Upload model

.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: model-name-or-path_Qwen25-32B-Instruct_meta_no_pipeline_100k
+  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. -->
+
+# model-name-or-path_Qwen25-32B-Instruct_meta_no_pipeline_100k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the mlfoundations-dev/meta_no_pipeline_100k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 512
+- 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: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- 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": 4.961240310077519,
+    "total_flos": 8.242697655180853e+18,
+    "train_loss": 0.45099904040495553,
+    "train_runtime": 77492.3925,
+    "train_samples_per_second": 1.597,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
+  "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 sha256:9f862da6403faeb0df1fd972cb13bea66ec90b54c1ec1713557f5a05abc593e6
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c7b62df02c7c1c6857b2c4a067e2c6efa9bd825c0eae8a0c71935e963156ff
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a52655179257be16c7a659c49d486fd6d421f2b3562f3e1ca7131fdfe2af62e
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a93e6c0a477fdf119627939aca2dc087e86b3e1b7ee6749086d3d3b349a1ec0
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd55cf230442deccf43fcf4b69bfca6bb077aa3a9cbd7df02210f6078f43cee
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25067769e3eeec8f2d64dc495d0e82df3f663d9baf798e4edc764bdaded0997
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d9f5caa67da4b92932e71aa15c8a52ca7707420d7d70275ab3c962a53445563
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c04bf1551a6609ee0394ef2b9e6842e070eb9124da947ebcf6a6e5fa579314
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b2e1caabb31d272c66595cdcfea39ead559e58043d97115e66871ff4e52a22
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a190641e4b5bd741c69a9ac44667c5ec9487183fe1d90323514ea5b36dc2788
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61c350d1f8dc3cfacc70c75e0d30128bf15936d0df8c4293d058a90aad5c52b
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d174412af5b46234a299cc972ed7b8690bd52636b2865a5d7dd41b0b7f9d4a
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46af97a12cb34b08c70df4e10dde1b38e9c4bf6bf02f1592baf6c8a9e15428d
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1298ee1d8c7a3f730d7aa9569ba343e342b861e195a694a30129ba7c1b3e43
+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
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-19 10:53:26", "end_time": "2025-04-20 08:33:11"}

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": 4.961240310077519,
+    "total_flos": 8.242697655180853e+18,
+    "train_loss": 0.45099904040495553,
+    "train_runtime": 77492.3925,
+    "train_samples_per_second": 1.597,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,241 @@
+{"current_steps": 1, "total_steps": 240, "loss": 0.8883, "lr": 3.3333333333333333e-06, "epoch": 0.020671834625323, "percentage": 0.42, "elapsed_time": "0:06:04", "remaining_time": "1 day, 0:11:53"}
+{"current_steps": 2, "total_steps": 240, "loss": 0.8848, "lr": 6.666666666666667e-06, "epoch": 0.041343669250646, "percentage": 0.83, "elapsed_time": "0:11:22", "remaining_time": "22:33:39"}
+{"current_steps": 3, "total_steps": 240, "loss": 0.8795, "lr": 1e-05, "epoch": 0.06201550387596899, "percentage": 1.25, "elapsed_time": "0:16:40", "remaining_time": "21:57:04"}
+{"current_steps": 4, "total_steps": 240, "loss": 0.8245, "lr": 1.3333333333333333e-05, "epoch": 0.082687338501292, "percentage": 1.67, "elapsed_time": "0:21:58", "remaining_time": "21:36:34"}
+{"current_steps": 5, "total_steps": 240, "loss": 0.7893, "lr": 1.6666666666666667e-05, "epoch": 0.10335917312661498, "percentage": 2.08, "elapsed_time": "0:27:16", "remaining_time": "21:22:04"}
+{"current_steps": 6, "total_steps": 240, "loss": 0.7386, "lr": 2e-05, "epoch": 0.12403100775193798, "percentage": 2.5, "elapsed_time": "0:32:34", "remaining_time": "21:10:23"}
+{"current_steps": 7, "total_steps": 240, "loss": 0.7205, "lr": 2.3333333333333336e-05, "epoch": 0.14470284237726097, "percentage": 2.92, "elapsed_time": "0:37:52", "remaining_time": "21:00:50"}
+{"current_steps": 8, "total_steps": 240, "loss": 0.6846, "lr": 2.6666666666666667e-05, "epoch": 0.165374677002584, "percentage": 3.33, "elapsed_time": "0:43:10", "remaining_time": "20:52:15"}
+{"current_steps": 9, "total_steps": 240, "loss": 0.6703, "lr": 3.0000000000000004e-05, "epoch": 0.18604651162790697, "percentage": 3.75, "elapsed_time": "0:48:29", "remaining_time": "20:44:29"}
+{"current_steps": 10, "total_steps": 240, "loss": 0.6625, "lr": 3.3333333333333335e-05, "epoch": 0.20671834625322996, "percentage": 4.17, "elapsed_time": "0:53:47", "remaining_time": "20:37:05"}
+{"current_steps": 11, "total_steps": 240, "loss": 0.639, "lr": 3.6666666666666666e-05, "epoch": 0.22739018087855298, "percentage": 4.58, "elapsed_time": "0:59:05", "remaining_time": "20:30:10"}
+{"current_steps": 12, "total_steps": 240, "loss": 0.6387, "lr": 4e-05, "epoch": 0.24806201550387597, "percentage": 5.0, "elapsed_time": "1:04:23", "remaining_time": "20:23:26"}
+{"current_steps": 13, "total_steps": 240, "loss": 0.6344, "lr": 4.3333333333333334e-05, "epoch": 0.268733850129199, "percentage": 5.42, "elapsed_time": "1:09:41", "remaining_time": "20:16:58"}
+{"current_steps": 14, "total_steps": 240, "loss": 0.6157, "lr": 4.666666666666667e-05, "epoch": 0.28940568475452194, "percentage": 5.83, "elapsed_time": "1:14:59", "remaining_time": "20:10:33"}
+{"current_steps": 15, "total_steps": 240, "loss": 0.6132, "lr": 5e-05, "epoch": 0.31007751937984496, "percentage": 6.25, "elapsed_time": "1:20:17", "remaining_time": "20:04:23"}
+{"current_steps": 16, "total_steps": 240, "loss": 0.607, "lr": 5.333333333333333e-05, "epoch": 0.330749354005168, "percentage": 6.67, "elapsed_time": "1:25:35", "remaining_time": "19:58:18"}
+{"current_steps": 17, "total_steps": 240, "loss": 0.597, "lr": 5.666666666666668e-05, "epoch": 0.35142118863049093, "percentage": 7.08, "elapsed_time": "1:30:53", "remaining_time": "19:52:20"}
+{"current_steps": 18, "total_steps": 240, "loss": 0.5883, "lr": 6.000000000000001e-05, "epoch": 0.37209302325581395, "percentage": 7.5, "elapsed_time": "1:36:11", "remaining_time": "19:46:24"}
+{"current_steps": 19, "total_steps": 240, "loss": 0.585, "lr": 6.333333333333333e-05, "epoch": 0.39276485788113696, "percentage": 7.92, "elapsed_time": "1:41:29", "remaining_time": "19:40:29"}
+{"current_steps": 20, "total_steps": 240, "loss": 0.5823, "lr": 6.666666666666667e-05, "epoch": 0.4134366925064599, "percentage": 8.33, "elapsed_time": "1:46:47", "remaining_time": "19:34:40"}
+{"current_steps": 21, "total_steps": 240, "loss": 0.5826, "lr": 7.000000000000001e-05, "epoch": 0.43410852713178294, "percentage": 8.75, "elapsed_time": "1:52:05", "remaining_time": "19:28:56"}
+{"current_steps": 22, "total_steps": 240, "loss": 0.5725, "lr": 7.333333333333333e-05, "epoch": 0.45478036175710596, "percentage": 9.17, "elapsed_time": "1:57:22", "remaining_time": "19:23:09"}
+{"current_steps": 23, "total_steps": 240, "loss": 0.5794, "lr": 7.666666666666668e-05, "epoch": 0.4754521963824289, "percentage": 9.58, "elapsed_time": "2:02:41", "remaining_time": "19:17:32"}
+{"current_steps": 24, "total_steps": 240, "loss": 0.5739, "lr": 8e-05, "epoch": 0.49612403100775193, "percentage": 10.0, "elapsed_time": "2:07:59", "remaining_time": "19:11:54"}
+{"current_steps": 25, "total_steps": 240, "loss": 0.5738, "lr": 7.99957692770843e-05, "epoch": 0.5167958656330749, "percentage": 10.42, "elapsed_time": "2:13:17", "remaining_time": "19:06:19"}
+{"current_steps": 26, "total_steps": 240, "loss": 0.5676, "lr": 7.998307800328803e-05, "epoch": 0.537467700258398, "percentage": 10.83, "elapsed_time": "2:18:35", "remaining_time": "19:00:45"}
+{"current_steps": 27, "total_steps": 240, "loss": 0.5626, "lr": 7.996192886327432e-05, "epoch": 0.5581395348837209, "percentage": 11.25, "elapsed_time": "2:23:53", "remaining_time": "18:55:09"}
+{"current_steps": 28, "total_steps": 240, "loss": 0.5577, "lr": 7.993232633085074e-05, "epoch": 0.5788113695090439, "percentage": 11.67, "elapsed_time": "2:29:11", "remaining_time": "18:49:38"}
+{"current_steps": 29, "total_steps": 240, "loss": 0.5588, "lr": 7.98942766680229e-05, "epoch": 0.599483204134367, "percentage": 12.08, "elapsed_time": "2:34:30", "remaining_time": "18:44:07"}
+{"current_steps": 30, "total_steps": 240, "loss": 0.5576, "lr": 7.984778792366983e-05, "epoch": 0.6201550387596899, "percentage": 12.5, "elapsed_time": "2:39:47", "remaining_time": "18:38:35"}
+{"current_steps": 31, "total_steps": 240, "loss": 0.5543, "lr": 7.979286993184134e-05, "epoch": 0.6408268733850129, "percentage": 12.92, "elapsed_time": "2:45:06", "remaining_time": "18:33:06"}
+{"current_steps": 32, "total_steps": 240, "loss": 0.5546, "lr": 7.972953430967773e-05, "epoch": 0.661498708010336, "percentage": 13.33, "elapsed_time": "2:50:23", "remaining_time": "18:27:34"}
+{"current_steps": 33, "total_steps": 240, "loss": 0.5423, "lr": 7.965779445495243e-05, "epoch": 0.6821705426356589, "percentage": 13.75, "elapsed_time": "2:55:41", "remaining_time": "18:22:06"}
+{"current_steps": 34, "total_steps": 240, "loss": 0.5549, "lr": 7.957766554323778e-05, "epoch": 0.7028423772609819, "percentage": 14.17, "elapsed_time": "3:00:59", "remaining_time": "18:16:37"}
+{"current_steps": 35, "total_steps": 240, "loss": 0.5381, "lr": 7.948916452469497e-05, "epoch": 0.7235142118863049, "percentage": 14.58, "elapsed_time": "3:06:17", "remaining_time": "18:11:09"}
+{"current_steps": 36, "total_steps": 240, "loss": 0.5334, "lr": 7.939231012048833e-05, "epoch": 0.7441860465116279, "percentage": 15.0, "elapsed_time": "3:11:35", "remaining_time": "18:05:41"}
+{"current_steps": 37, "total_steps": 240, "loss": 0.546, "lr": 7.928712281882523e-05, "epoch": 0.7648578811369509, "percentage": 15.42, "elapsed_time": "3:16:53", "remaining_time": "18:00:16"}
+{"current_steps": 38, "total_steps": 240, "loss": 0.538, "lr": 7.917362487062207e-05, "epoch": 0.7855297157622739, "percentage": 15.83, "elapsed_time": "3:22:11", "remaining_time": "17:54:49"}
+{"current_steps": 39, "total_steps": 240, "loss": 0.5395, "lr": 7.905184028479734e-05, "epoch": 0.8062015503875969, "percentage": 16.25, "elapsed_time": "3:27:30", "remaining_time": "17:49:28"}
+{"current_steps": 40, "total_steps": 240, "loss": 0.5351, "lr": 7.892179482319297e-05, "epoch": 0.8268733850129198, "percentage": 16.67, "elapsed_time": "3:32:48", "remaining_time": "17:44:01"}
+{"current_steps": 41, "total_steps": 240, "loss": 0.5332, "lr": 7.878351599512465e-05, "epoch": 0.8475452196382429, "percentage": 17.08, "elapsed_time": "3:38:06", "remaining_time": "17:38:36"}
+{"current_steps": 42, "total_steps": 240, "loss": 0.5255, "lr": 7.863703305156273e-05, "epoch": 0.8682170542635659, "percentage": 17.5, "elapsed_time": "3:43:24", "remaining_time": "17:33:12"}
+{"current_steps": 43, "total_steps": 240, "loss": 0.5289, "lr": 7.848237697894453e-05, "epoch": 0.8888888888888888, "percentage": 17.92, "elapsed_time": "3:48:42", "remaining_time": "17:27:48"}
+{"current_steps": 44, "total_steps": 240, "loss": 0.53, "lr": 7.831958049261956e-05, "epoch": 0.9095607235142119, "percentage": 18.33, "elapsed_time": "3:54:01", "remaining_time": "17:22:26"}
+{"current_steps": 45, "total_steps": 240, "loss": 0.528, "lr": 7.814867802992907e-05, "epoch": 0.9302325581395349, "percentage": 18.75, "elapsed_time": "3:59:19", "remaining_time": "17:17:03"}
+{"current_steps": 46, "total_steps": 240, "loss": 0.5281, "lr": 7.796970574292136e-05, "epoch": 0.9509043927648578, "percentage": 19.17, "elapsed_time": "4:04:36", "remaining_time": "17:11:38"}
+{"current_steps": 47, "total_steps": 240, "loss": 0.5214, "lr": 7.77827014907042e-05, "epoch": 0.9715762273901809, "percentage": 19.58, "elapsed_time": "4:09:55", "remaining_time": "17:06:15"}
+{"current_steps": 48, "total_steps": 240, "loss": 0.5269, "lr": 7.758770483143634e-05, "epoch": 0.9922480620155039, "percentage": 20.0, "elapsed_time": "4:15:12", "remaining_time": "17:00:49"}
+{"current_steps": 49, "total_steps": 240, "loss": 0.5093, "lr": 7.738475701395955e-05, "epoch": 1.0129198966408268, "percentage": 20.42, "elapsed_time": "4:23:13", "remaining_time": "17:06:03"}
+{"current_steps": 50, "total_steps": 240, "loss": 0.4955, "lr": 7.71739009690729e-05, "epoch": 1.0335917312661498, "percentage": 20.83, "elapsed_time": "4:28:33", "remaining_time": "17:00:33"}
+{"current_steps": 51, "total_steps": 240, "loss": 0.4969, "lr": 7.695518130045147e-05, "epoch": 1.054263565891473, "percentage": 21.25, "elapsed_time": "4:33:51", "remaining_time": "16:54:54"}
+{"current_steps": 52, "total_steps": 240, "loss": 0.5087, "lr": 7.672864427521097e-05, "epoch": 1.074935400516796, "percentage": 21.67, "elapsed_time": "4:39:12", "remaining_time": "16:49:26"}
+{"current_steps": 53, "total_steps": 240, "loss": 0.5012, "lr": 7.649433781412058e-05, "epoch": 1.0956072351421189, "percentage": 22.08, "elapsed_time": "4:44:30", "remaining_time": "16:43:49"}
+{"current_steps": 54, "total_steps": 240, "loss": 0.4947, "lr": 7.625231148146601e-05, "epoch": 1.1162790697674418, "percentage": 22.5, "elapsed_time": "4:49:49", "remaining_time": "16:38:18"}
+{"current_steps": 55, "total_steps": 240, "loss": 0.501, "lr": 7.600261647456485e-05, "epoch": 1.1369509043927648, "percentage": 22.92, "elapsed_time": "4:55:07", "remaining_time": "16:32:43"}
+{"current_steps": 56, "total_steps": 240, "loss": 0.4909, "lr": 7.57453056129365e-05, "epoch": 1.1576227390180878, "percentage": 23.33, "elapsed_time": "5:00:25", "remaining_time": "16:27:07"}
+{"current_steps": 57, "total_steps": 240, "loss": 0.4889, "lr": 7.548043332712887e-05, "epoch": 1.178294573643411, "percentage": 23.75, "elapsed_time": "5:05:43", "remaining_time": "16:21:33"}
+{"current_steps": 58, "total_steps": 240, "loss": 0.4916, "lr": 7.520805564720444e-05, "epoch": 1.198966408268734, "percentage": 24.17, "elapsed_time": "5:11:02", "remaining_time": "16:16:00"}
+{"current_steps": 59, "total_steps": 240, "loss": 0.4876, "lr": 7.492823019088785e-05, "epoch": 1.2196382428940569, "percentage": 24.58, "elapsed_time": "5:16:20", "remaining_time": "16:10:27"}
+{"current_steps": 60, "total_steps": 240, "loss": 0.4903, "lr": 7.464101615137756e-05, "epoch": 1.2403100775193798, "percentage": 25.0, "elapsed_time": "5:21:38", "remaining_time": "16:04:55"}
+{"current_steps": 61, "total_steps": 240, "loss": 0.4852, "lr": 7.434647428482453e-05, "epoch": 1.2609819121447028, "percentage": 25.42, "elapsed_time": "5:26:56", "remaining_time": "15:59:22"}
+{"current_steps": 62, "total_steps": 240, "loss": 0.4824, "lr": 7.404466689747999e-05, "epoch": 1.2816537467700257, "percentage": 25.83, "elapsed_time": "5:32:14", "remaining_time": "15:53:50"}
+{"current_steps": 63, "total_steps": 240, "loss": 0.4862, "lr": 7.373565783251544e-05, "epoch": 1.302325581395349, "percentage": 26.25, "elapsed_time": "5:37:32", "remaining_time": "15:48:18"}
+{"current_steps": 64, "total_steps": 240, "loss": 0.4816, "lr": 7.341951245651747e-05, "epoch": 1.322997416020672, "percentage": 26.67, "elapsed_time": "5:42:49", "remaining_time": "15:42:47"}
+{"current_steps": 65, "total_steps": 240, "loss": 0.4849, "lr": 7.309629764566042e-05, "epoch": 1.3436692506459949, "percentage": 27.08, "elapsed_time": "5:48:07", "remaining_time": "15:37:16"}
+{"current_steps": 66, "total_steps": 240, "loss": 0.4806, "lr": 7.276608177155968e-05, "epoch": 1.3643410852713178, "percentage": 27.5, "elapsed_time": "5:53:25", "remaining_time": "15:31:46"}
+{"current_steps": 67, "total_steps": 240, "loss": 0.479, "lr": 7.242893468680849e-05, "epoch": 1.3850129198966408, "percentage": 27.92, "elapsed_time": "5:58:43", "remaining_time": "15:26:15"}
+{"current_steps": 68, "total_steps": 240, "loss": 0.4708, "lr": 7.208492771020176e-05, "epoch": 1.405684754521964, "percentage": 28.33, "elapsed_time": "6:04:03", "remaining_time": "15:20:52"}
+{"current_steps": 69, "total_steps": 240, "loss": 0.4743, "lr": 7.173413361164941e-05, "epoch": 1.4263565891472867, "percentage": 28.75, "elapsed_time": "6:09:21", "remaining_time": "15:15:22"}
+{"current_steps": 70, "total_steps": 240, "loss": 0.479, "lr": 7.137662659678303e-05, "epoch": 1.4470284237726099, "percentage": 29.17, "elapsed_time": "6:14:39", "remaining_time": "15:09:53"}
+{"current_steps": 71, "total_steps": 240, "loss": 0.4748, "lr": 7.101248229125864e-05, "epoch": 1.4677002583979328, "percentage": 29.58, "elapsed_time": "6:19:57", "remaining_time": "15:04:25"}
+{"current_steps": 72, "total_steps": 240, "loss": 0.483, "lr": 7.064177772475912e-05, "epoch": 1.4883720930232558, "percentage": 30.0, "elapsed_time": "6:25:15", "remaining_time": "14:58:56"}
+{"current_steps": 73, "total_steps": 240, "loss": 0.4806, "lr": 7.026459131469972e-05, "epoch": 1.509043927648579, "percentage": 30.42, "elapsed_time": "6:30:33", "remaining_time": "14:53:28"}
+{"current_steps": 74, "total_steps": 240, "loss": 0.4758, "lr": 6.988100284963985e-05, "epoch": 1.5297157622739017, "percentage": 30.83, "elapsed_time": "6:35:51", "remaining_time": "14:48:00"}
+{"current_steps": 75, "total_steps": 240, "loss": 0.478, "lr": 6.949109347240496e-05, "epoch": 1.550387596899225, "percentage": 31.25, "elapsed_time": "6:41:09", "remaining_time": "14:42:32"}
+{"current_steps": 76, "total_steps": 240, "loss": 0.4794, "lr": 6.909494566292195e-05, "epoch": 1.5710594315245479, "percentage": 31.67, "elapsed_time": "6:46:27", "remaining_time": "14:37:05"}
+{"current_steps": 77, "total_steps": 240, "loss": 0.4741, "lr": 6.869264322077158e-05, "epoch": 1.5917312661498708, "percentage": 32.08, "elapsed_time": "6:51:45", "remaining_time": "14:31:39"}
+{"current_steps": 78, "total_steps": 240, "loss": 0.4719, "lr": 6.828427124746191e-05, "epoch": 1.6124031007751938, "percentage": 32.5, "elapsed_time": "6:57:03", "remaining_time": "14:26:12"}
+{"current_steps": 79, "total_steps": 240, "loss": 0.4778, "lr": 6.786991612842621e-05, "epoch": 1.6330749354005167, "percentage": 32.92, "elapsed_time": "7:02:21", "remaining_time": "14:20:45"}
+{"current_steps": 80, "total_steps": 240, "loss": 0.4761, "lr": 6.744966551474936e-05, "epoch": 1.65374677002584, "percentage": 33.33, "elapsed_time": "7:07:41", "remaining_time": "14:15:22"}
+{"current_steps": 81, "total_steps": 240, "loss": 0.475, "lr": 6.702360830462642e-05, "epoch": 1.6744186046511627, "percentage": 33.75, "elapsed_time": "7:12:59", "remaining_time": "14:09:56"}
+{"current_steps": 82, "total_steps": 240, "loss": 0.4752, "lr": 6.659183462455751e-05, "epoch": 1.6950904392764858, "percentage": 34.17, "elapsed_time": "7:18:17", "remaining_time": "14:04:30"}
+{"current_steps": 83, "total_steps": 240, "loss": 0.4773, "lr": 6.615443581028279e-05, "epoch": 1.7157622739018088, "percentage": 34.58, "elapsed_time": "7:23:35", "remaining_time": "13:59:04"}
+{"current_steps": 84, "total_steps": 240, "loss": 0.4695, "lr": 6.571150438746157e-05, "epoch": 1.7364341085271318, "percentage": 35.0, "elapsed_time": "7:28:53", "remaining_time": "13:53:38"}
+{"current_steps": 85, "total_steps": 240, "loss": 0.4663, "lr": 6.526313405209991e-05, "epoch": 1.757105943152455, "percentage": 35.42, "elapsed_time": "7:34:11", "remaining_time": "13:48:13"}
+{"current_steps": 86, "total_steps": 240, "loss": 0.4749, "lr": 6.480941965073041e-05, "epoch": 1.7777777777777777, "percentage": 35.83, "elapsed_time": "7:39:28", "remaining_time": "13:42:47"}
+{"current_steps": 87, "total_steps": 240, "loss": 0.4736, "lr": 6.435045716034883e-05, "epoch": 1.7984496124031009, "percentage": 36.25, "elapsed_time": "7:44:46", "remaining_time": "13:37:22"}
+{"current_steps": 88, "total_steps": 240, "loss": 0.4708, "lr": 6.388634366811146e-05, "epoch": 1.8191214470284238, "percentage": 36.67, "elapsed_time": "7:50:04", "remaining_time": "13:31:57"}
+{"current_steps": 89, "total_steps": 240, "loss": 0.4752, "lr": 6.341717735079763e-05, "epoch": 1.8397932816537468, "percentage": 37.08, "elapsed_time": "7:55:22", "remaining_time": "13:26:32"}
+{"current_steps": 90, "total_steps": 240, "loss": 0.4754, "lr": 6.294305745404185e-05, "epoch": 1.8604651162790697, "percentage": 37.5, "elapsed_time": "8:00:40", "remaining_time": "13:21:08"}
+{"current_steps": 91, "total_steps": 240, "loss": 0.4786, "lr": 6.246408427133972e-05, "epoch": 1.8811369509043927, "percentage": 37.92, "elapsed_time": "8:05:58", "remaining_time": "13:15:43"}
+{"current_steps": 92, "total_steps": 240, "loss": 0.481, "lr": 6.198035912283225e-05, "epoch": 1.9018087855297159, "percentage": 38.33, "elapsed_time": "8:11:16", "remaining_time": "13:10:18"}
+{"current_steps": 93, "total_steps": 240, "loss": 0.4729, "lr": 6.149198433387297e-05, "epoch": 1.9224806201550386, "percentage": 38.75, "elapsed_time": "8:16:34", "remaining_time": "13:04:54"}
+{"current_steps": 94, "total_steps": 240, "loss": 0.4741, "lr": 6.099906321338241e-05, "epoch": 1.9431524547803618, "percentage": 39.17, "elapsed_time": "8:21:51", "remaining_time": "12:59:29"}
+{"current_steps": 95, "total_steps": 240, "loss": 0.474, "lr": 6.0501700031994613e-05, "epoch": 1.9638242894056848, "percentage": 39.58, "elapsed_time": "8:27:09", "remaining_time": "12:54:05"}
+{"current_steps": 96, "total_steps": 240, "loss": 0.4739, "lr": 6.000000000000001e-05, "epoch": 1.9844961240310077, "percentage": 40.0, "elapsed_time": "8:32:27", "remaining_time": "12:48:40"}
+{"current_steps": 97, "total_steps": 240, "loss": 0.4659, "lr": 5.94940692450897e-05, "epoch": 2.005167958656331, "percentage": 40.42, "elapsed_time": "8:40:26", "remaining_time": "12:47:14"}
+{"current_steps": 98, "total_steps": 240, "loss": 0.4321, "lr": 5.8984014789905625e-05, "epoch": 2.0258397932816536, "percentage": 40.83, "elapsed_time": "8:45:44", "remaining_time": "12:41:47"}
+{"current_steps": 99, "total_steps": 240, "loss": 0.4324, "lr": 5.846994452940137e-05, "epoch": 2.046511627906977, "percentage": 41.25, "elapsed_time": "8:51:03", "remaining_time": "12:36:20"}
+{"current_steps": 100, "total_steps": 240, "loss": 0.4343, "lr": 5.79519672080185e-05, "epoch": 2.0671834625322996, "percentage": 41.67, "elapsed_time": "8:56:21", "remaining_time": "12:30:53"}
+{"current_steps": 101, "total_steps": 240, "loss": 0.4348, "lr": 5.743019239668318e-05, "epoch": 2.0878552971576227, "percentage": 42.08, "elapsed_time": "9:01:40", "remaining_time": "12:25:27"}
+{"current_steps": 102, "total_steps": 240, "loss": 0.4287, "lr": 5.6904730469627985e-05, "epoch": 2.108527131782946, "percentage": 42.5, "elapsed_time": "9:06:58", "remaining_time": "12:20:01"}
+{"current_steps": 103, "total_steps": 240, "loss": 0.4256, "lr": 5.6375692581043705e-05, "epoch": 2.1291989664082687, "percentage": 42.92, "elapsed_time": "9:12:16", "remaining_time": "12:14:34"}
+{"current_steps": 104, "total_steps": 240, "loss": 0.4255, "lr": 5.584319064156628e-05, "epoch": 2.149870801033592, "percentage": 43.33, "elapsed_time": "9:17:34", "remaining_time": "12:09:08"}
+{"current_steps": 105, "total_steps": 240, "loss": 0.4297, "lr": 5.5307337294603595e-05, "epoch": 2.1705426356589146, "percentage": 43.75, "elapsed_time": "9:22:52", "remaining_time": "12:03:42"}
+{"current_steps": 106, "total_steps": 240, "loss": 0.4265, "lr": 5.476824589250738e-05, "epoch": 2.1912144702842378, "percentage": 44.17, "elapsed_time": "9:28:16", "remaining_time": "11:58:23"}
+{"current_steps": 107, "total_steps": 240, "loss": 0.4273, "lr": 5.4226030472595075e-05, "epoch": 2.2118863049095605, "percentage": 44.58, "elapsed_time": "9:33:35", "remaining_time": "11:52:57"}
+{"current_steps": 108, "total_steps": 240, "loss": 0.4274, "lr": 5.368080573302676e-05, "epoch": 2.2325581395348837, "percentage": 45.0, "elapsed_time": "9:38:54", "remaining_time": "11:47:33"}
+{"current_steps": 109, "total_steps": 240, "loss": 0.4266, "lr": 5.3132687008542454e-05, "epoch": 2.253229974160207, "percentage": 45.42, "elapsed_time": "9:44:13", "remaining_time": "11:42:08"}
+{"current_steps": 110, "total_steps": 240, "loss": 0.4233, "lr": 5.258179024606455e-05, "epoch": 2.2739018087855296, "percentage": 45.83, "elapsed_time": "9:49:33", "remaining_time": "11:36:44"}
+{"current_steps": 111, "total_steps": 240, "loss": 0.4201, "lr": 5.202823198017092e-05, "epoch": 2.294573643410853, "percentage": 46.25, "elapsed_time": "9:54:52", "remaining_time": "11:31:19"}
+{"current_steps": 112, "total_steps": 240, "loss": 0.4281, "lr": 5.1472129308443616e-05, "epoch": 2.3152454780361755, "percentage": 46.67, "elapsed_time": "10:00:12", "remaining_time": "11:25:57"}
+{"current_steps": 113, "total_steps": 240, "loss": 0.4275, "lr": 5.091359986669845e-05, "epoch": 2.3359173126614987, "percentage": 47.08, "elapsed_time": "10:05:36", "remaining_time": "11:20:38"}
+{"current_steps": 114, "total_steps": 240, "loss": 0.4244, "lr": 5.0352761804100835e-05, "epoch": 2.356589147286822, "percentage": 47.5, "elapsed_time": "10:10:55", "remaining_time": "11:15:14"}
+{"current_steps": 115, "total_steps": 240, "loss": 0.4233, "lr": 4.9789733758172956e-05, "epoch": 2.3772609819121446, "percentage": 47.92, "elapsed_time": "10:16:21", "remaining_time": "11:09:56"}
+{"current_steps": 116, "total_steps": 240, "loss": 0.4257, "lr": 4.922463482969761e-05, "epoch": 2.397932816537468, "percentage": 48.33, "elapsed_time": "10:21:41", "remaining_time": "11:04:33"}
+{"current_steps": 117, "total_steps": 240, "loss": 0.4238, "lr": 4.8657584557524116e-05, "epoch": 2.4186046511627906, "percentage": 48.75, "elapsed_time": "10:27:00", "remaining_time": "10:59:09"}
+{"current_steps": 118, "total_steps": 240, "loss": 0.4237, "lr": 4.808870289328153e-05, "epoch": 2.4392764857881137, "percentage": 49.17, "elapsed_time": "10:32:19", "remaining_time": "10:53:45"}
+{"current_steps": 119, "total_steps": 240, "loss": 0.428, "lr": 4.751811017600448e-05, "epoch": 2.459948320413437, "percentage": 49.58, "elapsed_time": "10:37:38", "remaining_time": "10:48:21"}
+{"current_steps": 120, "total_steps": 240, "loss": 0.4177, "lr": 4.694592710667723e-05, "epoch": 2.4806201550387597, "percentage": 50.0, "elapsed_time": "10:43:04", "remaining_time": "10:43:04"}
+{"current_steps": 121, "total_steps": 240, "loss": 0.4212, "lr": 4.637227472270091e-05, "epoch": 2.501291989664083, "percentage": 50.42, "elapsed_time": "10:48:23", "remaining_time": "10:37:40"}
+{"current_steps": 122, "total_steps": 240, "loss": 0.4259, "lr": 4.579727437228987e-05, "epoch": 2.5219638242894056, "percentage": 50.83, "elapsed_time": "10:53:42", "remaining_time": "10:32:16"}
+{"current_steps": 123, "total_steps": 240, "loss": 0.4237, "lr": 4.522104768880208e-05, "epoch": 2.5426356589147288, "percentage": 51.25, "elapsed_time": "10:59:01", "remaining_time": "10:26:52"}
+{"current_steps": 124, "total_steps": 240, "loss": 0.4162, "lr": 4.464371656500921e-05, "epoch": 2.5633074935400515, "percentage": 51.67, "elapsed_time": "11:04:20", "remaining_time": "10:21:28"}
+{"current_steps": 125, "total_steps": 240, "loss": 0.4245, "lr": 4.406540312731208e-05, "epoch": 2.5839793281653747, "percentage": 52.08, "elapsed_time": "11:09:42", "remaining_time": "10:16:07"}
+{"current_steps": 126, "total_steps": 240, "loss": 0.4244, "lr": 4.348622970990634e-05, "epoch": 2.604651162790698, "percentage": 52.5, "elapsed_time": "11:15:00", "remaining_time": "10:10:43"}
+{"current_steps": 127, "total_steps": 240, "loss": 0.4206, "lr": 4.290631882890443e-05, "epoch": 2.6253229974160206, "percentage": 52.92, "elapsed_time": "11:20:19", "remaining_time": "10:05:19"}
+{"current_steps": 128, "total_steps": 240, "loss": 0.422, "lr": 4.2325793156419035e-05, "epoch": 2.645994832041344, "percentage": 53.33, "elapsed_time": "11:25:38", "remaining_time": "9:59:56"}
+{"current_steps": 129, "total_steps": 240, "loss": 0.4234, "lr": 4.174477549461345e-05, "epoch": 2.6666666666666665, "percentage": 53.75, "elapsed_time": "11:30:56", "remaining_time": "9:54:32"}
+{"current_steps": 130, "total_steps": 240, "loss": 0.4232, "lr": 4.116338874972446e-05, "epoch": 2.6873385012919897, "percentage": 54.17, "elapsed_time": "11:36:15", "remaining_time": "9:49:08"}
+{"current_steps": 131, "total_steps": 240, "loss": 0.4218, "lr": 4.058175590606332e-05, "epoch": 2.7080103359173124, "percentage": 54.58, "elapsed_time": "11:41:35", "remaining_time": "9:43:45"}
+{"current_steps": 132, "total_steps": 240, "loss": 0.4252, "lr": 4e-05, "epoch": 2.7286821705426356, "percentage": 55.0, "elapsed_time": "11:46:56", "remaining_time": "9:38:24"}
+{"current_steps": 133, "total_steps": 240, "loss": 0.4204, "lr": 3.9418244093936694e-05, "epoch": 2.749354005167959, "percentage": 55.42, "elapsed_time": "11:52:14", "remaining_time": "9:33:00"}
+{"current_steps": 134, "total_steps": 240, "loss": 0.4241, "lr": 3.8836611250275546e-05, "epoch": 2.7700258397932815, "percentage": 55.83, "elapsed_time": "11:57:34", "remaining_time": "9:27:37"}
+{"current_steps": 135, "total_steps": 240, "loss": 0.4275, "lr": 3.825522450538657e-05, "epoch": 2.7906976744186047, "percentage": 56.25, "elapsed_time": "12:02:52", "remaining_time": "9:22:14"}
+{"current_steps": 136, "total_steps": 240, "loss": 0.4213, "lr": 3.767420684358097e-05, "epoch": 2.811369509043928, "percentage": 56.67, "elapsed_time": "12:08:11", "remaining_time": "9:16:51"}
+{"current_steps": 137, "total_steps": 240, "loss": 0.4234, "lr": 3.709368117109558e-05, "epoch": 2.8320413436692506, "percentage": 57.08, "elapsed_time": "12:13:30", "remaining_time": "9:11:28"}
+{"current_steps": 138, "total_steps": 240, "loss": 0.4242, "lr": 3.6513770290093674e-05, "epoch": 2.8527131782945734, "percentage": 57.5, "elapsed_time": "12:18:49", "remaining_time": "9:06:05"}
+{"current_steps": 139, "total_steps": 240, "loss": 0.4225, "lr": 3.5934596872687924e-05, "epoch": 2.8733850129198966, "percentage": 57.92, "elapsed_time": "12:24:08", "remaining_time": "9:00:42"}
+{"current_steps": 140, "total_steps": 240, "loss": 0.4193, "lr": 3.535628343499079e-05, "epoch": 2.8940568475452197, "percentage": 58.33, "elapsed_time": "12:29:27", "remaining_time": "8:55:19"}
+{"current_steps": 141, "total_steps": 240, "loss": 0.429, "lr": 3.477895231119795e-05, "epoch": 2.9147286821705425, "percentage": 58.75, "elapsed_time": "12:34:47", "remaining_time": "8:49:57"}
+{"current_steps": 142, "total_steps": 240, "loss": 0.4244, "lr": 3.4202725627710136e-05, "epoch": 2.9354005167958657, "percentage": 59.17, "elapsed_time": "12:40:05", "remaining_time": "8:44:34"}
+{"current_steps": 143, "total_steps": 240, "loss": 0.4178, "lr": 3.3627725277299103e-05, "epoch": 2.956072351421189, "percentage": 59.58, "elapsed_time": "12:45:24", "remaining_time": "8:39:11"}
+{"current_steps": 144, "total_steps": 240, "loss": 0.4193, "lr": 3.305407289332279e-05, "epoch": 2.9767441860465116, "percentage": 60.0, "elapsed_time": "12:50:43", "remaining_time": "8:33:48"}
+{"current_steps": 145, "total_steps": 240, "loss": 0.4268, "lr": 3.248188982399553e-05, "epoch": 2.9974160206718348, "percentage": 60.42, "elapsed_time": "12:56:01", "remaining_time": "8:28:25"}
+{"current_steps": 146, "total_steps": 240, "loss": 0.3943, "lr": 3.191129710671849e-05, "epoch": 3.0180878552971575, "percentage": 60.83, "elapsed_time": "13:03:55", "remaining_time": "8:24:43"}
+{"current_steps": 147, "total_steps": 240, "loss": 0.3843, "lr": 3.134241544247589e-05, "epoch": 3.0387596899224807, "percentage": 61.25, "elapsed_time": "13:09:14", "remaining_time": "8:19:19"}
+{"current_steps": 148, "total_steps": 240, "loss": 0.3875, "lr": 3.07753651703024e-05, "epoch": 3.0594315245478034, "percentage": 61.67, "elapsed_time": "13:14:34", "remaining_time": "8:13:55"}
+{"current_steps": 149, "total_steps": 240, "loss": 0.3807, "lr": 3.0210266241827047e-05, "epoch": 3.0801033591731266, "percentage": 62.08, "elapsed_time": "13:19:53", "remaining_time": "8:08:31"}
+{"current_steps": 150, "total_steps": 240, "loss": 0.3838, "lr": 2.9647238195899168e-05, "epoch": 3.10077519379845, "percentage": 62.5, "elapsed_time": "13:25:13", "remaining_time": "8:03:07"}
+{"current_steps": 151, "total_steps": 240, "loss": 0.3751, "lr": 2.9086400133301573e-05, "epoch": 3.1214470284237725, "percentage": 62.92, "elapsed_time": "13:30:32", "remaining_time": "7:57:43"}
+{"current_steps": 152, "total_steps": 240, "loss": 0.3826, "lr": 2.8527870691556404e-05, "epoch": 3.1421188630490957, "percentage": 63.33, "elapsed_time": "13:35:51", "remaining_time": "7:52:20"}
+{"current_steps": 153, "total_steps": 240, "loss": 0.3804, "lr": 2.7971768019829083e-05, "epoch": 3.1627906976744184, "percentage": 63.75, "elapsed_time": "13:41:10", "remaining_time": "7:46:56"}
+{"current_steps": 154, "total_steps": 240, "loss": 0.3806, "lr": 2.7418209753935464e-05, "epoch": 3.1834625322997416, "percentage": 64.17, "elapsed_time": "13:46:29", "remaining_time": "7:41:32"}
+{"current_steps": 155, "total_steps": 240, "loss": 0.3806, "lr": 2.6867312991457563e-05, "epoch": 3.2041343669250644, "percentage": 64.58, "elapsed_time": "13:51:48", "remaining_time": "7:36:09"}
+{"current_steps": 156, "total_steps": 240, "loss": 0.3813, "lr": 2.6319194266973256e-05, "epoch": 3.2248062015503876, "percentage": 65.0, "elapsed_time": "13:57:07", "remaining_time": "7:30:45"}
+{"current_steps": 157, "total_steps": 240, "loss": 0.3838, "lr": 2.577396952740495e-05, "epoch": 3.2454780361757107, "percentage": 65.42, "elapsed_time": "14:02:27", "remaining_time": "7:25:22"}
+{"current_steps": 158, "total_steps": 240, "loss": 0.379, "lr": 2.523175410749263e-05, "epoch": 3.2661498708010335, "percentage": 65.83, "elapsed_time": "14:07:46", "remaining_time": "7:19:59"}
+{"current_steps": 159, "total_steps": 240, "loss": 0.3798, "lr": 2.4692662705396412e-05, "epoch": 3.2868217054263567, "percentage": 66.25, "elapsed_time": "14:13:05", "remaining_time": "7:14:35"}
+{"current_steps": 160, "total_steps": 240, "loss": 0.3829, "lr": 2.4156809358433728e-05, "epoch": 3.3074935400516794, "percentage": 66.67, "elapsed_time": "14:18:24", "remaining_time": "7:09:12"}
+{"current_steps": 161, "total_steps": 240, "loss": 0.3854, "lr": 2.3624307418956298e-05, "epoch": 3.3281653746770026, "percentage": 67.08, "elapsed_time": "14:23:42", "remaining_time": "7:03:48"}
+{"current_steps": 162, "total_steps": 240, "loss": 0.3846, "lr": 2.3095269530372032e-05, "epoch": 3.3488372093023258, "percentage": 67.5, "elapsed_time": "14:29:02", "remaining_time": "6:58:25"}
+{"current_steps": 163, "total_steps": 240, "loss": 0.3799, "lr": 2.2569807603316836e-05, "epoch": 3.3695090439276485, "percentage": 67.92, "elapsed_time": "14:34:20", "remaining_time": "6:53:02"}
+{"current_steps": 164, "total_steps": 240, "loss": 0.3816, "lr": 2.2048032791981515e-05, "epoch": 3.3901808785529717, "percentage": 68.33, "elapsed_time": "14:39:39", "remaining_time": "6:47:38"}
+{"current_steps": 165, "total_steps": 240, "loss": 0.3805, "lr": 2.1530055470598654e-05, "epoch": 3.4108527131782944, "percentage": 68.75, "elapsed_time": "14:44:58", "remaining_time": "6:42:15"}
+{"current_steps": 166, "total_steps": 240, "loss": 0.3838, "lr": 2.1015985210094385e-05, "epoch": 3.4315245478036176, "percentage": 69.17, "elapsed_time": "14:50:17", "remaining_time": "6:36:52"}
+{"current_steps": 167, "total_steps": 240, "loss": 0.3796, "lr": 2.050593075491031e-05, "epoch": 3.452196382428941, "percentage": 69.58, "elapsed_time": "14:55:36", "remaining_time": "6:31:29"}
+{"current_steps": 168, "total_steps": 240, "loss": 0.382, "lr": 2.0000000000000012e-05, "epoch": 3.4728682170542635, "percentage": 70.0, "elapsed_time": "15:00:54", "remaining_time": "6:26:06"}
+{"current_steps": 169, "total_steps": 240, "loss": 0.376, "lr": 1.9498299968005393e-05, "epoch": 3.4935400516795867, "percentage": 70.42, "elapsed_time": "15:06:13", "remaining_time": "6:20:43"}
+{"current_steps": 170, "total_steps": 240, "loss": 0.3828, "lr": 1.90009367866176e-05, "epoch": 3.5142118863049094, "percentage": 70.83, "elapsed_time": "15:11:32", "remaining_time": "6:15:20"}
+{"current_steps": 171, "total_steps": 240, "loss": 0.3827, "lr": 1.8508015666127043e-05, "epoch": 3.5348837209302326, "percentage": 71.25, "elapsed_time": "15:16:51", "remaining_time": "6:09:57"}
+{"current_steps": 172, "total_steps": 240, "loss": 0.3839, "lr": 1.8019640877167763e-05, "epoch": 3.5555555555555554, "percentage": 71.67, "elapsed_time": "15:22:10", "remaining_time": "6:04:34"}
+{"current_steps": 173, "total_steps": 240, "loss": 0.375, "lr": 1.753591572866029e-05, "epoch": 3.5762273901808785, "percentage": 72.08, "elapsed_time": "15:27:30", "remaining_time": "5:59:12"}
+{"current_steps": 174, "total_steps": 240, "loss": 0.3804, "lr": 1.7056942545958167e-05, "epoch": 3.5968992248062017, "percentage": 72.5, "elapsed_time": "15:32:49", "remaining_time": "5:53:49"}
+{"current_steps": 175, "total_steps": 240, "loss": 0.3835, "lr": 1.6582822649202382e-05, "epoch": 3.6175710594315245, "percentage": 72.92, "elapsed_time": "15:38:08", "remaining_time": "5:48:27"}
+{"current_steps": 176, "total_steps": 240, "loss": 0.3807, "lr": 1.6113656331888563e-05, "epoch": 3.6382428940568476, "percentage": 73.33, "elapsed_time": "15:43:27", "remaining_time": "5:43:04"}
+{"current_steps": 177, "total_steps": 240, "loss": 0.3764, "lr": 1.5649542839651175e-05, "epoch": 3.6589147286821704, "percentage": 73.75, "elapsed_time": "15:48:47", "remaining_time": "5:37:42"}
+{"current_steps": 178, "total_steps": 240, "loss": 0.3804, "lr": 1.5190580349269604e-05, "epoch": 3.6795865633074936, "percentage": 74.17, "elapsed_time": "15:54:06", "remaining_time": "5:32:19"}
+{"current_steps": 179, "total_steps": 240, "loss": 0.3796, "lr": 1.4736865947900106e-05, "epoch": 3.7002583979328163, "percentage": 74.58, "elapsed_time": "15:59:25", "remaining_time": "5:26:57"}
+{"current_steps": 180, "total_steps": 240, "loss": 0.3797, "lr": 1.4288495612538427e-05, "epoch": 3.7209302325581395, "percentage": 75.0, "elapsed_time": "16:04:43", "remaining_time": "5:21:34"}
+{"current_steps": 181, "total_steps": 240, "loss": 0.3745, "lr": 1.3845564189717218e-05, "epoch": 3.7416020671834627, "percentage": 75.42, "elapsed_time": "16:10:02", "remaining_time": "5:16:12"}
+{"current_steps": 182, "total_steps": 240, "loss": 0.383, "lr": 1.3408165375442486e-05, "epoch": 3.7622739018087854, "percentage": 75.83, "elapsed_time": "16:15:27", "remaining_time": "5:10:51"}
+{"current_steps": 183, "total_steps": 240, "loss": 0.3795, "lr": 1.297639169537359e-05, "epoch": 3.7829457364341086, "percentage": 76.25, "elapsed_time": "16:20:46", "remaining_time": "5:05:29"}
+{"current_steps": 184, "total_steps": 240, "loss": 0.3825, "lr": 1.2550334485250661e-05, "epoch": 3.8036175710594318, "percentage": 76.67, "elapsed_time": "16:26:05", "remaining_time": "5:00:06"}
+{"current_steps": 185, "total_steps": 240, "loss": 0.3814, "lr": 1.2130083871573812e-05, "epoch": 3.8242894056847545, "percentage": 77.08, "elapsed_time": "16:31:23", "remaining_time": "4:54:44"}
+{"current_steps": 186, "total_steps": 240, "loss": 0.3763, "lr": 1.1715728752538103e-05, "epoch": 3.8449612403100772, "percentage": 77.5, "elapsed_time": "16:36:45", "remaining_time": "4:49:22"}
+{"current_steps": 187, "total_steps": 240, "loss": 0.382, "lr": 1.130735677922842e-05, "epoch": 3.8656330749354004, "percentage": 77.92, "elapsed_time": "16:42:04", "remaining_time": "4:44:00"}
+{"current_steps": 188, "total_steps": 240, "loss": 0.3816, "lr": 1.0905054337078051e-05, "epoch": 3.8863049095607236, "percentage": 78.33, "elapsed_time": "16:47:30", "remaining_time": "4:38:40"}
+{"current_steps": 189, "total_steps": 240, "loss": 0.3758, "lr": 1.0508906527595042e-05, "epoch": 3.9069767441860463, "percentage": 78.75, "elapsed_time": "16:52:49", "remaining_time": "4:33:17"}
+{"current_steps": 190, "total_steps": 240, "loss": 0.3822, "lr": 1.0118997150360169e-05, "epoch": 3.9276485788113695, "percentage": 79.17, "elapsed_time": "16:58:07", "remaining_time": "4:27:55"}
+{"current_steps": 191, "total_steps": 240, "loss": 0.3826, "lr": 9.735408685300287e-06, "epoch": 3.9483204134366927, "percentage": 79.58, "elapsed_time": "17:03:26", "remaining_time": "4:22:33"}
+{"current_steps": 192, "total_steps": 240, "loss": 0.3828, "lr": 9.358222275240884e-06, "epoch": 3.9689922480620154, "percentage": 80.0, "elapsed_time": "17:08:51", "remaining_time": "4:17:12"}
+{"current_steps": 193, "total_steps": 240, "loss": 0.378, "lr": 8.987517708741364e-06, "epoch": 3.9896640826873386, "percentage": 80.42, "elapsed_time": "17:14:09", "remaining_time": "4:11:50"}
+{"current_steps": 194, "total_steps": 240, "loss": 0.3677, "lr": 8.623373403216972e-06, "epoch": 4.010335917312662, "percentage": 80.83, "elapsed_time": "17:22:10", "remaining_time": "4:07:06"}
+{"current_steps": 195, "total_steps": 240, "loss": 0.3617, "lr": 8.265866388350598e-06, "epoch": 4.0310077519379846, "percentage": 81.25, "elapsed_time": "17:27:34", "remaining_time": "4:01:44"}
+{"current_steps": 196, "total_steps": 240, "loss": 0.3537, "lr": 7.915072289798247e-06, "epoch": 4.051679586563307, "percentage": 81.67, "elapsed_time": "17:32:53", "remaining_time": "3:56:21"}
+{"current_steps": 197, "total_steps": 240, "loss": 0.3627, "lr": 7.5710653131915125e-06, "epoch": 4.072351421188631, "percentage": 82.08, "elapsed_time": "17:38:14", "remaining_time": "3:50:59"}
+{"current_steps": 198, "total_steps": 240, "loss": 0.363, "lr": 7.233918228440324e-06, "epoch": 4.093023255813954, "percentage": 82.5, "elapsed_time": "17:43:33", "remaining_time": "3:45:36"}
+{"current_steps": 199, "total_steps": 240, "loss": 0.3572, "lr": 6.903702354339578e-06, "epoch": 4.113695090439276, "percentage": 82.92, "elapsed_time": "17:48:52", "remaining_time": "3:40:13"}
+{"current_steps": 200, "total_steps": 240, "loss": 0.3656, "lr": 6.58048754348255e-06, "epoch": 4.134366925064599, "percentage": 83.33, "elapsed_time": "17:54:13", "remaining_time": "3:34:50"}
+{"current_steps": 201, "total_steps": 240, "loss": 0.357, "lr": 6.26434216748458e-06, "epoch": 4.155038759689923, "percentage": 83.75, "elapsed_time": "17:59:32", "remaining_time": "3:29:27"}
+{"current_steps": 202, "total_steps": 240, "loss": 0.3579, "lr": 5.955333102520011e-06, "epoch": 4.1757105943152455, "percentage": 84.17, "elapsed_time": "18:04:51", "remaining_time": "3:24:04"}
+{"current_steps": 203, "total_steps": 240, "loss": 0.3551, "lr": 5.653525715175483e-06, "epoch": 4.196382428940568, "percentage": 84.58, "elapsed_time": "18:10:10", "remaining_time": "3:18:42"}
+{"current_steps": 204, "total_steps": 240, "loss": 0.3561, "lr": 5.358983848622452e-06, "epoch": 4.217054263565892, "percentage": 85.0, "elapsed_time": "18:15:29", "remaining_time": "3:13:19"}
+{"current_steps": 205, "total_steps": 240, "loss": 0.3612, "lr": 5.07176980911217e-06, "epoch": 4.237726098191215, "percentage": 85.42, "elapsed_time": "18:20:49", "remaining_time": "3:07:56"}
+{"current_steps": 206, "total_steps": 240, "loss": 0.3576, "lr": 4.791944352795561e-06, "epoch": 4.258397932816537, "percentage": 85.83, "elapsed_time": "18:26:10", "remaining_time": "3:02:34"}
+{"current_steps": 207, "total_steps": 240, "loss": 0.3596, "lr": 4.519566672871132e-06, "epoch": 4.27906976744186, "percentage": 86.25, "elapsed_time": "18:31:32", "remaining_time": "2:57:12"}
+{"current_steps": 208, "total_steps": 240, "loss": 0.358, "lr": 4.254694387063514e-06, "epoch": 4.299741602067184, "percentage": 86.67, "elapsed_time": "18:36:55", "remaining_time": "2:51:50"}
+{"current_steps": 209, "total_steps": 240, "loss": 0.3532, "lr": 3.997383525435154e-06, "epoch": 4.320413436692506, "percentage": 87.08, "elapsed_time": "18:42:14", "remaining_time": "2:46:27"}
+{"current_steps": 210, "total_steps": 240, "loss": 0.3608, "lr": 3.747688518534003e-06, "epoch": 4.341085271317829, "percentage": 87.5, "elapsed_time": "18:47:33", "remaining_time": "2:41:04"}
+{"current_steps": 211, "total_steps": 240, "loss": 0.3521, "lr": 3.5056621858794393e-06, "epoch": 4.361757105943153, "percentage": 87.92, "elapsed_time": "18:52:52", "remaining_time": "2:35:42"}
+{"current_steps": 212, "total_steps": 240, "loss": 0.3617, "lr": 3.2713557247890447e-06, "epoch": 4.3824289405684755, "percentage": 88.33, "elapsed_time": "18:58:17", "remaining_time": "2:30:20"}
+{"current_steps": 213, "total_steps": 240, "loss": 0.3601, "lr": 3.0448186995485307e-06, "epoch": 4.403100775193798, "percentage": 88.75, "elapsed_time": "19:03:37", "remaining_time": "2:24:57"}
+{"current_steps": 214, "total_steps": 240, "loss": 0.3479, "lr": 2.8260990309270987e-06, "epoch": 4.423772609819121, "percentage": 89.17, "elapsed_time": "19:08:57", "remaining_time": "2:19:35"}
+{"current_steps": 215, "total_steps": 240, "loss": 0.3614, "lr": 2.6152429860404647e-06, "epoch": 4.444444444444445, "percentage": 89.58, "elapsed_time": "19:14:15", "remaining_time": "2:14:12"}
+{"current_steps": 216, "total_steps": 240, "loss": 0.3561, "lr": 2.4122951685636674e-06, "epoch": 4.465116279069767, "percentage": 90.0, "elapsed_time": "19:19:35", "remaining_time": "2:08:50"}
+{"current_steps": 217, "total_steps": 240, "loss": 0.3555, "lr": 2.217298509295813e-06, "epoch": 4.48578811369509, "percentage": 90.42, "elapsed_time": "19:24:53", "remaining_time": "2:03:28"}
+{"current_steps": 218, "total_steps": 240, "loss": 0.3584, "lr": 2.0302942570786446e-06, "epoch": 4.506459948320414, "percentage": 90.83, "elapsed_time": "19:30:12", "remaining_time": "1:58:05"}
+{"current_steps": 219, "total_steps": 240, "loss": 0.3581, "lr": 1.8513219700709272e-06, "epoch": 4.5271317829457365, "percentage": 91.25, "elapsed_time": "19:35:32", "remaining_time": "1:52:43"}
+{"current_steps": 220, "total_steps": 240, "loss": 0.352, "lr": 1.6804195073804442e-06, "epoch": 4.547803617571059, "percentage": 91.67, "elapsed_time": "19:40:52", "remaining_time": "1:47:21"}
+{"current_steps": 221, "total_steps": 240, "loss": 0.3509, "lr": 1.5176230210554744e-06, "epoch": 4.568475452196383, "percentage": 92.08, "elapsed_time": "19:46:11", "remaining_time": "1:41:58"}
+{"current_steps": 222, "total_steps": 240, "loss": 0.3574, "lr": 1.3629669484372722e-06, "epoch": 4.589147286821706, "percentage": 92.5, "elapsed_time": "19:51:30", "remaining_time": "1:36:36"}
+{"current_steps": 223, "total_steps": 240, "loss": 0.3569, "lr": 1.2164840048753602e-06, "epoch": 4.609819121447028, "percentage": 92.92, "elapsed_time": "19:56:49", "remaining_time": "1:31:14"}
+{"current_steps": 224, "total_steps": 240, "loss": 0.3582, "lr": 1.0782051768070477e-06, "epoch": 4.630490956072351, "percentage": 93.33, "elapsed_time": "20:02:08", "remaining_time": "1:25:52"}
+{"current_steps": 225, "total_steps": 240, "loss": 0.3493, "lr": 9.481597152026656e-07, "epoch": 4.651162790697675, "percentage": 93.75, "elapsed_time": "20:07:26", "remaining_time": "1:20:29"}
+{"current_steps": 226, "total_steps": 240, "loss": 0.3533, "lr": 8.263751293779409e-07, "epoch": 4.671834625322997, "percentage": 94.17, "elapsed_time": "20:12:45", "remaining_time": "1:15:07"}
+{"current_steps": 227, "total_steps": 240, "loss": 0.353, "lr": 7.128771811747737e-07, "epoch": 4.69250645994832, "percentage": 94.58, "elapsed_time": "20:18:04", "remaining_time": "1:09:45"}
+{"current_steps": 228, "total_steps": 240, "loss": 0.359, "lr": 6.076898795116792e-07, "epoch": 4.713178294573644, "percentage": 95.0, "elapsed_time": "20:23:23", "remaining_time": "1:04:23"}
+{"current_steps": 229, "total_steps": 240, "loss": 0.3548, "lr": 5.108354753050381e-07, "epoch": 4.7338501291989665, "percentage": 95.42, "elapsed_time": "20:28:41", "remaining_time": "0:59:01"}
+{"current_steps": 230, "total_steps": 240, "loss": 0.3509, "lr": 4.223344567622212e-07, "epoch": 4.754521963824289, "percentage": 95.83, "elapsed_time": "20:34:00", "remaining_time": "0:53:39"}
+{"current_steps": 231, "total_steps": 240, "loss": 0.3576, "lr": 3.4220554504758475e-07, "epoch": 4.775193798449612, "percentage": 96.25, "elapsed_time": "20:39:19", "remaining_time": "0:48:17"}
+{"current_steps": 232, "total_steps": 240, "loss": 0.3591, "lr": 2.704656903222791e-07, "epoch": 4.795865633074936, "percentage": 96.67, "elapsed_time": "20:44:37", "remaining_time": "0:42:55"}
+{"current_steps": 233, "total_steps": 240, "loss": 0.358, "lr": 2.0713006815868075e-07, "epoch": 4.816537467700258, "percentage": 97.08, "elapsed_time": "20:49:59", "remaining_time": "0:37:33"}
+{"current_steps": 234, "total_steps": 240, "loss": 0.3586, "lr": 1.522120763301782e-07, "epoch": 4.837209302325581, "percentage": 97.5, "elapsed_time": "20:55:17", "remaining_time": "0:32:11"}
+{"current_steps": 235, "total_steps": 240, "loss": 0.3543, "lr": 1.0572333197711005e-07, "epoch": 4.857881136950905, "percentage": 97.92, "elapsed_time": "21:00:36", "remaining_time": "0:26:49"}
+{"current_steps": 236, "total_steps": 240, "loss": 0.3566, "lr": 6.767366914927298e-08, "epoch": 4.8785529715762275, "percentage": 98.33, "elapsed_time": "21:05:55", "remaining_time": "0:21:27"}
+{"current_steps": 237, "total_steps": 240, "loss": 0.3561, "lr": 3.8071136725688074e-08, "epoch": 4.89922480620155, "percentage": 98.75, "elapsed_time": "21:11:14", "remaining_time": "0:16:05"}
+{"current_steps": 238, "total_steps": 240, "loss": 0.3512, "lr": 1.6921996711976028e-08, "epoch": 4.919896640826874, "percentage": 99.17, "elapsed_time": "21:16:32", "remaining_time": "0:10:43"}
+{"current_steps": 239, "total_steps": 240, "loss": 0.3584, "lr": 4.230722915701257e-09, "epoch": 4.940568475452197, "percentage": 99.58, "elapsed_time": "21:21:51", "remaining_time": "0:05:21"}
+{"current_steps": 240, "total_steps": 240, "loss": 0.3541, "lr": 0.0, "epoch": 4.961240310077519, "percentage": 100.0, "elapsed_time": "21:27:10", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 4.961240310077519, "percentage": 100.0, "elapsed_time": "21:31:24", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1722 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.961240310077519,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020671834625323,
+      "grad_norm": 2.9160615895696287,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8883,
+      "step": 1
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 2.8580123177883006,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8848,
+      "step": 2
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 2.7122432751897176,
+      "learning_rate": 1e-05,
+      "loss": 0.8795,
+      "step": 3
+    },
+    {
+      "epoch": 0.082687338501292,
+      "grad_norm": 1.513030205425536,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8245,
+      "step": 4
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 1.3443713492280498,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7893,
+      "step": 5
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 1.1804286091298655,
+      "learning_rate": 2e-05,
+      "loss": 0.7386,
+      "step": 6
+    },
+    {
+      "epoch": 0.14470284237726097,
+      "grad_norm": 1.4145959109105715,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.7205,
+      "step": 7
+    },
+    {
+      "epoch": 0.165374677002584,
+      "grad_norm": 1.2357655230641855,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6846,
+      "step": 8
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 1.0044529380434546,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.6703,
+      "step": 9
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 0.7736903323340503,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6625,
+      "step": 10
+    },
+    {
+      "epoch": 0.22739018087855298,
+      "grad_norm": 0.8691083811443499,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.639,
+      "step": 11
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 0.7248603690109244,
+      "learning_rate": 4e-05,
+      "loss": 0.6387,
+      "step": 12
+    },
+    {
+      "epoch": 0.268733850129199,
+      "grad_norm": 0.8294236796702565,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.6344,
+      "step": 13
+    },
+    {
+      "epoch": 0.28940568475452194,
+      "grad_norm": 0.5760472222889121,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6157,
+      "step": 14
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 0.5595513798990738,
+      "learning_rate": 5e-05,
+      "loss": 0.6132,
+      "step": 15
+    },
+    {
+      "epoch": 0.330749354005168,
+      "grad_norm": 0.6094355123731108,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.607,
+      "step": 16
+    },
+    {
+      "epoch": 0.35142118863049093,
+      "grad_norm": 0.4550744555441343,
+      "learning_rate": 5.666666666666668e-05,
+      "loss": 0.597,
+      "step": 17
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.5503338541742518,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.5883,
+      "step": 18
+    },
+    {
+      "epoch": 0.39276485788113696,
+      "grad_norm": 0.38787592050569225,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.585,
+      "step": 19
+    },
+    {
+      "epoch": 0.4134366925064599,
+      "grad_norm": 0.5311180440664859,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5823,
+      "step": 20
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 0.5233803608939733,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 0.5826,
+      "step": 21
+    },
+    {
+      "epoch": 0.45478036175710596,
+      "grad_norm": 0.5080450227129891,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.5725,
+      "step": 22
+    },
+    {
+      "epoch": 0.4754521963824289,
+      "grad_norm": 0.6170489561809843,
+      "learning_rate": 7.666666666666668e-05,
+      "loss": 0.5794,
+      "step": 23
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 0.8492871852161974,
+      "learning_rate": 8e-05,
+      "loss": 0.5739,
+      "step": 24
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "grad_norm": 1.0957049612040843,
+      "learning_rate": 7.99957692770843e-05,
+      "loss": 0.5738,
+      "step": 25
+    },
+    {
+      "epoch": 0.537467700258398,
+      "grad_norm": 1.1467346259917117,
+      "learning_rate": 7.998307800328803e-05,
+      "loss": 0.5676,
+      "step": 26
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.9479677758413664,
+      "learning_rate": 7.996192886327432e-05,
+      "loss": 0.5626,
+      "step": 27
+    },
+    {
+      "epoch": 0.5788113695090439,
+      "grad_norm": 0.645380904520113,
+      "learning_rate": 7.993232633085074e-05,
+      "loss": 0.5577,
+      "step": 28
+    },
+    {
+      "epoch": 0.599483204134367,
+      "grad_norm": 0.7182744075304529,
+      "learning_rate": 7.98942766680229e-05,
+      "loss": 0.5588,
+      "step": 29
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 0.5127412291089614,
+      "learning_rate": 7.984778792366983e-05,
+      "loss": 0.5576,
+      "step": 30
+    },
+    {
+      "epoch": 0.6408268733850129,
+      "grad_norm": 0.5717315410000132,
+      "learning_rate": 7.979286993184134e-05,
+      "loss": 0.5543,
+      "step": 31
+    },
+    {
+      "epoch": 0.661498708010336,
+      "grad_norm": 0.574802710774332,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 0.5546,
+      "step": 32
+    },
+    {
+      "epoch": 0.6821705426356589,
+      "grad_norm": 0.38071050250313326,
+      "learning_rate": 7.965779445495243e-05,
+      "loss": 0.5423,
+      "step": 33
+    },
+    {
+      "epoch": 0.7028423772609819,
+      "grad_norm": 0.560940638806937,
+      "learning_rate": 7.957766554323778e-05,
+      "loss": 0.5549,
+      "step": 34
+    },
+    {
+      "epoch": 0.7235142118863049,
+      "grad_norm": 0.3195456558063643,
+      "learning_rate": 7.948916452469497e-05,
+      "loss": 0.5381,
+      "step": 35
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.5120309870626497,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.5334,
+      "step": 36
+    },
+    {
+      "epoch": 0.7648578811369509,
+      "grad_norm": 0.41200122065705974,
+      "learning_rate": 7.928712281882523e-05,
+      "loss": 0.546,
+      "step": 37
+    },
+    {
+      "epoch": 0.7855297157622739,
+      "grad_norm": 0.34801915896030955,
+      "learning_rate": 7.917362487062207e-05,
+      "loss": 0.538,
+      "step": 38
+    },
+    {
+      "epoch": 0.8062015503875969,
+      "grad_norm": 0.4814496611227264,
+      "learning_rate": 7.905184028479734e-05,
+      "loss": 0.5395,
+      "step": 39
+    },
+    {
+      "epoch": 0.8268733850129198,
+      "grad_norm": 0.343357625146377,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 0.5351,
+      "step": 40
+    },
+    {
+      "epoch": 0.8475452196382429,
+      "grad_norm": 0.3732374596704409,
+      "learning_rate": 7.878351599512465e-05,
+      "loss": 0.5332,
+      "step": 41
+    },
+    {
+      "epoch": 0.8682170542635659,
+      "grad_norm": 0.35877511208535684,
+      "learning_rate": 7.863703305156273e-05,
+      "loss": 0.5255,
+      "step": 42
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.2718043315180321,
+      "learning_rate": 7.848237697894453e-05,
+      "loss": 0.5289,
+      "step": 43
+    },
+    {
+      "epoch": 0.9095607235142119,
+      "grad_norm": 0.3538773839345982,
+      "learning_rate": 7.831958049261956e-05,
+      "loss": 0.53,
+      "step": 44
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.23197832751573458,
+      "learning_rate": 7.814867802992907e-05,
+      "loss": 0.528,
+      "step": 45
+    },
+    {
+      "epoch": 0.9509043927648578,
+      "grad_norm": 0.3210740150407701,
+      "learning_rate": 7.796970574292136e-05,
+      "loss": 0.5281,
+      "step": 46
+    },
+    {
+      "epoch": 0.9715762273901809,
+      "grad_norm": 0.3700032416130845,
+      "learning_rate": 7.77827014907042e-05,
+      "loss": 0.5214,
+      "step": 47
+    },
+    {
+      "epoch": 0.9922480620155039,
+      "grad_norm": 0.3009183027050577,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.5269,
+      "step": 48
+    },
+    {
+      "epoch": 1.0129198966408268,
+      "grad_norm": 0.3896828923021403,
+      "learning_rate": 7.738475701395955e-05,
+      "loss": 0.5093,
+      "step": 49
+    },
+    {
+      "epoch": 1.0335917312661498,
+      "grad_norm": 0.543202361441145,
+      "learning_rate": 7.71739009690729e-05,
+      "loss": 0.4955,
+      "step": 50
+    },
+    {
+      "epoch": 1.054263565891473,
+      "grad_norm": 0.7625591010952377,
+      "learning_rate": 7.695518130045147e-05,
+      "loss": 0.4969,
+      "step": 51
+    },
+    {
+      "epoch": 1.074935400516796,
+      "grad_norm": 1.193784060003013,
+      "learning_rate": 7.672864427521097e-05,
+      "loss": 0.5087,
+      "step": 52
+    },
+    {
+      "epoch": 1.0956072351421189,
+      "grad_norm": 0.7752291239959456,
+      "learning_rate": 7.649433781412058e-05,
+      "loss": 0.5012,
+      "step": 53
+    },
+    {
+      "epoch": 1.1162790697674418,
+      "grad_norm": 0.6474587717802546,
+      "learning_rate": 7.625231148146601e-05,
+      "loss": 0.4947,
+      "step": 54
+    },
+    {
+      "epoch": 1.1369509043927648,
+      "grad_norm": 0.7738304727686638,
+      "learning_rate": 7.600261647456485e-05,
+      "loss": 0.501,
+      "step": 55
+    },
+    {
+      "epoch": 1.1576227390180878,
+      "grad_norm": 0.6980515832191755,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 0.4909,
+      "step": 56
+    },
+    {
+      "epoch": 1.178294573643411,
+      "grad_norm": 0.6004371658326068,
+      "learning_rate": 7.548043332712887e-05,
+      "loss": 0.4889,
+      "step": 57
+    },
+    {
+      "epoch": 1.198966408268734,
+      "grad_norm": 0.6165348115304269,
+      "learning_rate": 7.520805564720444e-05,
+      "loss": 0.4916,
+      "step": 58
+    },
+    {
+      "epoch": 1.2196382428940569,
+      "grad_norm": 0.6291962094809461,
+      "learning_rate": 7.492823019088785e-05,
+      "loss": 0.4876,
+      "step": 59
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 0.5151425388987184,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.4903,
+      "step": 60
+    },
+    {
+      "epoch": 1.2609819121447028,
+      "grad_norm": 0.6152043162282845,
+      "learning_rate": 7.434647428482453e-05,
+      "loss": 0.4852,
+      "step": 61
+    },
+    {
+      "epoch": 1.2816537467700257,
+      "grad_norm": 0.4108530991008805,
+      "learning_rate": 7.404466689747999e-05,
+      "loss": 0.4824,
+      "step": 62
+    },
+    {
+      "epoch": 1.302325581395349,
+      "grad_norm": 0.5619333094656168,
+      "learning_rate": 7.373565783251544e-05,
+      "loss": 0.4862,
+      "step": 63
+    },
+    {
+      "epoch": 1.322997416020672,
+      "grad_norm": 0.36736616896387303,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 0.4816,
+      "step": 64
+    },
+    {
+      "epoch": 1.3436692506459949,
+      "grad_norm": 0.5007899896930137,
+      "learning_rate": 7.309629764566042e-05,
+      "loss": 0.4849,
+      "step": 65
+    },
+    {
+      "epoch": 1.3643410852713178,
+      "grad_norm": 0.3567245531783105,
+      "learning_rate": 7.276608177155968e-05,
+      "loss": 0.4806,
+      "step": 66
+    },
+    {
+      "epoch": 1.3850129198966408,
+      "grad_norm": 0.4042585004384195,
+      "learning_rate": 7.242893468680849e-05,
+      "loss": 0.479,
+      "step": 67
+    },
+    {
+      "epoch": 1.405684754521964,
+      "grad_norm": 0.3071251372629263,
+      "learning_rate": 7.208492771020176e-05,
+      "loss": 0.4708,
+      "step": 68
+    },
+    {
+      "epoch": 1.4263565891472867,
+      "grad_norm": 0.3178098545746679,
+      "learning_rate": 7.173413361164941e-05,
+      "loss": 0.4743,
+      "step": 69
+    },
+    {
+      "epoch": 1.4470284237726099,
+      "grad_norm": 0.32791656769788197,
+      "learning_rate": 7.137662659678303e-05,
+      "loss": 0.479,
+      "step": 70
+    },
+    {
+      "epoch": 1.4677002583979328,
+      "grad_norm": 0.31073048837177464,
+      "learning_rate": 7.101248229125864e-05,
+      "loss": 0.4748,
+      "step": 71
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": 0.23092670638656684,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.483,
+      "step": 72
+    },
+    {
+      "epoch": 1.509043927648579,
+      "grad_norm": 0.29202717623796903,
+      "learning_rate": 7.026459131469972e-05,
+      "loss": 0.4806,
+      "step": 73
+    },
+    {
+      "epoch": 1.5297157622739017,
+      "grad_norm": 0.24757644213273783,
+      "learning_rate": 6.988100284963985e-05,
+      "loss": 0.4758,
+      "step": 74
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 0.21393996054013467,
+      "learning_rate": 6.949109347240496e-05,
+      "loss": 0.478,
+      "step": 75
+    },
+    {
+      "epoch": 1.5710594315245479,
+      "grad_norm": 0.21940059670661766,
+      "learning_rate": 6.909494566292195e-05,
+      "loss": 0.4794,
+      "step": 76
+    },
+    {
+      "epoch": 1.5917312661498708,
+      "grad_norm": 0.25120510290065323,
+      "learning_rate": 6.869264322077158e-05,
+      "loss": 0.4741,
+      "step": 77
+    },
+    {
+      "epoch": 1.6124031007751938,
+      "grad_norm": 0.26922385323839254,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.4719,
+      "step": 78
+    },
+    {
+      "epoch": 1.6330749354005167,
+      "grad_norm": 0.20344576961977537,
+      "learning_rate": 6.786991612842621e-05,
+      "loss": 0.4778,
+      "step": 79
+    },
+    {
+      "epoch": 1.65374677002584,
+      "grad_norm": 0.22604786354074988,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 0.4761,
+      "step": 80
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": 0.18625757521916195,
+      "learning_rate": 6.702360830462642e-05,
+      "loss": 0.475,
+      "step": 81
+    },
+    {
+      "epoch": 1.6950904392764858,
+      "grad_norm": 0.20462391670532523,
+      "learning_rate": 6.659183462455751e-05,
+      "loss": 0.4752,
+      "step": 82
+    },
+    {
+      "epoch": 1.7157622739018088,
+      "grad_norm": 0.18546909132461142,
+      "learning_rate": 6.615443581028279e-05,
+      "loss": 0.4773,
+      "step": 83
+    },
+    {
+      "epoch": 1.7364341085271318,
+      "grad_norm": 0.18510363335943614,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.4695,
+      "step": 84
+    },
+    {
+      "epoch": 1.757105943152455,
+      "grad_norm": 0.15034980115459998,
+      "learning_rate": 6.526313405209991e-05,
+      "loss": 0.4663,
+      "step": 85
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.19615925097698703,
+      "learning_rate": 6.480941965073041e-05,
+      "loss": 0.4749,
+      "step": 86
+    },
+    {
+      "epoch": 1.7984496124031009,
+      "grad_norm": 0.2654011493760909,
+      "learning_rate": 6.435045716034883e-05,
+      "loss": 0.4736,
+      "step": 87
+    },
+    {
+      "epoch": 1.8191214470284238,
+      "grad_norm": 0.3111773040871724,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.4708,
+      "step": 88
+    },
+    {
+      "epoch": 1.8397932816537468,
+      "grad_norm": 0.36927812675111354,
+      "learning_rate": 6.341717735079763e-05,
+      "loss": 0.4752,
+      "step": 89
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 0.4160789587496509,
+      "learning_rate": 6.294305745404185e-05,
+      "loss": 0.4754,
+      "step": 90
+    },
+    {
+      "epoch": 1.8811369509043927,
+      "grad_norm": 0.3977585119965555,
+      "learning_rate": 6.246408427133972e-05,
+      "loss": 0.4786,
+      "step": 91
+    },
+    {
+      "epoch": 1.9018087855297159,
+      "grad_norm": 0.3516911724442998,
+      "learning_rate": 6.198035912283225e-05,
+      "loss": 0.481,
+      "step": 92
+    },
+    {
+      "epoch": 1.9224806201550386,
+      "grad_norm": 0.293513841505873,
+      "learning_rate": 6.149198433387297e-05,
+      "loss": 0.4729,
+      "step": 93
+    },
+    {
+      "epoch": 1.9431524547803618,
+      "grad_norm": 0.2731022151882442,
+      "learning_rate": 6.099906321338241e-05,
+      "loss": 0.4741,
+      "step": 94
+    },
+    {
+      "epoch": 1.9638242894056848,
+      "grad_norm": 0.35410712723586696,
+      "learning_rate": 6.0501700031994613e-05,
+      "loss": 0.474,
+      "step": 95
+    },
+    {
+      "epoch": 1.9844961240310077,
+      "grad_norm": 0.4538676453325634,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.4739,
+      "step": 96
+    },
+    {
+      "epoch": 2.005167958656331,
+      "grad_norm": 0.46816594534216643,
+      "learning_rate": 5.94940692450897e-05,
+      "loss": 0.4659,
+      "step": 97
+    },
+    {
+      "epoch": 2.0258397932816536,
+      "grad_norm": 0.3490457312607184,
+      "learning_rate": 5.8984014789905625e-05,
+      "loss": 0.4321,
+      "step": 98
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": 0.3313437102668528,
+      "learning_rate": 5.846994452940137e-05,
+      "loss": 0.4324,
+      "step": 99
+    },
+    {
+      "epoch": 2.0671834625322996,
+      "grad_norm": 0.4268324278027606,
+      "learning_rate": 5.79519672080185e-05,
+      "loss": 0.4343,
+      "step": 100
+    },
+    {
+      "epoch": 2.0878552971576227,
+      "grad_norm": 0.46532373355417445,
+      "learning_rate": 5.743019239668318e-05,
+      "loss": 0.4348,
+      "step": 101
+    },
+    {
+      "epoch": 2.108527131782946,
+      "grad_norm": 0.3656350937833029,
+      "learning_rate": 5.6904730469627985e-05,
+      "loss": 0.4287,
+      "step": 102
+    },
+    {
+      "epoch": 2.1291989664082687,
+      "grad_norm": 0.341576849989435,
+      "learning_rate": 5.6375692581043705e-05,
+      "loss": 0.4256,
+      "step": 103
+    },
+    {
+      "epoch": 2.149870801033592,
+      "grad_norm": 0.3435636006449175,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.4255,
+      "step": 104
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 0.3674851087079681,
+      "learning_rate": 5.5307337294603595e-05,
+      "loss": 0.4297,
+      "step": 105
+    },
+    {
+      "epoch": 2.1912144702842378,
+      "grad_norm": 0.25757942003867124,
+      "learning_rate": 5.476824589250738e-05,
+      "loss": 0.4265,
+      "step": 106
+    },
+    {
+      "epoch": 2.2118863049095605,
+      "grad_norm": 0.29319082903907967,
+      "learning_rate": 5.4226030472595075e-05,
+      "loss": 0.4273,
+      "step": 107
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": 0.30912735428671423,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.4274,
+      "step": 108
+    },
+    {
+      "epoch": 2.253229974160207,
+      "grad_norm": 0.2946112564630265,
+      "learning_rate": 5.3132687008542454e-05,
+      "loss": 0.4266,
+      "step": 109
+    },
+    {
+      "epoch": 2.2739018087855296,
+      "grad_norm": 0.24956667963282786,
+      "learning_rate": 5.258179024606455e-05,
+      "loss": 0.4233,
+      "step": 110
+    },
+    {
+      "epoch": 2.294573643410853,
+      "grad_norm": 0.24495972859727833,
+      "learning_rate": 5.202823198017092e-05,
+      "loss": 0.4201,
+      "step": 111
+    },
+    {
+      "epoch": 2.3152454780361755,
+      "grad_norm": 0.25189356412883607,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.4281,
+      "step": 112
+    },
+    {
+      "epoch": 2.3359173126614987,
+      "grad_norm": 0.24882897366306153,
+      "learning_rate": 5.091359986669845e-05,
+      "loss": 0.4275,
+      "step": 113
+    },
+    {
+      "epoch": 2.356589147286822,
+      "grad_norm": 0.2505341488622872,
+      "learning_rate": 5.0352761804100835e-05,
+      "loss": 0.4244,
+      "step": 114
+    },
+    {
+      "epoch": 2.3772609819121446,
+      "grad_norm": 0.23709144675798577,
+      "learning_rate": 4.9789733758172956e-05,
+      "loss": 0.4233,
+      "step": 115
+    },
+    {
+      "epoch": 2.397932816537468,
+      "grad_norm": 0.22216591251943948,
+      "learning_rate": 4.922463482969761e-05,
+      "loss": 0.4257,
+      "step": 116
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 0.2485822812049657,
+      "learning_rate": 4.8657584557524116e-05,
+      "loss": 0.4238,
+      "step": 117
+    },
+    {
+      "epoch": 2.4392764857881137,
+      "grad_norm": 0.20581013393206954,
+      "learning_rate": 4.808870289328153e-05,
+      "loss": 0.4237,
+      "step": 118
+    },
+    {
+      "epoch": 2.459948320413437,
+      "grad_norm": 0.2683694988919976,
+      "learning_rate": 4.751811017600448e-05,
+      "loss": 0.428,
+      "step": 119
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 0.2732119282896145,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.4177,
+      "step": 120
+    },
+    {
+      "epoch": 2.501291989664083,
+      "grad_norm": 0.16985653465966316,
+      "learning_rate": 4.637227472270091e-05,
+      "loss": 0.4212,
+      "step": 121
+    },
+    {
+      "epoch": 2.5219638242894056,
+      "grad_norm": 0.24083993805158754,
+      "learning_rate": 4.579727437228987e-05,
+      "loss": 0.4259,
+      "step": 122
+    },
+    {
+      "epoch": 2.5426356589147288,
+      "grad_norm": 0.19049366411569346,
+      "learning_rate": 4.522104768880208e-05,
+      "loss": 0.4237,
+      "step": 123
+    },
+    {
+      "epoch": 2.5633074935400515,
+      "grad_norm": 0.18921694866288802,
+      "learning_rate": 4.464371656500921e-05,
+      "loss": 0.4162,
+      "step": 124
+    },
+    {
+      "epoch": 2.5839793281653747,
+      "grad_norm": 0.11515867618528139,
+      "learning_rate": 4.406540312731208e-05,
+      "loss": 0.4245,
+      "step": 125
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": 0.16805334717409715,
+      "learning_rate": 4.348622970990634e-05,
+      "loss": 0.4244,
+      "step": 126
+    },
+    {
+      "epoch": 2.6253229974160206,
+      "grad_norm": 0.14624332678173066,
+      "learning_rate": 4.290631882890443e-05,
+      "loss": 0.4206,
+      "step": 127
+    },
+    {
+      "epoch": 2.645994832041344,
+      "grad_norm": 0.1226966632599885,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.422,
+      "step": 128
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.12200828138561001,
+      "learning_rate": 4.174477549461345e-05,
+      "loss": 0.4234,
+      "step": 129
+    },
+    {
+      "epoch": 2.6873385012919897,
+      "grad_norm": 0.13700653705541546,
+      "learning_rate": 4.116338874972446e-05,
+      "loss": 0.4232,
+      "step": 130
+    },
+    {
+      "epoch": 2.7080103359173124,
+      "grad_norm": 0.11557203582812532,
+      "learning_rate": 4.058175590606332e-05,
+      "loss": 0.4218,
+      "step": 131
+    },
+    {
+      "epoch": 2.7286821705426356,
+      "grad_norm": 0.11956605011466209,
+      "learning_rate": 4e-05,
+      "loss": 0.4252,
+      "step": 132
+    },
+    {
+      "epoch": 2.749354005167959,
+      "grad_norm": 0.10473648355726717,
+      "learning_rate": 3.9418244093936694e-05,
+      "loss": 0.4204,
+      "step": 133
+    },
+    {
+      "epoch": 2.7700258397932815,
+      "grad_norm": 0.1186616842930409,
+      "learning_rate": 3.8836611250275546e-05,
+      "loss": 0.4241,
+      "step": 134
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.10525513152325092,
+      "learning_rate": 3.825522450538657e-05,
+      "loss": 0.4275,
+      "step": 135
+    },
+    {
+      "epoch": 2.811369509043928,
+      "grad_norm": 0.11453121919183189,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.4213,
+      "step": 136
+    },
+    {
+      "epoch": 2.8320413436692506,
+      "grad_norm": 0.09206489385884514,
+      "learning_rate": 3.709368117109558e-05,
+      "loss": 0.4234,
+      "step": 137
+    },
+    {
+      "epoch": 2.8527131782945734,
+      "grad_norm": 0.118433918645971,
+      "learning_rate": 3.6513770290093674e-05,
+      "loss": 0.4242,
+      "step": 138
+    },
+    {
+      "epoch": 2.8733850129198966,
+      "grad_norm": 0.0943985454829677,
+      "learning_rate": 3.5934596872687924e-05,
+      "loss": 0.4225,
+      "step": 139
+    },
+    {
+      "epoch": 2.8940568475452197,
+      "grad_norm": 0.11050468674335369,
+      "learning_rate": 3.535628343499079e-05,
+      "loss": 0.4193,
+      "step": 140
+    },
+    {
+      "epoch": 2.9147286821705425,
+      "grad_norm": 0.09949452607563593,
+      "learning_rate": 3.477895231119795e-05,
+      "loss": 0.429,
+      "step": 141
+    },
+    {
+      "epoch": 2.9354005167958657,
+      "grad_norm": 0.1106090290134035,
+      "learning_rate": 3.4202725627710136e-05,
+      "loss": 0.4244,
+      "step": 142
+    },
+    {
+      "epoch": 2.956072351421189,
+      "grad_norm": 0.12048140894086738,
+      "learning_rate": 3.3627725277299103e-05,
+      "loss": 0.4178,
+      "step": 143
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": 0.09941200224739741,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.4193,
+      "step": 144
+    },
+    {
+      "epoch": 2.9974160206718348,
+      "grad_norm": 0.11191324212004439,
+      "learning_rate": 3.248188982399553e-05,
+      "loss": 0.4268,
+      "step": 145
+    },
+    {
+      "epoch": 3.0180878552971575,
+      "grad_norm": 0.1927802146617283,
+      "learning_rate": 3.191129710671849e-05,
+      "loss": 0.3943,
+      "step": 146
+    },
+    {
+      "epoch": 3.0387596899224807,
+      "grad_norm": 0.13601769681186723,
+      "learning_rate": 3.134241544247589e-05,
+      "loss": 0.3843,
+      "step": 147
+    },
+    {
+      "epoch": 3.0594315245478034,
+      "grad_norm": 0.18128467277952806,
+      "learning_rate": 3.07753651703024e-05,
+      "loss": 0.3875,
+      "step": 148
+    },
+    {
+      "epoch": 3.0801033591731266,
+      "grad_norm": 0.22945154955579947,
+      "learning_rate": 3.0210266241827047e-05,
+      "loss": 0.3807,
+      "step": 149
+    },
+    {
+      "epoch": 3.10077519379845,
+      "grad_norm": 0.16654454526224097,
+      "learning_rate": 2.9647238195899168e-05,
+      "loss": 0.3838,
+      "step": 150
+    },
+    {
+      "epoch": 3.1214470284237725,
+      "grad_norm": 0.22750866213777649,
+      "learning_rate": 2.9086400133301573e-05,
+      "loss": 0.3751,
+      "step": 151
+    },
+    {
+      "epoch": 3.1421188630490957,
+      "grad_norm": 0.17973030546542432,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.3826,
+      "step": 152
+    },
+    {
+      "epoch": 3.1627906976744184,
+      "grad_norm": 0.17029401369958916,
+      "learning_rate": 2.7971768019829083e-05,
+      "loss": 0.3804,
+      "step": 153
+    },
+    {
+      "epoch": 3.1834625322997416,
+      "grad_norm": 0.1852119301785162,
+      "learning_rate": 2.7418209753935464e-05,
+      "loss": 0.3806,
+      "step": 154
+    },
+    {
+      "epoch": 3.2041343669250644,
+      "grad_norm": 0.14136299318153245,
+      "learning_rate": 2.6867312991457563e-05,
+      "loss": 0.3806,
+      "step": 155
+    },
+    {
+      "epoch": 3.2248062015503876,
+      "grad_norm": 0.16072645831339827,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.3813,
+      "step": 156
+    },
+    {
+      "epoch": 3.2454780361757107,
+      "grad_norm": 0.13278616146506314,
+      "learning_rate": 2.577396952740495e-05,
+      "loss": 0.3838,
+      "step": 157
+    },
+    {
+      "epoch": 3.2661498708010335,
+      "grad_norm": 0.14768004119760159,
+      "learning_rate": 2.523175410749263e-05,
+      "loss": 0.379,
+      "step": 158
+    },
+    {
+      "epoch": 3.2868217054263567,
+      "grad_norm": 0.12905452066326767,
+      "learning_rate": 2.4692662705396412e-05,
+      "loss": 0.3798,
+      "step": 159
+    },
+    {
+      "epoch": 3.3074935400516794,
+      "grad_norm": 0.12981775553641342,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.3829,
+      "step": 160
+    },
+    {
+      "epoch": 3.3281653746770026,
+      "grad_norm": 0.11735923882875593,
+      "learning_rate": 2.3624307418956298e-05,
+      "loss": 0.3854,
+      "step": 161
+    },
+    {
+      "epoch": 3.3488372093023258,
+      "grad_norm": 0.1094304758715909,
+      "learning_rate": 2.3095269530372032e-05,
+      "loss": 0.3846,
+      "step": 162
+    },
+    {
+      "epoch": 3.3695090439276485,
+      "grad_norm": 0.12552108042358762,
+      "learning_rate": 2.2569807603316836e-05,
+      "loss": 0.3799,
+      "step": 163
+    },
+    {
+      "epoch": 3.3901808785529717,
+      "grad_norm": 0.09960480491775725,
+      "learning_rate": 2.2048032791981515e-05,
+      "loss": 0.3816,
+      "step": 164
+    },
+    {
+      "epoch": 3.4108527131782944,
+      "grad_norm": 0.13048633977534593,
+      "learning_rate": 2.1530055470598654e-05,
+      "loss": 0.3805,
+      "step": 165
+    },
+    {
+      "epoch": 3.4315245478036176,
+      "grad_norm": 0.10265331283268403,
+      "learning_rate": 2.1015985210094385e-05,
+      "loss": 0.3838,
+      "step": 166
+    },
+    {
+      "epoch": 3.452196382428941,
+      "grad_norm": 0.12636258686674082,
+      "learning_rate": 2.050593075491031e-05,
+      "loss": 0.3796,
+      "step": 167
+    },
+    {
+      "epoch": 3.4728682170542635,
+      "grad_norm": 0.09627358297975736,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.382,
+      "step": 168
+    },
+    {
+      "epoch": 3.4935400516795867,
+      "grad_norm": 0.10144594851320451,
+      "learning_rate": 1.9498299968005393e-05,
+      "loss": 0.376,
+      "step": 169
+    },
+    {
+      "epoch": 3.5142118863049094,
+      "grad_norm": 0.09960892836011123,
+      "learning_rate": 1.90009367866176e-05,
+      "loss": 0.3828,
+      "step": 170
+    },
+    {
+      "epoch": 3.5348837209302326,
+      "grad_norm": 0.08649589297067169,
+      "learning_rate": 1.8508015666127043e-05,
+      "loss": 0.3827,
+      "step": 171
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.10384196159292765,
+      "learning_rate": 1.8019640877167763e-05,
+      "loss": 0.3839,
+      "step": 172
+    },
+    {
+      "epoch": 3.5762273901808785,
+      "grad_norm": 0.08656341678898698,
+      "learning_rate": 1.753591572866029e-05,
+      "loss": 0.375,
+      "step": 173
+    },
+    {
+      "epoch": 3.5968992248062017,
+      "grad_norm": 0.08511926948170766,
+      "learning_rate": 1.7056942545958167e-05,
+      "loss": 0.3804,
+      "step": 174
+    },
+    {
+      "epoch": 3.6175710594315245,
+      "grad_norm": 0.09259550643790064,
+      "learning_rate": 1.6582822649202382e-05,
+      "loss": 0.3835,
+      "step": 175
+    },
+    {
+      "epoch": 3.6382428940568476,
+      "grad_norm": 0.08328195157299345,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.3807,
+      "step": 176
+    },
+    {
+      "epoch": 3.6589147286821704,
+      "grad_norm": 0.08877299434086175,
+      "learning_rate": 1.5649542839651175e-05,
+      "loss": 0.3764,
+      "step": 177
+    },
+    {
+      "epoch": 3.6795865633074936,
+      "grad_norm": 0.08380640318280198,
+      "learning_rate": 1.5190580349269604e-05,
+      "loss": 0.3804,
+      "step": 178
+    },
+    {
+      "epoch": 3.7002583979328163,
+      "grad_norm": 0.07699776373434924,
+      "learning_rate": 1.4736865947900106e-05,
+      "loss": 0.3796,
+      "step": 179
+    },
+    {
+      "epoch": 3.7209302325581395,
+      "grad_norm": 0.09256081817751462,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.3797,
+      "step": 180
+    },
+    {
+      "epoch": 3.7416020671834627,
+      "grad_norm": 0.08359373379077649,
+      "learning_rate": 1.3845564189717218e-05,
+      "loss": 0.3745,
+      "step": 181
+    },
+    {
+      "epoch": 3.7622739018087854,
+      "grad_norm": 0.08520678172410531,
+      "learning_rate": 1.3408165375442486e-05,
+      "loss": 0.383,
+      "step": 182
+    },
+    {
+      "epoch": 3.7829457364341086,
+      "grad_norm": 0.09122883357806844,
+      "learning_rate": 1.297639169537359e-05,
+      "loss": 0.3795,
+      "step": 183
+    },
+    {
+      "epoch": 3.8036175710594318,
+      "grad_norm": 0.0779176471928561,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.3825,
+      "step": 184
+    },
+    {
+      "epoch": 3.8242894056847545,
+      "grad_norm": 0.08154088851689886,
+      "learning_rate": 1.2130083871573812e-05,
+      "loss": 0.3814,
+      "step": 185
+    },
+    {
+      "epoch": 3.8449612403100772,
+      "grad_norm": 0.10166515233750176,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.3763,
+      "step": 186
+    },
+    {
+      "epoch": 3.8656330749354004,
+      "grad_norm": 0.07978891816708118,
+      "learning_rate": 1.130735677922842e-05,
+      "loss": 0.382,
+      "step": 187
+    },
+    {
+      "epoch": 3.8863049095607236,
+      "grad_norm": 0.08247932494598004,
+      "learning_rate": 1.0905054337078051e-05,
+      "loss": 0.3816,
+      "step": 188
+    },
+    {
+      "epoch": 3.9069767441860463,
+      "grad_norm": 0.08617393492477488,
+      "learning_rate": 1.0508906527595042e-05,
+      "loss": 0.3758,
+      "step": 189
+    },
+    {
+      "epoch": 3.9276485788113695,
+      "grad_norm": 0.07076644296330604,
+      "learning_rate": 1.0118997150360169e-05,
+      "loss": 0.3822,
+      "step": 190
+    },
+    {
+      "epoch": 3.9483204134366927,
+      "grad_norm": 0.07065814361505379,
+      "learning_rate": 9.735408685300287e-06,
+      "loss": 0.3826,
+      "step": 191
+    },
+    {
+      "epoch": 3.9689922480620154,
+      "grad_norm": 0.08938154240197935,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.3828,
+      "step": 192
+    },
+    {
+      "epoch": 3.9896640826873386,
+      "grad_norm": 0.07941435941658158,
+      "learning_rate": 8.987517708741364e-06,
+      "loss": 0.378,
+      "step": 193
+    },
+    {
+      "epoch": 4.010335917312662,
+      "grad_norm": 0.09711457338727685,
+      "learning_rate": 8.623373403216972e-06,
+      "loss": 0.3677,
+      "step": 194
+    },
+    {
+      "epoch": 4.0310077519379846,
+      "grad_norm": 0.13105925666440368,
+      "learning_rate": 8.265866388350598e-06,
+      "loss": 0.3617,
+      "step": 195
+    },
+    {
+      "epoch": 4.051679586563307,
+      "grad_norm": 0.08933195191567478,
+      "learning_rate": 7.915072289798247e-06,
+      "loss": 0.3537,
+      "step": 196
+    },
+    {
+      "epoch": 4.072351421188631,
+      "grad_norm": 0.08419493114811873,
+      "learning_rate": 7.5710653131915125e-06,
+      "loss": 0.3627,
+      "step": 197
+    },
+    {
+      "epoch": 4.093023255813954,
+      "grad_norm": 0.09855757707090335,
+      "learning_rate": 7.233918228440324e-06,
+      "loss": 0.363,
+      "step": 198
+    },
+    {
+      "epoch": 4.113695090439276,
+      "grad_norm": 0.10644403332249518,
+      "learning_rate": 6.903702354339578e-06,
+      "loss": 0.3572,
+      "step": 199
+    },
+    {
+      "epoch": 4.134366925064599,
+      "grad_norm": 0.10474868764346248,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.3656,
+      "step": 200
+    },
+    {
+      "epoch": 4.155038759689923,
+      "grad_norm": 0.08998213945424546,
+      "learning_rate": 6.26434216748458e-06,
+      "loss": 0.357,
+      "step": 201
+    },
+    {
+      "epoch": 4.1757105943152455,
+      "grad_norm": 0.0874382734058534,
+      "learning_rate": 5.955333102520011e-06,
+      "loss": 0.3579,
+      "step": 202
+    },
+    {
+      "epoch": 4.196382428940568,
+      "grad_norm": 0.09229516478584097,
+      "learning_rate": 5.653525715175483e-06,
+      "loss": 0.3551,
+      "step": 203
+    },
+    {
+      "epoch": 4.217054263565892,
+      "grad_norm": 0.0899139620609084,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.3561,
+      "step": 204
+    },
+    {
+      "epoch": 4.237726098191215,
+      "grad_norm": 0.09480003016590481,
+      "learning_rate": 5.07176980911217e-06,
+      "loss": 0.3612,
+      "step": 205
+    },
+    {
+      "epoch": 4.258397932816537,
+      "grad_norm": 0.07955059469841694,
+      "learning_rate": 4.791944352795561e-06,
+      "loss": 0.3576,
+      "step": 206
+    },
+    {
+      "epoch": 4.27906976744186,
+      "grad_norm": 0.08281316418812414,
+      "learning_rate": 4.519566672871132e-06,
+      "loss": 0.3596,
+      "step": 207
+    },
+    {
+      "epoch": 4.299741602067184,
+      "grad_norm": 0.08360162648406322,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.358,
+      "step": 208
+    },
+    {
+      "epoch": 4.320413436692506,
+      "grad_norm": 0.07640740401473636,
+      "learning_rate": 3.997383525435154e-06,
+      "loss": 0.3532,
+      "step": 209
+    },
+    {
+      "epoch": 4.341085271317829,
+      "grad_norm": 0.07916200584935532,
+      "learning_rate": 3.747688518534003e-06,
+      "loss": 0.3608,
+      "step": 210
+    },
+    {
+      "epoch": 4.361757105943153,
+      "grad_norm": 0.06910995508249697,
+      "learning_rate": 3.5056621858794393e-06,
+      "loss": 0.3521,
+      "step": 211
+    },
+    {
+      "epoch": 4.3824289405684755,
+      "grad_norm": 0.07374366802772589,
+      "learning_rate": 3.2713557247890447e-06,
+      "loss": 0.3617,
+      "step": 212
+    },
+    {
+      "epoch": 4.403100775193798,
+      "grad_norm": 0.0710814968114632,
+      "learning_rate": 3.0448186995485307e-06,
+      "loss": 0.3601,
+      "step": 213
+    },
+    {
+      "epoch": 4.423772609819121,
+      "grad_norm": 0.06896603986098794,
+      "learning_rate": 2.8260990309270987e-06,
+      "loss": 0.3479,
+      "step": 214
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.06185011564865765,
+      "learning_rate": 2.6152429860404647e-06,
+      "loss": 0.3614,
+      "step": 215
+    },
+    {
+      "epoch": 4.465116279069767,
+      "grad_norm": 0.06549697826461233,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.3561,
+      "step": 216
+    },
+    {
+      "epoch": 4.48578811369509,
+      "grad_norm": 0.061438617551997,
+      "learning_rate": 2.217298509295813e-06,
+      "loss": 0.3555,
+      "step": 217
+    },
+    {
+      "epoch": 4.506459948320414,
+      "grad_norm": 0.060700891226855756,
+      "learning_rate": 2.0302942570786446e-06,
+      "loss": 0.3584,
+      "step": 218
+    },
+    {
+      "epoch": 4.5271317829457365,
+      "grad_norm": 0.06178488967139298,
+      "learning_rate": 1.8513219700709272e-06,
+      "loss": 0.3581,
+      "step": 219
+    },
+    {
+      "epoch": 4.547803617571059,
+      "grad_norm": 0.06183530674329798,
+      "learning_rate": 1.6804195073804442e-06,
+      "loss": 0.352,
+      "step": 220
+    },
+    {
+      "epoch": 4.568475452196383,
+      "grad_norm": 0.05866001427045164,
+      "learning_rate": 1.5176230210554744e-06,
+      "loss": 0.3509,
+      "step": 221
+    },
+    {
+      "epoch": 4.589147286821706,
+      "grad_norm": 0.05774735846339501,
+      "learning_rate": 1.3629669484372722e-06,
+      "loss": 0.3574,
+      "step": 222
+    },
+    {
+      "epoch": 4.609819121447028,
+      "grad_norm": 0.05601122893723008,
+      "learning_rate": 1.2164840048753602e-06,
+      "loss": 0.3569,
+      "step": 223
+    },
+    {
+      "epoch": 4.630490956072351,
+      "grad_norm": 0.05526767753253488,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.3582,
+      "step": 224
+    },
+    {
+      "epoch": 4.651162790697675,
+      "grad_norm": 0.05616027399981306,
+      "learning_rate": 9.481597152026656e-07,
+      "loss": 0.3493,
+      "step": 225
+    },
+    {
+      "epoch": 4.671834625322997,
+      "grad_norm": 0.05467514890147951,
+      "learning_rate": 8.263751293779409e-07,
+      "loss": 0.3533,
+      "step": 226
+    },
+    {
+      "epoch": 4.69250645994832,
+      "grad_norm": 0.05486244376026512,
+      "learning_rate": 7.128771811747737e-07,
+      "loss": 0.353,
+      "step": 227
+    },
+    {
+      "epoch": 4.713178294573644,
+      "grad_norm": 0.053720925123237416,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.359,
+      "step": 228
+    },
+    {
+      "epoch": 4.7338501291989665,
+      "grad_norm": 0.054529190806937466,
+      "learning_rate": 5.108354753050381e-07,
+      "loss": 0.3548,
+      "step": 229
+    },
+    {
+      "epoch": 4.754521963824289,
+      "grad_norm": 0.054284156157904224,
+      "learning_rate": 4.223344567622212e-07,
+      "loss": 0.3509,
+      "step": 230
+    },
+    {
+      "epoch": 4.775193798449612,
+      "grad_norm": 0.05169076157313685,
+      "learning_rate": 3.4220554504758475e-07,
+      "loss": 0.3576,
+      "step": 231
+    },
+    {
+      "epoch": 4.795865633074936,
+      "grad_norm": 0.05516028856228327,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.3591,
+      "step": 232
+    },
+    {
+      "epoch": 4.816537467700258,
+      "grad_norm": 0.05350115446089016,
+      "learning_rate": 2.0713006815868075e-07,
+      "loss": 0.358,
+      "step": 233
+    },
+    {
+      "epoch": 4.837209302325581,
+      "grad_norm": 0.052581881517593826,
+      "learning_rate": 1.522120763301782e-07,
+      "loss": 0.3586,
+      "step": 234
+    },
+    {
+      "epoch": 4.857881136950905,
+      "grad_norm": 0.053948835043271054,
+      "learning_rate": 1.0572333197711005e-07,
+      "loss": 0.3543,
+      "step": 235
+    },
+    {
+      "epoch": 4.8785529715762275,
+      "grad_norm": 0.0546909910210749,
+      "learning_rate": 6.767366914927298e-08,
+      "loss": 0.3566,
+      "step": 236
+    },
+    {
+      "epoch": 4.89922480620155,
+      "grad_norm": 0.05406684942381343,
+      "learning_rate": 3.8071136725688074e-08,
+      "loss": 0.3561,
+      "step": 237
+    },
+    {
+      "epoch": 4.919896640826874,
+      "grad_norm": 0.05108092626758996,
+      "learning_rate": 1.6921996711976028e-08,
+      "loss": 0.3512,
+      "step": 238
+    },
+    {
+      "epoch": 4.940568475452197,
+      "grad_norm": 0.053315673178670926,
+      "learning_rate": 4.230722915701257e-09,
+      "loss": 0.3584,
+      "step": 239
+    },
+    {
+      "epoch": 4.961240310077519,
+      "grad_norm": 0.05179414324279462,
+      "learning_rate": 0.0,
+      "loss": 0.3541,
+      "step": 240
+    },
+    {
+      "epoch": 4.961240310077519,
+      "step": 240,
+      "total_flos": 8.242697655180853e+18,
+      "train_loss": 0.45099904040495553,
+      "train_runtime": 77492.3925,
+      "train_samples_per_second": 1.597,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.242697655180853e+18,
+  "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:e623c7d1bac478b7bfed518a47bf81649f98e4e96faaa7398998eee9d1a8189e
+size 7480