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/Qwen2.5-32B-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/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-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": 1.9968,
+    "total_flos": 356056961384448.0,
+    "train_loss": 0.48249776661396027,
+    "train_runtime": 36791.677,
+    "train_samples_per_second": 0.272,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-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": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "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-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcf2a08dd448b4a7896e63816b79c5b88c515168201309c13bcdf1364129c72
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5055119c1c7b499298c808462c635ea88fa286b656c2f7291e67fa801b586a9e
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74ac577cfc791eb8205c5193c68bdddd2b38fac4759f6fb72ded87db4793af7
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f7b6d9cc630bcf2a2792ddd3e37b57e098f5511daedac90e50e27e2df6c957
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947aa4d3da66569f22926060044b6346fdb898436310242742b1d6a89001deac
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9be1d3013c2dd5f2bd70a47accfad62ccc5c7ffbe94954516063de861d5eda7
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ce7477c936e1f093e3e0fac39e8f16b391fba9b7c84b6927bc2fc5e8002a7c
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb17d0732882838294051f25426bc6e6c774659f259b12433d3f7f06a4b9a27
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af3e9bf9271c2f37573c27274b5e0d8cc325d1c6dd4c87b00fdc131adf3869a
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9b7437bd6ab528992a8e56335afde282b5d6acda6a2b11eea37b73deaa93d1
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d1202a4e306967adbc634f9bf23f08aca97e3580990a06308bc126a86091d4
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561d35a214b654a818bf1be01b17d34347baf441041da75d59df2aee3c24f991
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcbcb89cca2af1348867ea0414f24c72caa3c174a684fd7f318d96701fb9c68
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a0e6ec7e641d7e45bfd19aa3c41dd00696b972e3841ff7b31a0ef68571ed4e
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.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": 1.9968,
+    "total_flos": 356056961384448.0,
+    "train_loss": 0.48249776661396027,
+    "train_runtime": 36791.677,
+    "train_samples_per_second": 0.272,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,105 @@
+{"current_steps": 1, "total_steps": 104, "loss": 0.7932, "lr": 1.8181818181818183e-06, "epoch": 0.0192, "percentage": 0.96, "elapsed_time": "0:06:29", "remaining_time": "11:09:02"}
+{"current_steps": 2, "total_steps": 104, "loss": 0.7613, "lr": 3.6363636363636366e-06, "epoch": 0.0384, "percentage": 1.92, "elapsed_time": "0:11:51", "remaining_time": "10:04:53"}
+{"current_steps": 3, "total_steps": 104, "loss": 0.8108, "lr": 5.4545454545454545e-06, "epoch": 0.0576, "percentage": 2.88, "elapsed_time": "0:18:51", "remaining_time": "10:34:53"}
+{"current_steps": 4, "total_steps": 104, "loss": 0.7694, "lr": 7.272727272727273e-06, "epoch": 0.0768, "percentage": 3.85, "elapsed_time": "0:25:17", "remaining_time": "10:32:28"}
+{"current_steps": 5, "total_steps": 104, "loss": 0.7506, "lr": 9.090909090909091e-06, "epoch": 0.096, "percentage": 4.81, "elapsed_time": "0:31:01", "remaining_time": "10:14:19"}
+{"current_steps": 6, "total_steps": 104, "loss": 0.6907, "lr": 1.0909090909090909e-05, "epoch": 0.1152, "percentage": 5.77, "elapsed_time": "0:36:55", "remaining_time": "10:03:05"}
+{"current_steps": 7, "total_steps": 104, "loss": 0.68, "lr": 1.2727272727272728e-05, "epoch": 0.1344, "percentage": 6.73, "elapsed_time": "0:42:45", "remaining_time": "9:52:29"}
+{"current_steps": 8, "total_steps": 104, "loss": 0.6178, "lr": 1.4545454545454546e-05, "epoch": 0.1536, "percentage": 7.69, "elapsed_time": "0:48:04", "remaining_time": "9:36:59"}
+{"current_steps": 9, "total_steps": 104, "loss": 0.6484, "lr": 1.6363636363636366e-05, "epoch": 0.1728, "percentage": 8.65, "elapsed_time": "0:53:50", "remaining_time": "9:28:15"}
+{"current_steps": 10, "total_steps": 104, "loss": 0.6111, "lr": 1.8181818181818182e-05, "epoch": 0.192, "percentage": 9.62, "elapsed_time": "1:00:03", "remaining_time": "9:24:32"}
+{"current_steps": 11, "total_steps": 104, "loss": 0.6009, "lr": 2e-05, "epoch": 0.2112, "percentage": 10.58, "elapsed_time": "1:05:43", "remaining_time": "9:15:42"}
+{"current_steps": 12, "total_steps": 104, "loss": 0.6054, "lr": 1.999429490929718e-05, "epoch": 0.2304, "percentage": 11.54, "elapsed_time": "1:11:53", "remaining_time": "9:11:09"}
+{"current_steps": 13, "total_steps": 104, "loss": 0.5779, "lr": 1.9977186146800707e-05, "epoch": 0.2496, "percentage": 12.5, "elapsed_time": "1:18:24", "remaining_time": "9:08:48"}
+{"current_steps": 14, "total_steps": 104, "loss": 0.5472, "lr": 1.994869323391895e-05, "epoch": 0.2688, "percentage": 13.46, "elapsed_time": "1:24:26", "remaining_time": "9:02:47"}
+{"current_steps": 15, "total_steps": 104, "loss": 0.5776, "lr": 1.990884868158239e-05, "epoch": 0.288, "percentage": 14.42, "elapsed_time": "1:29:52", "remaining_time": "8:53:12"}
+{"current_steps": 16, "total_steps": 104, "loss": 0.5392, "lr": 1.985769795314804e-05, "epoch": 0.3072, "percentage": 15.38, "elapsed_time": "1:36:01", "remaining_time": "8:48:09"}
+{"current_steps": 17, "total_steps": 104, "loss": 0.5566, "lr": 1.9795299412524948e-05, "epoch": 0.3264, "percentage": 16.35, "elapsed_time": "1:42:06", "remaining_time": "8:42:31"}
+{"current_steps": 18, "total_steps": 104, "loss": 0.5294, "lr": 1.9721724257579907e-05, "epoch": 0.3456, "percentage": 17.31, "elapsed_time": "1:47:05", "remaining_time": "8:31:40"}
+{"current_steps": 19, "total_steps": 104, "loss": 0.5143, "lr": 1.963705643889941e-05, "epoch": 0.3648, "percentage": 18.27, "elapsed_time": "1:52:02", "remaining_time": "8:21:14"}
+{"current_steps": 20, "total_steps": 104, "loss": 0.5348, "lr": 1.954139256400049e-05, "epoch": 0.384, "percentage": 19.23, "elapsed_time": "1:58:36", "remaining_time": "8:18:09"}
+{"current_steps": 21, "total_steps": 104, "loss": 0.5125, "lr": 1.9434841787099804e-05, "epoch": 0.4032, "percentage": 20.19, "elapsed_time": "2:05:03", "remaining_time": "8:14:15"}
+{"current_steps": 22, "total_steps": 104, "loss": 0.523, "lr": 1.9317525684566686e-05, "epoch": 0.4224, "percentage": 21.15, "elapsed_time": "2:10:43", "remaining_time": "8:07:13"}
+{"current_steps": 23, "total_steps": 104, "loss": 0.5475, "lr": 1.918957811620231e-05, "epoch": 0.4416, "percentage": 22.12, "elapsed_time": "2:16:06", "remaining_time": "7:59:18"}
+{"current_steps": 24, "total_steps": 104, "loss": 0.5069, "lr": 1.9051145072503216e-05, "epoch": 0.4608, "percentage": 23.08, "elapsed_time": "2:21:54", "remaining_time": "7:53:00"}
+{"current_steps": 25, "total_steps": 104, "loss": 0.5207, "lr": 1.8902384508083518e-05, "epoch": 0.48, "percentage": 24.04, "elapsed_time": "2:27:03", "remaining_time": "7:44:41"}
+{"current_steps": 26, "total_steps": 104, "loss": 0.4958, "lr": 1.8743466161445823e-05, "epoch": 0.4992, "percentage": 25.0, "elapsed_time": "2:32:34", "remaining_time": "7:37:43"}
+{"current_steps": 27, "total_steps": 104, "loss": 0.4893, "lr": 1.857457136130651e-05, "epoch": 0.5184, "percentage": 25.96, "elapsed_time": "2:38:24", "remaining_time": "7:31:46"}
+{"current_steps": 28, "total_steps": 104, "loss": 0.5023, "lr": 1.839589281969639e-05, "epoch": 0.5376, "percentage": 26.92, "elapsed_time": "2:43:57", "remaining_time": "7:25:01"}
+{"current_steps": 29, "total_steps": 104, "loss": 0.4896, "lr": 1.8207634412072765e-05, "epoch": 0.5568, "percentage": 27.88, "elapsed_time": "2:49:46", "remaining_time": "7:19:04"}
+{"current_steps": 30, "total_steps": 104, "loss": 0.5175, "lr": 1.8010010944693846e-05, "epoch": 0.576, "percentage": 28.85, "elapsed_time": "2:55:19", "remaining_time": "7:12:28"}
+{"current_steps": 31, "total_steps": 104, "loss": 0.4903, "lr": 1.780324790952092e-05, "epoch": 0.5952, "percentage": 29.81, "elapsed_time": "3:00:35", "remaining_time": "7:05:15"}
+{"current_steps": 32, "total_steps": 104, "loss": 0.4788, "lr": 1.758758122692791e-05, "epoch": 0.6144, "percentage": 30.77, "elapsed_time": "3:06:31", "remaining_time": "6:59:39"}
+{"current_steps": 33, "total_steps": 104, "loss": 0.4968, "lr": 1.7363256976511972e-05, "epoch": 0.6336, "percentage": 31.73, "elapsed_time": "3:12:47", "remaining_time": "6:54:48"}
+{"current_steps": 34, "total_steps": 104, "loss": 0.4759, "lr": 1.7130531116312202e-05, "epoch": 0.6528, "percentage": 32.69, "elapsed_time": "3:18:40", "remaining_time": "6:49:01"}
+{"current_steps": 35, "total_steps": 104, "loss": 0.4855, "lr": 1.688966919075687e-05, "epoch": 0.672, "percentage": 33.65, "elapsed_time": "3:24:09", "remaining_time": "6:42:28"}
+{"current_steps": 36, "total_steps": 104, "loss": 0.4848, "lr": 1.6640946027672395e-05, "epoch": 0.6912, "percentage": 34.62, "elapsed_time": "3:30:19", "remaining_time": "6:37:16"}
+{"current_steps": 37, "total_steps": 104, "loss": 0.4924, "lr": 1.6384645424699835e-05, "epoch": 0.7104, "percentage": 35.58, "elapsed_time": "3:36:45", "remaining_time": "6:32:31"}
+{"current_steps": 38, "total_steps": 104, "loss": 0.4847, "lr": 1.612105982547663e-05, "epoch": 0.7296, "percentage": 36.54, "elapsed_time": "3:43:29", "remaining_time": "6:28:09"}
+{"current_steps": 39, "total_steps": 104, "loss": 0.4889, "lr": 1.5850489985953076e-05, "epoch": 0.7488, "percentage": 37.5, "elapsed_time": "3:49:08", "remaining_time": "6:21:54"}
+{"current_steps": 40, "total_steps": 104, "loss": 0.4797, "lr": 1.5573244631224364e-05, "epoch": 0.768, "percentage": 38.46, "elapsed_time": "3:55:14", "remaining_time": "6:16:23"}
+{"current_steps": 41, "total_steps": 104, "loss": 0.4884, "lr": 1.5289640103269626e-05, "epoch": 0.7872, "percentage": 39.42, "elapsed_time": "4:01:01", "remaining_time": "6:10:21"}
+{"current_steps": 42, "total_steps": 104, "loss": 0.4464, "lr": 1.5000000000000002e-05, "epoch": 0.8064, "percentage": 40.38, "elapsed_time": "4:07:05", "remaining_time": "6:04:44"}
+{"current_steps": 43, "total_steps": 104, "loss": 0.4762, "lr": 1.4704654806027558e-05, "epoch": 0.8256, "percentage": 41.35, "elapsed_time": "4:12:45", "remaining_time": "5:58:33"}
+{"current_steps": 44, "total_steps": 104, "loss": 0.4554, "lr": 1.4403941515576344e-05, "epoch": 0.8448, "percentage": 42.31, "elapsed_time": "4:19:54", "remaining_time": "5:54:25"}
+{"current_steps": 45, "total_steps": 104, "loss": 0.4893, "lr": 1.4098203247965876e-05, "epoch": 0.864, "percentage": 43.27, "elapsed_time": "4:25:43", "remaining_time": "5:48:23"}
+{"current_steps": 46, "total_steps": 104, "loss": 0.4668, "lr": 1.3787788856105762e-05, "epoch": 0.8832, "percentage": 44.23, "elapsed_time": "4:31:13", "remaining_time": "5:41:58"}
+{"current_steps": 47, "total_steps": 104, "loss": 0.4757, "lr": 1.3473052528448203e-05, "epoch": 0.9024, "percentage": 45.19, "elapsed_time": "4:37:40", "remaining_time": "5:36:45"}
+{"current_steps": 48, "total_steps": 104, "loss": 0.487, "lr": 1.3154353384852559e-05, "epoch": 0.9216, "percentage": 46.15, "elapsed_time": "4:44:04", "remaining_time": "5:31:25"}
+{"current_steps": 49, "total_steps": 104, "loss": 0.4862, "lr": 1.283205506682304e-05, "epoch": 0.9408, "percentage": 47.12, "elapsed_time": "4:49:36", "remaining_time": "5:25:04"}
+{"current_steps": 50, "total_steps": 104, "loss": 0.4633, "lr": 1.2506525322587207e-05, "epoch": 0.96, "percentage": 48.08, "elapsed_time": "4:54:20", "remaining_time": "5:17:53"}
+{"current_steps": 51, "total_steps": 104, "loss": 0.4542, "lr": 1.2178135587488515e-05, "epoch": 0.9792, "percentage": 49.04, "elapsed_time": "4:59:46", "remaining_time": "5:11:31"}
+{"current_steps": 52, "total_steps": 104, "loss": 0.4683, "lr": 1.1847260560171895e-05, "epoch": 0.9984, "percentage": 50.0, "elapsed_time": "5:04:30", "remaining_time": "5:04:30"}
+{"current_steps": 53, "total_steps": 104, "loss": 0.8037, "lr": 1.1514277775045768e-05, "epoch": 1.0176, "percentage": 50.96, "elapsed_time": "5:10:07", "remaining_time": "4:58:25"}
+{"current_steps": 54, "total_steps": 104, "loss": 0.4256, "lr": 1.1179567171508463e-05, "epoch": 1.0368, "percentage": 51.92, "elapsed_time": "5:15:52", "remaining_time": "4:52:28"}
+{"current_steps": 55, "total_steps": 104, "loss": 0.3927, "lr": 1.0843510660430447e-05, "epoch": 1.056, "percentage": 52.88, "elapsed_time": "5:20:59", "remaining_time": "4:45:58"}
+{"current_steps": 56, "total_steps": 104, "loss": 0.4463, "lr": 1.0506491688387128e-05, "epoch": 1.0752, "percentage": 53.85, "elapsed_time": "5:26:34", "remaining_time": "4:39:55"}
+{"current_steps": 57, "total_steps": 104, "loss": 0.4116, "lr": 1.0168894800139311e-05, "epoch": 1.0944, "percentage": 54.81, "elapsed_time": "5:33:11", "remaining_time": "4:34:44"}
+{"current_steps": 58, "total_steps": 104, "loss": 0.463, "lr": 9.83110519986069e-06, "epoch": 1.1136, "percentage": 55.77, "elapsed_time": "5:40:58", "remaining_time": "4:30:25"}
+{"current_steps": 59, "total_steps": 104, "loss": 0.4379, "lr": 9.493508311612874e-06, "epoch": 1.1328, "percentage": 56.73, "elapsed_time": "5:46:32", "remaining_time": "4:24:18"}
+{"current_steps": 60, "total_steps": 104, "loss": 0.4133, "lr": 9.156489339569555e-06, "epoch": 1.152, "percentage": 57.69, "elapsed_time": "5:52:21", "remaining_time": "4:18:24"}
+{"current_steps": 61, "total_steps": 104, "loss": 0.4336, "lr": 8.820432828491542e-06, "epoch": 1.1712, "percentage": 58.65, "elapsed_time": "5:58:54", "remaining_time": "4:13:00"}
+{"current_steps": 62, "total_steps": 104, "loss": 0.4075, "lr": 8.485722224954237e-06, "epoch": 1.1904, "percentage": 59.62, "elapsed_time": "6:04:34", "remaining_time": "4:06:58"}
+{"current_steps": 63, "total_steps": 104, "loss": 0.3901, "lr": 8.15273943982811e-06, "epoch": 1.2096, "percentage": 60.58, "elapsed_time": "6:09:43", "remaining_time": "4:00:36"}
+{"current_steps": 64, "total_steps": 104, "loss": 0.4606, "lr": 7.821864412511485e-06, "epoch": 1.2288000000000001, "percentage": 61.54, "elapsed_time": "6:16:23", "remaining_time": "3:55:14"}
+{"current_steps": 65, "total_steps": 104, "loss": 0.3955, "lr": 7.493474677412795e-06, "epoch": 1.248, "percentage": 62.5, "elapsed_time": "6:22:13", "remaining_time": "3:49:20"}
+{"current_steps": 66, "total_steps": 104, "loss": 0.4068, "lr": 7.16794493317696e-06, "epoch": 1.2671999999999999, "percentage": 63.46, "elapsed_time": "6:28:13", "remaining_time": "3:43:31"}
+{"current_steps": 67, "total_steps": 104, "loss": 0.4234, "lr": 6.845646615147445e-06, "epoch": 1.2864, "percentage": 64.42, "elapsed_time": "6:33:39", "remaining_time": "3:37:23"}
+{"current_steps": 68, "total_steps": 104, "loss": 0.4408, "lr": 6.526947471551799e-06, "epoch": 1.3056, "percentage": 65.38, "elapsed_time": "6:39:54", "remaining_time": "3:31:42"}
+{"current_steps": 69, "total_steps": 104, "loss": 0.3869, "lr": 6.21221114389424e-06, "epoch": 1.3248, "percentage": 66.35, "elapsed_time": "6:45:38", "remaining_time": "3:25:45"}
+{"current_steps": 70, "total_steps": 104, "loss": 0.3938, "lr": 5.901796752034128e-06, "epoch": 1.3439999999999999, "percentage": 67.31, "elapsed_time": "6:51:48", "remaining_time": "3:20:01"}
+{"current_steps": 71, "total_steps": 104, "loss": 0.4234, "lr": 5.5960584844236565e-06, "epoch": 1.3632, "percentage": 68.27, "elapsed_time": "6:58:02", "remaining_time": "3:14:18"}
+{"current_steps": 72, "total_steps": 104, "loss": 0.4703, "lr": 5.295345193972445e-06, "epoch": 1.3824, "percentage": 69.23, "elapsed_time": "7:05:09", "remaining_time": "3:08:57"}
+{"current_steps": 73, "total_steps": 104, "loss": 0.3932, "lr": 5.000000000000003e-06, "epoch": 1.4016, "percentage": 70.19, "elapsed_time": "7:10:04", "remaining_time": "3:02:37"}
+{"current_steps": 74, "total_steps": 104, "loss": 0.4027, "lr": 4.710359896730379e-06, "epoch": 1.4208, "percentage": 71.15, "elapsed_time": "7:15:18", "remaining_time": "2:56:28"}
+{"current_steps": 75, "total_steps": 104, "loss": 0.4311, "lr": 4.426755368775637e-06, "epoch": 1.44, "percentage": 72.12, "elapsed_time": "7:20:48", "remaining_time": "2:50:26"}
+{"current_steps": 76, "total_steps": 104, "loss": 0.376, "lr": 4.149510014046922e-06, "epoch": 1.4592, "percentage": 73.08, "elapsed_time": "7:26:38", "remaining_time": "2:44:33"}
+{"current_steps": 77, "total_steps": 104, "loss": 0.4595, "lr": 3.878940174523371e-06, "epoch": 1.4784, "percentage": 74.04, "elapsed_time": "7:32:51", "remaining_time": "2:38:47"}
+{"current_steps": 78, "total_steps": 104, "loss": 0.3897, "lr": 3.6153545753001663e-06, "epoch": 1.4976, "percentage": 75.0, "elapsed_time": "7:38:33", "remaining_time": "2:32:51"}
+{"current_steps": 79, "total_steps": 104, "loss": 0.4137, "lr": 3.3590539723276083e-06, "epoch": 1.5168, "percentage": 75.96, "elapsed_time": "7:43:53", "remaining_time": "2:26:48"}
+{"current_steps": 80, "total_steps": 104, "loss": 0.3905, "lr": 3.110330809243134e-06, "epoch": 1.536, "percentage": 76.92, "elapsed_time": "7:49:12", "remaining_time": "2:20:45"}
+{"current_steps": 81, "total_steps": 104, "loss": 0.4473, "lr": 2.869468883687798e-06, "epoch": 1.5552000000000001, "percentage": 77.88, "elapsed_time": "7:54:55", "remaining_time": "2:14:51"}
+{"current_steps": 82, "total_steps": 104, "loss": 0.3892, "lr": 2.6367430234880286e-06, "epoch": 1.5744, "percentage": 78.85, "elapsed_time": "8:01:28", "remaining_time": "2:09:10"}
+{"current_steps": 83, "total_steps": 104, "loss": 0.4159, "lr": 2.4124187730720916e-06, "epoch": 1.5936, "percentage": 79.81, "elapsed_time": "8:07:17", "remaining_time": "2:03:17"}
+{"current_steps": 84, "total_steps": 104, "loss": 0.3836, "lr": 2.196752090479083e-06, "epoch": 1.6128, "percentage": 80.77, "elapsed_time": "8:12:04", "remaining_time": "1:57:09"}
+{"current_steps": 85, "total_steps": 104, "loss": 0.409, "lr": 1.9899890553061565e-06, "epoch": 1.6320000000000001, "percentage": 81.73, "elapsed_time": "8:18:25", "remaining_time": "1:51:24"}
+{"current_steps": 86, "total_steps": 104, "loss": 0.4006, "lr": 1.7923655879272395e-06, "epoch": 1.6512, "percentage": 82.69, "elapsed_time": "8:22:51", "remaining_time": "1:45:14"}
+{"current_steps": 87, "total_steps": 104, "loss": 0.3883, "lr": 1.60410718030361e-06, "epoch": 1.6703999999999999, "percentage": 83.65, "elapsed_time": "8:28:18", "remaining_time": "1:39:19"}
+{"current_steps": 88, "total_steps": 104, "loss": 0.4117, "lr": 1.425428638693489e-06, "epoch": 1.6896, "percentage": 84.62, "elapsed_time": "8:34:08", "remaining_time": "1:33:28"}
+{"current_steps": 89, "total_steps": 104, "loss": 0.4345, "lr": 1.2565338385541792e-06, "epoch": 1.7088, "percentage": 85.58, "elapsed_time": "8:39:07", "remaining_time": "1:27:29"}
+{"current_steps": 90, "total_steps": 104, "loss": 0.4002, "lr": 1.097615491916485e-06, "epoch": 1.728, "percentage": 86.54, "elapsed_time": "8:43:55", "remaining_time": "1:21:29"}
+{"current_steps": 91, "total_steps": 104, "loss": 0.4242, "lr": 9.488549274967873e-07, "epoch": 1.7471999999999999, "percentage": 87.5, "elapsed_time": "8:49:53", "remaining_time": "1:15:41"}
+{"current_steps": 92, "total_steps": 104, "loss": 0.3806, "lr": 8.10421883797694e-07, "epoch": 1.7664, "percentage": 88.46, "elapsed_time": "8:55:38", "remaining_time": "1:09:51"}
+{"current_steps": 93, "total_steps": 104, "loss": 0.4056, "lr": 6.824743154333157e-07, "epoch": 1.7856, "percentage": 89.42, "elapsed_time": "9:01:29", "remaining_time": "1:04:02"}
+{"current_steps": 94, "total_steps": 104, "loss": 0.3898, "lr": 5.651582129001987e-07, "epoch": 1.8048, "percentage": 90.38, "elapsed_time": "9:07:05", "remaining_time": "0:58:12"}
+{"current_steps": 95, "total_steps": 104, "loss": 0.3878, "lr": 4.5860743599951186e-07, "epoch": 1.8239999999999998, "percentage": 91.35, "elapsed_time": "9:12:09", "remaining_time": "0:52:18"}
+{"current_steps": 96, "total_steps": 104, "loss": 0.4132, "lr": 3.629435611005916e-07, "epoch": 1.8432, "percentage": 92.31, "elapsed_time": "9:17:07", "remaining_time": "0:46:25"}
+{"current_steps": 97, "total_steps": 104, "loss": 0.3657, "lr": 2.7827574242009434e-07, "epoch": 1.8624, "percentage": 93.27, "elapsed_time": "9:22:46", "remaining_time": "0:40:36"}
+{"current_steps": 98, "total_steps": 104, "loss": 0.4006, "lr": 2.0470058747505516e-07, "epoch": 1.8816000000000002, "percentage": 94.23, "elapsed_time": "9:28:05", "remaining_time": "0:34:46"}
+{"current_steps": 99, "total_steps": 104, "loss": 0.3919, "lr": 1.4230204685196202e-07, "epoch": 1.9008, "percentage": 95.19, "elapsed_time": "9:34:01", "remaining_time": "0:28:59"}
+{"current_steps": 100, "total_steps": 104, "loss": 0.4231, "lr": 9.11513184176116e-08, "epoch": 1.92, "percentage": 96.15, "elapsed_time": "9:40:20", "remaining_time": "0:23:12"}
+{"current_steps": 101, "total_steps": 104, "loss": 0.3911, "lr": 5.1306766081048456e-08, "epoch": 1.9392, "percentage": 97.12, "elapsed_time": "9:51:13", "remaining_time": "0:17:33"}
+{"current_steps": 102, "total_steps": 104, "loss": 0.4391, "lr": 2.2813853199292745e-08, "epoch": 1.9584000000000001, "percentage": 98.08, "elapsed_time": "9:56:53", "remaining_time": "0:11:42"}
+{"current_steps": 103, "total_steps": 104, "loss": 0.4069, "lr": 5.705090702819993e-09, "epoch": 1.9776, "percentage": 99.04, "elapsed_time": "10:01:40", "remaining_time": "0:05:50"}
+{"current_steps": 104, "total_steps": 104, "loss": 0.4599, "lr": 0.0, "epoch": 1.9968, "percentage": 100.0, "elapsed_time": "10:08:13", "remaining_time": "0:00:00"}
+{"current_steps": 104, "total_steps": 104, "epoch": 1.9968, "percentage": 100.0, "elapsed_time": "10:13:10", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,770 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9968,
+  "eval_steps": 500,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0192,
+      "grad_norm": 2.423678398132324,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7932,
+      "step": 1
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 2.6566708087921143,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7613,
+      "step": 2
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 2.337695837020874,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.8108,
+      "step": 3
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 1.94878351688385,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.7694,
+      "step": 4
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 1.4400192499160767,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.7506,
+      "step": 5
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 1.514625906944275,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.6907,
+      "step": 6
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 1.185624599456787,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.68,
+      "step": 7
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 1.3777049779891968,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.6178,
+      "step": 8
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 1.2356456518173218,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.6484,
+      "step": 9
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.9463790059089661,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.6111,
+      "step": 10
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 1.3397246599197388,
+      "learning_rate": 2e-05,
+      "loss": 0.6009,
+      "step": 11
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 1.0940124988555908,
+      "learning_rate": 1.999429490929718e-05,
+      "loss": 0.6054,
+      "step": 12
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 0.9236961007118225,
+      "learning_rate": 1.9977186146800707e-05,
+      "loss": 0.5779,
+      "step": 13
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.9376490712165833,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.5472,
+      "step": 14
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.8171873688697815,
+      "learning_rate": 1.990884868158239e-05,
+      "loss": 0.5776,
+      "step": 15
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.5843209624290466,
+      "learning_rate": 1.985769795314804e-05,
+      "loss": 0.5392,
+      "step": 16
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 0.8455219864845276,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 0.5566,
+      "step": 17
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.8293880224227905,
+      "learning_rate": 1.9721724257579907e-05,
+      "loss": 0.5294,
+      "step": 18
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 0.5752674341201782,
+      "learning_rate": 1.963705643889941e-05,
+      "loss": 0.5143,
+      "step": 19
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.6286266446113586,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 0.5348,
+      "step": 20
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 0.6185891032218933,
+      "learning_rate": 1.9434841787099804e-05,
+      "loss": 0.5125,
+      "step": 21
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.6374247074127197,
+      "learning_rate": 1.9317525684566686e-05,
+      "loss": 0.523,
+      "step": 22
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 0.5338121652603149,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 0.5475,
+      "step": 23
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.46796715259552,
+      "learning_rate": 1.9051145072503216e-05,
+      "loss": 0.5069,
+      "step": 24
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5485299825668335,
+      "learning_rate": 1.8902384508083518e-05,
+      "loss": 0.5207,
+      "step": 25
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.4771216809749603,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 0.4958,
+      "step": 26
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 0.41287821531295776,
+      "learning_rate": 1.857457136130651e-05,
+      "loss": 0.4893,
+      "step": 27
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 0.42082297801971436,
+      "learning_rate": 1.839589281969639e-05,
+      "loss": 0.5023,
+      "step": 28
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 0.44994717836380005,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.4896,
+      "step": 29
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.4245263934135437,
+      "learning_rate": 1.8010010944693846e-05,
+      "loss": 0.5175,
+      "step": 30
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 0.3610984981060028,
+      "learning_rate": 1.780324790952092e-05,
+      "loss": 0.4903,
+      "step": 31
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.32125937938690186,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 0.4788,
+      "step": 32
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 0.382164865732193,
+      "learning_rate": 1.7363256976511972e-05,
+      "loss": 0.4968,
+      "step": 33
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 0.33746933937072754,
+      "learning_rate": 1.7130531116312202e-05,
+      "loss": 0.4759,
+      "step": 34
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.38712188601493835,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 0.4855,
+      "step": 35
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.3574568033218384,
+      "learning_rate": 1.6640946027672395e-05,
+      "loss": 0.4848,
+      "step": 36
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 0.33736875653266907,
+      "learning_rate": 1.6384645424699835e-05,
+      "loss": 0.4924,
+      "step": 37
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.3253867030143738,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.4847,
+      "step": 38
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 0.40177786350250244,
+      "learning_rate": 1.5850489985953076e-05,
+      "loss": 0.4889,
+      "step": 39
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.41558143496513367,
+      "learning_rate": 1.5573244631224364e-05,
+      "loss": 0.4797,
+      "step": 40
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 0.35887712240219116,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 0.4884,
+      "step": 41
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.3083953559398651,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4464,
+      "step": 42
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 0.3898048996925354,
+      "learning_rate": 1.4704654806027558e-05,
+      "loss": 0.4762,
+      "step": 43
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.3718198239803314,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.4554,
+      "step": 44
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.4089162349700928,
+      "learning_rate": 1.4098203247965876e-05,
+      "loss": 0.4893,
+      "step": 45
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.3150208592414856,
+      "learning_rate": 1.3787788856105762e-05,
+      "loss": 0.4668,
+      "step": 46
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 0.3481711447238922,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 0.4757,
+      "step": 47
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.343963086605072,
+      "learning_rate": 1.3154353384852559e-05,
+      "loss": 0.487,
+      "step": 48
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 0.328693151473999,
+      "learning_rate": 1.283205506682304e-05,
+      "loss": 0.4862,
+      "step": 49
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3076961636543274,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 0.4633,
+      "step": 50
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 0.3493748605251312,
+      "learning_rate": 1.2178135587488515e-05,
+      "loss": 0.4542,
+      "step": 51
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.3048100769519806,
+      "learning_rate": 1.1847260560171895e-05,
+      "loss": 0.4683,
+      "step": 52
+    },
+    {
+      "epoch": 1.0176,
+      "grad_norm": 0.8771734237670898,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 0.8037,
+      "step": 53
+    },
+    {
+      "epoch": 1.0368,
+      "grad_norm": 0.3285163640975952,
+      "learning_rate": 1.1179567171508463e-05,
+      "loss": 0.4256,
+      "step": 54
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.3323395252227783,
+      "learning_rate": 1.0843510660430447e-05,
+      "loss": 0.3927,
+      "step": 55
+    },
+    {
+      "epoch": 1.0752,
+      "grad_norm": 0.3365606963634491,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 0.4463,
+      "step": 56
+    },
+    {
+      "epoch": 1.0944,
+      "grad_norm": 0.31812021136283875,
+      "learning_rate": 1.0168894800139311e-05,
+      "loss": 0.4116,
+      "step": 57
+    },
+    {
+      "epoch": 1.1136,
+      "grad_norm": 0.38818055391311646,
+      "learning_rate": 9.83110519986069e-06,
+      "loss": 0.463,
+      "step": 58
+    },
+    {
+      "epoch": 1.1328,
+      "grad_norm": 0.30687442421913147,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.4379,
+      "step": 59
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.2939879596233368,
+      "learning_rate": 9.156489339569555e-06,
+      "loss": 0.4133,
+      "step": 60
+    },
+    {
+      "epoch": 1.1712,
+      "grad_norm": 0.3425482511520386,
+      "learning_rate": 8.820432828491542e-06,
+      "loss": 0.4336,
+      "step": 61
+    },
+    {
+      "epoch": 1.1904,
+      "grad_norm": 0.2907508909702301,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 0.4075,
+      "step": 62
+    },
+    {
+      "epoch": 1.2096,
+      "grad_norm": 0.3222837448120117,
+      "learning_rate": 8.15273943982811e-06,
+      "loss": 0.3901,
+      "step": 63
+    },
+    {
+      "epoch": 1.2288000000000001,
+      "grad_norm": 0.31006520986557007,
+      "learning_rate": 7.821864412511485e-06,
+      "loss": 0.4606,
+      "step": 64
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.264212042093277,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 0.3955,
+      "step": 65
+    },
+    {
+      "epoch": 1.2671999999999999,
+      "grad_norm": 0.27319130301475525,
+      "learning_rate": 7.16794493317696e-06,
+      "loss": 0.4068,
+      "step": 66
+    },
+    {
+      "epoch": 1.2864,
+      "grad_norm": 0.28153327107429504,
+      "learning_rate": 6.845646615147445e-06,
+      "loss": 0.4234,
+      "step": 67
+    },
+    {
+      "epoch": 1.3056,
+      "grad_norm": 0.3072468042373657,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.4408,
+      "step": 68
+    },
+    {
+      "epoch": 1.3248,
+      "grad_norm": 0.2795600891113281,
+      "learning_rate": 6.21221114389424e-06,
+      "loss": 0.3869,
+      "step": 69
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.2556418180465698,
+      "learning_rate": 5.901796752034128e-06,
+      "loss": 0.3938,
+      "step": 70
+    },
+    {
+      "epoch": 1.3632,
+      "grad_norm": 0.28127527236938477,
+      "learning_rate": 5.5960584844236565e-06,
+      "loss": 0.4234,
+      "step": 71
+    },
+    {
+      "epoch": 1.3824,
+      "grad_norm": 0.2638583481311798,
+      "learning_rate": 5.295345193972445e-06,
+      "loss": 0.4703,
+      "step": 72
+    },
+    {
+      "epoch": 1.4016,
+      "grad_norm": 0.2525731325149536,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3932,
+      "step": 73
+    },
+    {
+      "epoch": 1.4208,
+      "grad_norm": 0.25701409578323364,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.4027,
+      "step": 74
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.29077157378196716,
+      "learning_rate": 4.426755368775637e-06,
+      "loss": 0.4311,
+      "step": 75
+    },
+    {
+      "epoch": 1.4592,
+      "grad_norm": 0.2595595717430115,
+      "learning_rate": 4.149510014046922e-06,
+      "loss": 0.376,
+      "step": 76
+    },
+    {
+      "epoch": 1.4784,
+      "grad_norm": 0.30198609828948975,
+      "learning_rate": 3.878940174523371e-06,
+      "loss": 0.4595,
+      "step": 77
+    },
+    {
+      "epoch": 1.4976,
+      "grad_norm": 0.2653771936893463,
+      "learning_rate": 3.6153545753001663e-06,
+      "loss": 0.3897,
+      "step": 78
+    },
+    {
+      "epoch": 1.5168,
+      "grad_norm": 0.25373411178588867,
+      "learning_rate": 3.3590539723276083e-06,
+      "loss": 0.4137,
+      "step": 79
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.22587552666664124,
+      "learning_rate": 3.110330809243134e-06,
+      "loss": 0.3905,
+      "step": 80
+    },
+    {
+      "epoch": 1.5552000000000001,
+      "grad_norm": 0.2660175859928131,
+      "learning_rate": 2.869468883687798e-06,
+      "loss": 0.4473,
+      "step": 81
+    },
+    {
+      "epoch": 1.5744,
+      "grad_norm": 0.23747386038303375,
+      "learning_rate": 2.6367430234880286e-06,
+      "loss": 0.3892,
+      "step": 82
+    },
+    {
+      "epoch": 1.5936,
+      "grad_norm": 0.22769302129745483,
+      "learning_rate": 2.4124187730720916e-06,
+      "loss": 0.4159,
+      "step": 83
+    },
+    {
+      "epoch": 1.6128,
+      "grad_norm": 0.27097997069358826,
+      "learning_rate": 2.196752090479083e-06,
+      "loss": 0.3836,
+      "step": 84
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.2471567988395691,
+      "learning_rate": 1.9899890553061565e-06,
+      "loss": 0.409,
+      "step": 85
+    },
+    {
+      "epoch": 1.6512,
+      "grad_norm": 0.263854056596756,
+      "learning_rate": 1.7923655879272395e-06,
+      "loss": 0.4006,
+      "step": 86
+    },
+    {
+      "epoch": 1.6703999999999999,
+      "grad_norm": 0.23444706201553345,
+      "learning_rate": 1.60410718030361e-06,
+      "loss": 0.3883,
+      "step": 87
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.23784613609313965,
+      "learning_rate": 1.425428638693489e-06,
+      "loss": 0.4117,
+      "step": 88
+    },
+    {
+      "epoch": 1.7088,
+      "grad_norm": 0.25254783034324646,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.4345,
+      "step": 89
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.2234947681427002,
+      "learning_rate": 1.097615491916485e-06,
+      "loss": 0.4002,
+      "step": 90
+    },
+    {
+      "epoch": 1.7471999999999999,
+      "grad_norm": 0.2332143634557724,
+      "learning_rate": 9.488549274967873e-07,
+      "loss": 0.4242,
+      "step": 91
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.21657587587833405,
+      "learning_rate": 8.10421883797694e-07,
+      "loss": 0.3806,
+      "step": 92
+    },
+    {
+      "epoch": 1.7856,
+      "grad_norm": 0.20751075446605682,
+      "learning_rate": 6.824743154333157e-07,
+      "loss": 0.4056,
+      "step": 93
+    },
+    {
+      "epoch": 1.8048,
+      "grad_norm": 0.2177955061197281,
+      "learning_rate": 5.651582129001987e-07,
+      "loss": 0.3898,
+      "step": 94
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.22828799486160278,
+      "learning_rate": 4.5860743599951186e-07,
+      "loss": 0.3878,
+      "step": 95
+    },
+    {
+      "epoch": 1.8432,
+      "grad_norm": 0.2466111183166504,
+      "learning_rate": 3.629435611005916e-07,
+      "loss": 0.4132,
+      "step": 96
+    },
+    {
+      "epoch": 1.8624,
+      "grad_norm": 0.21871791779994965,
+      "learning_rate": 2.7827574242009434e-07,
+      "loss": 0.3657,
+      "step": 97
+    },
+    {
+      "epoch": 1.8816000000000002,
+      "grad_norm": 0.2354569435119629,
+      "learning_rate": 2.0470058747505516e-07,
+      "loss": 0.4006,
+      "step": 98
+    },
+    {
+      "epoch": 1.9008,
+      "grad_norm": 0.20780694484710693,
+      "learning_rate": 1.4230204685196202e-07,
+      "loss": 0.3919,
+      "step": 99
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.19831795990467072,
+      "learning_rate": 9.11513184176116e-08,
+      "loss": 0.4231,
+      "step": 100
+    },
+    {
+      "epoch": 1.9392,
+      "grad_norm": 0.21838048100471497,
+      "learning_rate": 5.1306766081048456e-08,
+      "loss": 0.3911,
+      "step": 101
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.21957120299339294,
+      "learning_rate": 2.2813853199292745e-08,
+      "loss": 0.4391,
+      "step": 102
+    },
+    {
+      "epoch": 1.9776,
+      "grad_norm": 0.22633568942546844,
+      "learning_rate": 5.705090702819993e-09,
+      "loss": 0.4069,
+      "step": 103
+    },
+    {
+      "epoch": 1.9968,
+      "grad_norm": 0.2150619626045227,
+      "learning_rate": 0.0,
+      "loss": 0.4599,
+      "step": 104
+    },
+    {
+      "epoch": 1.9968,
+      "step": 104,
+      "total_flos": 356056961384448.0,
+      "train_loss": 0.48249776661396027,
+      "train_runtime": 36791.677,
+      "train_samples_per_second": 0.272,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 104,
+  "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": 356056961384448.0,
+  "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:ea33973a7c38834a8b66cd5dadae21ccdb1f9aa214e852f18cf265fb23a8d793
+size 7416