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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.991111111111111,
+    "total_flos": 467112937127936.0,
+    "train_loss": 0.6003679327134576,
+    "train_runtime": 29362.7142,
+    "train_samples_per_second": 0.367,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "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-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6979ecaba7a70fdd40f98a5363c2c910628a552fd97029567389272dc6ee3d93
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2035623ce1f59e47c9b43564777faec45ad002f62339fb7b49cd9118426620f3
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2fb49bf687533e81aa2a6ee0ff99a36346df6a6f0553c74d4affcecb37e602
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de239e14fb6816e92f454bea8484e899d23ea78293c23c558e8563cee1576c0a
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da02db525c199c03a4356c6463a1a2e45804c026b908f1ae59028cfc7c0c7379
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf8914e7f19b1f8957d178c8a4707745f27afcb3660bea0f4102bb9889cf1e36
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.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": 1.991111111111111,
+    "total_flos": 467112937127936.0,
+    "train_loss": 0.6003679327134576,
+    "train_runtime": 29362.7142,
+    "train_samples_per_second": 0.367,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,113 @@
+{"current_steps": 1, "total_steps": 112, "loss": 0.9094, "lr": 1.6666666666666667e-06, "epoch": 0.017777777777777778, "percentage": 0.89, "elapsed_time": "0:04:37", "remaining_time": "8:32:59"}
+{"current_steps": 2, "total_steps": 112, "loss": 0.9199, "lr": 3.3333333333333333e-06, "epoch": 0.035555555555555556, "percentage": 1.79, "elapsed_time": "0:09:19", "remaining_time": "8:32:31"}
+{"current_steps": 3, "total_steps": 112, "loss": 0.8971, "lr": 5e-06, "epoch": 0.05333333333333334, "percentage": 2.68, "elapsed_time": "0:13:19", "remaining_time": "8:03:50"}
+{"current_steps": 4, "total_steps": 112, "loss": 0.8814, "lr": 6.666666666666667e-06, "epoch": 0.07111111111111111, "percentage": 3.57, "elapsed_time": "0:18:08", "remaining_time": "8:10:01"}
+{"current_steps": 5, "total_steps": 112, "loss": 0.8735, "lr": 8.333333333333334e-06, "epoch": 0.08888888888888889, "percentage": 4.46, "elapsed_time": "0:22:23", "remaining_time": "7:59:13"}
+{"current_steps": 6, "total_steps": 112, "loss": 0.8465, "lr": 1e-05, "epoch": 0.10666666666666667, "percentage": 5.36, "elapsed_time": "0:26:12", "remaining_time": "7:42:54"}
+{"current_steps": 7, "total_steps": 112, "loss": 0.8162, "lr": 1.1666666666666668e-05, "epoch": 0.12444444444444444, "percentage": 6.25, "elapsed_time": "0:30:24", "remaining_time": "7:36:05"}
+{"current_steps": 8, "total_steps": 112, "loss": 0.7766, "lr": 1.3333333333333333e-05, "epoch": 0.14222222222222222, "percentage": 7.14, "elapsed_time": "0:34:49", "remaining_time": "7:32:39"}
+{"current_steps": 9, "total_steps": 112, "loss": 0.7484, "lr": 1.5000000000000002e-05, "epoch": 0.16, "percentage": 8.04, "elapsed_time": "0:38:55", "remaining_time": "7:25:26"}
+{"current_steps": 10, "total_steps": 112, "loss": 0.7333, "lr": 1.6666666666666667e-05, "epoch": 0.17777777777777778, "percentage": 8.93, "elapsed_time": "0:43:29", "remaining_time": "7:23:32"}
+{"current_steps": 11, "total_steps": 112, "loss": 0.7199, "lr": 1.8333333333333333e-05, "epoch": 0.19555555555555557, "percentage": 9.82, "elapsed_time": "0:47:48", "remaining_time": "7:19:00"}
+{"current_steps": 12, "total_steps": 112, "loss": 0.7146, "lr": 2e-05, "epoch": 0.21333333333333335, "percentage": 10.71, "elapsed_time": "0:52:44", "remaining_time": "7:19:33"}
+{"current_steps": 13, "total_steps": 112, "loss": 0.7104, "lr": 1.9995065603657317e-05, "epoch": 0.2311111111111111, "percentage": 11.61, "elapsed_time": "0:57:27", "remaining_time": "7:17:34"}
+{"current_steps": 14, "total_steps": 112, "loss": 0.6716, "lr": 1.9980267284282718e-05, "epoch": 0.24888888888888888, "percentage": 12.5, "elapsed_time": "1:01:58", "remaining_time": "7:13:49"}
+{"current_steps": 15, "total_steps": 112, "loss": 0.6816, "lr": 1.99556196460308e-05, "epoch": 0.26666666666666666, "percentage": 13.39, "elapsed_time": "1:05:49", "remaining_time": "7:05:38"}
+{"current_steps": 16, "total_steps": 112, "loss": 0.6847, "lr": 1.9921147013144782e-05, "epoch": 0.28444444444444444, "percentage": 14.29, "elapsed_time": "1:09:38", "remaining_time": "6:57:52"}
+{"current_steps": 17, "total_steps": 112, "loss": 0.6453, "lr": 1.9876883405951378e-05, "epoch": 0.3022222222222222, "percentage": 15.18, "elapsed_time": "1:13:31", "remaining_time": "6:50:54"}
+{"current_steps": 18, "total_steps": 112, "loss": 0.6504, "lr": 1.982287250728689e-05, "epoch": 0.32, "percentage": 16.07, "elapsed_time": "1:18:04", "remaining_time": "6:47:43"}
+{"current_steps": 19, "total_steps": 112, "loss": 0.6482, "lr": 1.9759167619387474e-05, "epoch": 0.3377777777777778, "percentage": 16.96, "elapsed_time": "1:22:27", "remaining_time": "6:43:35"}
+{"current_steps": 20, "total_steps": 112, "loss": 0.6399, "lr": 1.9685831611286312e-05, "epoch": 0.35555555555555557, "percentage": 17.86, "elapsed_time": "1:26:18", "remaining_time": "6:37:00"}
+{"current_steps": 21, "total_steps": 112, "loss": 0.6304, "lr": 1.9602936856769432e-05, "epoch": 0.37333333333333335, "percentage": 18.75, "elapsed_time": "1:30:11", "remaining_time": "6:30:49"}
+{"current_steps": 22, "total_steps": 112, "loss": 0.6415, "lr": 1.9510565162951538e-05, "epoch": 0.39111111111111113, "percentage": 19.64, "elapsed_time": "1:34:57", "remaining_time": "6:28:28"}
+{"current_steps": 23, "total_steps": 112, "loss": 0.6439, "lr": 1.9408807689542257e-05, "epoch": 0.4088888888888889, "percentage": 20.54, "elapsed_time": "1:39:15", "remaining_time": "6:24:06"}
+{"current_steps": 24, "total_steps": 112, "loss": 0.6368, "lr": 1.9297764858882516e-05, "epoch": 0.4266666666666667, "percentage": 21.43, "elapsed_time": "1:43:31", "remaining_time": "6:19:34"}
+{"current_steps": 25, "total_steps": 112, "loss": 0.623, "lr": 1.9177546256839814e-05, "epoch": 0.4444444444444444, "percentage": 22.32, "elapsed_time": "1:47:41", "remaining_time": "6:14:46"}
+{"current_steps": 26, "total_steps": 112, "loss": 0.6155, "lr": 1.9048270524660197e-05, "epoch": 0.4622222222222222, "percentage": 23.21, "elapsed_time": "1:52:20", "remaining_time": "6:11:34"}
+{"current_steps": 27, "total_steps": 112, "loss": 0.617, "lr": 1.891006524188368e-05, "epoch": 0.48, "percentage": 24.11, "elapsed_time": "1:56:47", "remaining_time": "6:07:41"}
+{"current_steps": 28, "total_steps": 112, "loss": 0.6253, "lr": 1.8763066800438638e-05, "epoch": 0.49777777777777776, "percentage": 25.0, "elapsed_time": "2:01:19", "remaining_time": "6:03:57"}
+{"current_steps": 29, "total_steps": 112, "loss": 0.6267, "lr": 1.860742027003944e-05, "epoch": 0.5155555555555555, "percentage": 25.89, "elapsed_time": "2:05:40", "remaining_time": "5:59:42"}
+{"current_steps": 30, "total_steps": 112, "loss": 0.6087, "lr": 1.8443279255020153e-05, "epoch": 0.5333333333333333, "percentage": 26.79, "elapsed_time": "2:10:05", "remaining_time": "5:55:34"}
+{"current_steps": 31, "total_steps": 112, "loss": 0.6103, "lr": 1.827080574274562e-05, "epoch": 0.5511111111111111, "percentage": 27.68, "elapsed_time": "2:14:54", "remaining_time": "5:52:29"}
+{"current_steps": 32, "total_steps": 112, "loss": 0.5908, "lr": 1.8090169943749477e-05, "epoch": 0.5688888888888889, "percentage": 28.57, "elapsed_time": "2:19:37", "remaining_time": "5:49:04"}
+{"current_steps": 33, "total_steps": 112, "loss": 0.6251, "lr": 1.7901550123756906e-05, "epoch": 0.5866666666666667, "percentage": 29.46, "elapsed_time": "2:23:34", "remaining_time": "5:43:43"}
+{"current_steps": 34, "total_steps": 112, "loss": 0.5963, "lr": 1.7705132427757895e-05, "epoch": 0.6044444444444445, "percentage": 30.36, "elapsed_time": "2:27:41", "remaining_time": "5:38:49"}
+{"current_steps": 35, "total_steps": 112, "loss": 0.5929, "lr": 1.7501110696304598e-05, "epoch": 0.6222222222222222, "percentage": 31.25, "elapsed_time": "2:31:57", "remaining_time": "5:34:19"}
+{"current_steps": 36, "total_steps": 112, "loss": 0.6027, "lr": 1.7289686274214116e-05, "epoch": 0.64, "percentage": 32.14, "elapsed_time": "2:36:02", "remaining_time": "5:29:25"}
+{"current_steps": 37, "total_steps": 112, "loss": 0.6085, "lr": 1.7071067811865477e-05, "epoch": 0.6577777777777778, "percentage": 33.04, "elapsed_time": "2:40:23", "remaining_time": "5:25:07"}
+{"current_steps": 38, "total_steps": 112, "loss": 0.6019, "lr": 1.684547105928689e-05, "epoch": 0.6755555555555556, "percentage": 33.93, "elapsed_time": "2:44:32", "remaining_time": "5:20:25"}
+{"current_steps": 39, "total_steps": 112, "loss": 0.6007, "lr": 1.661311865323652e-05, "epoch": 0.6933333333333334, "percentage": 34.82, "elapsed_time": "2:49:12", "remaining_time": "5:16:43"}
+{"current_steps": 40, "total_steps": 112, "loss": 0.5827, "lr": 1.63742398974869e-05, "epoch": 0.7111111111111111, "percentage": 35.71, "elapsed_time": "2:53:14", "remaining_time": "5:11:50"}
+{"current_steps": 41, "total_steps": 112, "loss": 0.6047, "lr": 1.6129070536529767e-05, "epoch": 0.7288888888888889, "percentage": 36.61, "elapsed_time": "2:57:40", "remaining_time": "5:07:41"}
+{"current_steps": 42, "total_steps": 112, "loss": 0.6041, "lr": 1.5877852522924733e-05, "epoch": 0.7466666666666667, "percentage": 37.5, "elapsed_time": "3:01:50", "remaining_time": "5:03:03"}
+{"current_steps": 43, "total_steps": 112, "loss": 0.5888, "lr": 1.5620833778521306e-05, "epoch": 0.7644444444444445, "percentage": 38.39, "elapsed_time": "3:06:06", "remaining_time": "4:58:37"}
+{"current_steps": 44, "total_steps": 112, "loss": 0.5927, "lr": 1.5358267949789968e-05, "epoch": 0.7822222222222223, "percentage": 39.29, "elapsed_time": "3:10:47", "remaining_time": "4:54:51"}
+{"current_steps": 45, "total_steps": 112, "loss": 0.6037, "lr": 1.5090414157503715e-05, "epoch": 0.8, "percentage": 40.18, "elapsed_time": "3:14:50", "remaining_time": "4:50:06"}
+{"current_steps": 46, "total_steps": 112, "loss": 0.59, "lr": 1.4817536741017153e-05, "epoch": 0.8177777777777778, "percentage": 41.07, "elapsed_time": "3:19:13", "remaining_time": "4:45:50"}
+{"current_steps": 47, "total_steps": 112, "loss": 0.6038, "lr": 1.4539904997395468e-05, "epoch": 0.8355555555555556, "percentage": 41.96, "elapsed_time": "3:23:50", "remaining_time": "4:41:53"}
+{"current_steps": 48, "total_steps": 112, "loss": 0.5796, "lr": 1.4257792915650728e-05, "epoch": 0.8533333333333334, "percentage": 42.86, "elapsed_time": "3:28:04", "remaining_time": "4:37:26"}
+{"current_steps": 49, "total_steps": 112, "loss": 0.5842, "lr": 1.3971478906347806e-05, "epoch": 0.8711111111111111, "percentage": 43.75, "elapsed_time": "3:31:57", "remaining_time": "4:32:31"}
+{"current_steps": 50, "total_steps": 112, "loss": 0.5824, "lr": 1.3681245526846782e-05, "epoch": 0.8888888888888888, "percentage": 44.64, "elapsed_time": "3:36:26", "remaining_time": "4:28:22"}
+{"current_steps": 51, "total_steps": 112, "loss": 0.5766, "lr": 1.3387379202452917e-05, "epoch": 0.9066666666666666, "percentage": 45.54, "elapsed_time": "3:40:31", "remaining_time": "4:23:45"}
+{"current_steps": 52, "total_steps": 112, "loss": 0.5917, "lr": 1.3090169943749475e-05, "epoch": 0.9244444444444444, "percentage": 46.43, "elapsed_time": "3:45:16", "remaining_time": "4:19:56"}
+{"current_steps": 53, "total_steps": 112, "loss": 0.5862, "lr": 1.2789911060392295e-05, "epoch": 0.9422222222222222, "percentage": 47.32, "elapsed_time": "3:49:56", "remaining_time": "4:15:58"}
+{"current_steps": 54, "total_steps": 112, "loss": 0.5941, "lr": 1.2486898871648552e-05, "epoch": 0.96, "percentage": 48.21, "elapsed_time": "3:54:03", "remaining_time": "4:11:24"}
+{"current_steps": 55, "total_steps": 112, "loss": 0.5792, "lr": 1.2181432413965428e-05, "epoch": 0.9777777777777777, "percentage": 49.11, "elapsed_time": "3:58:13", "remaining_time": "4:06:52"}
+{"current_steps": 56, "total_steps": 112, "loss": 0.5949, "lr": 1.187381314585725e-05, "epoch": 0.9955555555555555, "percentage": 50.0, "elapsed_time": "4:02:21", "remaining_time": "4:02:21"}
+{"current_steps": 57, "total_steps": 112, "loss": 0.9832, "lr": 1.156434465040231e-05, "epoch": 1.0133333333333334, "percentage": 50.89, "elapsed_time": "4:06:34", "remaining_time": "3:57:55"}
+{"current_steps": 58, "total_steps": 112, "loss": 0.579, "lr": 1.1253332335643043e-05, "epoch": 1.031111111111111, "percentage": 51.79, "elapsed_time": "4:11:00", "remaining_time": "3:53:41"}
+{"current_steps": 59, "total_steps": 112, "loss": 0.5473, "lr": 1.0941083133185146e-05, "epoch": 1.048888888888889, "percentage": 52.68, "elapsed_time": "4:15:52", "remaining_time": "3:49:50"}
+{"current_steps": 60, "total_steps": 112, "loss": 0.5123, "lr": 1.0627905195293135e-05, "epoch": 1.0666666666666667, "percentage": 53.57, "elapsed_time": "4:20:07", "remaining_time": "3:45:26"}
+{"current_steps": 61, "total_steps": 112, "loss": 0.5945, "lr": 1.0314107590781284e-05, "epoch": 1.0844444444444445, "percentage": 54.46, "elapsed_time": "4:24:14", "remaining_time": "3:40:55"}
+{"current_steps": 62, "total_steps": 112, "loss": 0.525, "lr": 1e-05, "epoch": 1.1022222222222222, "percentage": 55.36, "elapsed_time": "4:29:00", "remaining_time": "3:36:56"}
+{"current_steps": 63, "total_steps": 112, "loss": 0.5318, "lr": 9.685892409218718e-06, "epoch": 1.12, "percentage": 56.25, "elapsed_time": "4:33:08", "remaining_time": "3:32:26"}
+{"current_steps": 64, "total_steps": 112, "loss": 0.5176, "lr": 9.372094804706867e-06, "epoch": 1.1377777777777778, "percentage": 57.14, "elapsed_time": "4:37:43", "remaining_time": "3:28:17"}
+{"current_steps": 65, "total_steps": 112, "loss": 0.5637, "lr": 9.058916866814857e-06, "epoch": 1.1555555555555554, "percentage": 58.04, "elapsed_time": "4:42:30", "remaining_time": "3:24:16"}
+{"current_steps": 66, "total_steps": 112, "loss": 0.5567, "lr": 8.746667664356957e-06, "epoch": 1.1733333333333333, "percentage": 58.93, "elapsed_time": "4:46:54", "remaining_time": "3:19:57"}
+{"current_steps": 67, "total_steps": 112, "loss": 0.5005, "lr": 8.43565534959769e-06, "epoch": 1.1911111111111112, "percentage": 59.82, "elapsed_time": "4:50:53", "remaining_time": "3:15:22"}
+{"current_steps": 68, "total_steps": 112, "loss": 0.5691, "lr": 8.126186854142752e-06, "epoch": 1.208888888888889, "percentage": 60.71, "elapsed_time": "4:55:35", "remaining_time": "3:11:16"}
+{"current_steps": 69, "total_steps": 112, "loss": 0.5169, "lr": 7.818567586034578e-06, "epoch": 1.2266666666666666, "percentage": 61.61, "elapsed_time": "4:59:58", "remaining_time": "3:06:56"}
+{"current_steps": 70, "total_steps": 112, "loss": 0.5474, "lr": 7.513101128351454e-06, "epoch": 1.2444444444444445, "percentage": 62.5, "elapsed_time": "5:04:01", "remaining_time": "3:02:24"}
+{"current_steps": 71, "total_steps": 112, "loss": 0.499, "lr": 7.210088939607709e-06, "epoch": 1.2622222222222224, "percentage": 63.39, "elapsed_time": "5:08:26", "remaining_time": "2:58:07"}
+{"current_steps": 72, "total_steps": 112, "loss": 0.5772, "lr": 6.909830056250527e-06, "epoch": 1.28, "percentage": 64.29, "elapsed_time": "5:12:48", "remaining_time": "2:53:46"}
+{"current_steps": 73, "total_steps": 112, "loss": 0.4868, "lr": 6.612620797547087e-06, "epoch": 1.2977777777777777, "percentage": 65.18, "elapsed_time": "5:16:55", "remaining_time": "2:49:19"}
+{"current_steps": 74, "total_steps": 112, "loss": 0.5599, "lr": 6.318754473153221e-06, "epoch": 1.3155555555555556, "percentage": 66.07, "elapsed_time": "5:21:48", "remaining_time": "2:45:15"}
+{"current_steps": 75, "total_steps": 112, "loss": 0.5101, "lr": 6.028521093652195e-06, "epoch": 1.3333333333333333, "percentage": 66.96, "elapsed_time": "5:26:07", "remaining_time": "2:40:53"}
+{"current_steps": 76, "total_steps": 112, "loss": 0.5604, "lr": 5.742207084349274e-06, "epoch": 1.3511111111111112, "percentage": 67.86, "elapsed_time": "5:31:00", "remaining_time": "2:36:47"}
+{"current_steps": 77, "total_steps": 112, "loss": 0.5351, "lr": 5.460095002604533e-06, "epoch": 1.3688888888888888, "percentage": 68.75, "elapsed_time": "5:35:20", "remaining_time": "2:32:25"}
+{"current_steps": 78, "total_steps": 112, "loss": 0.5609, "lr": 5.1824632589828465e-06, "epoch": 1.3866666666666667, "percentage": 69.64, "elapsed_time": "5:39:50", "remaining_time": "2:28:08"}
+{"current_steps": 79, "total_steps": 112, "loss": 0.4945, "lr": 4.909585842496287e-06, "epoch": 1.4044444444444444, "percentage": 70.54, "elapsed_time": "5:44:10", "remaining_time": "2:23:46"}
+{"current_steps": 80, "total_steps": 112, "loss": 0.529, "lr": 4.641732050210032e-06, "epoch": 1.4222222222222223, "percentage": 71.43, "elapsed_time": "5:48:26", "remaining_time": "2:19:22"}
+{"current_steps": 81, "total_steps": 112, "loss": 0.5456, "lr": 4.379166221478697e-06, "epoch": 1.44, "percentage": 72.32, "elapsed_time": "5:52:40", "remaining_time": "2:14:58"}
+{"current_steps": 82, "total_steps": 112, "loss": 0.5672, "lr": 4.12214747707527e-06, "epoch": 1.4577777777777778, "percentage": 73.21, "elapsed_time": "5:57:06", "remaining_time": "2:10:38"}
+{"current_steps": 83, "total_steps": 112, "loss": 0.4796, "lr": 3.8709294634702374e-06, "epoch": 1.4755555555555555, "percentage": 74.11, "elapsed_time": "6:01:05", "remaining_time": "2:06:09"}
+{"current_steps": 84, "total_steps": 112, "loss": 0.5144, "lr": 3.625760102513103e-06, "epoch": 1.4933333333333334, "percentage": 75.0, "elapsed_time": "6:05:03", "remaining_time": "2:01:41"}
+{"current_steps": 85, "total_steps": 112, "loss": 0.5563, "lr": 3.3868813467634833e-06, "epoch": 1.511111111111111, "percentage": 75.89, "elapsed_time": "6:09:16", "remaining_time": "1:57:18"}
+{"current_steps": 86, "total_steps": 112, "loss": 0.5267, "lr": 3.1545289407131128e-06, "epoch": 1.528888888888889, "percentage": 76.79, "elapsed_time": "6:13:14", "remaining_time": "1:52:50"}
+{"current_steps": 87, "total_steps": 112, "loss": 0.5464, "lr": 2.9289321881345257e-06, "epoch": 1.5466666666666666, "percentage": 77.68, "elapsed_time": "6:17:23", "remaining_time": "1:48:26"}
+{"current_steps": 88, "total_steps": 112, "loss": 0.5406, "lr": 2.7103137257858867e-06, "epoch": 1.5644444444444443, "percentage": 78.57, "elapsed_time": "6:21:21", "remaining_time": "1:44:00"}
+{"current_steps": 89, "total_steps": 112, "loss": 0.5094, "lr": 2.4988893036954045e-06, "epoch": 1.5822222222222222, "percentage": 79.46, "elapsed_time": "6:25:36", "remaining_time": "1:39:39"}
+{"current_steps": 90, "total_steps": 112, "loss": 0.5433, "lr": 2.2948675722421086e-06, "epoch": 1.6, "percentage": 80.36, "elapsed_time": "6:29:35", "remaining_time": "1:35:14"}
+{"current_steps": 91, "total_steps": 112, "loss": 0.5239, "lr": 2.098449876243096e-06, "epoch": 1.6177777777777778, "percentage": 81.25, "elapsed_time": "6:34:24", "remaining_time": "1:31:01"}
+{"current_steps": 92, "total_steps": 112, "loss": 0.5626, "lr": 1.9098300562505266e-06, "epoch": 1.6355555555555554, "percentage": 82.14, "elapsed_time": "6:39:17", "remaining_time": "1:26:48"}
+{"current_steps": 93, "total_steps": 112, "loss": 0.5097, "lr": 1.7291942572543806e-06, "epoch": 1.6533333333333333, "percentage": 83.04, "elapsed_time": "6:43:16", "remaining_time": "1:22:23"}
+{"current_steps": 94, "total_steps": 112, "loss": 0.5432, "lr": 1.5567207449798517e-06, "epoch": 1.6711111111111112, "percentage": 83.93, "elapsed_time": "6:47:52", "remaining_time": "1:18:06"}
+{"current_steps": 95, "total_steps": 112, "loss": 0.5245, "lr": 1.3925797299605649e-06, "epoch": 1.6888888888888889, "percentage": 84.82, "elapsed_time": "6:52:00", "remaining_time": "1:13:43"}
+{"current_steps": 96, "total_steps": 112, "loss": 0.5438, "lr": 1.2369331995613664e-06, "epoch": 1.7066666666666666, "percentage": 85.71, "elapsed_time": "6:56:10", "remaining_time": "1:09:21"}
+{"current_steps": 97, "total_steps": 112, "loss": 0.5418, "lr": 1.0899347581163222e-06, "epoch": 1.7244444444444444, "percentage": 86.61, "elapsed_time": "7:00:53", "remaining_time": "1:05:05"}
+{"current_steps": 98, "total_steps": 112, "loss": 0.5258, "lr": 9.517294753398066e-07, "epoch": 1.7422222222222223, "percentage": 87.5, "elapsed_time": "7:05:31", "remaining_time": "1:00:47"}
+{"current_steps": 99, "total_steps": 112, "loss": 0.4905, "lr": 8.224537431601886e-07, "epoch": 1.76, "percentage": 88.39, "elapsed_time": "7:09:46", "remaining_time": "0:56:26"}
+{"current_steps": 100, "total_steps": 112, "loss": 0.5436, "lr": 7.022351411174866e-07, "epoch": 1.7777777777777777, "percentage": 89.29, "elapsed_time": "7:13:56", "remaining_time": "0:52:04"}
+{"current_steps": 101, "total_steps": 112, "loss": 0.5322, "lr": 5.911923104577455e-07, "epoch": 1.7955555555555556, "percentage": 90.18, "elapsed_time": "7:20:40", "remaining_time": "0:47:59"}
+{"current_steps": 102, "total_steps": 112, "loss": 0.5142, "lr": 4.894348370484648e-07, "epoch": 1.8133333333333335, "percentage": 91.07, "elapsed_time": "7:25:09", "remaining_time": "0:43:38"}
+{"current_steps": 103, "total_steps": 112, "loss": 0.5264, "lr": 3.9706314323056936e-07, "epoch": 1.8311111111111111, "percentage": 91.96, "elapsed_time": "7:29:13", "remaining_time": "0:39:15"}
+{"current_steps": 104, "total_steps": 112, "loss": 0.5069, "lr": 3.1416838871368925e-07, "epoch": 1.8488888888888888, "percentage": 92.86, "elapsed_time": "7:32:34", "remaining_time": "0:34:48"}
+{"current_steps": 105, "total_steps": 112, "loss": 0.5694, "lr": 2.4083238061252565e-07, "epoch": 1.8666666666666667, "percentage": 93.75, "elapsed_time": "7:36:33", "remaining_time": "0:30:26"}
+{"current_steps": 106, "total_steps": 112, "loss": 0.4963, "lr": 1.7712749271311392e-07, "epoch": 1.8844444444444446, "percentage": 94.64, "elapsed_time": "7:40:31", "remaining_time": "0:26:04"}
+{"current_steps": 107, "total_steps": 112, "loss": 0.512, "lr": 1.231165940486234e-07, "epoch": 1.9022222222222223, "percentage": 95.54, "elapsed_time": "7:45:04", "remaining_time": "0:21:43"}
+{"current_steps": 108, "total_steps": 112, "loss": 0.5168, "lr": 7.885298685522235e-08, "epoch": 1.92, "percentage": 96.43, "elapsed_time": "7:48:51", "remaining_time": "0:17:21"}
+{"current_steps": 109, "total_steps": 112, "loss": 0.5412, "lr": 4.438035396920004e-08, "epoch": 1.9377777777777778, "percentage": 97.32, "elapsed_time": "7:53:05", "remaining_time": "0:13:01"}
+{"current_steps": 110, "total_steps": 112, "loss": 0.5511, "lr": 1.973271571728441e-08, "epoch": 1.9555555555555557, "percentage": 98.21, "elapsed_time": "7:58:09", "remaining_time": "0:08:41"}
+{"current_steps": 111, "total_steps": 112, "loss": 0.5274, "lr": 4.9343963426840006e-09, "epoch": 1.9733333333333334, "percentage": 99.11, "elapsed_time": "8:03:04", "remaining_time": "0:04:21"}
+{"current_steps": 112, "total_steps": 112, "loss": 0.544, "lr": 0.0, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "8:07:19", "remaining_time": "0:00:00"}
+{"current_steps": 112, "total_steps": 112, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "8:09:21", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.991111111111111,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.0161187648773193,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.9094,
+      "step": 1
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 3.0456559658050537,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9199,
+      "step": 2
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.8616299629211426,
+      "learning_rate": 5e-06,
+      "loss": 0.8971,
+      "step": 3
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.2876524925231934,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8814,
+      "step": 4
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 3.967463493347168,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8735,
+      "step": 5
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.9434279203414917,
+      "learning_rate": 1e-05,
+      "loss": 0.8465,
+      "step": 6
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 2.0345959663391113,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8162,
+      "step": 7
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.519321084022522,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7766,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.5613726377487183,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7484,
+      "step": 9
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1348494291305542,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7333,
+      "step": 10
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.3956992626190186,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7199,
+      "step": 11
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.2517744302749634,
+      "learning_rate": 2e-05,
+      "loss": 0.7146,
+      "step": 12
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.2728958129882812,
+      "learning_rate": 1.9995065603657317e-05,
+      "loss": 0.7104,
+      "step": 13
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.0933605432510376,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 0.6716,
+      "step": 14
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8169775605201721,
+      "learning_rate": 1.99556196460308e-05,
+      "loss": 0.6816,
+      "step": 15
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.0378296375274658,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.6847,
+      "step": 16
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.7941539883613586,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.6453,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.6657661199569702,
+      "learning_rate": 1.982287250728689e-05,
+      "loss": 0.6504,
+      "step": 18
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.7748784422874451,
+      "learning_rate": 1.9759167619387474e-05,
+      "loss": 0.6482,
+      "step": 19
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.7648543119430542,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.6399,
+      "step": 20
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.6626160740852356,
+      "learning_rate": 1.9602936856769432e-05,
+      "loss": 0.6304,
+      "step": 21
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.6575434803962708,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.6415,
+      "step": 22
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.6369120478630066,
+      "learning_rate": 1.9408807689542257e-05,
+      "loss": 0.6439,
+      "step": 23
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.6337743401527405,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.6368,
+      "step": 24
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6001498699188232,
+      "learning_rate": 1.9177546256839814e-05,
+      "loss": 0.623,
+      "step": 25
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.48166558146476746,
+      "learning_rate": 1.9048270524660197e-05,
+      "loss": 0.6155,
+      "step": 26
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5851263403892517,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.617,
+      "step": 27
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.603469729423523,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.6253,
+      "step": 28
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.45908477902412415,
+      "learning_rate": 1.860742027003944e-05,
+      "loss": 0.6267,
+      "step": 29
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.5786503553390503,
+      "learning_rate": 1.8443279255020153e-05,
+      "loss": 0.6087,
+      "step": 30
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.5608594417572021,
+      "learning_rate": 1.827080574274562e-05,
+      "loss": 0.6103,
+      "step": 31
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.43821826577186584,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.5908,
+      "step": 32
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.5472081899642944,
+      "learning_rate": 1.7901550123756906e-05,
+      "loss": 0.6251,
+      "step": 33
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.4198133945465088,
+      "learning_rate": 1.7705132427757895e-05,
+      "loss": 0.5963,
+      "step": 34
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.524138867855072,
+      "learning_rate": 1.7501110696304598e-05,
+      "loss": 0.5929,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.399955153465271,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.6027,
+      "step": 36
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.43022847175598145,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.6085,
+      "step": 37
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.4289129972457886,
+      "learning_rate": 1.684547105928689e-05,
+      "loss": 0.6019,
+      "step": 38
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.4198264181613922,
+      "learning_rate": 1.661311865323652e-05,
+      "loss": 0.6007,
+      "step": 39
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.3680365979671478,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.5827,
+      "step": 40
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.4037115275859833,
+      "learning_rate": 1.6129070536529767e-05,
+      "loss": 0.6047,
+      "step": 41
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.473398894071579,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.6041,
+      "step": 42
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.33001384139060974,
+      "learning_rate": 1.5620833778521306e-05,
+      "loss": 0.5888,
+      "step": 43
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.34208983182907104,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.5927,
+      "step": 44
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3997894823551178,
+      "learning_rate": 1.5090414157503715e-05,
+      "loss": 0.6037,
+      "step": 45
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.3622935712337494,
+      "learning_rate": 1.4817536741017153e-05,
+      "loss": 0.59,
+      "step": 46
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.35205668210983276,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.6038,
+      "step": 47
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.38642618060112,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.5796,
+      "step": 48
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.34358909726142883,
+      "learning_rate": 1.3971478906347806e-05,
+      "loss": 0.5842,
+      "step": 49
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3424360752105713,
+      "learning_rate": 1.3681245526846782e-05,
+      "loss": 0.5824,
+      "step": 50
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.3290707468986511,
+      "learning_rate": 1.3387379202452917e-05,
+      "loss": 0.5766,
+      "step": 51
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.3417136073112488,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5917,
+      "step": 52
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.3143644332885742,
+      "learning_rate": 1.2789911060392295e-05,
+      "loss": 0.5862,
+      "step": 53
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3264472782611847,
+      "learning_rate": 1.2486898871648552e-05,
+      "loss": 0.5941,
+      "step": 54
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.3463677167892456,
+      "learning_rate": 1.2181432413965428e-05,
+      "loss": 0.5792,
+      "step": 55
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.3562481105327606,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.5949,
+      "step": 56
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.6014902591705322,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.9832,
+      "step": 57
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.4315400719642639,
+      "learning_rate": 1.1253332335643043e-05,
+      "loss": 0.579,
+      "step": 58
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 0.4110487401485443,
+      "learning_rate": 1.0941083133185146e-05,
+      "loss": 0.5473,
+      "step": 59
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.3785395920276642,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.5123,
+      "step": 60
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 0.41390877962112427,
+      "learning_rate": 1.0314107590781284e-05,
+      "loss": 0.5945,
+      "step": 61
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 0.35746318101882935,
+      "learning_rate": 1e-05,
+      "loss": 0.525,
+      "step": 62
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.4079684019088745,
+      "learning_rate": 9.685892409218718e-06,
+      "loss": 0.5318,
+      "step": 63
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 0.36759430170059204,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.5176,
+      "step": 64
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.41054409742355347,
+      "learning_rate": 9.058916866814857e-06,
+      "loss": 0.5637,
+      "step": 65
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.3619822859764099,
+      "learning_rate": 8.746667664356957e-06,
+      "loss": 0.5567,
+      "step": 66
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 0.3154706656932831,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.5005,
+      "step": 67
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 0.38217437267303467,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.5691,
+      "step": 68
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.30643534660339355,
+      "learning_rate": 7.818567586034578e-06,
+      "loss": 0.5169,
+      "step": 69
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.335054486989975,
+      "learning_rate": 7.513101128351454e-06,
+      "loss": 0.5474,
+      "step": 70
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 0.32074597477912903,
+      "learning_rate": 7.210088939607709e-06,
+      "loss": 0.499,
+      "step": 71
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3078364431858063,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.5772,
+      "step": 72
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 0.26938191056251526,
+      "learning_rate": 6.612620797547087e-06,
+      "loss": 0.4868,
+      "step": 73
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 0.34066033363342285,
+      "learning_rate": 6.318754473153221e-06,
+      "loss": 0.5599,
+      "step": 74
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.28962934017181396,
+      "learning_rate": 6.028521093652195e-06,
+      "loss": 0.5101,
+      "step": 75
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 0.2816958427429199,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.5604,
+      "step": 76
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 0.31672269105911255,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.5351,
+      "step": 77
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.307559609413147,
+      "learning_rate": 5.1824632589828465e-06,
+      "loss": 0.5609,
+      "step": 78
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 0.3002449572086334,
+      "learning_rate": 4.909585842496287e-06,
+      "loss": 0.4945,
+      "step": 79
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.4366104304790497,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.529,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.2942907214164734,
+      "learning_rate": 4.379166221478697e-06,
+      "loss": 0.5456,
+      "step": 81
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 0.29603904485702515,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.5672,
+      "step": 82
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 0.26003167033195496,
+      "learning_rate": 3.8709294634702374e-06,
+      "loss": 0.4796,
+      "step": 83
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.2945937514305115,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.5144,
+      "step": 84
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.32350650429725647,
+      "learning_rate": 3.3868813467634833e-06,
+      "loss": 0.5563,
+      "step": 85
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 0.28247952461242676,
+      "learning_rate": 3.1545289407131128e-06,
+      "loss": 0.5267,
+      "step": 86
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.2574496269226074,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.5464,
+      "step": 87
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 0.2627605199813843,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.5406,
+      "step": 88
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 0.2714482545852661,
+      "learning_rate": 2.4988893036954045e-06,
+      "loss": 0.5094,
+      "step": 89
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.28099218010902405,
+      "learning_rate": 2.2948675722421086e-06,
+      "loss": 0.5433,
+      "step": 90
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 0.24211485683918,
+      "learning_rate": 2.098449876243096e-06,
+      "loss": 0.5239,
+      "step": 91
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 0.2546832859516144,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.5626,
+      "step": 92
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.2391272783279419,
+      "learning_rate": 1.7291942572543806e-06,
+      "loss": 0.5097,
+      "step": 93
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 0.2698579430580139,
+      "learning_rate": 1.5567207449798517e-06,
+      "loss": 0.5432,
+      "step": 94
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.2520196735858917,
+      "learning_rate": 1.3925797299605649e-06,
+      "loss": 0.5245,
+      "step": 95
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.25460532307624817,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.5438,
+      "step": 96
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 0.26885905861854553,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.5418,
+      "step": 97
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 0.22826924920082092,
+      "learning_rate": 9.517294753398066e-07,
+      "loss": 0.5258,
+      "step": 98
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.2222457379102707,
+      "learning_rate": 8.224537431601886e-07,
+      "loss": 0.4905,
+      "step": 99
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.24972008168697357,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.5436,
+      "step": 100
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 0.24206911027431488,
+      "learning_rate": 5.911923104577455e-07,
+      "loss": 0.5322,
+      "step": 101
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.2620464861392975,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.5142,
+      "step": 102
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 0.25102680921554565,
+      "learning_rate": 3.9706314323056936e-07,
+      "loss": 0.5264,
+      "step": 103
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 0.24889089167118073,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.5069,
+      "step": 104
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.24384674429893494,
+      "learning_rate": 2.4083238061252565e-07,
+      "loss": 0.5694,
+      "step": 105
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 0.2293427288532257,
+      "learning_rate": 1.7712749271311392e-07,
+      "loss": 0.4963,
+      "step": 106
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 0.2467752993106842,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.512,
+      "step": 107
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.2353520542383194,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.5168,
+      "step": 108
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 0.2465604692697525,
+      "learning_rate": 4.438035396920004e-08,
+      "loss": 0.5412,
+      "step": 109
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.23654182255268097,
+      "learning_rate": 1.973271571728441e-08,
+      "loss": 0.5511,
+      "step": 110
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.22757108509540558,
+      "learning_rate": 4.9343963426840006e-09,
+      "loss": 0.5274,
+      "step": 111
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 0.24920369684696198,
+      "learning_rate": 0.0,
+      "loss": 0.544,
+      "step": 112
+    },
+    {
+      "epoch": 1.991111111111111,
+      "step": 112,
+      "total_flos": 467112937127936.0,
+      "train_loss": 0.6003679327134576,
+      "train_runtime": 29362.7142,
+      "train_samples_per_second": 0.367,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 467112937127936.0,
+  "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 sha256:4e23ae6c461f010be57387939f326d588b30ebc5b3d66c680bd33ea4ce7057fd
+size 7416