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": 2.980891719745223,
+    "total_flos": 9.25222495000658e+16,
+    "train_loss": 0.7492156773805618,
+    "train_runtime": 2914.5015,
+    "train_samples_per_second": 5.147,
+    "train_steps_per_second": 0.054
+}

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:acff8d14f3163c62c0fcd98b0b67c8b84f4b67f3f5c2f722b8ea6cdf53bc9e00
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7295212a5aa810ae4042e309bfd829974015720a12e891b67749e1274a0b228c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0cd521936a7791a328fe2b3bf3848859dfcffd46aa8d56788e7b0f53fa1e5f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b3b9ce834aef879226fb4596ef9a9b0918e4f75a2eb109094813d7bbc554f4
+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": 2.980891719745223,
+    "total_flos": 9.25222495000658e+16,
+    "train_loss": 0.7492156773805618,
+    "train_runtime": 2914.5015,
+    "train_samples_per_second": 5.147,
+    "train_steps_per_second": 0.054
+}

trainer_log.jsonl

@@ -0,0 +1,157 @@
+{"current_steps": 1, "total_steps": 156, "loss": 1.2512, "lr": 6.25e-07, "epoch": 0.01910828025477707, "percentage": 0.64, "elapsed_time": "0:00:28", "remaining_time": "1:13:18"}
+{"current_steps": 2, "total_steps": 156, "loss": 1.2318, "lr": 1.25e-06, "epoch": 0.03821656050955414, "percentage": 1.28, "elapsed_time": "0:00:46", "remaining_time": "0:59:38"}
+{"current_steps": 3, "total_steps": 156, "loss": 1.2433, "lr": 1.8750000000000003e-06, "epoch": 0.05732484076433121, "percentage": 1.92, "elapsed_time": "0:01:06", "remaining_time": "0:56:17"}
+{"current_steps": 4, "total_steps": 156, "loss": 1.2361, "lr": 2.5e-06, "epoch": 0.07643312101910828, "percentage": 2.56, "elapsed_time": "0:01:20", "remaining_time": "0:51:05"}
+{"current_steps": 5, "total_steps": 156, "loss": 1.2129, "lr": 3.125e-06, "epoch": 0.09554140127388536, "percentage": 3.21, "elapsed_time": "0:01:39", "remaining_time": "0:50:05"}
+{"current_steps": 6, "total_steps": 156, "loss": 1.1534, "lr": 3.7500000000000005e-06, "epoch": 0.11464968152866242, "percentage": 3.85, "elapsed_time": "0:01:57", "remaining_time": "0:48:56"}
+{"current_steps": 7, "total_steps": 156, "loss": 1.1355, "lr": 4.3750000000000005e-06, "epoch": 0.1337579617834395, "percentage": 4.49, "elapsed_time": "0:02:12", "remaining_time": "0:47:10"}
+{"current_steps": 8, "total_steps": 156, "loss": 1.0924, "lr": 5e-06, "epoch": 0.15286624203821655, "percentage": 5.13, "elapsed_time": "0:02:32", "remaining_time": "0:46:57"}
+{"current_steps": 9, "total_steps": 156, "loss": 1.0943, "lr": 5.625e-06, "epoch": 0.17197452229299362, "percentage": 5.77, "elapsed_time": "0:02:46", "remaining_time": "0:45:22"}
+{"current_steps": 10, "total_steps": 156, "loss": 1.0389, "lr": 6.25e-06, "epoch": 0.1910828025477707, "percentage": 6.41, "elapsed_time": "0:03:12", "remaining_time": "0:46:48"}
+{"current_steps": 11, "total_steps": 156, "loss": 1.0224, "lr": 6.875e-06, "epoch": 0.21019108280254778, "percentage": 7.05, "elapsed_time": "0:03:26", "remaining_time": "0:45:26"}
+{"current_steps": 12, "total_steps": 156, "loss": 1.0536, "lr": 7.500000000000001e-06, "epoch": 0.22929936305732485, "percentage": 7.69, "elapsed_time": "0:03:43", "remaining_time": "0:44:39"}
+{"current_steps": 13, "total_steps": 156, "loss": 1.0143, "lr": 8.125000000000001e-06, "epoch": 0.2484076433121019, "percentage": 8.33, "elapsed_time": "0:04:04", "remaining_time": "0:44:47"}
+{"current_steps": 14, "total_steps": 156, "loss": 0.9741, "lr": 8.750000000000001e-06, "epoch": 0.267515923566879, "percentage": 8.97, "elapsed_time": "0:04:21", "remaining_time": "0:44:15"}
+{"current_steps": 15, "total_steps": 156, "loss": 0.9494, "lr": 9.375000000000001e-06, "epoch": 0.28662420382165604, "percentage": 9.62, "elapsed_time": "0:04:34", "remaining_time": "0:43:02"}
+{"current_steps": 16, "total_steps": 156, "loss": 0.9275, "lr": 1e-05, "epoch": 0.3057324840764331, "percentage": 10.26, "elapsed_time": "0:05:01", "remaining_time": "0:43:55"}
+{"current_steps": 17, "total_steps": 156, "loss": 0.9178, "lr": 9.998741174712534e-06, "epoch": 0.3248407643312102, "percentage": 10.9, "elapsed_time": "0:05:24", "remaining_time": "0:44:09"}
+{"current_steps": 18, "total_steps": 156, "loss": 0.8882, "lr": 9.994965332706574e-06, "epoch": 0.34394904458598724, "percentage": 11.54, "elapsed_time": "0:05:42", "remaining_time": "0:43:43"}
+{"current_steps": 19, "total_steps": 156, "loss": 0.8857, "lr": 9.98867437523228e-06, "epoch": 0.3630573248407643, "percentage": 12.18, "elapsed_time": "0:05:58", "remaining_time": "0:43:06"}
+{"current_steps": 20, "total_steps": 156, "loss": 0.9158, "lr": 9.979871469976197e-06, "epoch": 0.3821656050955414, "percentage": 12.82, "elapsed_time": "0:06:14", "remaining_time": "0:42:28"}
+{"current_steps": 21, "total_steps": 156, "loss": 0.9254, "lr": 9.968561049466214e-06, "epoch": 0.4012738853503185, "percentage": 13.46, "elapsed_time": "0:06:35", "remaining_time": "0:42:21"}
+{"current_steps": 22, "total_steps": 156, "loss": 0.9127, "lr": 9.954748808839675e-06, "epoch": 0.42038216560509556, "percentage": 14.1, "elapsed_time": "0:06:52", "remaining_time": "0:41:51"}
+{"current_steps": 23, "total_steps": 156, "loss": 0.8819, "lr": 9.938441702975689e-06, "epoch": 0.4394904458598726, "percentage": 14.74, "elapsed_time": "0:07:08", "remaining_time": "0:41:19"}
+{"current_steps": 24, "total_steps": 156, "loss": 0.8983, "lr": 9.91964794299315e-06, "epoch": 0.4585987261146497, "percentage": 15.38, "elapsed_time": "0:07:33", "remaining_time": "0:41:32"}
+{"current_steps": 25, "total_steps": 156, "loss": 0.9112, "lr": 9.898376992116179e-06, "epoch": 0.47770700636942676, "percentage": 16.03, "elapsed_time": "0:07:51", "remaining_time": "0:41:10"}
+{"current_steps": 26, "total_steps": 156, "loss": 0.8848, "lr": 9.874639560909118e-06, "epoch": 0.4968152866242038, "percentage": 16.67, "elapsed_time": "0:08:05", "remaining_time": "0:40:27"}
+{"current_steps": 27, "total_steps": 156, "loss": 0.8977, "lr": 9.848447601883436e-06, "epoch": 0.5159235668789809, "percentage": 17.31, "elapsed_time": "0:08:20", "remaining_time": "0:39:53"}
+{"current_steps": 28, "total_steps": 156, "loss": 0.8912, "lr": 9.819814303479268e-06, "epoch": 0.535031847133758, "percentage": 17.95, "elapsed_time": "0:08:38", "remaining_time": "0:39:28"}
+{"current_steps": 29, "total_steps": 156, "loss": 0.8851, "lr": 9.788754083424654e-06, "epoch": 0.554140127388535, "percentage": 18.59, "elapsed_time": "0:08:59", "remaining_time": "0:39:23"}
+{"current_steps": 30, "total_steps": 156, "loss": 0.8716, "lr": 9.755282581475769e-06, "epoch": 0.5732484076433121, "percentage": 19.23, "elapsed_time": "0:09:16", "remaining_time": "0:38:55"}
+{"current_steps": 31, "total_steps": 156, "loss": 0.8603, "lr": 9.719416651541839e-06, "epoch": 0.5923566878980892, "percentage": 19.87, "elapsed_time": "0:09:37", "remaining_time": "0:38:48"}
+{"current_steps": 32, "total_steps": 156, "loss": 0.8885, "lr": 9.681174353198687e-06, "epoch": 0.6114649681528662, "percentage": 20.51, "elapsed_time": "0:09:52", "remaining_time": "0:38:16"}
+{"current_steps": 33, "total_steps": 156, "loss": 0.8426, "lr": 9.640574942595195e-06, "epoch": 0.6305732484076433, "percentage": 21.15, "elapsed_time": "0:10:11", "remaining_time": "0:37:58"}
+{"current_steps": 34, "total_steps": 156, "loss": 0.8413, "lr": 9.597638862757255e-06, "epoch": 0.6496815286624203, "percentage": 21.79, "elapsed_time": "0:10:25", "remaining_time": "0:37:25"}
+{"current_steps": 35, "total_steps": 156, "loss": 0.8398, "lr": 9.552387733294081e-06, "epoch": 0.6687898089171974, "percentage": 22.44, "elapsed_time": "0:10:46", "remaining_time": "0:37:14"}
+{"current_steps": 36, "total_steps": 156, "loss": 0.8738, "lr": 9.504844339512096e-06, "epoch": 0.6878980891719745, "percentage": 23.08, "elapsed_time": "0:11:07", "remaining_time": "0:37:06"}
+{"current_steps": 37, "total_steps": 156, "loss": 0.8632, "lr": 9.45503262094184e-06, "epoch": 0.7070063694267515, "percentage": 23.72, "elapsed_time": "0:11:23", "remaining_time": "0:36:38"}
+{"current_steps": 38, "total_steps": 156, "loss": 0.832, "lr": 9.40297765928369e-06, "epoch": 0.7261146496815286, "percentage": 24.36, "elapsed_time": "0:11:41", "remaining_time": "0:36:18"}
+{"current_steps": 39, "total_steps": 156, "loss": 0.8392, "lr": 9.348705665778479e-06, "epoch": 0.7452229299363057, "percentage": 25.0, "elapsed_time": "0:12:02", "remaining_time": "0:36:08"}
+{"current_steps": 40, "total_steps": 156, "loss": 0.8553, "lr": 9.292243968009332e-06, "epoch": 0.7643312101910829, "percentage": 25.64, "elapsed_time": "0:12:20", "remaining_time": "0:35:48"}
+{"current_steps": 41, "total_steps": 156, "loss": 0.8169, "lr": 9.233620996141421e-06, "epoch": 0.7834394904458599, "percentage": 26.28, "elapsed_time": "0:12:41", "remaining_time": "0:35:35"}
+{"current_steps": 42, "total_steps": 156, "loss": 0.8268, "lr": 9.172866268606514e-06, "epoch": 0.802547770700637, "percentage": 26.92, "elapsed_time": "0:12:57", "remaining_time": "0:35:09"}
+{"current_steps": 43, "total_steps": 156, "loss": 0.8662, "lr": 9.110010377239552e-06, "epoch": 0.821656050955414, "percentage": 27.56, "elapsed_time": "0:13:11", "remaining_time": "0:34:40"}
+{"current_steps": 44, "total_steps": 156, "loss": 0.8184, "lr": 9.045084971874738e-06, "epoch": 0.8407643312101911, "percentage": 28.21, "elapsed_time": "0:13:28", "remaining_time": "0:34:18"}
+{"current_steps": 45, "total_steps": 156, "loss": 0.8376, "lr": 8.978122744408905e-06, "epoch": 0.8598726114649682, "percentage": 28.85, "elapsed_time": "0:13:48", "remaining_time": "0:34:04"}
+{"current_steps": 46, "total_steps": 156, "loss": 0.8462, "lr": 8.90915741234015e-06, "epoch": 0.8789808917197452, "percentage": 29.49, "elapsed_time": "0:14:09", "remaining_time": "0:33:51"}
+{"current_steps": 47, "total_steps": 156, "loss": 0.8462, "lr": 8.838223701790057e-06, "epoch": 0.8980891719745223, "percentage": 30.13, "elapsed_time": "0:14:30", "remaining_time": "0:33:38"}
+{"current_steps": 48, "total_steps": 156, "loss": 0.8161, "lr": 8.765357330018056e-06, "epoch": 0.9171974522292994, "percentage": 30.77, "elapsed_time": "0:14:47", "remaining_time": "0:33:17"}
+{"current_steps": 49, "total_steps": 156, "loss": 0.8612, "lr": 8.690594987436705e-06, "epoch": 0.9363057324840764, "percentage": 31.41, "elapsed_time": "0:15:02", "remaining_time": "0:32:51"}
+{"current_steps": 50, "total_steps": 156, "loss": 0.8474, "lr": 8.613974319136959e-06, "epoch": 0.9554140127388535, "percentage": 32.05, "elapsed_time": "0:15:21", "remaining_time": "0:32:34"}
+{"current_steps": 51, "total_steps": 156, "loss": 0.8366, "lr": 8.535533905932739e-06, "epoch": 0.9745222929936306, "percentage": 32.69, "elapsed_time": "0:15:38", "remaining_time": "0:32:12"}
+{"current_steps": 52, "total_steps": 156, "loss": 0.869, "lr": 8.455313244934324e-06, "epoch": 0.9936305732484076, "percentage": 33.33, "elapsed_time": "0:15:55", "remaining_time": "0:31:50"}
+{"current_steps": 53, "total_steps": 156, "loss": 0.7792, "lr": 8.373352729660373e-06, "epoch": 1.0127388535031847, "percentage": 33.97, "elapsed_time": "0:16:51", "remaining_time": "0:32:45"}
+{"current_steps": 54, "total_steps": 156, "loss": 0.7468, "lr": 8.289693629698564e-06, "epoch": 1.0318471337579618, "percentage": 34.62, "elapsed_time": "0:17:13", "remaining_time": "0:32:31"}
+{"current_steps": 55, "total_steps": 156, "loss": 0.7348, "lr": 8.204378069925121e-06, "epoch": 1.0509554140127388, "percentage": 35.26, "elapsed_time": "0:17:33", "remaining_time": "0:32:14"}
+{"current_steps": 56, "total_steps": 156, "loss": 0.7509, "lr": 8.117449009293668e-06, "epoch": 1.070063694267516, "percentage": 35.9, "elapsed_time": "0:17:58", "remaining_time": "0:32:05"}
+{"current_steps": 57, "total_steps": 156, "loss": 0.6954, "lr": 8.0289502192041e-06, "epoch": 1.089171974522293, "percentage": 36.54, "elapsed_time": "0:18:19", "remaining_time": "0:31:49"}
+{"current_steps": 58, "total_steps": 156, "loss": 0.7201, "lr": 7.938926261462366e-06, "epoch": 1.10828025477707, "percentage": 37.18, "elapsed_time": "0:18:34", "remaining_time": "0:31:23"}
+{"current_steps": 59, "total_steps": 156, "loss": 0.7429, "lr": 7.84742246584226e-06, "epoch": 1.127388535031847, "percentage": 37.82, "elapsed_time": "0:18:45", "remaining_time": "0:30:51"}
+{"current_steps": 60, "total_steps": 156, "loss": 0.7031, "lr": 7.754484907260513e-06, "epoch": 1.1464968152866242, "percentage": 38.46, "elapsed_time": "0:18:59", "remaining_time": "0:30:23"}
+{"current_steps": 61, "total_steps": 156, "loss": 0.7004, "lr": 7.660160382576683e-06, "epoch": 1.1656050955414012, "percentage": 39.1, "elapsed_time": "0:19:20", "remaining_time": "0:30:06"}
+{"current_steps": 62, "total_steps": 156, "loss": 0.7189, "lr": 7.564496387029532e-06, "epoch": 1.1847133757961783, "percentage": 39.74, "elapsed_time": "0:19:34", "remaining_time": "0:29:40"}
+{"current_steps": 63, "total_steps": 156, "loss": 0.7075, "lr": 7.467541090321735e-06, "epoch": 1.2038216560509554, "percentage": 40.38, "elapsed_time": "0:19:49", "remaining_time": "0:29:16"}
+{"current_steps": 64, "total_steps": 156, "loss": 0.7137, "lr": 7.369343312364994e-06, "epoch": 1.2229299363057324, "percentage": 41.03, "elapsed_time": "0:20:06", "remaining_time": "0:28:54"}
+{"current_steps": 65, "total_steps": 156, "loss": 0.7145, "lr": 7.269952498697734e-06, "epoch": 1.2420382165605095, "percentage": 41.67, "elapsed_time": "0:20:27", "remaining_time": "0:28:38"}
+{"current_steps": 66, "total_steps": 156, "loss": 0.7113, "lr": 7.169418695587791e-06, "epoch": 1.2611464968152866, "percentage": 42.31, "elapsed_time": "0:20:40", "remaining_time": "0:28:11"}
+{"current_steps": 67, "total_steps": 156, "loss": 0.7053, "lr": 7.067792524832604e-06, "epoch": 1.2802547770700636, "percentage": 42.95, "elapsed_time": "0:21:06", "remaining_time": "0:28:02"}
+{"current_steps": 68, "total_steps": 156, "loss": 0.7037, "lr": 6.965125158269619e-06, "epoch": 1.2993630573248407, "percentage": 43.59, "elapsed_time": "0:21:18", "remaining_time": "0:27:34"}
+{"current_steps": 69, "total_steps": 156, "loss": 0.7267, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:21:36", "remaining_time": "0:27:15"}
+{"current_steps": 70, "total_steps": 156, "loss": 0.7474, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:22:01", "remaining_time": "0:27:03"}
+{"current_steps": 71, "total_steps": 156, "loss": 0.7328, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:22:15", "remaining_time": "0:26:39"}
+{"current_steps": 72, "total_steps": 156, "loss": 0.6917, "lr": 6.545084971874738e-06, "epoch": 1.3757961783439492, "percentage": 46.15, "elapsed_time": "0:22:37", "remaining_time": "0:26:24"}
+{"current_steps": 73, "total_steps": 156, "loss": 0.6991, "lr": 6.437996637160086e-06, "epoch": 1.394904458598726, "percentage": 46.79, "elapsed_time": "0:22:52", "remaining_time": "0:26:00"}
+{"current_steps": 74, "total_steps": 156, "loss": 0.6909, "lr": 6.330184227833376e-06, "epoch": 1.4140127388535033, "percentage": 47.44, "elapsed_time": "0:23:07", "remaining_time": "0:25:37"}
+{"current_steps": 75, "total_steps": 156, "loss": 0.7098, "lr": 6.2217020306894705e-06, "epoch": 1.4331210191082802, "percentage": 48.08, "elapsed_time": "0:23:27", "remaining_time": "0:25:20"}
+{"current_steps": 76, "total_steps": 156, "loss": 0.6726, "lr": 6.112604669781572e-06, "epoch": 1.4522292993630574, "percentage": 48.72, "elapsed_time": "0:23:51", "remaining_time": "0:25:07"}
+{"current_steps": 77, "total_steps": 156, "loss": 0.7012, "lr": 6.002947078916365e-06, "epoch": 1.4713375796178343, "percentage": 49.36, "elapsed_time": "0:24:10", "remaining_time": "0:24:48"}
+{"current_steps": 78, "total_steps": 156, "loss": 0.6638, "lr": 5.892784473993184e-06, "epoch": 1.4904458598726116, "percentage": 50.0, "elapsed_time": "0:24:25", "remaining_time": "0:24:25"}
+{"current_steps": 79, "total_steps": 156, "loss": 0.6997, "lr": 5.782172325201155e-06, "epoch": 1.5095541401273884, "percentage": 50.64, "elapsed_time": "0:24:43", "remaining_time": "0:24:06"}
+{"current_steps": 80, "total_steps": 156, "loss": 0.692, "lr": 5.671166329088278e-06, "epoch": 1.5286624203821657, "percentage": 51.28, "elapsed_time": "0:24:56", "remaining_time": "0:23:41"}
+{"current_steps": 81, "total_steps": 156, "loss": 0.6929, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:25:12", "remaining_time": "0:23:20"}
+{"current_steps": 82, "total_steps": 156, "loss": 0.7193, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:25:32", "remaining_time": "0:23:02"}
+{"current_steps": 83, "total_steps": 156, "loss": 0.7338, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:25:50", "remaining_time": "0:22:43"}
+{"current_steps": 84, "total_steps": 156, "loss": 0.7025, "lr": 5.224324151752575e-06, "epoch": 1.605095541401274, "percentage": 53.85, "elapsed_time": "0:26:03", "remaining_time": "0:22:20"}
+{"current_steps": 85, "total_steps": 156, "loss": 0.7052, "lr": 5.112190321479026e-06, "epoch": 1.6242038216560508, "percentage": 54.49, "elapsed_time": "0:26:18", "remaining_time": "0:21:58"}
+{"current_steps": 86, "total_steps": 156, "loss": 0.6931, "lr": 5e-06, "epoch": 1.643312101910828, "percentage": 55.13, "elapsed_time": "0:26:38", "remaining_time": "0:21:40"}
+{"current_steps": 87, "total_steps": 156, "loss": 0.6833, "lr": 4.887809678520976e-06, "epoch": 1.662420382165605, "percentage": 55.77, "elapsed_time": "0:26:50", "remaining_time": "0:21:17"}
+{"current_steps": 88, "total_steps": 156, "loss": 0.7073, "lr": 4.775675848247427e-06, "epoch": 1.6815286624203822, "percentage": 56.41, "elapsed_time": "0:27:05", "remaining_time": "0:20:55"}
+{"current_steps": 89, "total_steps": 156, "loss": 0.7184, "lr": 4.663654971939802e-06, "epoch": 1.700636942675159, "percentage": 57.05, "elapsed_time": "0:27:22", "remaining_time": "0:20:36"}
+{"current_steps": 90, "total_steps": 156, "loss": 0.7035, "lr": 4.551803455482833e-06, "epoch": 1.7197452229299364, "percentage": 57.69, "elapsed_time": "0:27:42", "remaining_time": "0:20:18"}
+{"current_steps": 91, "total_steps": 156, "loss": 0.6988, "lr": 4.4401776194834615e-06, "epoch": 1.7388535031847132, "percentage": 58.33, "elapsed_time": "0:28:07", "remaining_time": "0:20:05"}
+{"current_steps": 92, "total_steps": 156, "loss": 0.7121, "lr": 4.3288336709117246e-06, "epoch": 1.7579617834394905, "percentage": 58.97, "elapsed_time": "0:28:25", "remaining_time": "0:19:46"}
+{"current_steps": 93, "total_steps": 156, "loss": 0.689, "lr": 4.217827674798845e-06, "epoch": 1.7770700636942676, "percentage": 59.62, "elapsed_time": "0:28:44", "remaining_time": "0:19:28"}
+{"current_steps": 94, "total_steps": 156, "loss": 0.6857, "lr": 4.107215526006818e-06, "epoch": 1.7961783439490446, "percentage": 60.26, "elapsed_time": "0:29:01", "remaining_time": "0:19:08"}
+{"current_steps": 95, "total_steps": 156, "loss": 0.6992, "lr": 3.997052921083637e-06, "epoch": 1.8152866242038217, "percentage": 60.9, "elapsed_time": "0:29:16", "remaining_time": "0:18:47"}
+{"current_steps": 96, "total_steps": 156, "loss": 0.6848, "lr": 3.887395330218429e-06, "epoch": 1.8343949044585988, "percentage": 61.54, "elapsed_time": "0:29:37", "remaining_time": "0:18:31"}
+{"current_steps": 97, "total_steps": 156, "loss": 0.6604, "lr": 3.778297969310529e-06, "epoch": 1.8535031847133758, "percentage": 62.18, "elapsed_time": "0:29:55", "remaining_time": "0:18:12"}
+{"current_steps": 98, "total_steps": 156, "loss": 0.6961, "lr": 3.669815772166625e-06, "epoch": 1.872611464968153, "percentage": 62.82, "elapsed_time": "0:30:07", "remaining_time": "0:17:49"}
+{"current_steps": 99, "total_steps": 156, "loss": 0.71, "lr": 3.562003362839914e-06, "epoch": 1.89171974522293, "percentage": 63.46, "elapsed_time": "0:30:27", "remaining_time": "0:17:31"}
+{"current_steps": 100, "total_steps": 156, "loss": 0.6946, "lr": 3.4549150281252635e-06, "epoch": 1.910828025477707, "percentage": 64.1, "elapsed_time": "0:30:40", "remaining_time": "0:17:10"}
+{"current_steps": 101, "total_steps": 156, "loss": 0.6786, "lr": 3.3486046902241663e-06, "epoch": 1.929936305732484, "percentage": 64.74, "elapsed_time": "0:31:02", "remaining_time": "0:16:54"}
+{"current_steps": 102, "total_steps": 156, "loss": 0.699, "lr": 3.2431258795932863e-06, "epoch": 1.9490445859872612, "percentage": 65.38, "elapsed_time": "0:31:20", "remaining_time": "0:16:35"}
+{"current_steps": 103, "total_steps": 156, "loss": 0.7014, "lr": 3.1385317079902743e-06, "epoch": 1.9681528662420382, "percentage": 66.03, "elapsed_time": "0:31:40", "remaining_time": "0:16:17"}
+{"current_steps": 104, "total_steps": 156, "loss": 0.6903, "lr": 3.0348748417303826e-06, "epoch": 1.9872611464968153, "percentage": 66.67, "elapsed_time": "0:31:54", "remaining_time": "0:15:57"}
+{"current_steps": 105, "total_steps": 156, "loss": 0.6627, "lr": 2.932207475167398e-06, "epoch": 2.0063694267515926, "percentage": 67.31, "elapsed_time": "0:32:41", "remaining_time": "0:15:52"}
+{"current_steps": 106, "total_steps": 156, "loss": 0.6365, "lr": 2.83058130441221e-06, "epoch": 2.0254777070063694, "percentage": 67.95, "elapsed_time": "0:32:57", "remaining_time": "0:15:32"}
+{"current_steps": 107, "total_steps": 156, "loss": 0.6299, "lr": 2.7300475013022666e-06, "epoch": 2.0445859872611467, "percentage": 68.59, "elapsed_time": "0:33:10", "remaining_time": "0:15:11"}
+{"current_steps": 108, "total_steps": 156, "loss": 0.6289, "lr": 2.6306566876350072e-06, "epoch": 2.0636942675159236, "percentage": 69.23, "elapsed_time": "0:33:28", "remaining_time": "0:14:52"}
+{"current_steps": 109, "total_steps": 156, "loss": 0.6208, "lr": 2.532458909678266e-06, "epoch": 2.082802547770701, "percentage": 69.87, "elapsed_time": "0:33:48", "remaining_time": "0:14:34"}
+{"current_steps": 110, "total_steps": 156, "loss": 0.6027, "lr": 2.43550361297047e-06, "epoch": 2.1019108280254777, "percentage": 70.51, "elapsed_time": "0:34:07", "remaining_time": "0:14:16"}
+{"current_steps": 111, "total_steps": 156, "loss": 0.6021, "lr": 2.339839617423318e-06, "epoch": 2.121019108280255, "percentage": 71.15, "elapsed_time": "0:34:29", "remaining_time": "0:13:58"}
+{"current_steps": 112, "total_steps": 156, "loss": 0.6031, "lr": 2.245515092739488e-06, "epoch": 2.140127388535032, "percentage": 71.79, "elapsed_time": "0:34:41", "remaining_time": "0:13:37"}
+{"current_steps": 113, "total_steps": 156, "loss": 0.6343, "lr": 2.1525775341577404e-06, "epoch": 2.159235668789809, "percentage": 72.44, "elapsed_time": "0:34:57", "remaining_time": "0:13:18"}
+{"current_steps": 114, "total_steps": 156, "loss": 0.574, "lr": 2.061073738537635e-06, "epoch": 2.178343949044586, "percentage": 73.08, "elapsed_time": "0:35:11", "remaining_time": "0:12:57"}
+{"current_steps": 115, "total_steps": 156, "loss": 0.6022, "lr": 1.971049780795901e-06, "epoch": 2.1974522292993632, "percentage": 73.72, "elapsed_time": "0:35:28", "remaining_time": "0:12:38"}
+{"current_steps": 116, "total_steps": 156, "loss": 0.5928, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:35:44", "remaining_time": "0:12:19"}
+{"current_steps": 117, "total_steps": 156, "loss": 0.607, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:36:04", "remaining_time": "0:12:01"}
+{"current_steps": 118, "total_steps": 156, "loss": 0.606, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:36:25", "remaining_time": "0:11:43"}
+{"current_steps": 119, "total_steps": 156, "loss": 0.6023, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:36:43", "remaining_time": "0:11:25"}
+{"current_steps": 120, "total_steps": 156, "loss": 0.6034, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:36:58", "remaining_time": "0:11:05"}
+{"current_steps": 121, "total_steps": 156, "loss": 0.5776, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:37:19", "remaining_time": "0:10:47"}
+{"current_steps": 122, "total_steps": 156, "loss": 0.5965, "lr": 1.3860256808630429e-06, "epoch": 2.3312101910828025, "percentage": 78.21, "elapsed_time": "0:37:40", "remaining_time": "0:10:30"}
+{"current_steps": 123, "total_steps": 156, "loss": 0.6159, "lr": 1.3094050125632973e-06, "epoch": 2.3503184713375798, "percentage": 78.85, "elapsed_time": "0:37:59", "remaining_time": "0:10:11"}
+{"current_steps": 124, "total_steps": 156, "loss": 0.6122, "lr": 1.234642669981946e-06, "epoch": 2.3694267515923566, "percentage": 79.49, "elapsed_time": "0:38:12", "remaining_time": "0:09:51"}
+{"current_steps": 125, "total_steps": 156, "loss": 0.5929, "lr": 1.1617762982099446e-06, "epoch": 2.388535031847134, "percentage": 80.13, "elapsed_time": "0:38:29", "remaining_time": "0:09:32"}
+{"current_steps": 126, "total_steps": 156, "loss": 0.5706, "lr": 1.0908425876598512e-06, "epoch": 2.4076433121019107, "percentage": 80.77, "elapsed_time": "0:38:53", "remaining_time": "0:09:15"}
+{"current_steps": 127, "total_steps": 156, "loss": 0.6076, "lr": 1.0218772555910955e-06, "epoch": 2.426751592356688, "percentage": 81.41, "elapsed_time": "0:39:13", "remaining_time": "0:08:57"}
+{"current_steps": 128, "total_steps": 156, "loss": 0.6054, "lr": 9.549150281252633e-07, "epoch": 2.445859872611465, "percentage": 82.05, "elapsed_time": "0:39:38", "remaining_time": "0:08:40"}
+{"current_steps": 129, "total_steps": 156, "loss": 0.5989, "lr": 8.899896227604509e-07, "epoch": 2.464968152866242, "percentage": 82.69, "elapsed_time": "0:39:55", "remaining_time": "0:08:21"}
+{"current_steps": 130, "total_steps": 156, "loss": 0.5972, "lr": 8.271337313934869e-07, "epoch": 2.484076433121019, "percentage": 83.33, "elapsed_time": "0:40:12", "remaining_time": "0:08:02"}
+{"current_steps": 131, "total_steps": 156, "loss": 0.5954, "lr": 7.663790038585794e-07, "epoch": 2.5031847133757963, "percentage": 83.97, "elapsed_time": "0:40:31", "remaining_time": "0:07:43"}
+{"current_steps": 132, "total_steps": 156, "loss": 0.6132, "lr": 7.077560319906696e-07, "epoch": 2.522292993630573, "percentage": 84.62, "elapsed_time": "0:40:53", "remaining_time": "0:07:26"}
+{"current_steps": 133, "total_steps": 156, "loss": 0.6082, "lr": 6.512943342215234e-07, "epoch": 2.5414012738853504, "percentage": 85.26, "elapsed_time": "0:41:10", "remaining_time": "0:07:07"}
+{"current_steps": 134, "total_steps": 156, "loss": 0.5908, "lr": 5.9702234071631e-07, "epoch": 2.5605095541401273, "percentage": 85.9, "elapsed_time": "0:41:25", "remaining_time": "0:06:48"}
+{"current_steps": 135, "total_steps": 156, "loss": 0.6164, "lr": 5.449673790581611e-07, "epoch": 2.5796178343949046, "percentage": 86.54, "elapsed_time": "0:41:45", "remaining_time": "0:06:29"}
+{"current_steps": 136, "total_steps": 156, "loss": 0.6123, "lr": 4.951556604879049e-07, "epoch": 2.5987261146496814, "percentage": 87.18, "elapsed_time": "0:42:01", "remaining_time": "0:06:10"}
+{"current_steps": 137, "total_steps": 156, "loss": 0.601, "lr": 4.4761226670592074e-07, "epoch": 2.6178343949044587, "percentage": 87.82, "elapsed_time": "0:42:16", "remaining_time": "0:05:51"}
+{"current_steps": 138, "total_steps": 156, "loss": 0.6018, "lr": 4.0236113724274716e-07, "epoch": 2.6369426751592355, "percentage": 88.46, "elapsed_time": "0:42:33", "remaining_time": "0:05:33"}
+{"current_steps": 139, "total_steps": 156, "loss": 0.6081, "lr": 3.5942505740480583e-07, "epoch": 2.656050955414013, "percentage": 89.1, "elapsed_time": "0:42:50", "remaining_time": "0:05:14"}
+{"current_steps": 140, "total_steps": 156, "loss": 0.5801, "lr": 3.18825646801314e-07, "epoch": 2.6751592356687897, "percentage": 89.74, "elapsed_time": "0:43:10", "remaining_time": "0:04:56"}
+{"current_steps": 141, "total_steps": 156, "loss": 0.581, "lr": 2.8058334845816214e-07, "epoch": 2.694267515923567, "percentage": 90.38, "elapsed_time": "0:43:26", "remaining_time": "0:04:37"}
+{"current_steps": 142, "total_steps": 156, "loss": 0.5949, "lr": 2.447174185242324e-07, "epoch": 2.713375796178344, "percentage": 91.03, "elapsed_time": "0:43:46", "remaining_time": "0:04:18"}
+{"current_steps": 143, "total_steps": 156, "loss": 0.5946, "lr": 2.1124591657534776e-07, "epoch": 2.732484076433121, "percentage": 91.67, "elapsed_time": "0:44:04", "remaining_time": "0:04:00"}
+{"current_steps": 144, "total_steps": 156, "loss": 0.6176, "lr": 1.801856965207338e-07, "epoch": 2.7515923566878984, "percentage": 92.31, "elapsed_time": "0:44:18", "remaining_time": "0:03:41"}
+{"current_steps": 145, "total_steps": 156, "loss": 0.5866, "lr": 1.5155239811656562e-07, "epoch": 2.770700636942675, "percentage": 92.95, "elapsed_time": "0:44:33", "remaining_time": "0:03:22"}
+{"current_steps": 146, "total_steps": 156, "loss": 0.5793, "lr": 1.253604390908819e-07, "epoch": 2.789808917197452, "percentage": 93.59, "elapsed_time": "0:44:47", "remaining_time": "0:03:04"}
+{"current_steps": 147, "total_steps": 156, "loss": 0.5808, "lr": 1.0162300788382263e-07, "epoch": 2.8089171974522293, "percentage": 94.23, "elapsed_time": "0:45:01", "remaining_time": "0:02:45"}
+{"current_steps": 148, "total_steps": 156, "loss": 0.586, "lr": 8.035205700685167e-08, "epoch": 2.8280254777070066, "percentage": 94.87, "elapsed_time": "0:45:19", "remaining_time": "0:02:27"}
+{"current_steps": 149, "total_steps": 156, "loss": 0.5998, "lr": 6.15582970243117e-08, "epoch": 2.8471337579617835, "percentage": 95.51, "elapsed_time": "0:45:35", "remaining_time": "0:02:08"}
+{"current_steps": 150, "total_steps": 156, "loss": 0.5839, "lr": 4.52511911603265e-08, "epoch": 2.8662420382165603, "percentage": 96.15, "elapsed_time": "0:45:53", "remaining_time": "0:01:50"}
+{"current_steps": 151, "total_steps": 156, "loss": 0.6035, "lr": 3.143895053378698e-08, "epoch": 2.8853503184713376, "percentage": 96.79, "elapsed_time": "0:46:15", "remaining_time": "0:01:31"}
+{"current_steps": 152, "total_steps": 156, "loss": 0.6129, "lr": 2.012853002380466e-08, "epoch": 2.904458598726115, "percentage": 97.44, "elapsed_time": "0:46:26", "remaining_time": "0:01:13"}
+{"current_steps": 153, "total_steps": 156, "loss": 0.5796, "lr": 1.132562476771959e-08, "epoch": 2.9235668789808917, "percentage": 98.08, "elapsed_time": "0:46:44", "remaining_time": "0:00:54"}
+{"current_steps": 154, "total_steps": 156, "loss": 0.574, "lr": 5.034667293427053e-09, "epoch": 2.9426751592356686, "percentage": 98.72, "elapsed_time": "0:47:01", "remaining_time": "0:00:36"}
+{"current_steps": 155, "total_steps": 156, "loss": 0.5974, "lr": 1.2588252874673469e-09, "epoch": 2.961783439490446, "percentage": 99.36, "elapsed_time": "0:47:16", "remaining_time": "0:00:18"}
+{"current_steps": 156, "total_steps": 156, "loss": 0.6357, "lr": 0.0, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:47:28", "remaining_time": "0:00:00"}
+{"current_steps": 156, "total_steps": 156, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:48:26", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1134 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.980891719745223,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01910828025477707,
+      "grad_norm": 7.547975540161133,
+      "learning_rate": 6.25e-07,
+      "loss": 1.2512,
+      "step": 1
+    },
+    {
+      "epoch": 0.03821656050955414,
+      "grad_norm": 7.374826431274414,
+      "learning_rate": 1.25e-06,
+      "loss": 1.2318,
+      "step": 2
+    },
+    {
+      "epoch": 0.05732484076433121,
+      "grad_norm": 7.294417381286621,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.2433,
+      "step": 3
+    },
+    {
+      "epoch": 0.07643312101910828,
+      "grad_norm": 7.174262523651123,
+      "learning_rate": 2.5e-06,
+      "loss": 1.2361,
+      "step": 4
+    },
+    {
+      "epoch": 0.09554140127388536,
+      "grad_norm": 6.600234031677246,
+      "learning_rate": 3.125e-06,
+      "loss": 1.2129,
+      "step": 5
+    },
+    {
+      "epoch": 0.11464968152866242,
+      "grad_norm": 4.914210796356201,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.1534,
+      "step": 6
+    },
+    {
+      "epoch": 0.1337579617834395,
+      "grad_norm": 2.7489099502563477,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.1355,
+      "step": 7
+    },
+    {
+      "epoch": 0.15286624203821655,
+      "grad_norm": 2.5778281688690186,
+      "learning_rate": 5e-06,
+      "loss": 1.0924,
+      "step": 8
+    },
+    {
+      "epoch": 0.17197452229299362,
+      "grad_norm": 4.604168891906738,
+      "learning_rate": 5.625e-06,
+      "loss": 1.0943,
+      "step": 9
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 4.840404987335205,
+      "learning_rate": 6.25e-06,
+      "loss": 1.0389,
+      "step": 10
+    },
+    {
+      "epoch": 0.21019108280254778,
+      "grad_norm": 4.339366436004639,
+      "learning_rate": 6.875e-06,
+      "loss": 1.0224,
+      "step": 11
+    },
+    {
+      "epoch": 0.22929936305732485,
+      "grad_norm": 3.31107234954834,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0536,
+      "step": 12
+    },
+    {
+      "epoch": 0.2484076433121019,
+      "grad_norm": 3.4537413120269775,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.0143,
+      "step": 13
+    },
+    {
+      "epoch": 0.267515923566879,
+      "grad_norm": 2.662017345428467,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.9741,
+      "step": 14
+    },
+    {
+      "epoch": 0.28662420382165604,
+      "grad_norm": 2.157660722732544,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.9494,
+      "step": 15
+    },
+    {
+      "epoch": 0.3057324840764331,
+      "grad_norm": 2.1211636066436768,
+      "learning_rate": 1e-05,
+      "loss": 0.9275,
+      "step": 16
+    },
+    {
+      "epoch": 0.3248407643312102,
+      "grad_norm": 1.895501732826233,
+      "learning_rate": 9.998741174712534e-06,
+      "loss": 0.9178,
+      "step": 17
+    },
+    {
+      "epoch": 0.34394904458598724,
+      "grad_norm": 1.7070763111114502,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.8882,
+      "step": 18
+    },
+    {
+      "epoch": 0.3630573248407643,
+      "grad_norm": 1.585816502571106,
+      "learning_rate": 9.98867437523228e-06,
+      "loss": 0.8857,
+      "step": 19
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 1.6084542274475098,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.9158,
+      "step": 20
+    },
+    {
+      "epoch": 0.4012738853503185,
+      "grad_norm": 1.507398009300232,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.9254,
+      "step": 21
+    },
+    {
+      "epoch": 0.42038216560509556,
+      "grad_norm": 0.9898801445960999,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.9127,
+      "step": 22
+    },
+    {
+      "epoch": 0.4394904458598726,
+      "grad_norm": 0.9775479435920715,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.8819,
+      "step": 23
+    },
+    {
+      "epoch": 0.4585987261146497,
+      "grad_norm": 1.253936529159546,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.8983,
+      "step": 24
+    },
+    {
+      "epoch": 0.47770700636942676,
+      "grad_norm": 1.239895224571228,
+      "learning_rate": 9.898376992116179e-06,
+      "loss": 0.9112,
+      "step": 25
+    },
+    {
+      "epoch": 0.4968152866242038,
+      "grad_norm": 0.9475780129432678,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.8848,
+      "step": 26
+    },
+    {
+      "epoch": 0.5159235668789809,
+      "grad_norm": 1.0773193836212158,
+      "learning_rate": 9.848447601883436e-06,
+      "loss": 0.8977,
+      "step": 27
+    },
+    {
+      "epoch": 0.535031847133758,
+      "grad_norm": 1.1501091718673706,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.8912,
+      "step": 28
+    },
+    {
+      "epoch": 0.554140127388535,
+      "grad_norm": 0.9324758648872375,
+      "learning_rate": 9.788754083424654e-06,
+      "loss": 0.8851,
+      "step": 29
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 0.9901764988899231,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.8716,
+      "step": 30
+    },
+    {
+      "epoch": 0.5923566878980892,
+      "grad_norm": 1.0067858695983887,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.8603,
+      "step": 31
+    },
+    {
+      "epoch": 0.6114649681528662,
+      "grad_norm": 0.8844172358512878,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.8885,
+      "step": 32
+    },
+    {
+      "epoch": 0.6305732484076433,
+      "grad_norm": 1.0087534189224243,
+      "learning_rate": 9.640574942595195e-06,
+      "loss": 0.8426,
+      "step": 33
+    },
+    {
+      "epoch": 0.6496815286624203,
+      "grad_norm": 0.8578860759735107,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.8413,
+      "step": 34
+    },
+    {
+      "epoch": 0.6687898089171974,
+      "grad_norm": 0.8848086595535278,
+      "learning_rate": 9.552387733294081e-06,
+      "loss": 0.8398,
+      "step": 35
+    },
+    {
+      "epoch": 0.6878980891719745,
+      "grad_norm": 0.8705900311470032,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.8738,
+      "step": 36
+    },
+    {
+      "epoch": 0.7070063694267515,
+      "grad_norm": 0.8821431398391724,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.8632,
+      "step": 37
+    },
+    {
+      "epoch": 0.7261146496815286,
+      "grad_norm": 0.82889324426651,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.832,
+      "step": 38
+    },
+    {
+      "epoch": 0.7452229299363057,
+      "grad_norm": 0.8025405406951904,
+      "learning_rate": 9.348705665778479e-06,
+      "loss": 0.8392,
+      "step": 39
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 0.8777817487716675,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.8553,
+      "step": 40
+    },
+    {
+      "epoch": 0.7834394904458599,
+      "grad_norm": 0.7455444931983948,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.8169,
+      "step": 41
+    },
+    {
+      "epoch": 0.802547770700637,
+      "grad_norm": 0.7949671745300293,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.8268,
+      "step": 42
+    },
+    {
+      "epoch": 0.821656050955414,
+      "grad_norm": 0.8802870512008667,
+      "learning_rate": 9.110010377239552e-06,
+      "loss": 0.8662,
+      "step": 43
+    },
+    {
+      "epoch": 0.8407643312101911,
+      "grad_norm": 0.8528987765312195,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.8184,
+      "step": 44
+    },
+    {
+      "epoch": 0.8598726114649682,
+      "grad_norm": 0.8329055309295654,
+      "learning_rate": 8.978122744408905e-06,
+      "loss": 0.8376,
+      "step": 45
+    },
+    {
+      "epoch": 0.8789808917197452,
+      "grad_norm": 0.7796112895011902,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.8462,
+      "step": 46
+    },
+    {
+      "epoch": 0.8980891719745223,
+      "grad_norm": 0.8821595311164856,
+      "learning_rate": 8.838223701790057e-06,
+      "loss": 0.8462,
+      "step": 47
+    },
+    {
+      "epoch": 0.9171974522292994,
+      "grad_norm": 0.8074951171875,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.8161,
+      "step": 48
+    },
+    {
+      "epoch": 0.9363057324840764,
+      "grad_norm": 0.8599761724472046,
+      "learning_rate": 8.690594987436705e-06,
+      "loss": 0.8612,
+      "step": 49
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 0.8650784492492676,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.8474,
+      "step": 50
+    },
+    {
+      "epoch": 0.9745222929936306,
+      "grad_norm": 0.7465563416481018,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.8366,
+      "step": 51
+    },
+    {
+      "epoch": 0.9936305732484076,
+      "grad_norm": 0.8294474482536316,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.869,
+      "step": 52
+    },
+    {
+      "epoch": 1.0127388535031847,
+      "grad_norm": 0.8520503044128418,
+      "learning_rate": 8.373352729660373e-06,
+      "loss": 0.7792,
+      "step": 53
+    },
+    {
+      "epoch": 1.0318471337579618,
+      "grad_norm": 0.8020623326301575,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.7468,
+      "step": 54
+    },
+    {
+      "epoch": 1.0509554140127388,
+      "grad_norm": 0.7566718459129333,
+      "learning_rate": 8.204378069925121e-06,
+      "loss": 0.7348,
+      "step": 55
+    },
+    {
+      "epoch": 1.070063694267516,
+      "grad_norm": 0.7379488348960876,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.7509,
+      "step": 56
+    },
+    {
+      "epoch": 1.089171974522293,
+      "grad_norm": 0.6847801208496094,
+      "learning_rate": 8.0289502192041e-06,
+      "loss": 0.6954,
+      "step": 57
+    },
+    {
+      "epoch": 1.10828025477707,
+      "grad_norm": 0.784027636051178,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.7201,
+      "step": 58
+    },
+    {
+      "epoch": 1.127388535031847,
+      "grad_norm": 0.7846508622169495,
+      "learning_rate": 7.84742246584226e-06,
+      "loss": 0.7429,
+      "step": 59
+    },
+    {
+      "epoch": 1.1464968152866242,
+      "grad_norm": 0.764062225818634,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.7031,
+      "step": 60
+    },
+    {
+      "epoch": 1.1656050955414012,
+      "grad_norm": 0.7919678092002869,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.7004,
+      "step": 61
+    },
+    {
+      "epoch": 1.1847133757961783,
+      "grad_norm": 0.7915036678314209,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.7189,
+      "step": 62
+    },
+    {
+      "epoch": 1.2038216560509554,
+      "grad_norm": 0.7123846411705017,
+      "learning_rate": 7.467541090321735e-06,
+      "loss": 0.7075,
+      "step": 63
+    },
+    {
+      "epoch": 1.2229299363057324,
+      "grad_norm": 0.8034456372261047,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.7137,
+      "step": 64
+    },
+    {
+      "epoch": 1.2420382165605095,
+      "grad_norm": 0.7536247968673706,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.7145,
+      "step": 65
+    },
+    {
+      "epoch": 1.2611464968152866,
+      "grad_norm": 0.7744494080543518,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.7113,
+      "step": 66
+    },
+    {
+      "epoch": 1.2802547770700636,
+      "grad_norm": 0.7711228132247925,
+      "learning_rate": 7.067792524832604e-06,
+      "loss": 0.7053,
+      "step": 67
+    },
+    {
+      "epoch": 1.2993630573248407,
+      "grad_norm": 0.8071858882904053,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.7037,
+      "step": 68
+    },
+    {
+      "epoch": 1.3184713375796178,
+      "grad_norm": 0.780947744846344,
+      "learning_rate": 6.8614682920097265e-06,
+      "loss": 0.7267,
+      "step": 69
+    },
+    {
+      "epoch": 1.3375796178343948,
+      "grad_norm": 0.7653530240058899,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.7474,
+      "step": 70
+    },
+    {
+      "epoch": 1.356687898089172,
+      "grad_norm": 0.7996588945388794,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.7328,
+      "step": 71
+    },
+    {
+      "epoch": 1.3757961783439492,
+      "grad_norm": 0.7123798131942749,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.6917,
+      "step": 72
+    },
+    {
+      "epoch": 1.394904458598726,
+      "grad_norm": 0.6633033156394958,
+      "learning_rate": 6.437996637160086e-06,
+      "loss": 0.6991,
+      "step": 73
+    },
+    {
+      "epoch": 1.4140127388535033,
+      "grad_norm": 0.8307355642318726,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.6909,
+      "step": 74
+    },
+    {
+      "epoch": 1.4331210191082802,
+      "grad_norm": 0.6795753240585327,
+      "learning_rate": 6.2217020306894705e-06,
+      "loss": 0.7098,
+      "step": 75
+    },
+    {
+      "epoch": 1.4522292993630574,
+      "grad_norm": 0.6153970956802368,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.6726,
+      "step": 76
+    },
+    {
+      "epoch": 1.4713375796178343,
+      "grad_norm": 0.7344216108322144,
+      "learning_rate": 6.002947078916365e-06,
+      "loss": 0.7012,
+      "step": 77
+    },
+    {
+      "epoch": 1.4904458598726116,
+      "grad_norm": 0.7123773097991943,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.6638,
+      "step": 78
+    },
+    {
+      "epoch": 1.5095541401273884,
+      "grad_norm": 0.7022320032119751,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.6997,
+      "step": 79
+    },
+    {
+      "epoch": 1.5286624203821657,
+      "grad_norm": 0.7084267139434814,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.692,
+      "step": 80
+    },
+    {
+      "epoch": 1.5477707006369426,
+      "grad_norm": 0.68487948179245,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.6929,
+      "step": 81
+    },
+    {
+      "epoch": 1.5668789808917198,
+      "grad_norm": 0.7181028723716736,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.7193,
+      "step": 82
+    },
+    {
+      "epoch": 1.5859872611464967,
+      "grad_norm": 0.7298808693885803,
+      "learning_rate": 5.336345028060199e-06,
+      "loss": 0.7338,
+      "step": 83
+    },
+    {
+      "epoch": 1.605095541401274,
+      "grad_norm": 0.6929397583007812,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.7025,
+      "step": 84
+    },
+    {
+      "epoch": 1.6242038216560508,
+      "grad_norm": 0.6811756491661072,
+      "learning_rate": 5.112190321479026e-06,
+      "loss": 0.7052,
+      "step": 85
+    },
+    {
+      "epoch": 1.643312101910828,
+      "grad_norm": 0.6826193332672119,
+      "learning_rate": 5e-06,
+      "loss": 0.6931,
+      "step": 86
+    },
+    {
+      "epoch": 1.662420382165605,
+      "grad_norm": 0.654704749584198,
+      "learning_rate": 4.887809678520976e-06,
+      "loss": 0.6833,
+      "step": 87
+    },
+    {
+      "epoch": 1.6815286624203822,
+      "grad_norm": 0.6750189065933228,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.7073,
+      "step": 88
+    },
+    {
+      "epoch": 1.700636942675159,
+      "grad_norm": 0.6871541142463684,
+      "learning_rate": 4.663654971939802e-06,
+      "loss": 0.7184,
+      "step": 89
+    },
+    {
+      "epoch": 1.7197452229299364,
+      "grad_norm": 0.6716470122337341,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.7035,
+      "step": 90
+    },
+    {
+      "epoch": 1.7388535031847132,
+      "grad_norm": 0.6717052459716797,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.6988,
+      "step": 91
+    },
+    {
+      "epoch": 1.7579617834394905,
+      "grad_norm": 0.7127666473388672,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.7121,
+      "step": 92
+    },
+    {
+      "epoch": 1.7770700636942676,
+      "grad_norm": 0.6773775219917297,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.689,
+      "step": 93
+    },
+    {
+      "epoch": 1.7961783439490446,
+      "grad_norm": 0.6683153510093689,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.6857,
+      "step": 94
+    },
+    {
+      "epoch": 1.8152866242038217,
+      "grad_norm": 0.6821578741073608,
+      "learning_rate": 3.997052921083637e-06,
+      "loss": 0.6992,
+      "step": 95
+    },
+    {
+      "epoch": 1.8343949044585988,
+      "grad_norm": 0.6637680530548096,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.6848,
+      "step": 96
+    },
+    {
+      "epoch": 1.8535031847133758,
+      "grad_norm": 0.6395952105522156,
+      "learning_rate": 3.778297969310529e-06,
+      "loss": 0.6604,
+      "step": 97
+    },
+    {
+      "epoch": 1.872611464968153,
+      "grad_norm": 0.6628071069717407,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.6961,
+      "step": 98
+    },
+    {
+      "epoch": 1.89171974522293,
+      "grad_norm": 0.6521620154380798,
+      "learning_rate": 3.562003362839914e-06,
+      "loss": 0.71,
+      "step": 99
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 0.6818088889122009,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6946,
+      "step": 100
+    },
+    {
+      "epoch": 1.929936305732484,
+      "grad_norm": 0.6266446113586426,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.6786,
+      "step": 101
+    },
+    {
+      "epoch": 1.9490445859872612,
+      "grad_norm": 0.6931262612342834,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.699,
+      "step": 102
+    },
+    {
+      "epoch": 1.9681528662420382,
+      "grad_norm": 0.644861102104187,
+      "learning_rate": 3.1385317079902743e-06,
+      "loss": 0.7014,
+      "step": 103
+    },
+    {
+      "epoch": 1.9872611464968153,
+      "grad_norm": 0.67961186170578,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.6903,
+      "step": 104
+    },
+    {
+      "epoch": 2.0063694267515926,
+      "grad_norm": 0.7411230802536011,
+      "learning_rate": 2.932207475167398e-06,
+      "loss": 0.6627,
+      "step": 105
+    },
+    {
+      "epoch": 2.0254777070063694,
+      "grad_norm": 0.7194402813911438,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.6365,
+      "step": 106
+    },
+    {
+      "epoch": 2.0445859872611467,
+      "grad_norm": 0.6588802933692932,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.6299,
+      "step": 107
+    },
+    {
+      "epoch": 2.0636942675159236,
+      "grad_norm": 0.6904900074005127,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.6289,
+      "step": 108
+    },
+    {
+      "epoch": 2.082802547770701,
+      "grad_norm": 0.6685463786125183,
+      "learning_rate": 2.532458909678266e-06,
+      "loss": 0.6208,
+      "step": 109
+    },
+    {
+      "epoch": 2.1019108280254777,
+      "grad_norm": 0.6020084023475647,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.6027,
+      "step": 110
+    },
+    {
+      "epoch": 2.121019108280255,
+      "grad_norm": 0.6874512434005737,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.6021,
+      "step": 111
+    },
+    {
+      "epoch": 2.140127388535032,
+      "grad_norm": 0.6943764090538025,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.6031,
+      "step": 112
+    },
+    {
+      "epoch": 2.159235668789809,
+      "grad_norm": 0.7539130449295044,
+      "learning_rate": 2.1525775341577404e-06,
+      "loss": 0.6343,
+      "step": 113
+    },
+    {
+      "epoch": 2.178343949044586,
+      "grad_norm": 0.64998459815979,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.574,
+      "step": 114
+    },
+    {
+      "epoch": 2.1974522292993632,
+      "grad_norm": 0.6652138829231262,
+      "learning_rate": 1.971049780795901e-06,
+      "loss": 0.6022,
+      "step": 115
+    },
+    {
+      "epoch": 2.21656050955414,
+      "grad_norm": 0.6873827576637268,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.5928,
+      "step": 116
+    },
+    {
+      "epoch": 2.2356687898089174,
+      "grad_norm": 0.6433504819869995,
+      "learning_rate": 1.7956219300748796e-06,
+      "loss": 0.607,
+      "step": 117
+    },
+    {
+      "epoch": 2.254777070063694,
+      "grad_norm": 0.620965301990509,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.606,
+      "step": 118
+    },
+    {
+      "epoch": 2.2738853503184715,
+      "grad_norm": 0.6539048552513123,
+      "learning_rate": 1.6266472703396286e-06,
+      "loss": 0.6023,
+      "step": 119
+    },
+    {
+      "epoch": 2.2929936305732483,
+      "grad_norm": 0.6151559948921204,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.6034,
+      "step": 120
+    },
+    {
+      "epoch": 2.3121019108280256,
+      "grad_norm": 0.636107325553894,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5776,
+      "step": 121
+    },
+    {
+      "epoch": 2.3312101910828025,
+      "grad_norm": 0.6516319513320923,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.5965,
+      "step": 122
+    },
+    {
+      "epoch": 2.3503184713375798,
+      "grad_norm": 0.6334967613220215,
+      "learning_rate": 1.3094050125632973e-06,
+      "loss": 0.6159,
+      "step": 123
+    },
+    {
+      "epoch": 2.3694267515923566,
+      "grad_norm": 0.6599099636077881,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.6122,
+      "step": 124
+    },
+    {
+      "epoch": 2.388535031847134,
+      "grad_norm": 0.6333508491516113,
+      "learning_rate": 1.1617762982099446e-06,
+      "loss": 0.5929,
+      "step": 125
+    },
+    {
+      "epoch": 2.4076433121019107,
+      "grad_norm": 0.6153550148010254,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5706,
+      "step": 126
+    },
+    {
+      "epoch": 2.426751592356688,
+      "grad_norm": 0.6106190085411072,
+      "learning_rate": 1.0218772555910955e-06,
+      "loss": 0.6076,
+      "step": 127
+    },
+    {
+      "epoch": 2.445859872611465,
+      "grad_norm": 0.6668431162834167,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.6054,
+      "step": 128
+    },
+    {
+      "epoch": 2.464968152866242,
+      "grad_norm": 0.6144554615020752,
+      "learning_rate": 8.899896227604509e-07,
+      "loss": 0.5989,
+      "step": 129
+    },
+    {
+      "epoch": 2.484076433121019,
+      "grad_norm": 0.621407151222229,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.5972,
+      "step": 130
+    },
+    {
+      "epoch": 2.5031847133757963,
+      "grad_norm": 0.6157580614089966,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.5954,
+      "step": 131
+    },
+    {
+      "epoch": 2.522292993630573,
+      "grad_norm": 0.6083014607429504,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.6132,
+      "step": 132
+    },
+    {
+      "epoch": 2.5414012738853504,
+      "grad_norm": 0.5859634876251221,
+      "learning_rate": 6.512943342215234e-07,
+      "loss": 0.6082,
+      "step": 133
+    },
+    {
+      "epoch": 2.5605095541401273,
+      "grad_norm": 0.5937418341636658,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.5908,
+      "step": 134
+    },
+    {
+      "epoch": 2.5796178343949046,
+      "grad_norm": 0.604749321937561,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.6164,
+      "step": 135
+    },
+    {
+      "epoch": 2.5987261146496814,
+      "grad_norm": 0.599074125289917,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.6123,
+      "step": 136
+    },
+    {
+      "epoch": 2.6178343949044587,
+      "grad_norm": 0.6109683513641357,
+      "learning_rate": 4.4761226670592074e-07,
+      "loss": 0.601,
+      "step": 137
+    },
+    {
+      "epoch": 2.6369426751592355,
+      "grad_norm": 0.6154210567474365,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.6018,
+      "step": 138
+    },
+    {
+      "epoch": 2.656050955414013,
+      "grad_norm": 0.6092813611030579,
+      "learning_rate": 3.5942505740480583e-07,
+      "loss": 0.6081,
+      "step": 139
+    },
+    {
+      "epoch": 2.6751592356687897,
+      "grad_norm": 0.6313538551330566,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.5801,
+      "step": 140
+    },
+    {
+      "epoch": 2.694267515923567,
+      "grad_norm": 0.5989095568656921,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.581,
+      "step": 141
+    },
+    {
+      "epoch": 2.713375796178344,
+      "grad_norm": 0.5897513628005981,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5949,
+      "step": 142
+    },
+    {
+      "epoch": 2.732484076433121,
+      "grad_norm": 0.6216192245483398,
+      "learning_rate": 2.1124591657534776e-07,
+      "loss": 0.5946,
+      "step": 143
+    },
+    {
+      "epoch": 2.7515923566878984,
+      "grad_norm": 0.6057581901550293,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.6176,
+      "step": 144
+    },
+    {
+      "epoch": 2.770700636942675,
+      "grad_norm": 0.5893821120262146,
+      "learning_rate": 1.5155239811656562e-07,
+      "loss": 0.5866,
+      "step": 145
+    },
+    {
+      "epoch": 2.789808917197452,
+      "grad_norm": 0.5728128552436829,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.5793,
+      "step": 146
+    },
+    {
+      "epoch": 2.8089171974522293,
+      "grad_norm": 0.5864872932434082,
+      "learning_rate": 1.0162300788382263e-07,
+      "loss": 0.5808,
+      "step": 147
+    },
+    {
+      "epoch": 2.8280254777070066,
+      "grad_norm": 0.5862218737602234,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.586,
+      "step": 148
+    },
+    {
+      "epoch": 2.8471337579617835,
+      "grad_norm": 0.6472737789154053,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.5998,
+      "step": 149
+    },
+    {
+      "epoch": 2.8662420382165603,
+      "grad_norm": 0.576315701007843,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.5839,
+      "step": 150
+    },
+    {
+      "epoch": 2.8853503184713376,
+      "grad_norm": 0.5896339416503906,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.6035,
+      "step": 151
+    },
+    {
+      "epoch": 2.904458598726115,
+      "grad_norm": 0.6027177572250366,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.6129,
+      "step": 152
+    },
+    {
+      "epoch": 2.9235668789808917,
+      "grad_norm": 0.5746337175369263,
+      "learning_rate": 1.132562476771959e-08,
+      "loss": 0.5796,
+      "step": 153
+    },
+    {
+      "epoch": 2.9426751592356686,
+      "grad_norm": 0.5898021459579468,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.574,
+      "step": 154
+    },
+    {
+      "epoch": 2.961783439490446,
+      "grad_norm": 0.6063404083251953,
+      "learning_rate": 1.2588252874673469e-09,
+      "loss": 0.5974,
+      "step": 155
+    },
+    {
+      "epoch": 2.980891719745223,
+      "grad_norm": 0.6394419074058533,
+      "learning_rate": 0.0,
+      "loss": 0.6357,
+      "step": 156
+    },
+    {
+      "epoch": 2.980891719745223,
+      "step": 156,
+      "total_flos": 9.25222495000658e+16,
+      "train_loss": 0.7492156773805618,
+      "train_runtime": 2914.5015,
+      "train_samples_per_second": 5.147,
+      "train_steps_per_second": 0.054
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 156,
+  "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": 9.25222495000658e+16,
+  "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 sha256:49452be0e71a071448104b223b6a5177fe1d9293ee8a02be430b2bcf197ac58d
+size 7608