch": 1.9648562300319488, "percentage": 65.71, "elapsed_time": "1:32:53", "remaining_time": "0:48:29"}
+{"current_steps": 206, "total_steps": 312, "loss": 0.5784, "lr": 3.1385317079902743e-06, "epoch": 1.9744408945686902, "percentage": 66.03, "elapsed_time": "1:33:19", "remaining_time": "0:48:01"}
+{"current_steps": 207, "total_steps": 312, "loss": 0.572, "lr": 3.0865828381745515e-06, "epoch": 1.9840255591054312, "percentage": 66.35, "elapsed_time": "1:33:46", "remaining_time": "0:47:34"}
+{"current_steps": 208, "total_steps": 312, "loss": 0.5578, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:34:15", "remaining_time": "0:47:07"}
+{"current_steps": 209, "total_steps": 312, "loss": 0.5419, "lr": 2.9834142279959754e-06, "epoch": 2.0031948881789137, "percentage": 66.99, "elapsed_time": "1:35:18", "remaining_time": "0:46:57"}
+{"current_steps": 210, "total_steps": 312, "loss": 0.5237, "lr": 2.932207475167398e-06, "epoch": 2.012779552715655, "percentage": 67.31, "elapsed_time": "1:35:51", "remaining_time": "0:46:33"}
+{"current_steps": 211, "total_steps": 312, "loss": 0.523, "lr": 2.8812610294830568e-06, "epoch": 2.022364217252396, "percentage": 67.63, "elapsed_time": "1:36:23", "remaining_time": "0:46:08"}
+{"current_steps": 212, "total_steps": 312, "loss": 0.5488, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:36:50", "remaining_time": "0:45:40"}
+{"current_steps": 213, "total_steps": 312, "loss": 0.5362, "lr": 2.7801746798475905e-06, "epoch": 2.0415335463258786, "percentage": 68.27, "elapsed_time": "1:37:13", "remaining_time": "0:45:11"}
+{"current_steps": 214, "total_steps": 312, "loss": 0.5117, "lr": 2.7300475013022666e-06, "epoch": 2.0511182108626196, "percentage": 68.59, "elapsed_time": "1:37:43", "remaining_time": "0:44:45"}
+{"current_steps": 215, "total_steps": 312, "loss": 0.4838, "lr": 2.6802060791108304e-06, "epoch": 2.060702875399361, "percentage": 68.91, "elapsed_time": "1:38:13", "remaining_time": "0:44:18"}
+{"current_steps": 216, "total_steps": 312, "loss": 0.5046, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "1:38:39", "remaining_time": "0:43:51"}
+{"current_steps": 217, "total_steps": 312, "loss": 0.5185, "lr": 2.5814055644738013e-06, "epoch": 2.0798722044728435, "percentage": 69.55, "elapsed_time": "1:39:08", "remaining_time": "0:43:24"}
+{"current_steps": 218, "total_steps": 312, "loss": 0.496, "lr": 2.532458909678266e-06, "epoch": 2.0894568690095845, "percentage": 69.87, "elapsed_time": "1:39:32", "remaining_time": "0:42:55"}
+{"current_steps": 219, "total_steps": 312, "loss": 0.5253, "lr": 2.483822884971e-06, "epoch": 2.099041533546326, "percentage": 70.19, "elapsed_time": "1:39:59", "remaining_time": "0:42:27"}
+{"current_steps": 220, "total_steps": 312, "loss": 0.5122, "lr": 2.43550361297047e-06, "epoch": 2.108626198083067, "percentage": 70.51, "elapsed_time": "1:40:22", "remaining_time": "0:41:58"}
+{"current_steps": 221, "total_steps": 312, "loss": 0.4836, "lr": 2.387507176420256e-06, "epoch": 2.1182108626198084, "percentage": 70.83, "elapsed_time": "1:40:52", "remaining_time": "0:41:32"}
+{"current_steps": 222, "total_steps": 312, "loss": 0.5254, "lr": 2.339839617423318e-06, "epoch": 2.1277955271565494, "percentage": 71.15, "elapsed_time": "1:41:23", "remaining_time": "0:41:06"}
+{"current_steps": 223, "total_steps": 312, "loss": 0.5279, "lr": 2.2925069366813718e-06, "epoch": 2.137380191693291, "percentage": 71.47, "elapsed_time": "1:41:53", "remaining_time": "0:40:39"}
+{"current_steps": 224, "total_steps": 312, "loss": 0.4915, "lr": 2.245515092739488e-06, "epoch": 2.146964856230032, "percentage": 71.79, "elapsed_time": "1:42:18", "remaining_time": "0:40:11"}
+{"current_steps": 225, "total_steps": 312, "loss": 0.5057, "lr": 2.1988700012359865e-06, "epoch": 2.1565495207667733, "percentage": 72.12, "elapsed_time": "1:42:48", "remaining_time": "0:39:45"}
+{"current_steps": 226, "total_steps": 312, "loss": 0.4826, "lr": 2.1525775341577404e-06, "epoch": 2.1661341853035143, "percentage": 72.44, "elapsed_time": "1:43:18", "remaining_time": "0:39:18"}
+{"current_steps": 227, "total_steps": 312, "loss": 0.5041, "lr": 2.1066435191009717e-06, "epoch": 2.1757188498402558, "percentage": 72.76, "elapsed_time": "1:43:44", "remaining_time": "0:38:50"}
+{"current_steps": 228, "total_steps": 312, "loss": 0.504, "lr": 2.061073738537635e-06, "epoch": 2.1853035143769968, "percentage": 73.08, "elapsed_time": "1:44:14", "remaining_time": "0:38:24"}
+{"current_steps": 229, "total_steps": 312, "loss": 0.4867, "lr": 2.0158739290874822e-06, "epoch": 2.194888178913738, "percentage": 73.4, "elapsed_time": "1:44:40", "remaining_time": "0:37:56"}
+{"current_steps": 230, "total_steps": 312, "loss": 0.5058, "lr": 1.971049780795901e-06, "epoch": 2.2044728434504792, "percentage": 73.72, "elapsed_time": "1:45:05", "remaining_time": "0:37:28"}
+{"current_steps": 231, "total_steps": 312, "loss": 0.491, "lr": 1.9266069364176144e-06, "epoch": 2.2140575079872207, "percentage": 74.04, "elapsed_time": "1:45:26", "remaining_time": "0:36:58"}
+{"current_steps": 232, "total_steps": 312, "loss": 0.4932, "lr": 1.8825509907063328e-06, "epoch": 2.2236421725239617, "percentage": 74.36, "elapsed_time": "1:45:51", "remaining_time": "0:36:30"}
+{"current_steps": 233, "total_steps": 312, "loss": 0.5167, "lr": 1.838887489710452e-06, "epoch": 2.2332268370607027, "percentage": 74.68, "elapsed_time": "1:46:25", "remaining_time": "0:36:04"}
+{"current_steps": 234, "total_steps": 312, "loss": 0.5106, "lr": 1.7956219300748796e-06, "epoch": 2.242811501597444, "percentage": 75.0, "elapsed_time": "1:46:53", "remaining_time": "0:35:37"}
+{"current_steps": 235, "total_steps": 312, "loss": 0.4985, "lr": 1.7527597583490825e-06, "epoch": 2.252396166134185, "percentage": 75.32, "elapsed_time": "1:47:15", "remaining_time": "0:35:08"}
+{"current_steps": 236, "total_steps": 312, "loss": 0.4861, "lr": 1.7103063703014372e-06, "epoch": 2.2619808306709266, "percentage": 75.64, "elapsed_time": "1:47:38", "remaining_time": "0:34:39"}
+{"current_steps": 237, "total_steps": 312, "loss": 0.5204, "lr": 1.6682671102399806e-06, "epoch": 2.2715654952076676, "percentage": 75.96, "elapsed_time": "1:48:04", "remaining_time": "0:34:12"}
+{"current_steps": 238, "total_steps": 312, "loss": 0.514, "lr": 1.6266472703396286e-06, "epoch": 2.281150159744409, "percentage": 76.28, "elapsed_time": "1:48:31", "remaining_time": "0:33:44"}
+{"current_steps": 239, "total_steps": 312, "loss": 0.5042, "lr": 1.5854520899759656e-06, "epoch": 2.29073482428115, "percentage": 76.6, "elapsed_time": "1:49:00", "remaining_time": "0:33:17"}
+{"current_steps": 240, "total_steps": 312, "loss": 0.5044, "lr": 1.544686755065677e-06, "epoch": 2.3003194888178915, "percentage": 76.92, "elapsed_time": "1:49:25", "remaining_time": "0:32:49"}
+{"current_steps": 241, "total_steps": 312, "loss": 0.5072, "lr": 1.5043563974137132e-06, "epoch": 2.3099041533546325, "percentage": 77.24, "elapsed_time": "1:49:54", "remaining_time": "0:32:22"}
+{"current_steps": 242, "total_steps": 312, "loss": 0.5302, "lr": 1.4644660940672628e-06, "epoch": 2.319488817891374, "percentage": 77.56, "elapsed_time": "1:50:25", "remaining_time": "0:31:56"}
+{"current_steps": 243, "total_steps": 312, "loss": 0.5042, "lr": 1.4250208666766235e-06, "epoch": 2.329073482428115, "percentage": 77.88, "elapsed_time": "1:50:57", "remaining_time": "0:31:30"}
+{"current_steps": 244, "total_steps": 312, "loss": 0.5111, "lr": 1.3860256808630429e-06, "epoch": 2.3386581469648564, "percentage": 78.21, "elapsed_time": "1:51:26", "remaining_time": "0:31:03"}
+{"current_steps": 245, "total_steps": 312, "loss": 0.515, "lr": 1.3474854455936126e-06, "epoch": 2.3482428115015974, "percentage": 78.53, "elapsed_time": "1:51:53", "remaining_time": "0:30:35"}
+{"current_steps": 246, "total_steps": 312, "loss": 0.5114, "lr": 1.3094050125632973e-06, "epoch": 2.357827476038339, "percentage": 78.85, "elapsed_time": "1:52:16", "remaining_time": "0:30:07"}
+{"current_steps": 247, "total_steps": 312, "loss": 0.4797, "lr": 1.2717891755841722e-06, "epoch": 2.36741214057508, "percentage": 79.17, "elapsed_time": "1:52:47", "remaining_time": "0:29:40"}
+{"current_steps": 248, "total_steps": 312, "loss": 0.4941, "lr": 1.234642669981946e-06, "epoch": 2.376996805111821, "percentage": 79.49, "elapsed_time": "1:53:15", "remaining_time": "0:29:13"}
+{"current_steps": 249, "total_steps": 312, "loss": 0.5222, "lr": 1.1979701719998454e-06, "epoch": 2.3865814696485623, "percentage": 79.81, "elapsed_time": "1:53:43", "remaining_time": "0:28:46"}
+{"current_steps": 250, "total_steps": 312, "loss": 0.518, "lr": 1.1617762982099446e-06, "epoch": 2.3961661341853033, "percentage": 80.13, "elapsed_time": "1:54:05", "remaining_time": "0:28:17"}
+{"current_steps": 251, "total_steps": 312, "loss": 0.4984, "lr": 1.1260656049319957e-06, "epoch": 2.405750798722045, "percentage": 80.45, "elapsed_time": "1:54:26", "remaining_time": "0:27:48"}
+{"current_steps": 252, "total_steps": 312, "loss": 0.5229, "lr": 1.0908425876598512e-06, "epoch": 2.415335463258786, "percentage": 80.77, "elapsed_time": "1:54:47", "remaining_time": "0:27:19"}
+{"current_steps": 253, "total_steps": 312, "loss": 0.5146, "lr": 1.0561116804955451e-06, "epoch": 2.4249201277955272, "percentage": 81.09, "elapsed_time": "1:55:10", "remaining_time": "0:26:51"}
+{"current_steps": 254, "total_steps": 312, "loss": 0.5131, "lr": 1.0218772555910955e-06, "epoch": 2.4345047923322682, "percentage": 81.41, "elapsed_time": "1:55:36", "remaining_time": "0:26:23"}
+{"current_steps": 255, "total_steps": 312, "loss": 0.4914, "lr": 9.881436225981107e-07, "epoch": 2.4440894568690097, "percentage": 81.73, "elapsed_time": "1:56:02", "remaining_time": "0:25:56"}
+{"current_steps": 256, "total_steps": 312, "loss": 0.5022, "lr": 9.549150281252633e-07, "epoch": 2.4536741214057507, "percentage": 82.05, "elapsed_time": "1:56:29", "remaining_time": "0:25:28"}
+{"current_steps": 257, "total_steps": 312, "loss": 0.4945, "lr": 9.221956552036992e-07, "epoch": 2.463258785942492, "percentage": 82.37, "elapsed_time": "1:57:00", "remaining_time": "0:25:02"}
+{"current_steps": 258, "total_steps": 312, "loss": 0.4967, "lr": 8.899896227604509e-07, "epoch": 2.472843450479233, "percentage": 82.69, "elapsed_time": "1:57:25", "remaining_time": "0:24:34"}
+{"current_steps": 259, "total_steps": 312, "loss": 0.4912, "lr": 8.58300985099918e-07, "epoch": 2.4824281150159746, "percentage": 83.01, "elapsed_time": "1:57:52", "remaining_time": "0:24:07"}
+{"current_steps": 260, "total_steps": 312, "loss": 0.4789, "lr": 8.271337313934869e-07, "epoch": 2.4920127795527156, "percentage": 83.33, "elapsed_time": "1:58:18", "remaining_time": "0:23:39"}
+{"current_steps": 261, "total_steps": 312, "loss": 0.5138, "lr": 7.964917851773496e-07, "epoch": 2.501597444089457, "percentage": 83.65, "elapsed_time": "1:58:48", "remaining_time": "0:23:12"}
+{"current_steps": 262, "total_steps": 312, "loss": 0.4869, "lr": 7.663790038585794e-07, "epoch": 2.511182108626198, "percentage": 83.97, "elapsed_time": "1:59:14", "remaining_time": "0:22:45"}
+{"current_steps": 263, "total_steps": 312, "loss": 0.487, "lr": 7.367991782295392e-07, "epoch": 2.520766773162939, "percentage": 84.29, "elapsed_time": "1:59:39", "remaining_time": "0:22:17"}
+{"current_steps": 264, "total_steps": 312, "loss": 0.5115, "lr": 7.077560319906696e-07, "epoch": 2.5303514376996805, "percentage": 84.62, "elapsed_time": "2:00:02", "remaining_time": "0:21:49"}
+{"current_steps": 265, "total_steps": 312, "loss": 0.5304, "lr": 6.792532212817271e-07, "epoch": 2.539936102236422, "percentage": 84.94, "elapsed_time": "2:00:26", "remaining_time": "0:21:21"}
+{"current_steps": 266, "total_steps": 312, "loss": 0.5268, "lr": 6.512943342215234e-07, "epoch": 2.549520766773163, "percentage": 85.26, "elapsed_time": "2:00:53", "remaining_time": "0:20:54"}
+{"current_steps": 267, "total_steps": 312, "loss": 0.4955, "lr": 6.238828904562316e-07, "epoch": 2.559105431309904, "percentage": 85.58, "elapsed_time": "2:01:23", "remaining_time": "0:20:27"}
+{"current_steps": 268, "total_steps": 312, "loss": 0.5186, "lr": 5.9702234071631e-07, "epoch": 2.5686900958466454, "percentage": 85.9, "elapsed_time": "2:01:50", "remaining_time": "0:20:00"}
+{"current_steps": 269, "total_steps": 312, "loss": 0.4998, "lr": 5.707160663821009e-07, "epoch": 2.5782747603833864, "percentage": 86.22, "elapsed_time": "2:02:18", "remaining_time": "0:19:33"}
+{"current_steps": 270, "total_steps": 312, "loss": 0.4974, "lr": 5.449673790581611e-07, "epoch": 2.587859424920128, "percentage": 86.54, "elapsed_time": "2:02:45", "remaining_time": "0:19:05"}
+{"current_steps": 271, "total_steps": 312, "loss": 0.4794, "lr": 5.197795201563744e-07, "epoch": 2.597444089456869, "percentage": 86.86, "elapsed_time": "2:03:14", "remaining_time": "0:18:38"}
+{"current_steps": 272, "total_steps": 312, "loss": 0.4974, "lr": 4.951556604879049e-07, "epoch": 2.6070287539936103, "percentage": 87.18, "elapsed_time": "2:03:48", "remaining_time": "0:18:12"}
+{"current_steps": 273, "total_steps": 312, "loss": 0.4988, "lr": 4.710988998640298e-07, "epoch": 2.6166134185303513, "percentage": 87.5, "elapsed_time": "2:04:16", "remaining_time": "0:17:45"}
+{"current_steps": 274, "total_steps": 312, "loss": 0.512, "lr": 4.4761226670592074e-07, "epoch": 2.626198083067093, "percentage": 87.82, "elapsed_time": "2:04:46", "remaining_time": "0:17:18"}
+{"current_steps": 275, "total_steps": 312, "loss": 0.4738, "lr": 4.2469871766340096e-07, "epoch": 2.635782747603834, "percentage": 88.14, "elapsed_time": "2:05:06", "remaining_time": "0:16:50"}
+{"current_steps": 276, "total_steps": 312, "loss": 0.5278, "lr": 4.0236113724274716e-07, "epoch": 2.6453674121405752, "percentage": 88.46, "elapsed_time": "2:05:35", "remaining_time": "0:16:22"}
+{"current_steps": 277, "total_steps": 312, "loss": 0.5055, "lr": 3.8060233744356634e-07, "epoch": 2.6549520766773163, "percentage": 88.78, "elapsed_time": "2:06:02", "remaining_time": "0:15:55"}
+{"current_steps": 278, "total_steps": 312, "loss": 0.4815, "lr": 3.5942505740480583e-07, "epoch": 2.6645367412140573, "percentage": 89.1, "elapsed_time": "2:06:29", "remaining_time": "0:15:28"}
+{"current_steps": 279, "total_steps": 312, "loss": 0.5133, "lr": 3.3883196305992906e-07, "epoch": 2.6741214057507987, "percentage": 89.42, "elapsed_time": "2:06:50", "remaining_time": "0:15:00"}
+{"current_steps": 280, "total_steps": 312, "loss": 0.5029, "lr": 3.18825646801314e-07, "epoch": 2.68370607028754, "percentage": 89.74, "elapsed_time": "2:07:19", "remaining_time": "0:14:33"}
+{"current_steps": 281, "total_steps": 312, "loss": 0.4995, "lr": 2.9940862715390483e-07, "epoch": 2.693290734824281, "percentage": 90.06, "elapsed_time": "2:07:45", "remaining_time": "0:14:05"}
+{"current_steps": 282, "total_steps": 312, "loss": 0.5045, "lr": 2.8058334845816214e-07, "epoch": 2.702875399361022, "percentage": 90.38, "elapsed_time": "2:08:12", "remaining_time": "0:13:38"}
+{"current_steps": 283, "total_steps": 312, "loss": 0.49, "lr": 2.6235218056235633e-07, "epoch": 2.7124600638977636, "percentage": 90.71, "elapsed_time": "2:08:40", "remaining_time": "0:13:11"}
+{"current_steps": 284, "total_steps": 312, "loss": 0.4986, "lr": 2.447174185242324e-07, "epoch": 2.722044728434505, "percentage": 91.03, "elapsed_time": "2:09:08", "remaining_time": "0:12:43"}
+{"current_steps": 285, "total_steps": 312, "loss": 0.4864, "lr": 2.276812823220964e-07, "epoch": 2.731629392971246, "percentage": 91.35, "elapsed_time": "2:09:35", "remaining_time": "0:12:16"}
+{"current_steps": 286, "total_steps": 312, "loss": 0.5138, "lr": 2.1124591657534776e-07, "epoch": 2.741214057507987, "percentage": 91.67, "elapsed_time": "2:10:08", "remaining_time": "0:11:49"}
+{"current_steps": 287, "total_steps": 312, "loss": 0.498, "lr": 1.9541339027450256e-07, "epoch": 2.7507987220447285, "percentage": 91.99, "elapsed_time": "2:10:37", "remaining_time": "0:11:22"}
+{"current_steps": 288, "total_steps": 312, "loss": 0.517, "lr": 1.801856965207338e-07, "epoch": 2.7603833865814695, "percentage": 92.31, "elapsed_time": "2:11:10", "remaining_time": "0:10:55"}
+{"current_steps": 289, "total_steps": 312, "loss": 0.5219, "lr": 1.6556475227496816e-07, "epoch": 2.769968051118211, "percentage": 92.63, "elapsed_time": "2:11:40", "remaining_time": "0:10:28"}
+{"current_steps": 290, "total_steps": 312, "loss": 0.5048, "lr": 1.5155239811656562e-07, "epoch": 2.779552715654952, "percentage": 92.95, "elapsed_time": "2:12:08", "remaining_time": "0:10:01"}
+{"current_steps": 291, "total_steps": 312, "loss": 0.5258, "lr": 1.3815039801161723e-07, "epoch": 2.7891373801916934, "percentage": 93.27, "elapsed_time": "2:12:31", "remaining_time": "0:09:33"}
+{"current_steps": 292, "total_steps": 312, "loss": 0.5056, "lr": 1.253604390908819e-07, "epoch": 2.7987220447284344, "percentage": 93.59, "elapsed_time": "2:12:57", "remaining_time": "0:09:06"}
+{"current_steps": 293, "total_steps": 312, "loss": 0.525, "lr": 1.1318413143740436e-07, "epoch": 2.8083067092651754, "percentage": 93.91, "elapsed_time": "2:13:23", "remaining_time": "0:08:39"}
+{"current_steps": 294, "total_steps": 312, "loss": 0.5028, "lr": 1.0162300788382263e-07, "epoch": 2.817891373801917, "percentage": 94.23, "elapsed_time": "2:13:48", "remaining_time": "0:08:11"}
+{"current_steps": 295, "total_steps": 312, "loss": 0.5026, "lr": 9.0678523819408e-08, "epoch": 2.8274760383386583, "percentage": 94.55, "elapsed_time": "2:14:13", "remaining_time": "0:07:44"}
+{"current_steps": 296, "total_steps": 312, "loss": 0.5173, "lr": 8.035205700685167e-08, "epoch": 2.8370607028753994, "percentage": 94.87, "elapsed_time": "2:14:41", "remaining_time": "0:07:16"}
+{"current_steps": 297, "total_steps": 312, "loss": 0.5111, "lr": 7.064490740882057e-08, "epoch": 2.8466453674121404, "percentage": 95.19, "elapsed_time": "2:15:09", "remaining_time": "0:06:49"}
+{"current_steps": 298, "total_steps": 312, "loss": 0.4989, "lr": 6.15582970243117e-08, "epoch": 2.856230031948882, "percentage": 95.51, "elapsed_time": "2:15:38", "remaining_time": "0:06:22"}
+{"current_steps": 299, "total_steps": 312, "loss": 0.5111, "lr": 5.3093369734816824e-08, "epoch": 2.8658146964856233, "percentage": 95.83, "elapsed_time": "2:16:10", "remaining_time": "0:05:55"}
+{"current_steps": 300, "total_steps": 312, "loss": 0.4896, "lr": 4.52511911603265e-08, "epoch": 2.8753993610223643, "percentage": 96.15, "elapsed_time": "2:16:34", "remaining_time": "0:05:27"}
+{"current_steps": 301, "total_steps": 312, "loss": 0.5274, "lr": 3.8032748525179684e-08, "epoch": 2.8849840255591053, "percentage": 96.47, "elapsed_time": "2:17:00", "remaining_time": "0:05:00"}
+{"current_steps": 302, "total_steps": 312, "loss": 0.4915, "lr": 3.143895053378698e-08, "epoch": 2.8945686900958467, "percentage": 96.79, "elapsed_time": "2:17:28", "remaining_time": "0:04:33"}
+{"current_steps": 303, "total_steps": 312, "loss": 0.5059, "lr": 2.547062725623828e-08, "epoch": 2.9041533546325877, "percentage": 97.12, "elapsed_time": "2:17:57", "remaining_time": "0:04:05"}
+{"current_steps": 304, "total_steps": 312, "loss": 0.4837, "lr": 2.012853002380466e-08, "epoch": 2.913738019169329, "percentage": 97.44, "elapsed_time": "2:18:23", "remaining_time": "0:03:38"}
+{"current_steps": 305, "total_steps": 312, "loss": 0.5137, "lr": 1.541333133436018e-08, "epoch": 2.92332268370607, "percentage": 97.76, "elapsed_time": "2:18:49", "remaining_time": "0:03:11"}
+{"current_steps": 306, "total_steps": 312, "loss": 0.5035, "lr": 1.132562476771959e-08, "epoch": 2.9329073482428116, "percentage": 98.08, "elapsed_time": "2:19:13", "remaining_time": "0:02:43"}
+{"current_steps": 307, "total_steps": 312, "loss": 0.5052, "lr": 7.865924910916977e-09, "epoch": 2.9424920127795526, "percentage": 98.4, "elapsed_time": "2:19:46", "remaining_time": "0:02:16"}
+{"current_steps": 308, "total_steps": 312, "loss": 0.4787, "lr": 5.034667293427053e-09, "epoch": 2.952076677316294, "percentage": 98.72, "elapsed_time": "2:20:11", "remaining_time": "0:01:49"}
+{"current_steps": 309, "total_steps": 312, "loss": 0.498, "lr": 2.8322083323334417e-09, "epoch": 2.961661341853035, "percentage": 99.04, "elapsed_time": "2:20:34", "remaining_time": "0:01:21"}
+{"current_steps": 310, "total_steps": 312, "loss": 0.5103, "lr": 1.2588252874673469e-09, "epoch": 2.9712460063897765, "percentage": 99.36, "elapsed_time": "2:21:01", "remaining_time": "0:00:54"}
+{"current_steps": 311, "total_steps": 312, "loss": 0.4959, "lr": 3.147162264971471e-10, "epoch": 2.9808306709265175, "percentage": 99.68, "elapsed_time": "2:21:32", "remaining_time": "0:00:27"}
+{"current_steps": 312, "total_steps": 312, "loss": 0.5048, "lr": 0.0, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:22:01", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "2:23:02", "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": 7.631757736206055,
+      "learning_rate": 3.125e-07,
+      "loss": 1.1437,
+      "step": 1
+    },
+    {
+      "epoch": 0.019169329073482427,
+      "grad_norm": 7.207672119140625,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0804,
+      "step": 2
+    },
+    {
+      "epoch": 0.02875399361022364,
+      "grad_norm": 8.071743965148926,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.155,
+      "step": 3
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 7.237469673156738,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0944,
+      "step": 4
+    },
+    {
+      "epoch": 0.04792332268370607,
+      "grad_norm": 7.192005157470703,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.1085,
+      "step": 5
+    },
+    {
+      "epoch": 0.05750798722044728,
+      "grad_norm": 7.114604473114014,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.099,
+      "step": 6
+    },
+    {
+      "epoch": 0.0670926517571885,
+      "grad_norm": 5.225025177001953,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 1.0407,
+      "step": 7
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 4.8877787590026855,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0256,
+      "step": 8
+    },
+    {
+      "epoch": 0.08626198083067092,
+      "grad_norm": 3.1853082180023193,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.9822,
+      "step": 9
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 2.9565036296844482,
+      "learning_rate": 3.125e-06,
+      "loss": 1.0148,
+      "step": 10
+    },
+    {
+      "epoch": 0.10543130990415335,
+      "grad_norm": 2.6891329288482666,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.9717,
+      "step": 11
+    },
+    {
+      "epoch": 0.11501597444089456,
+      "grad_norm": 3.217716693878174,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.9585,
+      "step": 12
+    },
+    {
+      "epoch": 0.12460063897763578,
+      "grad_norm": 3.6357855796813965,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.9466,
+      "step": 13
+    },
+    {
+      "epoch": 0.134185303514377,
+      "grad_norm": 3.2886316776275635,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.9149,
+      "step": 14
+    },
+    {
+      "epoch": 0.14376996805111822,
+      "grad_norm": 2.728691339492798,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.9003,
+      "step": 15
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 2.0728046894073486,
+      "learning_rate": 5e-06,
+      "loss": 0.8858,
+      "step": 16
+    },
+    {
+      "epoch": 0.16293929712460065,
+      "grad_norm": 2.3851478099823,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.8923,
+      "step": 17
+    },
+    {
+      "epoch": 0.17252396166134185,
+      "grad_norm": 2.1146421432495117,
+      "learning_rate": 5.625e-06,
+      "loss": 0.8444,
+      "step": 18
+    },
+    {
+      "epoch": 0.18210862619808307,
+      "grad_norm": 1.742587685585022,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.846,
+      "step": 19
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 1.4841606616973877,
+      "learning_rate": 6.25e-06,
+      "loss": 0.8413,
+      "step": 20
+    },
+    {
+      "epoch": 0.2012779552715655,
+      "grad_norm": 1.2848784923553467,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.7976,
+      "step": 21
+    },
+    {
+      "epoch": 0.2108626198083067,
+      "grad_norm": 1.739992380142212,
+      "learning_rate": 6.875e-06,
+      "loss": 0.7873,
+      "step": 22
+    },
+    {
+      "epoch": 0.22044728434504793,
+      "grad_norm": 1.633833408355713,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.7909,
+      "step": 23
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 1.2238140106201172,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.789,
+      "step": 24
+    },
+    {
+      "epoch": 0.23961661341853036,
+      "grad_norm": 1.1153886318206787,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.7688,
+      "step": 25
+    },
+    {
+      "epoch": 0.24920127795527156,
+      "grad_norm": 1.1999198198318481,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.7509,
+      "step": 26
+    },
+    {
+      "epoch": 0.25878594249201275,
+      "grad_norm": 1.0238111019134521,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.7451,
+      "step": 27
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.9762786626815796,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.7739,
+      "step": 28
+    },
+    {
+      "epoch": 0.2779552715654952,
+      "grad_norm": 0.931849479675293,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.7406,
+      "step": 29
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 0.8621435165405273,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.7302,
+      "step": 30
+    },
+    {
+      "epoch": 0.2971246006389776,
+      "grad_norm": 0.9465786218643188,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.7396,
+      "step": 31
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.9201045632362366,
+      "learning_rate": 1e-05,
+      "loss": 0.7593,
+      "step": 32
+    },
+    {
+      "epoch": 0.31629392971246006,
+      "grad_norm": 0.7977403402328491,
+      "learning_rate": 9.999685283773504e-06,
+      "loss": 0.7255,
+      "step": 33
+    },
+    {
+      "epoch": 0.3258785942492013,
+      "grad_norm": 0.8451075553894043,
+      "learning_rate": 9.998741174712534e-06,
+      "loss": 0.7172,
+      "step": 34
+    },
+    {
+      "epoch": 0.3354632587859425,
+      "grad_norm": 0.9500023126602173,
+      "learning_rate": 9.997167791667668e-06,
+      "loss": 0.7309,
+      "step": 35
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 0.8545159101486206,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.7316,
+      "step": 36
+    },
+    {
+      "epoch": 0.3546325878594249,
+      "grad_norm": 0.7496842741966248,
+      "learning_rate": 9.992134075089085e-06,
+      "loss": 0.7276,
+      "step": 37
+    },
+    {
+      "epoch": 0.36421725239616615,
+      "grad_norm": 0.9326169490814209,
+      "learning_rate": 9.98867437523228e-06,
+      "loss": 0.7029,
+      "step": 38
+    },
+    {
+      "epoch": 0.3738019169329074,
+      "grad_norm": 0.8307452201843262,
+      "learning_rate": 9.984586668665641e-06,
+      "loss": 0.7111,
+      "step": 39
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.8053420782089233,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.733,
+      "step": 40
+    },
+    {
+      "epoch": 0.3929712460063898,
+      "grad_norm": 0.81968092918396,
+      "learning_rate": 9.974529372743762e-06,
+      "loss": 0.7054,
+      "step": 41
+    },
+    {
+      "epoch": 0.402555910543131,
+      "grad_norm": 0.8351101875305176,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.6961,
+      "step": 42
+    },
+    {
+      "epoch": 0.41214057507987223,
+      "grad_norm": 0.8805105686187744,
+      "learning_rate": 9.961967251474823e-06,
+      "loss": 0.7093,
+      "step": 43
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 0.7041685581207275,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.6822,
+      "step": 44
+    },
+    {
+      "epoch": 0.43130990415335463,
+      "grad_norm": 0.7762527465820312,
+      "learning_rate": 9.946906630265184e-06,
+      "loss": 0.693,
+      "step": 45
+    },
+    {
+      "epoch": 0.44089456869009586,
+      "grad_norm": 0.7489679455757141,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.7289,
+      "step": 46
+    },
+    {
+      "epoch": 0.4504792332268371,
+      "grad_norm": 0.8490743041038513,
+      "learning_rate": 9.92935509259118e-06,
+      "loss": 0.6953,
+      "step": 47
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.7434765696525574,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.6735,
+      "step": 48
+    },
+    {
+      "epoch": 0.4696485623003195,
+      "grad_norm": 0.7000515460968018,
+      "learning_rate": 9.909321476180594e-06,
+      "loss": 0.6932,
+      "step": 49
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.891094446182251,
+      "learning_rate": 9.898376992116179e-06,
+      "loss": 0.6902,
+      "step": 50
+    },
+    {
+      "epoch": 0.48881789137380194,
+      "grad_norm": 0.711914598941803,
+      "learning_rate": 9.886815868562596e-06,
+      "loss": 0.6869,
+      "step": 51
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 0.6698287725448608,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.6825,
+      "step": 52
+    },
+    {
+      "epoch": 0.5079872204472844,
+      "grad_norm": 0.6114389300346375,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 0.6854,
+      "step": 53
+    },
+    {
+      "epoch": 0.5175718849840255,
+      "grad_norm": 0.7109593152999878,
+      "learning_rate": 9.848447601883436e-06,
+      "loss": 0.6904,
+      "step": 54
+    },
+    {
+      "epoch": 0.5271565495207667,
+      "grad_norm": 0.748586893081665,
+      "learning_rate": 9.834435247725032e-06,
+      "loss": 0.684,
+      "step": 55
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 0.7264263033866882,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.6821,
+      "step": 56
+    },
+    {
+      "epoch": 0.5463258785942492,
+      "grad_norm": 0.7709238529205322,
+      "learning_rate": 9.804586609725499e-06,
+      "loss": 0.7041,
+      "step": 57
+    },
+    {
+      "epoch": 0.5559105431309904,
+      "grad_norm": 0.7797627449035645,
+      "learning_rate": 9.788754083424654e-06,
+      "loss": 0.6591,
+      "step": 58
+    },
+    {
+      "epoch": 0.5654952076677316,
+      "grad_norm": 0.6770584583282471,
+      "learning_rate": 9.772318717677905e-06,
+      "loss": 0.668,
+      "step": 59
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.7253358364105225,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.6889,
+      "step": 60
+    },
+    {
+      "epoch": 0.5846645367412141,
+      "grad_norm": 0.8044716715812683,
+      "learning_rate": 9.737647819437645e-06,
+      "loss": 0.6824,
+      "step": 61
+    },
+    {
+      "epoch": 0.5942492012779552,
+      "grad_norm": 0.7814176082611084,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.6652,
+      "step": 62
+    },
+    {
+      "epoch": 0.6038338658146964,
+      "grad_norm": 0.8672887086868286,
+      "learning_rate": 9.700591372846096e-06,
+      "loss": 0.6681,
+      "step": 63
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.686853289604187,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.6741,
+      "step": 64
+    },
+    {
+      "epoch": 0.6230031948881789,
+      "grad_norm": 0.7145909667015076,
+      "learning_rate": 9.661168036940071e-06,
+      "loss": 0.6763,
+      "step": 65
+    },
+    {
+      "epoch": 0.6325878594249201,
+      "grad_norm": 0.7959132790565491,
+      "learning_rate": 9.640574942595195e-06,
+      "loss": 0.6863,
+      "step": 66
+    },
+    {
+      "epoch": 0.6421725239616614,
+      "grad_norm": 0.6892458200454712,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.6772,
+      "step": 67
+    },
+    {
+      "epoch": 0.6517571884984026,
+      "grad_norm": 0.7975493669509888,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.6726,
+      "step": 68
+    },
+    {
+      "epoch": 0.6613418530351438,
+      "grad_norm": 0.7013779282569885,
+      "learning_rate": 9.5753012823366e-06,
+      "loss": 0.6603,
+      "step": 69
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 0.7355247139930725,
+      "learning_rate": 9.552387733294081e-06,
+      "loss": 0.6855,
+      "step": 70
+    },
+    {
+      "epoch": 0.6805111821086262,
+      "grad_norm": 0.7918930649757385,
+      "learning_rate": 9.528901100135971e-06,
+      "loss": 0.6717,
+      "step": 71
+    },
+    {
+      "epoch": 0.6900958466453674,
+      "grad_norm": 0.7762782573699951,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.6842,
+      "step": 72
+    },
+    {
+      "epoch": 0.6996805111821086,
+      "grad_norm": 0.7748196721076965,
+      "learning_rate": 9.480220479843627e-06,
+      "loss": 0.666,
+      "step": 73
+    },
+    {
+      "epoch": 0.7092651757188498,
+      "grad_norm": 0.7611200213432312,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.6856,
+      "step": 74
+    },
+    {
+      "epoch": 0.7188498402555911,
+      "grad_norm": 0.8682624697685242,
+      "learning_rate": 9.4292839336179e-06,
+      "loss": 0.6581,
+      "step": 75
+    },
+    {
+      "epoch": 0.7284345047923323,
+      "grad_norm": 0.7679495811462402,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.6734,
+      "step": 76
+    },
+    {
+      "epoch": 0.7380191693290735,
+      "grad_norm": 0.7918921709060669,
+      "learning_rate": 9.376117109543769e-06,
+      "loss": 0.6694,
+      "step": 77
+    },
+    {
+      "epoch": 0.7476038338658147,
+      "grad_norm": 0.9087303280830383,
+      "learning_rate": 9.348705665778479e-06,
+      "loss": 0.6755,
+      "step": 78
+    },
+    {
+      "epoch": 0.7571884984025559,
+      "grad_norm": 0.6955181360244751,
+      "learning_rate": 9.320746778718274e-06,
+      "loss": 0.6469,
+      "step": 79
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.7844282388687134,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.6723,
+      "step": 80
+    },
+    {
+      "epoch": 0.7763578274760383,
+      "grad_norm": 0.7338053584098816,
+      "learning_rate": 9.263200821770462e-06,
+      "loss": 0.6757,
+      "step": 81
+    },
+    {
+      "epoch": 0.7859424920127795,
+      "grad_norm": 0.7353216409683228,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.6727,
+      "step": 82
+    },
+    {
+      "epoch": 0.7955271565495208,
+      "grad_norm": 0.7343015670776367,
+      "learning_rate": 9.203508214822652e-06,
+      "loss": 0.6635,
+      "step": 83
+    },
+    {
+      "epoch": 0.805111821086262,
+      "grad_norm": 0.792455792427063,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.6389,
+      "step": 84
+    },
+    {
+      "epoch": 0.8146964856230032,
+      "grad_norm": 0.7722944617271423,
+      "learning_rate": 9.141699014900084e-06,
+      "loss": 0.6848,
+      "step": 85
+    },
+    {
+      "epoch": 0.8242811501597445,
+      "grad_norm": 0.7590317130088806,
+      "learning_rate": 9.110010377239552e-06,
+      "loss": 0.6687,
+      "step": 86
+    },
+    {
+      "epoch": 0.8338658146964856,
+      "grad_norm": 0.6646780371665955,
+      "learning_rate": 9.077804344796302e-06,
+      "loss": 0.6772,
+      "step": 87
+    },
+    {
+      "epoch": 0.8434504792332268,
+      "grad_norm": 0.7406274676322937,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.649,
+      "step": 88
+    },
+    {
+      "epoch": 0.853035143769968,
+      "grad_norm": 0.7770557999610901,
+      "learning_rate": 9.011856377401891e-06,
+      "loss": 0.6667,
+      "step": 89
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 0.7461346387863159,
+      "learning_rate": 8.978122744408905e-06,
+      "loss": 0.6846,
+      "step": 90
+    },
+    {
+      "epoch": 0.8722044728434505,
+      "grad_norm": 0.8803783655166626,
+      "learning_rate": 8.943888319504456e-06,
+      "loss": 0.6694,
+      "step": 91
+    },
+    {
+      "epoch": 0.8817891373801917,
+      "grad_norm": 0.7138260006904602,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.6731,
+      "step": 92
+    },
+    {
+      "epoch": 0.8913738019169329,
+      "grad_norm": 0.7463406324386597,
+      "learning_rate": 8.873934395068006e-06,
+      "loss": 0.6445,
+      "step": 93
+    },
+    {
+      "epoch": 0.9009584664536742,
+      "grad_norm": 0.7805307507514954,
+      "learning_rate": 8.838223701790057e-06,
+      "loss": 0.6833,
+      "step": 94
+    },
+    {
+      "epoch": 0.9105431309904153,
+      "grad_norm": 0.7624490857124329,
+      "learning_rate": 8.802029828000157e-06,
+      "loss": 0.6291,
+      "step": 95
+    },
+    {
+      "epoch": 0.9201277955271565,
+      "grad_norm": 0.7260795831680298,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.6729,
+      "step": 96
+    },
+    {
+      "epoch": 0.9297124600638977,
+      "grad_norm": 0.8511263132095337,
+      "learning_rate": 8.728210824415829e-06,
+      "loss": 0.6617,
+      "step": 97
+    },
+    {
+      "epoch": 0.939297124600639,
+      "grad_norm": 0.7045103907585144,
+      "learning_rate": 8.690594987436705e-06,
+      "loss": 0.6557,
+      "step": 98
+    },
+    {
+      "epoch": 0.9488817891373802,
+      "grad_norm": 0.7786133885383606,
+      "learning_rate": 8.652514554406388e-06,
+      "loss": 0.6525,
+      "step": 99
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 0.9434441924095154,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.6618,
+      "step": 100
+    },
+    {
+      "epoch": 0.9680511182108626,
+      "grad_norm": 0.6732690930366516,
+      "learning_rate": 8.574979133323378e-06,
+      "loss": 0.6403,
+      "step": 101
+    },
+    {
+      "epoch": 0.9776357827476039,
+      "grad_norm": 0.8073576092720032,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.6523,
+      "step": 102
+    },
+    {
+      "epoch": 0.987220447284345,
+      "grad_norm": 0.7025145292282104,
+      "learning_rate": 8.495643602586287e-06,
+      "loss": 0.6454,
+      "step": 103
+    },
+    {
+      "epoch": 0.9968051118210862,
+      "grad_norm": 0.7717574238777161,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.6529,
+      "step": 104
+    },
+    {
+      "epoch": 1.0063897763578276,
+      "grad_norm": 0.6937882900238037,
+      "learning_rate": 8.414547910024035e-06,
+      "loss": 0.6219,
+      "step": 105
+    },
+    {
+      "epoch": 1.0159744408945688,
+      "grad_norm": 0.6880476474761963,
+      "learning_rate": 8.373352729660373e-06,
+      "loss": 0.5887,
+      "step": 106
+    },
+    {
+      "epoch": 1.0255591054313098,
+      "grad_norm": 0.7143478393554688,
+      "learning_rate": 8.331732889760021e-06,
+      "loss": 0.5787,
+      "step": 107
+    },
+    {
+      "epoch": 1.035143769968051,
+      "grad_norm": 0.7447161674499512,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.5986,
+      "step": 108
+    },
+    {
+      "epoch": 1.0447284345047922,
+      "grad_norm": 0.655197262763977,
+      "learning_rate": 8.247240241650918e-06,
+      "loss": 0.5626,
+      "step": 109
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.7953078746795654,
+      "learning_rate": 8.204378069925121e-06,
+      "loss": 0.5935,
+      "step": 110
+    },
+    {
+      "epoch": 1.0638977635782747,
+      "grad_norm": 0.712658166885376,
+      "learning_rate": 8.16111251028955e-06,
+      "loss": 0.5891,
+      "step": 111
+    },
+    {
+      "epoch": 1.073482428115016,
+      "grad_norm": 0.6255548000335693,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5729,
+      "step": 112
+    },
+    {
+      "epoch": 1.0830670926517572,
+      "grad_norm": 0.6540143489837646,
+      "learning_rate": 8.073393063582386e-06,
+      "loss": 0.5781,
+      "step": 113
+    },
+    {
+      "epoch": 1.0926517571884984,
+      "grad_norm": 0.6459587812423706,
+      "learning_rate": 8.0289502192041e-06,
+      "loss": 0.5843,
+      "step": 114
+    },
+    {
+      "epoch": 1.1022364217252396,
+      "grad_norm": 0.7313612103462219,
+      "learning_rate": 7.984126070912519e-06,
+      "loss": 0.5648,
+      "step": 115
+    },
+    {
+      "epoch": 1.1118210862619808,
+      "grad_norm": 0.6702539324760437,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.5617,
+      "step": 116
+    },
+    {
+      "epoch": 1.121405750798722,
+      "grad_norm": 0.6335576176643372,
+      "learning_rate": 7.89335648089903e-06,
+      "loss": 0.5983,
+      "step": 117
+    },
+    {
+      "epoch": 1.1309904153354633,
+      "grad_norm": 0.7993137836456299,
+      "learning_rate": 7.84742246584226e-06,
+      "loss": 0.6143,
+      "step": 118
+    },
+    {
+      "epoch": 1.1405750798722045,
+      "grad_norm": 0.7164519429206848,
+      "learning_rate": 7.801129998764014e-06,
+      "loss": 0.5664,
+      "step": 119
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.7602349519729614,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.5801,
+      "step": 120
+    },
+    {
+      "epoch": 1.159744408945687,
+      "grad_norm": 0.7163518071174622,
+      "learning_rate": 7.70749306331863e-06,
+      "loss": 0.5573,
+      "step": 121
+    },
+    {
+      "epoch": 1.1693290734824282,
+      "grad_norm": 0.6692156195640564,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.575,
+      "step": 122
+    },
+    {
+      "epoch": 1.1789137380191694,
+      "grad_norm": 0.8085399866104126,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.5878,
+      "step": 123
+    },
+    {
+      "epoch": 1.1884984025559104,
+      "grad_norm": 0.6267865896224976,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.5486,
+      "step": 124
+    },
+    {
+      "epoch": 1.1980830670926517,
+      "grad_norm": 0.6363678574562073,
+      "learning_rate": 7.516177115029002e-06,
+      "loss": 0.5884,
+      "step": 125
+    },
+    {
+      "epoch": 1.207667731629393,
+      "grad_norm": 0.7670935392379761,
+      "learning_rate": 7.467541090321735e-06,
+      "loss": 0.5565,
+      "step": 126
+    },
+    {
+      "epoch": 1.2172523961661341,
+      "grad_norm": 0.640592634677887,
+      "learning_rate": 7.4185944355261996e-06,
+      "loss": 0.5943,
+      "step": 127
+    },
+    {
+      "epoch": 1.2268370607028753,
+      "grad_norm": 0.7349753379821777,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.5965,
+      "step": 128
+    },
+    {
+      "epoch": 1.2364217252396166,
+      "grad_norm": 0.7965679168701172,
+      "learning_rate": 7.319793920889171e-06,
+      "loss": 0.5895,
+      "step": 129
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.5832921862602234,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.5785,
+      "step": 130
+    },
+    {
+      "epoch": 1.255591054313099,
+      "grad_norm": 0.7845919132232666,
+      "learning_rate": 7.219825320152411e-06,
+      "loss": 0.5873,
+      "step": 131
+    },
+    {
+      "epoch": 1.2651757188498403,
+      "grad_norm": 0.6836994886398315,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.5811,
+      "step": 132
+    },
+    {
+      "epoch": 1.2747603833865815,
+      "grad_norm": 0.5873911380767822,
+      "learning_rate": 7.118738970516944e-06,
+      "loss": 0.5854,
+      "step": 133
+    },
+    {
+      "epoch": 1.2843450479233227,
+      "grad_norm": 0.7451477646827698,
+      "learning_rate": 7.067792524832604e-06,
+      "loss": 0.5859,
+      "step": 134
+    },
+    {
+      "epoch": 1.293929712460064,
+      "grad_norm": 0.6415753364562988,
+      "learning_rate": 7.016585772004026e-06,
+      "loss": 0.5812,
+      "step": 135
+    },
+    {
+      "epoch": 1.3035143769968052,
+      "grad_norm": 0.6458070874214172,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.5712,
+      "step": 136
+    },
+    {
+      "epoch": 1.3130990415335464,
+      "grad_norm": 0.7372552752494812,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.5692,
+      "step": 137
+    },
+    {
+      "epoch": 1.3226837060702876,
+      "grad_norm": 0.6712161302566528,
+      "learning_rate": 6.8614682920097265e-06,
+      "loss": 0.5681,
+      "step": 138
+    },
+    {
+      "epoch": 1.3322683706070286,
+      "grad_norm": 0.6904409527778625,
+      "learning_rate": 6.809285088483361e-06,
+      "loss": 0.576,
+      "step": 139
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.636581540107727,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.5779,
+      "step": 140
+    },
+    {
+      "epoch": 1.351437699680511,
+      "grad_norm": 0.6586715579032898,
+      "learning_rate": 6.704241985612625e-06,
+      "loss": 0.5499,
+      "step": 141
+    },
+    {
+      "epoch": 1.3610223642172525,
+      "grad_norm": 0.6217679381370544,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.5603,
+      "step": 142
+    },
+    {
+      "epoch": 1.3706070287539935,
+      "grad_norm": 0.7175468802452087,
+      "learning_rate": 6.598340745578908e-06,
+      "loss": 0.5949,
+      "step": 143
+    },
+    {
+      "epoch": 1.3801916932907348,
+      "grad_norm": 0.6404513716697693,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5864,
+      "step": 144
+    },
+    {
+      "epoch": 1.389776357827476,
+      "grad_norm": 0.6180385947227478,
+      "learning_rate": 6.491634692845781e-06,
+      "loss": 0.5977,
+      "step": 145
+    },
+    {
+      "epoch": 1.3993610223642172,
+      "grad_norm": 0.6496903896331787,
+      "learning_rate": 6.437996637160086e-06,
+      "loss": 0.5824,
+      "step": 146
+    },
+    {
+      "epoch": 1.4089456869009584,
+      "grad_norm": 0.6618816256523132,
+      "learning_rate": 6.384177557124247e-06,
+      "loss": 0.5648,
+      "step": 147
+    },
+    {
+      "epoch": 1.4185303514376997,
+      "grad_norm": 0.6388576626777649,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.5641,
+      "step": 148
+    },
+    {
+      "epoch": 1.428115015974441,
+      "grad_norm": 0.6645902991294861,
+      "learning_rate": 6.276023446318214e-06,
+      "loss": 0.5642,
+      "step": 149
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 0.6369603872299194,
+      "learning_rate": 6.2217020306894705e-06,
+      "loss": 0.5672,
+      "step": 150
+    },
+    {
+      "epoch": 1.4472843450479234,
+      "grad_norm": 0.7125694751739502,
+      "learning_rate": 6.1672268192795285e-06,
+      "loss": 0.5738,
+      "step": 151
+    },
+    {
+      "epoch": 1.4568690095846646,
+      "grad_norm": 0.6303924918174744,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.574,
+      "step": 152
+    },
+    {
+      "epoch": 1.4664536741214058,
+      "grad_norm": 0.5970083475112915,
+      "learning_rate": 6.057842458386315e-06,
+      "loss": 0.5747,
+      "step": 153
+    },
+    {
+      "epoch": 1.476038338658147,
+      "grad_norm": 0.6371821761131287,
+      "learning_rate": 6.002947078916365e-06,
+      "loss": 0.5653,
+      "step": 154
+    },
+    {
+      "epoch": 1.4856230031948883,
+      "grad_norm": 0.7160565257072449,
+      "learning_rate": 5.947925441958393e-06,
+      "loss": 0.5493,
+      "step": 155
+    },
+    {
+      "epoch": 1.4952076677316293,
+      "grad_norm": 0.6290352940559387,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.5723,
+      "step": 156
+    },
+    {
+      "epoch": 1.5047923322683707,
+      "grad_norm": 0.5443238615989685,
+      "learning_rate": 5.837531116523683e-06,
+      "loss": 0.5914,
+      "step": 157
+    },
+    {
+      "epoch": 1.5143769968051117,
+      "grad_norm": 0.6566057205200195,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.5577,
+      "step": 158
+    },
+    {
+      "epoch": 1.5239616613418532,
+      "grad_norm": 0.6568493247032166,
+      "learning_rate": 5.726715068949564e-06,
+      "loss": 0.5672,
+      "step": 159
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 0.6268693208694458,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.5853,
+      "step": 160
+    },
+    {
+      "epoch": 1.5431309904153354,
+      "grad_norm": 0.6314179301261902,
+      "learning_rate": 5.615533098453215e-06,
+      "loss": 0.5599,
+      "step": 161
+    },
+    {
+      "epoch": 1.5527156549520766,
+      "grad_norm": 0.5839089155197144,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.5578,
+      "step": 162
+    },
+    {
+      "epoch": 1.5623003194888179,
+      "grad_norm": 0.5961830019950867,
+      "learning_rate": 5.504041188505022e-06,
+      "loss": 0.5634,
+      "step": 163
+    },
+    {
+      "epoch": 1.571884984025559,
+      "grad_norm": 0.6408848166465759,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.5677,
+      "step": 164
+    },
+    {
+      "epoch": 1.5814696485623003,
+      "grad_norm": 0.6148958802223206,
+      "learning_rate": 5.392295478639226e-06,
+      "loss": 0.5647,
+      "step": 165
+    },
+    {
+      "epoch": 1.5910543130990416,
+      "grad_norm": 0.5794315338134766,
+      "learning_rate": 5.336345028060199e-06,
+      "loss": 0.5792,
+      "step": 166
+    },
+    {
+      "epoch": 1.6006389776357828,
+      "grad_norm": 0.60219806432724,
+      "learning_rate": 5.2803522361859596e-06,
+      "loss": 0.5477,
+      "step": 167
+    },
+    {
+      "epoch": 1.610223642172524,
+      "grad_norm": 0.6012296676635742,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.583,
+      "step": 168
+    },
+    {
+      "epoch": 1.619808306709265,
+      "grad_norm": 0.6214751601219177,
+      "learning_rate": 5.168267827938971e-06,
+      "loss": 0.5439,
+      "step": 169
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6018662452697754,
+      "learning_rate": 5.112190321479026e-06,
+      "loss": 0.5671,
+      "step": 170
+    },
+    {
+      "epoch": 1.6389776357827475,
+      "grad_norm": 0.5933774709701538,
+      "learning_rate": 5.05609869177323e-06,
+      "loss": 0.5886,
+      "step": 171
+    },
+    {
+      "epoch": 1.648562300319489,
+      "grad_norm": 0.5990563035011292,
+      "learning_rate": 5e-06,
+      "loss": 0.5653,
+      "step": 172
+    },
+    {
+      "epoch": 1.65814696485623,
+      "grad_norm": 0.5904830694198608,
+      "learning_rate": 4.943901308226771e-06,
+      "loss": 0.5602,
+      "step": 173
+    },
+    {
+      "epoch": 1.6677316293929714,
+      "grad_norm": 0.6122473478317261,
+      "learning_rate": 4.887809678520976e-06,
+      "loss": 0.5801,
+      "step": 174
+    },
+    {
+      "epoch": 1.6773162939297124,
+      "grad_norm": 0.6307440400123596,
+      "learning_rate": 4.831732172061032e-06,
+      "loss": 0.5842,
+      "step": 175
+    },
+    {
+      "epoch": 1.6869009584664538,
+      "grad_norm": 0.6917486190795898,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.5595,
+      "step": 176
+    },
+    {
+      "epoch": 1.6964856230031948,
+      "grad_norm": 0.6185805797576904,
+      "learning_rate": 4.719647763814041e-06,
+      "loss": 0.5727,
+      "step": 177
+    },
+    {
+      "epoch": 1.706070287539936,
+      "grad_norm": 0.5742789506912231,
+      "learning_rate": 4.663654971939802e-06,
+      "loss": 0.5575,
+      "step": 178
+    },
+    {
+      "epoch": 1.7156549520766773,
+      "grad_norm": 0.6561394333839417,
+      "learning_rate": 4.6077045213607765e-06,
+      "loss": 0.5706,
+      "step": 179
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 0.6904816627502441,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.6007,
+      "step": 180
+    },
+    {
+      "epoch": 1.7348242811501597,
+      "grad_norm": 0.6116853356361389,
+      "learning_rate": 4.4959588114949785e-06,
+      "loss": 0.5686,
+      "step": 181
+    },
+    {
+      "epoch": 1.744408945686901,
+      "grad_norm": 0.6065500378608704,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.5829,
+      "step": 182
+    },
+    {
+      "epoch": 1.7539936102236422,
+      "grad_norm": 0.6076284050941467,
+      "learning_rate": 4.384466901546786e-06,
+      "loss": 0.5745,
+      "step": 183
+    },
+    {
+      "epoch": 1.7635782747603834,
+      "grad_norm": 0.5575659275054932,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.5708,
+      "step": 184
+    },
+    {
+      "epoch": 1.7731629392971247,
+      "grad_norm": 0.5849297046661377,
+      "learning_rate": 4.273284931050438e-06,
+      "loss": 0.5532,
+      "step": 185
+    },
+    {
+      "epoch": 1.7827476038338657,
+      "grad_norm": 0.5678250193595886,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.5676,
+      "step": 186
+    },
+    {
+      "epoch": 1.792332268370607,
+      "grad_norm": 0.5182955265045166,
+      "learning_rate": 4.162468883476319e-06,
+      "loss": 0.5656,
+      "step": 187
+    },
+    {
+      "epoch": 1.8019169329073481,
+      "grad_norm": 0.6109117269515991,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.5734,
+      "step": 188
+    },
+    {
+      "epoch": 1.8115015974440896,
+      "grad_norm": 0.6146546006202698,
+      "learning_rate": 4.052074558041608e-06,
+      "loss": 0.5891,
+      "step": 189
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 0.5946270823478699,
+      "learning_rate": 3.997052921083637e-06,
+      "loss": 0.5838,
+      "step": 190
+    },
+    {
+      "epoch": 1.830670926517572,
+      "grad_norm": 0.5628454089164734,
+      "learning_rate": 3.9421575416136866e-06,
+      "loss": 0.5682,
+      "step": 191
+    },
+    {
+      "epoch": 1.840255591054313,
+      "grad_norm": 0.5776045322418213,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.5774,
+      "step": 192
+    },
+    {
+      "epoch": 1.8498402555910545,
+      "grad_norm": 0.5610283017158508,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.5755,
+      "step": 193
+    },
+    {
+      "epoch": 1.8594249201277955,
+      "grad_norm": 0.5823736190795898,
+      "learning_rate": 3.778297969310529e-06,
+      "loss": 0.5894,
+      "step": 194
+    },
+    {
+      "epoch": 1.8690095846645367,
+      "grad_norm": 0.5524364709854126,
+      "learning_rate": 3.723976553681787e-06,
+      "loss": 0.5881,
+      "step": 195
+    },
+    {
+      "epoch": 1.878594249201278,
+      "grad_norm": 0.6131855249404907,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.5699,
+      "step": 196
+    },
+    {
+      "epoch": 1.8881789137380192,
+      "grad_norm": 0.6087161898612976,
+      "learning_rate": 3.6158224428757538e-06,
+      "loss": 0.5747,
+      "step": 197
+    },
+    {
+      "epoch": 1.8977635782747604,
+      "grad_norm": 0.591026782989502,
+      "learning_rate": 3.562003362839914e-06,
+      "loss": 0.5596,
+      "step": 198
+    },
+    {
+      "epoch": 1.9073482428115016,
+      "grad_norm": 0.5625490546226501,
+      "learning_rate": 3.50836530715422e-06,
+      "loss": 0.5709,
+      "step": 199
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.5438273549079895,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.5771,
+      "step": 200
+    },
+    {
+      "epoch": 1.926517571884984,
+      "grad_norm": 0.5201634764671326,
+      "learning_rate": 3.4016592544210937e-06,
+      "loss": 0.5763,
+      "step": 201
+    },
+    {
+      "epoch": 1.9361022364217253,
+      "grad_norm": 0.6035382151603699,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.5495,
+      "step": 202
+    },
+    {
+      "epoch": 1.9456869009584663,
+      "grad_norm": 0.539597749710083,
+      "learning_rate": 3.295758014387375e-06,
+      "loss": 0.5836,
+      "step": 203
+    },
+    {
+      "epoch": 1.9552715654952078,
+      "grad_norm": 0.4887038469314575,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.5865,
+      "step": 204
+    },
+    {
+      "epoch": 1.9648562300319488,
+      "grad_norm": 0.5846530795097351,
+      "learning_rate": 3.1907149115166403e-06,
+      "loss": 0.5638,
+      "step": 205
+    },
+    {
+      "epoch": 1.9744408945686902,
+      "grad_norm": 0.5618496537208557,
+      "learning_rate": 3.1385317079902743e-06,
+      "loss": 0.5784,
+      "step": 206
+    },
+    {
+      "epoch": 1.9840255591054312,
+      "grad_norm": 0.5010558366775513,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.572,
+      "step": 207
+    },
+    {
+      "epoch": 1.9936102236421727,
+      "grad_norm": 0.5525842308998108,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.5578,
+      "step": 208
+    },
+    {
+      "epoch": 2.0031948881789137,
+      "grad_norm": 0.5372030735015869,
+      "learning_rate": 2.9834142279959754e-06,
+      "loss": 0.5419,
+      "step": 209
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.5794517397880554,
+      "learning_rate": 2.932207475167398e-06,
+      "loss": 0.5237,
+      "step": 210
+    },
+    {
+      "epoch": 2.022364217252396,
+      "grad_norm": 0.5482734441757202,
+      "learning_rate": 2.8812610294830568e-06,
+      "loss": 0.523,
+      "step": 211
+    },
+    {
+      "epoch": 2.0319488817891376,
+      "grad_norm": 0.49512386322021484,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.5488,
+      "step": 212
+    },
+    {
+      "epoch": 2.0415335463258786,
+      "grad_norm": 0.5444460511207581,
+      "learning_rate": 2.7801746798475905e-06,
+      "loss": 0.5362,
+      "step": 213
+    },
+    {
+      "epoch": 2.0511182108626196,
+      "grad_norm": 0.5378485321998596,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.5117,
+      "step": 214
+    },
+    {
+      "epoch": 2.060702875399361,
+      "grad_norm": 0.570003092288971,
+      "learning_rate": 2.6802060791108304e-06,
+      "loss": 0.4838,
+      "step": 215
+    },
+    {
+      "epoch": 2.070287539936102,
+      "grad_norm": 0.6234847903251648,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.5046,
+      "step": 216
+    },
+    {
+      "epoch": 2.0798722044728435,
+      "grad_norm": 0.5408498644828796,
+      "learning_rate": 2.5814055644738013e-06,
+      "loss": 0.5185,
+      "step": 217
+    },
+    {
+      "epoch": 2.0894568690095845,
+      "grad_norm": 0.5204379558563232,
+      "learning_rate": 2.532458909678266e-06,
+      "loss": 0.496,
+      "step": 218
+    },
+    {
+      "epoch": 2.099041533546326,
+      "grad_norm": 0.5795621871948242,
+      "learning_rate": 2.483822884971e-06,
+      "loss": 0.5253,
+      "step": 219
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.5828584432601929,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.5122,
+      "step": 220
+    },
+    {
+      "epoch": 2.1182108626198084,
+      "grad_norm": 0.6278659105300903,
+      "learning_rate": 2.387507176420256e-06,
+      "loss": 0.4836,
+      "step": 221
+    },
+    {
+      "epoch": 2.1277955271565494,
+      "grad_norm": 0.5321851968765259,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.5254,
+      "step": 222
+    },
+    {
+      "epoch": 2.137380191693291,
+      "grad_norm": 0.5402694940567017,
+      "learning_rate": 2.2925069366813718e-06,
+      "loss": 0.5279,
+      "step": 223
+    },
+    {
+      "epoch": 2.146964856230032,
+      "grad_norm": 0.528405487537384,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.4915,
+      "step": 224
+    },
+    {
+      "epoch": 2.1565495207667733,
+      "grad_norm": 0.5780546069145203,
+      "learning_rate": 2.1988700012359865e-06,
+      "loss": 0.5057,
+      "step": 225
+    },
+    {
+      "epoch": 2.1661341853035143,
+      "grad_norm": 0.5286846160888672,
+      "learning_rate": 2.1525775341577404e-06,
+      "loss": 0.4826,
+      "step": 226
+    },
+    {
+      "epoch": 2.1757188498402558,
+      "grad_norm": 0.5604357719421387,
+      "learning_rate": 2.1066435191009717e-06,
+      "loss": 0.5041,
+      "step": 227
+    },
+    {
+      "epoch": 2.1853035143769968,
+      "grad_norm": 0.5224547386169434,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.504,
+      "step": 228
+    },
+    {
+      "epoch": 2.194888178913738,
+      "grad_norm": 0.49711328744888306,
+      "learning_rate": 2.0158739290874822e-06,
+      "loss": 0.4867,
+      "step": 229
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 0.5324923396110535,
+      "learning_rate": 1.971049780795901e-06,
+      "loss": 0.5058,
+      "step": 230
+    },
+    {
+      "epoch": 2.2140575079872207,
+      "grad_norm": 0.5620575547218323,
+      "learning_rate": 1.9266069364176144e-06,
+      "loss": 0.491,
+      "step": 231
+    },
+    {
+      "epoch": 2.2236421725239617,
+      "grad_norm": 0.6187978386878967,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.4932,
+      "step": 232
+    },
+    {
+      "epoch": 2.2332268370607027,
+      "grad_norm": 0.5564191937446594,
+      "learning_rate": 1.838887489710452e-06,
+      "loss": 0.5167,
+      "step": 233
+    },
+    {
+      "epoch": 2.242811501597444,
+      "grad_norm": 0.544456422328949,
+      "learning_rate": 1.7956219300748796e-06,
+      "loss": 0.5106,
+      "step": 234
+    },
+    {
+      "epoch": 2.252396166134185,
+      "grad_norm": 0.49560070037841797,
+      "learning_rate": 1.7527597583490825e-06,
+      "loss": 0.4985,
+      "step": 235
+    },
+    {
+      "epoch": 2.2619808306709266,
+      "grad_norm": 0.5730255246162415,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.4861,
+      "step": 236
+    },
+    {
+      "epoch": 2.2715654952076676,
+      "grad_norm": 0.5446303486824036,
+      "learning_rate": 1.6682671102399806e-06,
+      "loss": 0.5204,
+      "step": 237
+    },
+    {
+      "epoch": 2.281150159744409,
+      "grad_norm": 0.5347279906272888,
+      "learning_rate": 1.6266472703396286e-06,
+      "loss": 0.514,
+      "step": 238
+    },
+    {
+      "epoch": 2.29073482428115,
+      "grad_norm": 0.5006322860717773,
+      "learning_rate": 1.5854520899759656e-06,
+      "loss": 0.5042,
+      "step": 239
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 0.5397834777832031,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.5044,
+      "step": 240
+    },
+    {
+      "epoch": 2.3099041533546325,
+      "grad_norm": 0.5032399892807007,
+      "learning_rate": 1.5043563974137132e-06,
+      "loss": 0.5072,
+      "step": 241
+    },
+    {
+      "epoch": 2.319488817891374,
+      "grad_norm": 0.47611555457115173,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 2.329073482428115,
+      "grad_norm": 0.5055474042892456,
+      "learning_rate": 1.4250208666766235e-06,
+      "loss": 0.5042,
+      "step": 243
+    },
+    {
+      "epoch": 2.3386581469648564,
+      "grad_norm": 0.5255368947982788,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.5111,
+      "step": 244
+    },
+    {
+      "epoch": 2.3482428115015974,
+      "grad_norm": 0.5098780393600464,
+      "learning_rate": 1.3474854455936126e-06,
+      "loss": 0.515,
+      "step": 245
+    },
+    {
+      "epoch": 2.357827476038339,
+      "grad_norm": 0.4925176501274109,
+      "learning_rate": 1.3094050125632973e-06,
+      "loss": 0.5114,
+      "step": 246
+    },
+    {
+      "epoch": 2.36741214057508,
+      "grad_norm": 0.537067174911499,
+      "learning_rate": 1.2717891755841722e-06,
+      "loss": 0.4797,
+      "step": 247
+    },
+    {
+      "epoch": 2.376996805111821,
+      "grad_norm": 0.4920751750469208,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.4941,
+      "step": 248
+    },
+    {
+      "epoch": 2.3865814696485623,
+      "grad_norm": 0.4458199143409729,
+      "learning_rate": 1.1979701719998454e-06,
+      "loss": 0.5222,
+      "step": 249
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.48658084869384766,
+      "learning_rate": 1.1617762982099446e-06,
+      "loss": 0.518,
+      "step": 250
+    },
+    {
+      "epoch": 2.405750798722045,
+      "grad_norm": 0.5211532115936279,
+      "learning_rate": 1.1260656049319957e-06,
+      "loss": 0.4984,
+      "step": 251
+    },
+    {
+      "epoch": 2.415335463258786,
+      "grad_norm": 0.5080324411392212,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5229,
+      "step": 252
+    },
+    {
+      "epoch": 2.4249201277955272,
+      "grad_norm": 0.5140640735626221,
+      "learning_rate": 1.0561116804955451e-06,
+      "loss": 0.5146,
+      "step": 253
+    },
+    {
+      "epoch": 2.4345047923322682,
+      "grad_norm": 0.48215627670288086,
+      "learning_rate": 1.0218772555910955e-06,
+      "loss": 0.5131,
+      "step": 254
+    },
+    {
+      "epoch": 2.4440894568690097,
+      "grad_norm": 0.5040873289108276,
+      "learning_rate": 9.881436225981107e-07,
+      "loss": 0.4914,
+      "step": 255
+    },
+    {
+      "epoch": 2.4536741214057507,
+      "grad_norm": 0.5259299874305725,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5022,
+      "step": 256
+    },
+    {
+      "epoch": 2.463258785942492,
+      "grad_norm": 0.5273531079292297,
+      "learning_rate": 9.221956552036992e-07,
+      "loss": 0.4945,
+      "step": 257
+    },
+    {
+      "epoch": 2.472843450479233,
+      "grad_norm": 0.49242982268333435,
+      "learning_rate": 8.899896227604509e-07,
+      "loss": 0.4967,
+      "step": 258
+    },
+    {
+      "epoch": 2.4824281150159746,
+      "grad_norm": 0.48913198709487915,
+      "learning_rate": 8.58300985099918e-07,
+      "loss": 0.4912,
+      "step": 259
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 0.4919417202472687,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.4789,
+      "step": 260
+    },
+    {
+      "epoch": 2.501597444089457,
+      "grad_norm": 0.4618432819843292,
+      "learning_rate": 7.964917851773496e-07,
+      "loss": 0.5138,
+      "step": 261
+    },
+    {
+      "epoch": 2.511182108626198,
+      "grad_norm": 0.5181034207344055,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.4869,
+      "step": 262
+    },
+    {
+      "epoch": 2.520766773162939,
+      "grad_norm": 0.4994615912437439,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.487,
+      "step": 263
+    },
+    {
+      "epoch": 2.5303514376996805,
+      "grad_norm": 0.4796070158481598,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.5115,
+      "step": 264
+    },
+    {
+      "epoch": 2.539936102236422,
+      "grad_norm": 0.4891747832298279,
+      "learning_rate": 6.792532212817271e-07,
+      "loss": 0.5304,
+      "step": 265
+    },
+    {
+      "epoch": 2.549520766773163,
+      "grad_norm": 0.4947539269924164,
+      "learning_rate": 6.512943342215234e-07,
+      "loss": 0.5268,
+      "step": 266
+    },
+    {
+      "epoch": 2.559105431309904,
+      "grad_norm": 0.48322218656539917,
+      "learning_rate": 6.238828904562316e-07,
+      "loss": 0.4955,
+      "step": 267
+    },
+    {
+      "epoch": 2.5686900958466454,
+      "grad_norm": 0.4670308232307434,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.5186,
+      "step": 268
+    },
+    {
+      "epoch": 2.5782747603833864,
+      "grad_norm": 0.5252702236175537,
+      "learning_rate": 5.707160663821009e-07,
+      "loss": 0.4998,
+      "step": 269
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 0.4638543426990509,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.4974,
+      "step": 270
+    },
+    {
+      "epoch": 2.597444089456869,
+      "grad_norm": 0.5163476467132568,
+      "learning_rate": 5.197795201563744e-07,
+      "loss": 0.4794,
+      "step": 271
+    },
+    {
+      "epoch": 2.6070287539936103,
+      "grad_norm": 0.4854280948638916,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.4974,
+      "step": 272
+    },
+    {
+      "epoch": 2.6166134185303513,
+      "grad_norm": 0.4789203107357025,
+      "learning_rate": 4.710988998640298e-07,
+      "loss": 0.4988,
+      "step": 273
+    },
+    {
+      "epoch": 2.626198083067093,
+      "grad_norm": 0.4644279181957245,
+      "learning_rate": 4.4761226670592074e-07,
+      "loss": 0.512,
+      "step": 274
+    },
+    {
+      "epoch": 2.635782747603834,
+      "grad_norm": 0.5351918935775757,
+      "learning_rate": 4.2469871766340096e-07,
+      "loss": 0.4738,
+      "step": 275
+    },
+    {
+      "epoch": 2.6453674121405752,
+      "grad_norm": 0.48578253388404846,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.5278,
+      "step": 276
+    },
+    {
+      "epoch": 2.6549520766773163,
+      "grad_norm": 0.4682360291481018,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.5055,
+      "step": 277
+    },
+    {
+      "epoch": 2.6645367412140573,
+      "grad_norm": 0.49804800748825073,
+      "learning_rate": 3.5942505740480583e-07,
+      "loss": 0.4815,
+      "step": 278
+    },
+    {
+      "epoch": 2.6741214057507987,
+      "grad_norm": 0.48392346501350403,
+      "learning_rate": 3.3883196305992906e-07,
+      "loss": 0.5133,
+      "step": 279
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 0.4864685535430908,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.5029,
+      "step": 280
+    },
+    {
+      "epoch": 2.693290734824281,
+      "grad_norm": 0.5228228569030762,
+      "learning_rate": 2.9940862715390483e-07,
+      "loss": 0.4995,
+      "step": 281
+    },
+    {
+      "epoch": 2.702875399361022,
+      "grad_norm": 0.4820217192173004,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.5045,
+      "step": 282
+    },
+    {
+      "epoch": 2.7124600638977636,
+      "grad_norm": 0.4983007311820984,
+      "learning_rate": 2.6235218056235633e-07,
+      "loss": 0.49,
+      "step": 283
+    },
+    {
+      "epoch": 2.722044728434505,
+      "grad_norm": 0.48497146368026733,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.4986,
+      "step": 284
+    },
+    {
+      "epoch": 2.731629392971246,
+      "grad_norm": 0.4843176603317261,
+      "learning_rate": 2.276812823220964e-07,
+      "loss": 0.4864,
+      "step": 285
+    },
+    {
+      "epoch": 2.741214057507987,
+      "grad_norm": 0.4612375795841217,
+      "learning_rate": 2.1124591657534776e-07,
+      "loss": 0.5138,
+      "step": 286
+    },
+    {
+      "epoch": 2.7507987220447285,
+      "grad_norm": 0.4730239808559418,
+      "learning_rate": 1.9541339027450256e-07,
+      "loss": 0.498,
+      "step": 287
+    },
+    {
+      "epoch": 2.7603833865814695,
+      "grad_norm": 0.47294536232948303,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.517,
+      "step": 288
+    },
+    {
+      "epoch": 2.769968051118211,
+      "grad_norm": 0.490991473197937,
+      "learning_rate": 1.6556475227496816e-07,
+      "loss": 0.5219,
+      "step": 289
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 0.5257830619812012,
+      "learning_rate": 1.5155239811656562e-07,
+      "loss": 0.5048,
+      "step": 290
+    },
+    {
+      "epoch": 2.7891373801916934,
+      "grad_norm": 0.46119868755340576,
+      "learning_rate": 1.3815039801161723e-07,
+      "loss": 0.5258,
+      "step": 291
+    },
+    {
+      "epoch": 2.7987220447284344,
+      "grad_norm": 0.5001710653305054,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.5056,
+      "step": 292
+    },
+    {
+      "epoch": 2.8083067092651754,
+      "grad_norm": 0.45364686846733093,
+      "learning_rate": 1.1318413143740436e-07,
+      "loss": 0.525,
+      "step": 293
+    },
+    {
+      "epoch": 2.817891373801917,
+      "grad_norm": 0.511743426322937,
+      "learning_rate": 1.0162300788382263e-07,
+      "loss": 0.5028,
+      "step": 294
+    },
+    {
+      "epoch": 2.8274760383386583,
+      "grad_norm": 0.48278823494911194,
+      "learning_rate": 9.0678523819408e-08,
+      "loss": 0.5026,
+      "step": 295
+    },
+    {
+      "epoch": 2.8370607028753994,
+      "grad_norm": 0.4801782965660095,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.5173,
+      "step": 296
+    },
+    {
+      "epoch": 2.8466453674121404,
+      "grad_norm": 0.4829420745372772,
+      "learning_rate": 7.064490740882057e-08,
+      "loss": 0.5111,
+      "step": 297
+    },
+    {
+      "epoch": 2.856230031948882,
+      "grad_norm": 0.49983468651771545,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.4989,
+      "step": 298
+    },
+    {
+      "epoch": 2.8658146964856233,
+      "grad_norm": 0.4892556667327881,
+      "learning_rate": 5.3093369734816824e-08,
+      "loss": 0.5111,
+      "step": 299
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 0.5195422172546387,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.4896,
+      "step": 300
+    },
+    {
+      "epoch": 2.8849840255591053,
+      "grad_norm": 0.4906642436981201,
+      "learning_rate": 3.8032748525179684e-08,
+      "loss": 0.5274,
+      "step": 301
+    },
+    {
+      "epoch": 2.8945686900958467,
+      "grad_norm": 0.499541699886322,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.4915,
+      "step": 302
+    },
+    {
+      "epoch": 2.9041533546325877,
+      "grad_norm": 0.48538094758987427,
+      "learning_rate": 2.547062725623828e-08,
+      "loss": 0.5059,
+      "step": 303
+    },
+    {
+      "epoch": 2.913738019169329,
+      "grad_norm": 0.4701797366142273,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.4837,
+      "step": 304
+    },
+    {
+      "epoch": 2.92332268370607,
+      "grad_norm": 0.5019702315330505,
+      "learning_rate": 1.541333133436018e-08,
+      "loss": 0.5137,
+      "step": 305
+    },
+    {
+      "epoch": 2.9329073482428116,
+      "grad_norm": 0.5122066736221313,
+      "learning_rate": 1.132562476771959e-08,
+      "loss": 0.5035,
+      "step": 306
+    },
+    {
+      "epoch": 2.9424920127795526,
+      "grad_norm": 0.4683079719543457,
+      "learning_rate": 7.865924910916977e-09,
+      "loss": 0.5052,
+      "step": 307
+    },
+    {
+      "epoch": 2.952076677316294,
+      "grad_norm": 0.48147568106651306,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.4787,
+      "step": 308
+    },
+    {
+      "epoch": 2.961661341853035,
+      "grad_norm": 0.4846435487270355,
+      "learning_rate": 2.8322083323334417e-09,
+      "loss": 0.498,
+      "step": 309
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 0.4767644703388214,
+      "learning_rate": 1.2588252874673469e-09,
+      "loss": 0.5103,
+      "step": 310
+    },
+    {
+      "epoch": 2.9808306709265175,
+      "grad_norm": 0.48420077562332153,
+      "learning_rate": 3.147162264971471e-10,
+      "loss": 0.4959,
+      "step": 311
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "grad_norm": 0.4982874095439911,
+      "learning_rate": 0.0,
+      "loss": 0.5048,
+      "step": 312
+    },
+    {
+      "epoch": 2.9904153354632586,
+      "step": 312,
+      "total_flos": 2.995131507754271e+17,
+      "train_loss": 0.6095600314438343,
+      "train_runtime": 8590.5636,
+      "train_samples_per_second": 3.492,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "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": 2.995131507754271e+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 sha256:3c52043d9d429aa138e69968121bd9ee440ed712301541edee7fdc731f794518
+size 7608