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": 1.991111111111111,
+    "total_flos": 621868991119360.0,
+    "train_loss": 0.5655743213636535,
+    "train_runtime": 48561.3008,
+    "train_samples_per_second": 0.222,
+    "train_steps_per_second": 0.002
+}

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 sha256:1bf9bafff9daf46fd511e1954ec8cd6b253db132a13ac1fa807b76a5bbce8d06
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21885214973c6a2e814636c5196c1905bb9c79992f1da93b389ac02776be932b
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247ba74310b0621b3f651ea1366c4d968985728ebe77e81e1c3b740f1097df1e
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c768a5d619d0118c20c6b50fc868c69954f06f4d7e0c7d002d4c02de584b8b
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e3748de3ce9e7b9c55a65543ffafdad8083d26b621afc9e5c752c6f7401c5b
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27848719996d874d8a8d8f90907e0c21dcd03b9ea1acbaf7ea9203db853b1be4
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794780d61c8a98cf4f7945a87ec29e9075492b72d6a6e1b1b11a7feacf07ee1d
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5ccf8343be4271020449192e7a5de1fc8a73fd834c8165028d7f3d126770ed
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1eb21c0b136dda99e24a1f66cddd7e1c4d7c9905dc115ee45aa5403fe4151a6
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2e7087582575d7fffac87fac12cc342d7bfab86025da74495a114716430b4b
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d76837fb9a719abd1095f6dff1db964a7b6402f7510f1a3a3adb5d504eb783
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297bafcb5e9e1bb105132977edf30aa653fb8df82735b10aa9f40fe5ad7d95eb
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f4b51d6aafcbcbbbbede576022226cdd27f732e1f3617e539581a751c7deba
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a8c11820ee7c8506e542e024dfe3c3f8ccb0abbcae564f17ab3f8788a82b51
+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": 1.991111111111111,
+    "total_flos": 621868991119360.0,
+    "train_loss": 0.5655743213636535,
+    "train_runtime": 48561.3008,
+    "train_samples_per_second": 0.222,
+    "train_steps_per_second": 0.002
+}

trainer_log.jsonl

@@ -0,0 +1,113 @@
+{"current_steps": 1, "total_steps": 112, "loss": 0.8771, "lr": 1.6666666666666667e-06, "epoch": 0.017777777777777778, "percentage": 0.89, "elapsed_time": "0:07:35", "remaining_time": "14:03:27"}
+{"current_steps": 2, "total_steps": 112, "loss": 0.8888, "lr": 3.3333333333333333e-06, "epoch": 0.035555555555555556, "percentage": 1.79, "elapsed_time": "0:15:16", "remaining_time": "14:00:04"}
+{"current_steps": 3, "total_steps": 112, "loss": 0.8663, "lr": 5e-06, "epoch": 0.05333333333333334, "percentage": 2.68, "elapsed_time": "0:21:58", "remaining_time": "13:18:16"}
+{"current_steps": 4, "total_steps": 112, "loss": 0.8508, "lr": 6.666666666666667e-06, "epoch": 0.07111111111111111, "percentage": 3.57, "elapsed_time": "0:29:52", "remaining_time": "13:26:47"}
+{"current_steps": 5, "total_steps": 112, "loss": 0.835, "lr": 8.333333333333334e-06, "epoch": 0.08888888888888889, "percentage": 4.46, "elapsed_time": "0:36:56", "remaining_time": "13:10:32"}
+{"current_steps": 6, "total_steps": 112, "loss": 0.8097, "lr": 1e-05, "epoch": 0.10666666666666667, "percentage": 5.36, "elapsed_time": "0:43:25", "remaining_time": "12:47:18"}
+{"current_steps": 7, "total_steps": 112, "loss": 0.7754, "lr": 1.1666666666666668e-05, "epoch": 0.12444444444444444, "percentage": 6.25, "elapsed_time": "0:50:20", "remaining_time": "12:35:07"}
+{"current_steps": 8, "total_steps": 112, "loss": 0.7364, "lr": 1.3333333333333333e-05, "epoch": 0.14222222222222222, "percentage": 7.14, "elapsed_time": "0:57:35", "remaining_time": "12:28:46"}
+{"current_steps": 9, "total_steps": 112, "loss": 0.7091, "lr": 1.5000000000000002e-05, "epoch": 0.16, "percentage": 8.04, "elapsed_time": "1:04:26", "remaining_time": "12:17:25"}
+{"current_steps": 10, "total_steps": 112, "loss": 0.6956, "lr": 1.6666666666666667e-05, "epoch": 0.17777777777777778, "percentage": 8.93, "elapsed_time": "1:11:52", "remaining_time": "12:13:10"}
+{"current_steps": 11, "total_steps": 112, "loss": 0.6811, "lr": 1.8333333333333333e-05, "epoch": 0.19555555555555557, "percentage": 9.82, "elapsed_time": "1:19:06", "remaining_time": "12:06:20"}
+{"current_steps": 12, "total_steps": 112, "loss": 0.681, "lr": 2e-05, "epoch": 0.21333333333333335, "percentage": 10.71, "elapsed_time": "1:27:11", "remaining_time": "12:06:36"}
+{"current_steps": 13, "total_steps": 112, "loss": 0.6716, "lr": 1.9995065603657317e-05, "epoch": 0.2311111111111111, "percentage": 11.61, "elapsed_time": "1:34:50", "remaining_time": "12:02:16"}
+{"current_steps": 14, "total_steps": 112, "loss": 0.635, "lr": 1.9980267284282718e-05, "epoch": 0.24888888888888888, "percentage": 12.5, "elapsed_time": "1:42:09", "remaining_time": "11:55:04"}
+{"current_steps": 15, "total_steps": 112, "loss": 0.6447, "lr": 1.99556196460308e-05, "epoch": 0.26666666666666666, "percentage": 13.39, "elapsed_time": "1:48:43", "remaining_time": "11:43:07"}
+{"current_steps": 16, "total_steps": 112, "loss": 0.6476, "lr": 1.9921147013144782e-05, "epoch": 0.28444444444444444, "percentage": 14.29, "elapsed_time": "1:55:11", "remaining_time": "11:31:11"}
+{"current_steps": 17, "total_steps": 112, "loss": 0.6097, "lr": 1.9876883405951378e-05, "epoch": 0.3022222222222222, "percentage": 15.18, "elapsed_time": "2:01:44", "remaining_time": "11:20:17"}
+{"current_steps": 18, "total_steps": 112, "loss": 0.6127, "lr": 1.982287250728689e-05, "epoch": 0.32, "percentage": 16.07, "elapsed_time": "2:09:16", "remaining_time": "11:15:07"}
+{"current_steps": 19, "total_steps": 112, "loss": 0.6112, "lr": 1.9759167619387474e-05, "epoch": 0.3377777777777778, "percentage": 16.96, "elapsed_time": "2:16:32", "remaining_time": "11:08:17"}
+{"current_steps": 20, "total_steps": 112, "loss": 0.6022, "lr": 1.9685831611286312e-05, "epoch": 0.35555555555555557, "percentage": 17.86, "elapsed_time": "2:22:56", "remaining_time": "10:57:31"}
+{"current_steps": 21, "total_steps": 112, "loss": 0.595, "lr": 1.9602936856769432e-05, "epoch": 0.37333333333333335, "percentage": 18.75, "elapsed_time": "2:29:32", "remaining_time": "10:47:59"}
+{"current_steps": 22, "total_steps": 112, "loss": 0.6057, "lr": 1.9510565162951538e-05, "epoch": 0.39111111111111113, "percentage": 19.64, "elapsed_time": "2:37:13", "remaining_time": "10:43:12"}
+{"current_steps": 23, "total_steps": 112, "loss": 0.6067, "lr": 1.9408807689542257e-05, "epoch": 0.4088888888888889, "percentage": 20.54, "elapsed_time": "2:44:30", "remaining_time": "10:36:34"}
+{"current_steps": 24, "total_steps": 112, "loss": 0.599, "lr": 1.9297764858882516e-05, "epoch": 0.4266666666666667, "percentage": 21.43, "elapsed_time": "2:51:34", "remaining_time": "10:29:05"}
+{"current_steps": 25, "total_steps": 112, "loss": 0.5856, "lr": 1.9177546256839814e-05, "epoch": 0.4444444444444444, "percentage": 22.32, "elapsed_time": "2:58:29", "remaining_time": "10:21:10"}
+{"current_steps": 26, "total_steps": 112, "loss": 0.5798, "lr": 1.9048270524660197e-05, "epoch": 0.4622222222222222, "percentage": 23.21, "elapsed_time": "3:06:10", "remaining_time": "10:15:48"}
+{"current_steps": 27, "total_steps": 112, "loss": 0.5785, "lr": 1.891006524188368e-05, "epoch": 0.48, "percentage": 24.11, "elapsed_time": "3:13:26", "remaining_time": "10:08:58"}
+{"current_steps": 28, "total_steps": 112, "loss": 0.5885, "lr": 1.8763066800438638e-05, "epoch": 0.49777777777777776, "percentage": 25.0, "elapsed_time": "3:21:02", "remaining_time": "10:03:08"}
+{"current_steps": 29, "total_steps": 112, "loss": 0.5897, "lr": 1.860742027003944e-05, "epoch": 0.5155555555555555, "percentage": 25.89, "elapsed_time": "3:28:16", "remaining_time": "9:56:07"}
+{"current_steps": 30, "total_steps": 112, "loss": 0.5739, "lr": 1.8443279255020153e-05, "epoch": 0.5333333333333333, "percentage": 26.79, "elapsed_time": "3:35:30", "remaining_time": "9:49:02"}
+{"current_steps": 31, "total_steps": 112, "loss": 0.5742, "lr": 1.827080574274562e-05, "epoch": 0.5511111111111111, "percentage": 27.68, "elapsed_time": "3:43:18", "remaining_time": "9:43:29"}
+{"current_steps": 32, "total_steps": 112, "loss": 0.5548, "lr": 1.8090169943749477e-05, "epoch": 0.5688888888888889, "percentage": 28.57, "elapsed_time": "3:51:09", "remaining_time": "9:37:52"}
+{"current_steps": 33, "total_steps": 112, "loss": 0.5879, "lr": 1.7901550123756906e-05, "epoch": 0.5866666666666667, "percentage": 29.46, "elapsed_time": "3:57:50", "remaining_time": "9:29:22"}
+{"current_steps": 34, "total_steps": 112, "loss": 0.5588, "lr": 1.7705132427757895e-05, "epoch": 0.6044444444444445, "percentage": 30.36, "elapsed_time": "4:04:46", "remaining_time": "9:21:33"}
+{"current_steps": 35, "total_steps": 112, "loss": 0.5561, "lr": 1.7501110696304598e-05, "epoch": 0.6222222222222222, "percentage": 31.25, "elapsed_time": "4:11:52", "remaining_time": "9:14:06"}
+{"current_steps": 36, "total_steps": 112, "loss": 0.566, "lr": 1.7289686274214116e-05, "epoch": 0.64, "percentage": 32.14, "elapsed_time": "4:18:38", "remaining_time": "9:06:00"}
+{"current_steps": 37, "total_steps": 112, "loss": 0.5702, "lr": 1.7071067811865477e-05, "epoch": 0.6577777777777778, "percentage": 33.04, "elapsed_time": "4:25:45", "remaining_time": "8:58:42"}
+{"current_steps": 38, "total_steps": 112, "loss": 0.5646, "lr": 1.684547105928689e-05, "epoch": 0.6755555555555556, "percentage": 33.93, "elapsed_time": "4:32:42", "remaining_time": "8:51:03"}
+{"current_steps": 39, "total_steps": 112, "loss": 0.5629, "lr": 1.661311865323652e-05, "epoch": 0.6933333333333334, "percentage": 34.82, "elapsed_time": "4:40:19", "remaining_time": "8:44:42"}
+{"current_steps": 40, "total_steps": 112, "loss": 0.5461, "lr": 1.63742398974869e-05, "epoch": 0.7111111111111111, "percentage": 35.71, "elapsed_time": "4:46:58", "remaining_time": "8:36:33"}
+{"current_steps": 41, "total_steps": 112, "loss": 0.5668, "lr": 1.6129070536529767e-05, "epoch": 0.7288888888888889, "percentage": 36.61, "elapsed_time": "4:54:17", "remaining_time": "8:29:37"}
+{"current_steps": 42, "total_steps": 112, "loss": 0.5656, "lr": 1.5877852522924733e-05, "epoch": 0.7466666666666667, "percentage": 37.5, "elapsed_time": "5:01:14", "remaining_time": "8:22:03"}
+{"current_steps": 43, "total_steps": 112, "loss": 0.5529, "lr": 1.5620833778521306e-05, "epoch": 0.7644444444444445, "percentage": 38.39, "elapsed_time": "5:08:12", "remaining_time": "8:14:33"}
+{"current_steps": 44, "total_steps": 112, "loss": 0.5563, "lr": 1.5358267949789968e-05, "epoch": 0.7822222222222223, "percentage": 39.29, "elapsed_time": "5:15:48", "remaining_time": "8:08:03"}
+{"current_steps": 45, "total_steps": 112, "loss": 0.5665, "lr": 1.5090414157503715e-05, "epoch": 0.8, "percentage": 40.18, "elapsed_time": "5:22:33", "remaining_time": "8:00:15"}
+{"current_steps": 46, "total_steps": 112, "loss": 0.5527, "lr": 1.4817536741017153e-05, "epoch": 0.8177777777777778, "percentage": 41.07, "elapsed_time": "5:29:45", "remaining_time": "7:53:08"}
+{"current_steps": 47, "total_steps": 112, "loss": 0.5662, "lr": 1.4539904997395468e-05, "epoch": 0.8355555555555556, "percentage": 41.96, "elapsed_time": "5:37:22", "remaining_time": "7:46:35"}
+{"current_steps": 48, "total_steps": 112, "loss": 0.5447, "lr": 1.4257792915650728e-05, "epoch": 0.8533333333333334, "percentage": 42.86, "elapsed_time": "5:44:24", "remaining_time": "7:39:12"}
+{"current_steps": 49, "total_steps": 112, "loss": 0.5464, "lr": 1.3971478906347806e-05, "epoch": 0.8711111111111111, "percentage": 43.75, "elapsed_time": "5:50:54", "remaining_time": "7:31:09"}
+{"current_steps": 50, "total_steps": 112, "loss": 0.5449, "lr": 1.3681245526846782e-05, "epoch": 0.8888888888888888, "percentage": 44.64, "elapsed_time": "5:58:15", "remaining_time": "7:24:14"}
+{"current_steps": 51, "total_steps": 112, "loss": 0.54, "lr": 1.3387379202452917e-05, "epoch": 0.9066666666666666, "percentage": 45.54, "elapsed_time": "6:05:09", "remaining_time": "7:16:45"}
+{"current_steps": 52, "total_steps": 112, "loss": 0.5543, "lr": 1.3090169943749475e-05, "epoch": 0.9244444444444444, "percentage": 46.43, "elapsed_time": "6:12:55", "remaining_time": "7:10:17"}
+{"current_steps": 53, "total_steps": 112, "loss": 0.5514, "lr": 1.2789911060392295e-05, "epoch": 0.9422222222222222, "percentage": 47.32, "elapsed_time": "6:20:31", "remaining_time": "7:03:36"}
+{"current_steps": 54, "total_steps": 112, "loss": 0.5588, "lr": 1.2486898871648552e-05, "epoch": 0.96, "percentage": 48.21, "elapsed_time": "6:27:21", "remaining_time": "6:56:03"}
+{"current_steps": 55, "total_steps": 112, "loss": 0.5429, "lr": 1.2181432413965428e-05, "epoch": 0.9777777777777777, "percentage": 49.11, "elapsed_time": "6:34:18", "remaining_time": "6:48:38"}
+{"current_steps": 56, "total_steps": 112, "loss": 0.5585, "lr": 1.187381314585725e-05, "epoch": 0.9955555555555555, "percentage": 50.0, "elapsed_time": "6:41:08", "remaining_time": "6:41:08"}
+{"current_steps": 57, "total_steps": 112, "loss": 0.9233, "lr": 1.156434465040231e-05, "epoch": 1.0133333333333334, "percentage": 50.89, "elapsed_time": "6:48:07", "remaining_time": "6:33:48"}
+{"current_steps": 58, "total_steps": 112, "loss": 0.544, "lr": 1.1253332335643043e-05, "epoch": 1.031111111111111, "percentage": 51.79, "elapsed_time": "6:55:25", "remaining_time": "6:26:46"}
+{"current_steps": 59, "total_steps": 112, "loss": 0.5149, "lr": 1.0941083133185146e-05, "epoch": 1.048888888888889, "percentage": 52.68, "elapsed_time": "7:03:20", "remaining_time": "6:20:17"}
+{"current_steps": 60, "total_steps": 112, "loss": 0.4813, "lr": 1.0627905195293135e-05, "epoch": 1.0666666666666667, "percentage": 53.57, "elapsed_time": "7:10:17", "remaining_time": "6:12:55"}
+{"current_steps": 61, "total_steps": 112, "loss": 0.5588, "lr": 1.0314107590781284e-05, "epoch": 1.0844444444444445, "percentage": 54.46, "elapsed_time": "7:17:04", "remaining_time": "6:05:25"}
+{"current_steps": 62, "total_steps": 112, "loss": 0.4924, "lr": 1e-05, "epoch": 1.1022222222222222, "percentage": 55.36, "elapsed_time": "7:24:50", "remaining_time": "5:58:44"}
+{"current_steps": 63, "total_steps": 112, "loss": 0.4994, "lr": 9.685892409218718e-06, "epoch": 1.12, "percentage": 56.25, "elapsed_time": "7:31:40", "remaining_time": "5:51:18"}
+{"current_steps": 64, "total_steps": 112, "loss": 0.4862, "lr": 9.372094804706867e-06, "epoch": 1.1377777777777778, "percentage": 57.14, "elapsed_time": "7:39:12", "remaining_time": "5:44:24"}
+{"current_steps": 65, "total_steps": 112, "loss": 0.5294, "lr": 9.058916866814857e-06, "epoch": 1.1555555555555554, "percentage": 58.04, "elapsed_time": "7:47:01", "remaining_time": "5:37:41"}
+{"current_steps": 66, "total_steps": 112, "loss": 0.5222, "lr": 8.746667664356957e-06, "epoch": 1.1733333333333333, "percentage": 58.93, "elapsed_time": "7:54:11", "remaining_time": "5:30:29"}
+{"current_steps": 67, "total_steps": 112, "loss": 0.4697, "lr": 8.43565534959769e-06, "epoch": 1.1911111111111112, "percentage": 59.82, "elapsed_time": "8:00:43", "remaining_time": "5:22:52"}
+{"current_steps": 68, "total_steps": 112, "loss": 0.5343, "lr": 8.126186854142752e-06, "epoch": 1.208888888888889, "percentage": 60.71, "elapsed_time": "8:08:20", "remaining_time": "5:15:59"}
+{"current_steps": 69, "total_steps": 112, "loss": 0.4861, "lr": 7.818567586034578e-06, "epoch": 1.2266666666666666, "percentage": 61.61, "elapsed_time": "8:15:32", "remaining_time": "5:08:48"}
+{"current_steps": 70, "total_steps": 112, "loss": 0.5141, "lr": 7.513101128351454e-06, "epoch": 1.2444444444444445, "percentage": 62.5, "elapsed_time": "8:22:18", "remaining_time": "5:01:23"}
+{"current_steps": 71, "total_steps": 112, "loss": 0.4685, "lr": 7.210088939607709e-06, "epoch": 1.2622222222222224, "percentage": 63.39, "elapsed_time": "8:29:34", "remaining_time": "4:54:15"}
+{"current_steps": 72, "total_steps": 112, "loss": 0.5433, "lr": 6.909830056250527e-06, "epoch": 1.28, "percentage": 64.29, "elapsed_time": "8:36:46", "remaining_time": "4:47:06"}
+{"current_steps": 73, "total_steps": 112, "loss": 0.4569, "lr": 6.612620797547087e-06, "epoch": 1.2977777777777777, "percentage": 65.18, "elapsed_time": "8:43:31", "remaining_time": "4:39:41"}
+{"current_steps": 74, "total_steps": 112, "loss": 0.5253, "lr": 6.318754473153221e-06, "epoch": 1.3155555555555556, "percentage": 66.07, "elapsed_time": "8:51:25", "remaining_time": "4:32:53"}
+{"current_steps": 75, "total_steps": 112, "loss": 0.4791, "lr": 6.028521093652195e-06, "epoch": 1.3333333333333333, "percentage": 66.96, "elapsed_time": "8:58:29", "remaining_time": "4:25:39"}
+{"current_steps": 76, "total_steps": 112, "loss": 0.5268, "lr": 5.742207084349274e-06, "epoch": 1.3511111111111112, "percentage": 67.86, "elapsed_time": "9:06:20", "remaining_time": "4:18:47"}
+{"current_steps": 77, "total_steps": 112, "loss": 0.5033, "lr": 5.460095002604533e-06, "epoch": 1.3688888888888888, "percentage": 68.75, "elapsed_time": "9:13:31", "remaining_time": "4:11:35"}
+{"current_steps": 78, "total_steps": 112, "loss": 0.5263, "lr": 5.1824632589828465e-06, "epoch": 1.3866666666666667, "percentage": 69.64, "elapsed_time": "9:20:48", "remaining_time": "4:04:27"}
+{"current_steps": 79, "total_steps": 112, "loss": 0.4646, "lr": 4.909585842496287e-06, "epoch": 1.4044444444444444, "percentage": 70.54, "elapsed_time": "9:27:52", "remaining_time": "3:57:12"}
+{"current_steps": 80, "total_steps": 112, "loss": 0.4976, "lr": 4.641732050210032e-06, "epoch": 1.4222222222222223, "percentage": 71.43, "elapsed_time": "9:34:49", "remaining_time": "3:49:55"}
+{"current_steps": 81, "total_steps": 112, "loss": 0.5116, "lr": 4.379166221478697e-06, "epoch": 1.44, "percentage": 72.32, "elapsed_time": "9:41:46", "remaining_time": "3:42:39"}
+{"current_steps": 82, "total_steps": 112, "loss": 0.5323, "lr": 4.12214747707527e-06, "epoch": 1.4577777777777778, "percentage": 73.21, "elapsed_time": "9:49:03", "remaining_time": "3:35:30"}
+{"current_steps": 83, "total_steps": 112, "loss": 0.4499, "lr": 3.8709294634702374e-06, "epoch": 1.4755555555555555, "percentage": 74.11, "elapsed_time": "9:55:37", "remaining_time": "3:28:06"}
+{"current_steps": 84, "total_steps": 112, "loss": 0.4826, "lr": 3.625760102513103e-06, "epoch": 1.4933333333333334, "percentage": 75.0, "elapsed_time": "10:02:15", "remaining_time": "3:20:45"}
+{"current_steps": 85, "total_steps": 112, "loss": 0.5218, "lr": 3.3868813467634833e-06, "epoch": 1.511111111111111, "percentage": 75.89, "elapsed_time": "10:09:12", "remaining_time": "3:13:30"}
+{"current_steps": 86, "total_steps": 112, "loss": 0.4953, "lr": 3.1545289407131128e-06, "epoch": 1.528888888888889, "percentage": 76.79, "elapsed_time": "10:15:43", "remaining_time": "3:06:08"}
+{"current_steps": 87, "total_steps": 112, "loss": 0.5141, "lr": 2.9289321881345257e-06, "epoch": 1.5466666666666666, "percentage": 77.68, "elapsed_time": "10:22:35", "remaining_time": "2:58:54"}
+{"current_steps": 88, "total_steps": 112, "loss": 0.5073, "lr": 2.7103137257858867e-06, "epoch": 1.5644444444444443, "percentage": 78.57, "elapsed_time": "10:29:14", "remaining_time": "2:51:36"}
+{"current_steps": 89, "total_steps": 112, "loss": 0.4792, "lr": 2.4988893036954045e-06, "epoch": 1.5822222222222222, "percentage": 79.46, "elapsed_time": "10:36:13", "remaining_time": "2:44:24"}
+{"current_steps": 90, "total_steps": 112, "loss": 0.5097, "lr": 2.2948675722421086e-06, "epoch": 1.6, "percentage": 80.36, "elapsed_time": "10:42:56", "remaining_time": "2:37:09"}
+{"current_steps": 91, "total_steps": 112, "loss": 0.4919, "lr": 2.098449876243096e-06, "epoch": 1.6177777777777778, "percentage": 81.25, "elapsed_time": "10:50:39", "remaining_time": "2:30:09"}
+{"current_steps": 92, "total_steps": 112, "loss": 0.5275, "lr": 1.9098300562505266e-06, "epoch": 1.6355555555555554, "percentage": 82.14, "elapsed_time": "10:58:30", "remaining_time": "2:23:09"}
+{"current_steps": 93, "total_steps": 112, "loss": 0.4784, "lr": 1.7291942572543806e-06, "epoch": 1.6533333333333333, "percentage": 83.04, "elapsed_time": "11:05:05", "remaining_time": "2:15:52"}
+{"current_steps": 94, "total_steps": 112, "loss": 0.5102, "lr": 1.5567207449798517e-06, "epoch": 1.6711111111111112, "percentage": 83.93, "elapsed_time": "11:12:34", "remaining_time": "2:08:47"}
+{"current_steps": 95, "total_steps": 112, "loss": 0.4932, "lr": 1.3925797299605649e-06, "epoch": 1.6888888888888889, "percentage": 84.82, "elapsed_time": "11:19:30", "remaining_time": "2:01:35"}
+{"current_steps": 96, "total_steps": 112, "loss": 0.5106, "lr": 1.2369331995613664e-06, "epoch": 1.7066666666666666, "percentage": 85.71, "elapsed_time": "11:26:14", "remaining_time": "1:54:22"}
+{"current_steps": 97, "total_steps": 112, "loss": 0.51, "lr": 1.0899347581163222e-06, "epoch": 1.7244444444444444, "percentage": 86.61, "elapsed_time": "11:33:51", "remaining_time": "1:47:17"}
+{"current_steps": 98, "total_steps": 112, "loss": 0.4936, "lr": 9.517294753398066e-07, "epoch": 1.7422222222222223, "percentage": 87.5, "elapsed_time": "11:41:24", "remaining_time": "1:40:12"}
+{"current_steps": 99, "total_steps": 112, "loss": 0.4605, "lr": 8.224537431601886e-07, "epoch": 1.76, "percentage": 88.39, "elapsed_time": "11:48:23", "remaining_time": "1:33:01"}
+{"current_steps": 100, "total_steps": 112, "loss": 0.5104, "lr": 7.022351411174866e-07, "epoch": 1.7777777777777777, "percentage": 89.29, "elapsed_time": "11:55:19", "remaining_time": "1:25:50"}
+{"current_steps": 101, "total_steps": 112, "loss": 0.4996, "lr": 5.911923104577455e-07, "epoch": 1.7955555555555556, "percentage": 90.18, "elapsed_time": "12:07:43", "remaining_time": "1:19:15"}
+{"current_steps": 102, "total_steps": 112, "loss": 0.4835, "lr": 4.894348370484648e-07, "epoch": 1.8133333333333335, "percentage": 91.07, "elapsed_time": "12:15:01", "remaining_time": "1:12:03"}
+{"current_steps": 103, "total_steps": 112, "loss": 0.4947, "lr": 3.9706314323056936e-07, "epoch": 1.8311111111111111, "percentage": 91.96, "elapsed_time": "12:21:44", "remaining_time": "1:04:48"}
+{"current_steps": 104, "total_steps": 112, "loss": 0.4762, "lr": 3.1416838871368925e-07, "epoch": 1.8488888888888888, "percentage": 92.86, "elapsed_time": "12:27:31", "remaining_time": "0:57:30"}
+{"current_steps": 105, "total_steps": 112, "loss": 0.5344, "lr": 2.4083238061252565e-07, "epoch": 1.8666666666666667, "percentage": 93.75, "elapsed_time": "12:34:03", "remaining_time": "0:50:16"}
+{"current_steps": 106, "total_steps": 112, "loss": 0.4645, "lr": 1.7712749271311392e-07, "epoch": 1.8844444444444446, "percentage": 94.64, "elapsed_time": "12:40:35", "remaining_time": "0:43:03"}
+{"current_steps": 107, "total_steps": 112, "loss": 0.4809, "lr": 1.231165940486234e-07, "epoch": 1.9022222222222223, "percentage": 95.54, "elapsed_time": "12:47:56", "remaining_time": "0:35:53"}
+{"current_steps": 108, "total_steps": 112, "loss": 0.4858, "lr": 7.885298685522235e-08, "epoch": 1.92, "percentage": 96.43, "elapsed_time": "12:54:13", "remaining_time": "0:28:40"}
+{"current_steps": 109, "total_steps": 112, "loss": 0.5078, "lr": 4.438035396920004e-08, "epoch": 1.9377777777777778, "percentage": 97.32, "elapsed_time": "13:01:06", "remaining_time": "0:21:29"}
+{"current_steps": 110, "total_steps": 112, "loss": 0.5179, "lr": 1.973271571728441e-08, "epoch": 1.9555555555555557, "percentage": 98.21, "elapsed_time": "13:09:12", "remaining_time": "0:14:20"}
+{"current_steps": 111, "total_steps": 112, "loss": 0.4961, "lr": 4.9343963426840006e-09, "epoch": 1.9733333333333334, "percentage": 99.11, "elapsed_time": "13:17:05", "remaining_time": "0:07:10"}
+{"current_steps": 112, "total_steps": 112, "loss": 0.511, "lr": 0.0, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "13:24:04", "remaining_time": "0:00:00"}
+{"current_steps": 112, "total_steps": 112, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "13:29:20", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.991111111111111,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 2.4493284225463867,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8771,
+      "step": 1
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.5336005687713623,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8888,
+      "step": 2
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.3694822788238525,
+      "learning_rate": 5e-06,
+      "loss": 0.8663,
+      "step": 3
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.06482195854187,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8508,
+      "step": 4
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.5644984245300293,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.835,
+      "step": 5
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.4116849899291992,
+      "learning_rate": 1e-05,
+      "loss": 0.8097,
+      "step": 6
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.1847808361053467,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.7754,
+      "step": 7
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.0902292728424072,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7364,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.21918785572052,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7091,
+      "step": 9
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.9935525059700012,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6956,
+      "step": 10
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.4380978345870972,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.6811,
+      "step": 11
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.139083743095398,
+      "learning_rate": 2e-05,
+      "loss": 0.681,
+      "step": 12
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.3757270574569702,
+      "learning_rate": 1.9995065603657317e-05,
+      "loss": 0.6716,
+      "step": 13
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.0465571880340576,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 0.635,
+      "step": 14
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.9036633968353271,
+      "learning_rate": 1.99556196460308e-05,
+      "loss": 0.6447,
+      "step": 15
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.8748593330383301,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.6476,
+      "step": 16
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.7611545920372009,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.6097,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8435001373291016,
+      "learning_rate": 1.982287250728689e-05,
+      "loss": 0.6127,
+      "step": 18
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.1226811408996582,
+      "learning_rate": 1.9759167619387474e-05,
+      "loss": 0.6112,
+      "step": 19
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6948593258857727,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.6022,
+      "step": 20
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.7424058318138123,
+      "learning_rate": 1.9602936856769432e-05,
+      "loss": 0.595,
+      "step": 21
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.6478083729743958,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.6057,
+      "step": 22
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.6245326399803162,
+      "learning_rate": 1.9408807689542257e-05,
+      "loss": 0.6067,
+      "step": 23
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.6616186499595642,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.599,
+      "step": 24
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.5162010192871094,
+      "learning_rate": 1.9177546256839814e-05,
+      "loss": 0.5856,
+      "step": 25
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.46659624576568604,
+      "learning_rate": 1.9048270524660197e-05,
+      "loss": 0.5798,
+      "step": 26
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.48762547969818115,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.5785,
+      "step": 27
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.425236314535141,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.5885,
+      "step": 28
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.4328088164329529,
+      "learning_rate": 1.860742027003944e-05,
+      "loss": 0.5897,
+      "step": 29
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.495597779750824,
+      "learning_rate": 1.8443279255020153e-05,
+      "loss": 0.5739,
+      "step": 30
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.3705892264842987,
+      "learning_rate": 1.827080574274562e-05,
+      "loss": 0.5742,
+      "step": 31
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.35032135248184204,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.5548,
+      "step": 32
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.3868001103401184,
+      "learning_rate": 1.7901550123756906e-05,
+      "loss": 0.5879,
+      "step": 33
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.34849685430526733,
+      "learning_rate": 1.7705132427757895e-05,
+      "loss": 0.5588,
+      "step": 34
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.3659916818141937,
+      "learning_rate": 1.7501110696304598e-05,
+      "loss": 0.5561,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3479112982749939,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.566,
+      "step": 36
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.38614964485168457,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.5702,
+      "step": 37
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.32522615790367126,
+      "learning_rate": 1.684547105928689e-05,
+      "loss": 0.5646,
+      "step": 38
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.34715840220451355,
+      "learning_rate": 1.661311865323652e-05,
+      "loss": 0.5629,
+      "step": 39
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.38434770703315735,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.5461,
+      "step": 40
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.32962343096733093,
+      "learning_rate": 1.6129070536529767e-05,
+      "loss": 0.5668,
+      "step": 41
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.37483224272727966,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.5656,
+      "step": 42
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.30097684264183044,
+      "learning_rate": 1.5620833778521306e-05,
+      "loss": 0.5529,
+      "step": 43
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.33267274498939514,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.5563,
+      "step": 44
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.33388659358024597,
+      "learning_rate": 1.5090414157503715e-05,
+      "loss": 0.5665,
+      "step": 45
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.3299979269504547,
+      "learning_rate": 1.4817536741017153e-05,
+      "loss": 0.5527,
+      "step": 46
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.30535200238227844,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.5662,
+      "step": 47
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.32509496808052063,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.5447,
+      "step": 48
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.3176334798336029,
+      "learning_rate": 1.3971478906347806e-05,
+      "loss": 0.5464,
+      "step": 49
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.30327945947647095,
+      "learning_rate": 1.3681245526846782e-05,
+      "loss": 0.5449,
+      "step": 50
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.2697887718677521,
+      "learning_rate": 1.3387379202452917e-05,
+      "loss": 0.54,
+      "step": 51
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.2823696434497833,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5543,
+      "step": 52
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.30424606800079346,
+      "learning_rate": 1.2789911060392295e-05,
+      "loss": 0.5514,
+      "step": 53
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.26427096128463745,
+      "learning_rate": 1.2486898871648552e-05,
+      "loss": 0.5588,
+      "step": 54
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.27375537157058716,
+      "learning_rate": 1.2181432413965428e-05,
+      "loss": 0.5429,
+      "step": 55
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.2701137363910675,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.5585,
+      "step": 56
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.5673031806945801,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.9233,
+      "step": 57
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.29599809646606445,
+      "learning_rate": 1.1253332335643043e-05,
+      "loss": 0.544,
+      "step": 58
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 0.3540167808532715,
+      "learning_rate": 1.0941083133185146e-05,
+      "loss": 0.5149,
+      "step": 59
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.3205398917198181,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.4813,
+      "step": 60
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 0.35224997997283936,
+      "learning_rate": 1.0314107590781284e-05,
+      "loss": 0.5588,
+      "step": 61
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 0.2714930474758148,
+      "learning_rate": 1e-05,
+      "loss": 0.4924,
+      "step": 62
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2932974398136139,
+      "learning_rate": 9.685892409218718e-06,
+      "loss": 0.4994,
+      "step": 63
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 0.29003581404685974,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.4862,
+      "step": 64
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.31004598736763,
+      "learning_rate": 9.058916866814857e-06,
+      "loss": 0.5294,
+      "step": 65
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.26587504148483276,
+      "learning_rate": 8.746667664356957e-06,
+      "loss": 0.5222,
+      "step": 66
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 0.25245964527130127,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.4697,
+      "step": 67
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 0.27027666568756104,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.5343,
+      "step": 68
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.25415799021720886,
+      "learning_rate": 7.818567586034578e-06,
+      "loss": 0.4861,
+      "step": 69
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.25560981035232544,
+      "learning_rate": 7.513101128351454e-06,
+      "loss": 0.5141,
+      "step": 70
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 0.2490381896495819,
+      "learning_rate": 7.210088939607709e-06,
+      "loss": 0.4685,
+      "step": 71
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.2686901092529297,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.5433,
+      "step": 72
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 0.19526812434196472,
+      "learning_rate": 6.612620797547087e-06,
+      "loss": 0.4569,
+      "step": 73
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 0.2415803074836731,
+      "learning_rate": 6.318754473153221e-06,
+      "loss": 0.5253,
+      "step": 74
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.19613640010356903,
+      "learning_rate": 6.028521093652195e-06,
+      "loss": 0.4791,
+      "step": 75
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 0.23172248899936676,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.5268,
+      "step": 76
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 0.22319753468036652,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.5033,
+      "step": 77
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.253582626581192,
+      "learning_rate": 5.1824632589828465e-06,
+      "loss": 0.5263,
+      "step": 78
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 0.22795237600803375,
+      "learning_rate": 4.909585842496287e-06,
+      "loss": 0.4646,
+      "step": 79
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.21554000675678253,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.4976,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.22318841516971588,
+      "learning_rate": 4.379166221478697e-06,
+      "loss": 0.5116,
+      "step": 81
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 0.22658716142177582,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.5323,
+      "step": 82
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 0.20563125610351562,
+      "learning_rate": 3.8709294634702374e-06,
+      "loss": 0.4499,
+      "step": 83
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.20641934871673584,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.4826,
+      "step": 84
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.2252846360206604,
+      "learning_rate": 3.3868813467634833e-06,
+      "loss": 0.5218,
+      "step": 85
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 0.24224503338336945,
+      "learning_rate": 3.1545289407131128e-06,
+      "loss": 0.4953,
+      "step": 86
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.20531503856182098,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.5141,
+      "step": 87
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 0.2080065906047821,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.5073,
+      "step": 88
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 0.19242417812347412,
+      "learning_rate": 2.4988893036954045e-06,
+      "loss": 0.4792,
+      "step": 89
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2007436901330948,
+      "learning_rate": 2.2948675722421086e-06,
+      "loss": 0.5097,
+      "step": 90
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 0.19588816165924072,
+      "learning_rate": 2.098449876243096e-06,
+      "loss": 0.4919,
+      "step": 91
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 0.19348369538784027,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.5275,
+      "step": 92
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.19428110122680664,
+      "learning_rate": 1.7291942572543806e-06,
+      "loss": 0.4784,
+      "step": 93
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 0.1935623586177826,
+      "learning_rate": 1.5567207449798517e-06,
+      "loss": 0.5102,
+      "step": 94
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.20146863162517548,
+      "learning_rate": 1.3925797299605649e-06,
+      "loss": 0.4932,
+      "step": 95
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.2071317434310913,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.5106,
+      "step": 96
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 0.1940830498933792,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.51,
+      "step": 97
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 0.18540237843990326,
+      "learning_rate": 9.517294753398066e-07,
+      "loss": 0.4936,
+      "step": 98
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.18730789422988892,
+      "learning_rate": 8.224537431601886e-07,
+      "loss": 0.4605,
+      "step": 99
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.18820004165172577,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.5104,
+      "step": 100
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 0.18577077984809875,
+      "learning_rate": 5.911923104577455e-07,
+      "loss": 0.4996,
+      "step": 101
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.19338218867778778,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.4835,
+      "step": 102
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 0.19661261141300201,
+      "learning_rate": 3.9706314323056936e-07,
+      "loss": 0.4947,
+      "step": 103
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 0.19002115726470947,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.4762,
+      "step": 104
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.18881858885288239,
+      "learning_rate": 2.4083238061252565e-07,
+      "loss": 0.5344,
+      "step": 105
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 0.18790070712566376,
+      "learning_rate": 1.7712749271311392e-07,
+      "loss": 0.4645,
+      "step": 106
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 0.19742755591869354,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.4809,
+      "step": 107
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.19038796424865723,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.4858,
+      "step": 108
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 0.1900634616613388,
+      "learning_rate": 4.438035396920004e-08,
+      "loss": 0.5078,
+      "step": 109
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.19468751549720764,
+      "learning_rate": 1.973271571728441e-08,
+      "loss": 0.5179,
+      "step": 110
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.1910133957862854,
+      "learning_rate": 4.9343963426840006e-09,
+      "loss": 0.4961,
+      "step": 111
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 0.19184480607509613,
+      "learning_rate": 0.0,
+      "loss": 0.511,
+      "step": 112
+    },
+    {
+      "epoch": 1.991111111111111,
+      "step": 112,
+      "total_flos": 621868991119360.0,
+      "train_loss": 0.5655743213636535,
+      "train_runtime": 48561.3008,
+      "train_samples_per_second": 0.222,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 621868991119360.0,
+  "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 sha256:4d00d081ae1f94e166edd2c56af43cd45f5b3506e20592294113c40e6bcb36d3
+size 7416