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
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+datasets:
+- arrow
+model-index:
+- name: QwQ-32B_enable-liger-kernel_False_OpenThoughts3_3k
+  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. -->
+
+# QwQ-32B_enable-liger-kernel_False_OpenThoughts3_3k
+
+This model is a fine-tuned version of [/p/data1/mmlaion/dcft/hub/models--Qwen--QwQ-32B/snapshots/976055f8c83f394f35dbd3ab09a285a984907bd0](https://huggingface.co//p/data1/mmlaion/dcft/hub/models--Qwen--QwQ-32B/snapshots/976055f8c83f394f35dbd3ab09a285a984907bd0) on the /p/data1/mmlaion/dcft/hub/mlfoundations-dev___open_thoughts3_3k/default/0.0.0/12d2651dd3f4039c4ebe15e8f579d1e70a5541c0 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 96
+- total_train_batch_size: 96
+- total_eval_batch_size: 768
+- 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: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.6.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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": 7.0,
+    "total_flos": 2229330703810560.0,
+    "train_loss": 0.6009024948010713,
+    "train_runtime": 6779.558,
+    "train_samples_per_second": 3.263,
+    "train_steps_per_second": 0.034
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--QwQ-32B/snapshots/976055f8c83f394f35dbd3ab09a285a984907bd0",
+  "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": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "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 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 40,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce7d43cac652673474e99890bf05f9655cfbd2d94df9e9ed020e4a6490e5eb6
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4afb543e8cdbf9dc32bfa5882145721ee40022e5e6480621f1f9423e8969cb4
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0671363c4b771fa6ed426a8e2fdbe3ebdb71cce702f7e112de30046383ade85c
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7745b4f2c826df62ec84319ab2dd0cef70ea71e52bfd86f1b348d2bb91b04a78
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57524deb61b90307a918daa61d6e8b3e3994c7799c0fb039f5a19619fd139c4e
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7d9c3f52f2059660a70ee5e92c566d057f650a038a8681df12c30fcf5ec1b2
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1f835fcf6bdd685ea02cff6913d06cbf2a0317c8de31dde862a0a27c8127c8
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3826e419f916a1f5b289bd8e95100eef9d8d22436eb4f907a9b1374a08881f
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a36efd8f616fba51a4605997aa19f0a0b72cc18d1b9cb480a0a98cdc9904a4d
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2edfc20d497bf96a2a70046083ae18472e89fdff3afa34196cb665db55e34a
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63a78d6b058d569d69112609cbc189a94ddc0af058bb5d398ada5d17871e6e3
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62d85e00321c93953f5394c196cff054a27f85d15a5cb31ab583da8663a7353
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c077f872c64341c7a1580664e7df1340a9916a86479f058b836eb19f1d17b7f
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b2c9230960890180b60dfc98fca246342032236a5fdd5e77b98ae72787c993
+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"
+  }
+}

runs/Jun16_23-24-32_jpbo-001-20.jupiter.internal/events.out.tfevents.1750109313.jpbo-001-20.jupiter.internal.60727.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb3d960e652b74f984c620f77432d2a0b36c4c2d54d492b17aadc1d727346d1
+size 54224

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": "2025-06-16 23:24:32", "end_time": "2025-06-17 01:22:21"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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        {{- '' }}\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  {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" and not message.tool_calls %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + 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<think>\\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": 7.0,
+    "total_flos": 2229330703810560.0,
+    "train_loss": 0.6009024948010713,
+    "train_runtime": 6779.558,
+    "train_samples_per_second": 3.263,
+    "train_steps_per_second": 0.034
+}

trainer_log.jsonl

@@ -0,0 +1,232 @@
+{"current_steps": 1, "total_steps": 231, "loss": 0.8175, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:00:36", "remaining_time": "2:18:36"}
+{"current_steps": 2, "total_steps": 231, "loss": 0.8089, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:01:03", "remaining_time": "2:01:08"}
+{"current_steps": 3, "total_steps": 231, "loss": 0.7975, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:01:30", "remaining_time": "1:54:52"}
+{"current_steps": 4, "total_steps": 231, "loss": 0.8046, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:01:57", "remaining_time": "1:51:30"}
+{"current_steps": 5, "total_steps": 231, "loss": 0.8215, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:02:23", "remaining_time": "1:48:14"}
+{"current_steps": 6, "total_steps": 231, "loss": 0.7906, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:02:50", "remaining_time": "1:46:33"}
+{"current_steps": 7, "total_steps": 231, "loss": 0.793, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:03:16", "remaining_time": "1:44:49"}
+{"current_steps": 8, "total_steps": 231, "loss": 0.8245, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:03:42", "remaining_time": "1:43:34"}
+{"current_steps": 9, "total_steps": 231, "loss": 0.7622, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:04:09", "remaining_time": "1:42:41"}
+{"current_steps": 10, "total_steps": 231, "loss": 0.747, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:04:33", "remaining_time": "1:40:51"}
+{"current_steps": 11, "total_steps": 231, "loss": 0.7662, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:04:59", "remaining_time": "1:39:54"}
+{"current_steps": 12, "total_steps": 231, "loss": 0.7814, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:05:26", "remaining_time": "1:39:11"}
+{"current_steps": 13, "total_steps": 231, "loss": 0.7766, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:05:52", "remaining_time": "1:38:34"}
+{"current_steps": 14, "total_steps": 231, "loss": 0.8209, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:06:19", "remaining_time": "1:37:59"}
+{"current_steps": 15, "total_steps": 231, "loss": 0.7498, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:06:45", "remaining_time": "1:37:22"}
+{"current_steps": 16, "total_steps": 231, "loss": 0.7466, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:07:12", "remaining_time": "1:36:48"}
+{"current_steps": 17, "total_steps": 231, "loss": 0.7514, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:07:39", "remaining_time": "1:36:22"}
+{"current_steps": 18, "total_steps": 231, "loss": 0.7879, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:08:05", "remaining_time": "1:35:49"}
+{"current_steps": 19, "total_steps": 231, "loss": 0.804, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:08:32", "remaining_time": "1:35:18"}
+{"current_steps": 20, "total_steps": 231, "loss": 0.7816, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:08:59", "remaining_time": "1:34:56"}
+{"current_steps": 21, "total_steps": 231, "loss": 0.7771, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:09:26", "remaining_time": "1:34:22"}
+{"current_steps": 22, "total_steps": 231, "loss": 0.8016, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:09:52", "remaining_time": "1:33:45"}
+{"current_steps": 23, "total_steps": 231, "loss": 0.8217, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:10:18", "remaining_time": "1:33:15"}
+{"current_steps": 24, "total_steps": 231, "loss": 0.7633, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:10:46", "remaining_time": "1:32:52"}
+{"current_steps": 25, "total_steps": 231, "loss": 0.7889, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:11:12", "remaining_time": "1:32:21"}
+{"current_steps": 26, "total_steps": 231, "loss": 0.7973, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:11:39", "remaining_time": "1:31:55"}
+{"current_steps": 27, "total_steps": 231, "loss": 0.7742, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:12:06", "remaining_time": "1:31:31"}
+{"current_steps": 28, "total_steps": 231, "loss": 0.7885, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:12:33", "remaining_time": "1:31:03"}
+{"current_steps": 29, "total_steps": 231, "loss": 0.773, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:12:59", "remaining_time": "1:30:31"}
+{"current_steps": 30, "total_steps": 231, "loss": 0.7916, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:13:27", "remaining_time": "1:30:13"}
+{"current_steps": 31, "total_steps": 231, "loss": 0.8188, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:13:54", "remaining_time": "1:29:45"}
+{"current_steps": 32, "total_steps": 231, "loss": 0.7724, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:14:21", "remaining_time": "1:29:15"}
+{"current_steps": 33, "total_steps": 231, "loss": 0.7806, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:14:44", "remaining_time": "1:28:28"}
+{"current_steps": 34, "total_steps": 231, "loss": 0.7569, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:16:33", "remaining_time": "1:35:58"}
+{"current_steps": 35, "total_steps": 231, "loss": 0.7723, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:17:00", "remaining_time": "1:35:15"}
+{"current_steps": 36, "total_steps": 231, "loss": 0.7419, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:17:26", "remaining_time": "1:34:29"}
+{"current_steps": 37, "total_steps": 231, "loss": 0.7838, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:17:53", "remaining_time": "1:33:48"}
+{"current_steps": 38, "total_steps": 231, "loss": 0.732, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:18:19", "remaining_time": "1:33:04"}
+{"current_steps": 39, "total_steps": 231, "loss": 0.7479, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:18:45", "remaining_time": "1:32:18"}
+{"current_steps": 40, "total_steps": 231, "loss": 0.7416, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:19:11", "remaining_time": "1:31:36"}
+{"current_steps": 41, "total_steps": 231, "loss": 0.7445, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:19:38", "remaining_time": "1:30:59"}
+{"current_steps": 42, "total_steps": 231, "loss": 0.716, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:20:04", "remaining_time": "1:30:19"}
+{"current_steps": 43, "total_steps": 231, "loss": 0.7794, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:20:30", "remaining_time": "1:29:38"}
+{"current_steps": 44, "total_steps": 231, "loss": 0.7426, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:20:56", "remaining_time": "1:29:00"}
+{"current_steps": 45, "total_steps": 231, "loss": 0.7072, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:21:23", "remaining_time": "1:28:23"}
+{"current_steps": 46, "total_steps": 231, "loss": 0.7122, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:21:49", "remaining_time": "1:27:45"}
+{"current_steps": 47, "total_steps": 231, "loss": 0.7553, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:22:16", "remaining_time": "1:27:11"}
+{"current_steps": 48, "total_steps": 231, "loss": 0.7323, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:22:42", "remaining_time": "1:26:35"}
+{"current_steps": 49, "total_steps": 231, "loss": 0.719, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:23:10", "remaining_time": "1:26:03"}
+{"current_steps": 50, "total_steps": 231, "loss": 0.6852, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:23:36", "remaining_time": "1:25:29"}
+{"current_steps": 51, "total_steps": 231, "loss": 0.7347, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:24:03", "remaining_time": "1:24:54"}
+{"current_steps": 52, "total_steps": 231, "loss": 0.7037, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:24:28", "remaining_time": "1:24:16"}
+{"current_steps": 53, "total_steps": 231, "loss": 0.7463, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:24:55", "remaining_time": "1:23:42"}
+{"current_steps": 54, "total_steps": 231, "loss": 0.7404, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:25:22", "remaining_time": "1:23:09"}
+{"current_steps": 55, "total_steps": 231, "loss": 0.7248, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:25:48", "remaining_time": "1:22:35"}
+{"current_steps": 56, "total_steps": 231, "loss": 0.7691, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:26:15", "remaining_time": "1:22:02"}
+{"current_steps": 57, "total_steps": 231, "loss": 0.6955, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:26:42", "remaining_time": "1:21:30"}
+{"current_steps": 58, "total_steps": 231, "loss": 0.7683, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:27:09", "remaining_time": "1:20:59"}
+{"current_steps": 59, "total_steps": 231, "loss": 0.7197, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:27:35", "remaining_time": "1:20:27"}
+{"current_steps": 60, "total_steps": 231, "loss": 0.7289, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:28:03", "remaining_time": "1:19:56"}
+{"current_steps": 61, "total_steps": 231, "loss": 0.7193, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:28:29", "remaining_time": "1:19:25"}
+{"current_steps": 62, "total_steps": 231, "loss": 0.7219, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:28:55", "remaining_time": "1:18:51"}
+{"current_steps": 63, "total_steps": 231, "loss": 0.7396, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:29:22", "remaining_time": "1:18:19"}
+{"current_steps": 64, "total_steps": 231, "loss": 0.7745, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:29:49", "remaining_time": "1:17:49"}
+{"current_steps": 65, "total_steps": 231, "loss": 0.7324, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:30:16", "remaining_time": "1:17:19"}
+{"current_steps": 66, "total_steps": 231, "loss": 0.7409, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:30:42", "remaining_time": "1:16:45"}
+{"current_steps": 67, "total_steps": 231, "loss": 0.7062, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:32:29", "remaining_time": "1:19:30"}
+{"current_steps": 68, "total_steps": 231, "loss": 0.6927, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:32:53", "remaining_time": "1:18:50"}
+{"current_steps": 69, "total_steps": 231, "loss": 0.6612, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:33:18", "remaining_time": "1:18:12"}
+{"current_steps": 70, "total_steps": 231, "loss": 0.6412, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:33:46", "remaining_time": "1:17:40"}
+{"current_steps": 71, "total_steps": 231, "loss": 0.7077, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:34:12", "remaining_time": "1:17:06"}
+{"current_steps": 72, "total_steps": 231, "loss": 0.6949, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:34:38", "remaining_time": "1:16:29"}
+{"current_steps": 73, "total_steps": 231, "loss": 0.6669, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:35:04", "remaining_time": "1:15:54"}
+{"current_steps": 74, "total_steps": 231, "loss": 0.6681, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:35:29", "remaining_time": "1:15:18"}
+{"current_steps": 75, "total_steps": 231, "loss": 0.673, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:35:55", "remaining_time": "1:14:44"}
+{"current_steps": 76, "total_steps": 231, "loss": 0.6851, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:36:22", "remaining_time": "1:14:11"}
+{"current_steps": 77, "total_steps": 231, "loss": 0.6649, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:36:49", "remaining_time": "1:13:39"}
+{"current_steps": 78, "total_steps": 231, "loss": 0.634, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:37:16", "remaining_time": "1:13:06"}
+{"current_steps": 79, "total_steps": 231, "loss": 0.6878, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:37:43", "remaining_time": "1:12:34"}
+{"current_steps": 80, "total_steps": 231, "loss": 0.6794, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:38:08", "remaining_time": "1:12:00"}
+{"current_steps": 81, "total_steps": 231, "loss": 0.6718, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:38:35", "remaining_time": "1:11:27"}
+{"current_steps": 82, "total_steps": 231, "loss": 0.6493, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:39:02", "remaining_time": "1:10:56"}
+{"current_steps": 83, "total_steps": 231, "loss": 0.6824, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:39:27", "remaining_time": "1:10:21"}
+{"current_steps": 84, "total_steps": 231, "loss": 0.6479, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:39:54", "remaining_time": "1:09:49"}
+{"current_steps": 85, "total_steps": 231, "loss": 0.6697, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:40:20", "remaining_time": "1:09:17"}
+{"current_steps": 86, "total_steps": 231, "loss": 0.6665, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:40:47", "remaining_time": "1:08:46"}
+{"current_steps": 87, "total_steps": 231, "loss": 0.7038, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:41:14", "remaining_time": "1:08:15"}
+{"current_steps": 88, "total_steps": 231, "loss": 0.6859, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:41:40", "remaining_time": "1:07:43"}
+{"current_steps": 89, "total_steps": 231, "loss": 0.6807, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:42:05", "remaining_time": "1:07:10"}
+{"current_steps": 90, "total_steps": 231, "loss": 0.6751, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:42:32", "remaining_time": "1:06:39"}
+{"current_steps": 91, "total_steps": 231, "loss": 0.6925, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:42:59", "remaining_time": "1:06:08"}
+{"current_steps": 92, "total_steps": 231, "loss": 0.6116, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:43:25", "remaining_time": "1:05:36"}
+{"current_steps": 93, "total_steps": 231, "loss": 0.6581, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "0:43:52", "remaining_time": "1:05:06"}
+{"current_steps": 94, "total_steps": 231, "loss": 0.6705, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "0:44:19", "remaining_time": "1:04:36"}
+{"current_steps": 95, "total_steps": 231, "loss": 0.6386, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:44:46", "remaining_time": "1:04:05"}
+{"current_steps": 96, "total_steps": 231, "loss": 0.7049, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "0:45:13", "remaining_time": "1:03:35"}
+{"current_steps": 97, "total_steps": 231, "loss": 0.6951, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "0:45:40", "remaining_time": "1:03:05"}
+{"current_steps": 98, "total_steps": 231, "loss": 0.6954, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "0:46:06", "remaining_time": "1:02:34"}
+{"current_steps": 99, "total_steps": 231, "loss": 0.6461, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "0:46:33", "remaining_time": "1:02:04"}
+{"current_steps": 100, "total_steps": 231, "loss": 0.5918, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "0:48:32", "remaining_time": "1:03:35"}
+{"current_steps": 101, "total_steps": 231, "loss": 0.6034, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "0:48:57", "remaining_time": "1:03:00"}
+{"current_steps": 102, "total_steps": 231, "loss": 0.6231, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "0:49:24", "remaining_time": "1:02:28"}
+{"current_steps": 103, "total_steps": 231, "loss": 0.5976, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "0:49:50", "remaining_time": "1:01:56"}
+{"current_steps": 104, "total_steps": 231, "loss": 0.5539, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "0:50:17", "remaining_time": "1:01:24"}
+{"current_steps": 105, "total_steps": 231, "loss": 0.59, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:50:44", "remaining_time": "1:00:52"}
+{"current_steps": 106, "total_steps": 231, "loss": 0.556, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:51:10", "remaining_time": "1:00:21"}
+{"current_steps": 107, "total_steps": 231, "loss": 0.6463, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:51:36", "remaining_time": "0:59:49"}
+{"current_steps": 108, "total_steps": 231, "loss": 0.5826, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:52:04", "remaining_time": "0:59:18"}
+{"current_steps": 109, "total_steps": 231, "loss": 0.6166, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "0:52:31", "remaining_time": "0:58:47"}
+{"current_steps": 110, "total_steps": 231, "loss": 0.5746, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:52:58", "remaining_time": "0:58:16"}
+{"current_steps": 111, "total_steps": 231, "loss": 0.6117, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "0:53:23", "remaining_time": "0:57:43"}
+{"current_steps": 112, "total_steps": 231, "loss": 0.6295, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "0:53:50", "remaining_time": "0:57:12"}
+{"current_steps": 113, "total_steps": 231, "loss": 0.6137, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "0:54:17", "remaining_time": "0:56:41"}
+{"current_steps": 114, "total_steps": 231, "loss": 0.6456, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "0:54:44", "remaining_time": "0:56:11"}
+{"current_steps": 115, "total_steps": 231, "loss": 0.5677, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:55:10", "remaining_time": "0:55:39"}
+{"current_steps": 116, "total_steps": 231, "loss": 0.5601, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "0:55:36", "remaining_time": "0:55:07"}
+{"current_steps": 117, "total_steps": 231, "loss": 0.6025, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "0:56:02", "remaining_time": "0:54:36"}
+{"current_steps": 118, "total_steps": 231, "loss": 0.5983, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "0:56:29", "remaining_time": "0:54:05"}
+{"current_steps": 119, "total_steps": 231, "loss": 0.5693, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "0:56:55", "remaining_time": "0:53:34"}
+{"current_steps": 120, "total_steps": 231, "loss": 0.6084, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "0:57:22", "remaining_time": "0:53:04"}
+{"current_steps": 121, "total_steps": 231, "loss": 0.6265, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "0:57:49", "remaining_time": "0:52:33"}
+{"current_steps": 122, "total_steps": 231, "loss": 0.598, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "0:58:15", "remaining_time": "0:52:02"}
+{"current_steps": 123, "total_steps": 231, "loss": 0.5897, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "0:58:41", "remaining_time": "0:51:32"}
+{"current_steps": 124, "total_steps": 231, "loss": 0.5897, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "0:59:09", "remaining_time": "0:51:02"}
+{"current_steps": 125, "total_steps": 231, "loss": 0.5648, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "0:59:36", "remaining_time": "0:50:32"}
+{"current_steps": 126, "total_steps": 231, "loss": 0.6158, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "1:00:03", "remaining_time": "0:50:02"}
+{"current_steps": 127, "total_steps": 231, "loss": 0.6222, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "1:00:30", "remaining_time": "0:49:32"}
+{"current_steps": 128, "total_steps": 231, "loss": 0.6131, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "1:00:56", "remaining_time": "0:49:02"}
+{"current_steps": 129, "total_steps": 231, "loss": 0.5865, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "1:01:22", "remaining_time": "0:48:32"}
+{"current_steps": 130, "total_steps": 231, "loss": 0.6016, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:01:49", "remaining_time": "0:48:02"}
+{"current_steps": 131, "total_steps": 231, "loss": 0.6036, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "1:02:16", "remaining_time": "0:47:32"}
+{"current_steps": 132, "total_steps": 231, "loss": 0.5724, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:02:43", "remaining_time": "0:47:02"}
+{"current_steps": 133, "total_steps": 231, "loss": 0.5335, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:05:37", "remaining_time": "0:48:21"}
+{"current_steps": 134, "total_steps": 231, "loss": 0.5397, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:06:03", "remaining_time": "0:47:49"}
+{"current_steps": 135, "total_steps": 231, "loss": 0.4792, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:06:30", "remaining_time": "0:47:17"}
+{"current_steps": 136, "total_steps": 231, "loss": 0.5572, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:06:56", "remaining_time": "0:46:45"}
+{"current_steps": 137, "total_steps": 231, "loss": 0.5373, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:07:22", "remaining_time": "0:46:13"}
+{"current_steps": 138, "total_steps": 231, "loss": 0.5021, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:07:49", "remaining_time": "0:45:42"}
+{"current_steps": 139, "total_steps": 231, "loss": 0.5429, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:08:16", "remaining_time": "0:45:11"}
+{"current_steps": 140, "total_steps": 231, "loss": 0.5491, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:08:42", "remaining_time": "0:44:39"}
+{"current_steps": 141, "total_steps": 231, "loss": 0.5353, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:09:08", "remaining_time": "0:44:08"}
+{"current_steps": 142, "total_steps": 231, "loss": 0.5108, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:09:34", "remaining_time": "0:43:36"}
+{"current_steps": 143, "total_steps": 231, "loss": 0.5259, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:10:01", "remaining_time": "0:43:05"}
+{"current_steps": 144, "total_steps": 231, "loss": 0.4858, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:10:27", "remaining_time": "0:42:34"}
+{"current_steps": 145, "total_steps": 231, "loss": 0.5416, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:10:54", "remaining_time": "0:42:03"}
+{"current_steps": 146, "total_steps": 231, "loss": 0.5123, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:11:21", "remaining_time": "0:41:32"}
+{"current_steps": 147, "total_steps": 231, "loss": 0.5423, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:11:47", "remaining_time": "0:41:01"}
+{"current_steps": 148, "total_steps": 231, "loss": 0.5193, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:12:13", "remaining_time": "0:40:30"}
+{"current_steps": 149, "total_steps": 231, "loss": 0.4995, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:12:40", "remaining_time": "0:39:59"}
+{"current_steps": 150, "total_steps": 231, "loss": 0.4876, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:13:06", "remaining_time": "0:39:28"}
+{"current_steps": 151, "total_steps": 231, "loss": 0.51, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:13:33", "remaining_time": "0:38:58"}
+{"current_steps": 152, "total_steps": 231, "loss": 0.5099, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:14:00", "remaining_time": "0:38:27"}
+{"current_steps": 153, "total_steps": 231, "loss": 0.5031, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:14:26", "remaining_time": "0:37:57"}
+{"current_steps": 154, "total_steps": 231, "loss": 0.5239, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:14:53", "remaining_time": "0:37:26"}
+{"current_steps": 155, "total_steps": 231, "loss": 0.55, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:15:20", "remaining_time": "0:36:56"}
+{"current_steps": 156, "total_steps": 231, "loss": 0.5705, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:15:46", "remaining_time": "0:36:25"}
+{"current_steps": 157, "total_steps": 231, "loss": 0.4858, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:16:13", "remaining_time": "0:35:55"}
+{"current_steps": 158, "total_steps": 231, "loss": 0.5129, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:16:39", "remaining_time": "0:35:24"}
+{"current_steps": 159, "total_steps": 231, "loss": 0.5393, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:17:05", "remaining_time": "0:34:54"}
+{"current_steps": 160, "total_steps": 231, "loss": 0.5301, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:17:29", "remaining_time": "0:34:23"}
+{"current_steps": 161, "total_steps": 231, "loss": 0.5365, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:17:56", "remaining_time": "0:33:53"}
+{"current_steps": 162, "total_steps": 231, "loss": 0.5436, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:18:23", "remaining_time": "0:33:23"}
+{"current_steps": 163, "total_steps": 231, "loss": 0.4996, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:18:51", "remaining_time": "0:32:53"}
+{"current_steps": 164, "total_steps": 231, "loss": 0.4761, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:19:17", "remaining_time": "0:32:23"}
+{"current_steps": 165, "total_steps": 231, "loss": 0.5082, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:19:44", "remaining_time": "0:31:53"}
+{"current_steps": 166, "total_steps": 231, "loss": 0.4722, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:21:17", "remaining_time": "0:31:49"}
+{"current_steps": 167, "total_steps": 231, "loss": 0.5007, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:21:43", "remaining_time": "0:31:19"}
+{"current_steps": 168, "total_steps": 231, "loss": 0.4563, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:22:10", "remaining_time": "0:30:48"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.4219, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:22:36", "remaining_time": "0:30:18"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.4222, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:23:02", "remaining_time": "0:29:47"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.4563, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:23:29", "remaining_time": "0:29:17"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.473, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:23:55", "remaining_time": "0:28:47"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.4906, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:24:21", "remaining_time": "0:28:16"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.4917, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:24:47", "remaining_time": "0:27:46"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.4569, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:25:14", "remaining_time": "0:27:16"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.4635, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:25:40", "remaining_time": "0:26:46"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.4398, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:26:07", "remaining_time": "0:26:16"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.4284, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:26:33", "remaining_time": "0:25:46"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.4225, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:27:00", "remaining_time": "0:25:16"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.4641, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:27:26", "remaining_time": "0:24:46"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.4357, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:27:53", "remaining_time": "0:24:16"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.4329, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:28:19", "remaining_time": "0:23:46"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.4591, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:28:46", "remaining_time": "0:23:17"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.4422, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:29:13", "remaining_time": "0:22:47"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.5145, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:29:40", "remaining_time": "0:22:17"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.4473, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:30:07", "remaining_time": "0:21:48"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.4549, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:30:34", "remaining_time": "0:21:18"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.5098, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:30:57", "remaining_time": "0:20:48"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.4747, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:31:23", "remaining_time": "0:20:18"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.4705, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:31:49", "remaining_time": "0:19:48"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.4658, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:32:17", "remaining_time": "0:19:19"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.495, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:32:43", "remaining_time": "0:18:50"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.4912, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:33:09", "remaining_time": "0:18:20"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.4414, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:33:36", "remaining_time": "0:17:51"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.4428, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:34:02", "remaining_time": "0:17:21"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.4501, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "1:34:29", "remaining_time": "0:16:52"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.4156, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "1:34:56", "remaining_time": "0:16:23"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.4772, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "1:35:22", "remaining_time": "0:15:53"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.4291, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "1:36:51", "remaining_time": "0:15:34"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.4452, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:37:18", "remaining_time": "0:15:04"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.4869, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "1:37:44", "remaining_time": "0:14:35"}
+{"current_steps": 202, "total_steps": 231, "loss": 0.4514, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "1:38:11", "remaining_time": "0:14:05"}
+{"current_steps": 203, "total_steps": 231, "loss": 0.4111, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "1:38:37", "remaining_time": "0:13:36"}
+{"current_steps": 204, "total_steps": 231, "loss": 0.3967, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "1:39:03", "remaining_time": "0:13:06"}
+{"current_steps": 205, "total_steps": 231, "loss": 0.4209, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:39:29", "remaining_time": "0:12:37"}
+{"current_steps": 206, "total_steps": 231, "loss": 0.4709, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "1:39:57", "remaining_time": "0:12:07"}
+{"current_steps": 207, "total_steps": 231, "loss": 0.4057, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "1:40:23", "remaining_time": "0:11:38"}
+{"current_steps": 208, "total_steps": 231, "loss": 0.4025, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "1:40:50", "remaining_time": "0:11:09"}
+{"current_steps": 209, "total_steps": 231, "loss": 0.389, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "1:41:17", "remaining_time": "0:10:39"}
+{"current_steps": 210, "total_steps": 231, "loss": 0.4167, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "1:41:43", "remaining_time": "0:10:10"}
+{"current_steps": 211, "total_steps": 231, "loss": 0.4448, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "1:42:08", "remaining_time": "0:09:40"}
+{"current_steps": 212, "total_steps": 231, "loss": 0.4279, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "1:42:34", "remaining_time": "0:09:11"}
+{"current_steps": 213, "total_steps": 231, "loss": 0.4333, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "1:43:00", "remaining_time": "0:08:42"}
+{"current_steps": 214, "total_steps": 231, "loss": 0.4435, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "1:43:27", "remaining_time": "0:08:13"}
+{"current_steps": 215, "total_steps": 231, "loss": 0.4058, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "1:43:52", "remaining_time": "0:07:43"}
+{"current_steps": 216, "total_steps": 231, "loss": 0.4212, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "1:44:19", "remaining_time": "0:07:14"}
+{"current_steps": 217, "total_steps": 231, "loss": 0.433, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "1:44:45", "remaining_time": "0:06:45"}
+{"current_steps": 218, "total_steps": 231, "loss": 0.4114, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "1:45:11", "remaining_time": "0:06:16"}
+{"current_steps": 219, "total_steps": 231, "loss": 0.4208, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "1:45:37", "remaining_time": "0:05:47"}
+{"current_steps": 220, "total_steps": 231, "loss": 0.4377, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "1:46:04", "remaining_time": "0:05:18"}
+{"current_steps": 221, "total_steps": 231, "loss": 0.4335, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "1:46:31", "remaining_time": "0:04:49"}
+{"current_steps": 222, "total_steps": 231, "loss": 0.429, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "1:46:57", "remaining_time": "0:04:20"}
+{"current_steps": 223, "total_steps": 231, "loss": 0.4489, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "1:47:25", "remaining_time": "0:03:51"}
+{"current_steps": 224, "total_steps": 231, "loss": 0.4455, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "1:47:51", "remaining_time": "0:03:22"}
+{"current_steps": 225, "total_steps": 231, "loss": 0.4448, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "1:48:17", "remaining_time": "0:02:53"}
+{"current_steps": 226, "total_steps": 231, "loss": 0.4125, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "1:48:44", "remaining_time": "0:02:24"}
+{"current_steps": 227, "total_steps": 231, "loss": 0.4053, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "1:49:10", "remaining_time": "0:01:55"}
+{"current_steps": 228, "total_steps": 231, "loss": 0.449, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "1:49:36", "remaining_time": "0:01:26"}
+{"current_steps": 229, "total_steps": 231, "loss": 0.4298, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "1:50:03", "remaining_time": "0:00:57"}
+{"current_steps": 230, "total_steps": 231, "loss": 0.4316, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "1:50:30", "remaining_time": "0:00:28"}
+{"current_steps": 231, "total_steps": 231, "loss": 0.443, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:50:55", "remaining_time": "0:00:00"}
+{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:52:56", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1659 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 0.45404192269934357,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.8175,
+      "step": 1
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 0.4917731617433597,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8089,
+      "step": 2
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 0.43539133801235924,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7975,
+      "step": 3
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.4519256892966392,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8046,
+      "step": 4
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.28720192401944866,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.8215,
+      "step": 5
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.3677456465780556,
+      "learning_rate": 5e-06,
+      "loss": 0.7906,
+      "step": 6
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.9194352778005709,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.793,
+      "step": 7
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.7156412843519948,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8245,
+      "step": 8
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.5089150053764867,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7622,
+      "step": 9
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.3780110166718658,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5222565876804458,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.7662,
+      "step": 11
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.6222553686265413,
+      "learning_rate": 1e-05,
+      "loss": 0.7814,
+      "step": 12
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 0.5185673069907736,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.7766,
+      "step": 13
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.3854806334293932,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8209,
+      "step": 14
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.4663667588511311,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7498,
+      "step": 15
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.49386497838516236,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7466,
+      "step": 16
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 0.456157458159694,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 0.7514,
+      "step": 17
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.391640681561914,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7879,
+      "step": 18
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.4601977317335622,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.804,
+      "step": 19
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.4848501100787871,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7816,
+      "step": 20
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.41383228738964295,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.7771,
+      "step": 21
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.540316477528811,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.8016,
+      "step": 22
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.40379514416188667,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.8217,
+      "step": 23
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.4756570316376291,
+      "learning_rate": 2e-05,
+      "loss": 0.7633,
+      "step": 24
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.41399508025723236,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.7889,
+      "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.4457872415888005,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.7973,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.3956381370526351,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.7742,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.4455994153429883,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.7885,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.5001691581205011,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.773,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.3716715232168673,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.7916,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.42090023133566995,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.8188,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.4234847011956473,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.7724,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33502228724679345,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.7806,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.4751502077280668,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.7569,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.3945255799951885,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.7723,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.5000631707654161,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.7419,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.4299367812148087,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.7838,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.48123262096644726,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.732,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.4322275750955115,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.7479,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.4264785762340682,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.7416,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.42755114582110104,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.7445,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.4647888549497104,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.716,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.5548994096636525,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.7794,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.6512138493815964,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.7426,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6599233740244347,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.7072,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.4918413839868032,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.7122,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.46266316435390575,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.7553,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.5719611759228369,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.7323,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.4650467098543586,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.719,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.47262576040525817,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.6852,
+      "step": 50
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.4139673970067043,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.7347,
+      "step": 51
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.3749062072660008,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.7037,
+      "step": 52
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.4900872301837013,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.7463,
+      "step": 53
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.4304472787186808,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.7404,
+      "step": 54
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.41298688400235295,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.7248,
+      "step": 55
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.4114916666439847,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.7691,
+      "step": 56
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.4479321189387342,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.6955,
+      "step": 57
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.39505808462042286,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.7683,
+      "step": 58
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.4149877700202695,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.7197,
+      "step": 59
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.3699320087286979,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.7289,
+      "step": 60
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.41486600284521025,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.7193,
+      "step": 61
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.3567474690754212,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.7219,
+      "step": 62
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.40722062536298453,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.7396,
+      "step": 63
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.4010891948969097,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.7745,
+      "step": 64
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.33429885493126726,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.7324,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.39491205167588617,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.7409,
+      "step": 66
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.484969972603566,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.7062,
+      "step": 67
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.4863336277140621,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.6927,
+      "step": 68
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.5096357683183218,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.6612,
+      "step": 69
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.48322952651428286,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.6412,
+      "step": 70
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.4221595004501216,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.7077,
+      "step": 71
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.43611020839153114,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.6949,
+      "step": 72
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.45578329588946437,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.6669,
+      "step": 73
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.45417147247230943,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.6681,
+      "step": 74
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.4160955768518612,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.673,
+      "step": 75
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.4276838043195557,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.6851,
+      "step": 76
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.3928420657759498,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.6649,
+      "step": 77
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.399555483034014,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.634,
+      "step": 78
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.426521795086231,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.6878,
+      "step": 79
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.36158253835514503,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.6794,
+      "step": 80
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.39932078739571836,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.6718,
+      "step": 81
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.41834253839933744,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.6493,
+      "step": 82
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.3642773746555324,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.6824,
+      "step": 83
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.3801539406045018,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.6479,
+      "step": 84
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.36062164140177216,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.6697,
+      "step": 85
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.3609319591166014,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.6665,
+      "step": 86
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.3557810864627686,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.7038,
+      "step": 87
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.32571574930810243,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.6859,
+      "step": 88
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 0.35740454414375333,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.6807,
+      "step": 89
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.353293086570693,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.6751,
+      "step": 90
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 0.3635232148430636,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.6925,
+      "step": 91
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.32947551714233064,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.6116,
+      "step": 92
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.3948262094416439,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6581,
+      "step": 93
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.31363922102118225,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.6705,
+      "step": 94
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.35995682431320913,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.6386,
+      "step": 95
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.34315747409978997,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.7049,
+      "step": 96
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 0.3102359902459931,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.6951,
+      "step": 97
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.3313369384920703,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.6954,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3289930645921954,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.6461,
+      "step": 99
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 0.554418451579518,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.5918,
+      "step": 100
+    },
+    {
+      "epoch": 3.0606060606060606,
+      "grad_norm": 0.48985519582710435,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.6034,
+      "step": 101
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.588704246980213,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.6231,
+      "step": 102
+    },
+    {
+      "epoch": 3.121212121212121,
+      "grad_norm": 0.5417698851668765,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.5976,
+      "step": 103
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 0.48683148314426355,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.5539,
+      "step": 104
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.4404191388960243,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.59,
+      "step": 105
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 0.6044644583011649,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.556,
+      "step": 106
+    },
+    {
+      "epoch": 3.242424242424242,
+      "grad_norm": 0.4187532571010145,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.6463,
+      "step": 107
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.5029972310900598,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.5826,
+      "step": 108
+    },
+    {
+      "epoch": 3.303030303030303,
+      "grad_norm": 0.41282532864997246,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.6166,
+      "step": 109
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.47490843385272996,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.5746,
+      "step": 110
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 0.440401851756132,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.6117,
+      "step": 111
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.3967519472519431,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.6295,
+      "step": 112
+    },
+    {
+      "epoch": 3.4242424242424243,
+      "grad_norm": 0.44320916182805037,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.6137,
+      "step": 113
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.3794432860970576,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.6456,
+      "step": 114
+    },
+    {
+      "epoch": 3.484848484848485,
+      "grad_norm": 0.3715910139952054,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.5677,
+      "step": 115
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 0.4200754325291374,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.5601,
+      "step": 116
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 0.41667136318291725,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.6025,
+      "step": 117
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 0.3967776189508287,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.5983,
+      "step": 118
+    },
+    {
+      "epoch": 3.606060606060606,
+      "grad_norm": 0.38859872977785287,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.5693,
+      "step": 119
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.3657265255161343,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.6084,
+      "step": 120
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.3499353718681901,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.6265,
+      "step": 121
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 0.4094454939382451,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.598,
+      "step": 122
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.32892441325866917,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.5897,
+      "step": 123
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 0.3833177656299727,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.5897,
+      "step": 124
+    },
+    {
+      "epoch": 3.787878787878788,
+      "grad_norm": 0.3769241654165782,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.5648,
+      "step": 125
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 0.34272214405489915,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.6158,
+      "step": 126
+    },
+    {
+      "epoch": 3.8484848484848486,
+      "grad_norm": 0.3755040249036914,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.6222,
+      "step": 127
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.3364748840442625,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.6131,
+      "step": 128
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 0.3313129750694039,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.5865,
+      "step": 129
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 0.34004338305513937,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.6016,
+      "step": 130
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.35450131562874504,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.6036,
+      "step": 131
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2884340463320288,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.5724,
+      "step": 132
+    },
+    {
+      "epoch": 4.03030303030303,
+      "grad_norm": 0.8221980611820946,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.5335,
+      "step": 133
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 0.3593534333309625,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.5397,
+      "step": 134
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 1.016539585630258,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.4792,
+      "step": 135
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 0.3836515827869688,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.5572,
+      "step": 136
+    },
+    {
+      "epoch": 4.151515151515151,
+      "grad_norm": 0.654174879353079,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.5373,
+      "step": 137
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.4860925117352824,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.5021,
+      "step": 138
+    },
+    {
+      "epoch": 4.212121212121212,
+      "grad_norm": 0.44624230931575426,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.5429,
+      "step": 139
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 0.7365373727628527,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.5491,
+      "step": 140
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.34738655001456165,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.5353,
+      "step": 141
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 0.5685155911111173,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.5108,
+      "step": 142
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.5025844097814388,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.5259,
+      "step": 143
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.3485318123713458,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.4858,
+      "step": 144
+    },
+    {
+      "epoch": 4.393939393939394,
+      "grad_norm": 0.49548568133152016,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.5416,
+      "step": 145
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 0.38895260895412237,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.5123,
+      "step": 146
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.3787457287350692,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.5423,
+      "step": 147
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.4078612790532545,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.5193,
+      "step": 148
+    },
+    {
+      "epoch": 4.515151515151516,
+      "grad_norm": 0.35138547275802173,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.4995,
+      "step": 149
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.35711350869183073,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.4876,
+      "step": 150
+    },
+    {
+      "epoch": 4.575757575757576,
+      "grad_norm": 0.35616419823813167,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.51,
+      "step": 151
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 0.36474499374188823,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.5099,
+      "step": 152
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.3403698282794116,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.5031,
+      "step": 153
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.33883017236772794,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.5239,
+      "step": 154
+    },
+    {
+      "epoch": 4.696969696969697,
+      "grad_norm": 0.3398850608166464,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.55,
+      "step": 155
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.3753451324323081,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.5705,
+      "step": 156
+    },
+    {
+      "epoch": 4.757575757575758,
+      "grad_norm": 0.28415263780988786,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.4858,
+      "step": 157
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 0.3274461121683733,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.5129,
+      "step": 158
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.31333297032587853,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.5393,
+      "step": 159
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.3182090157724561,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.5301,
+      "step": 160
+    },
+    {
+      "epoch": 4.878787878787879,
+      "grad_norm": 0.3065689083522182,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.5365,
+      "step": 161
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.31168899765491165,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.5436,
+      "step": 162
+    },
+    {
+      "epoch": 4.9393939393939394,
+      "grad_norm": 0.32326413717899527,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.4996,
+      "step": 163
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 0.286612363019893,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.4761,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2951379128595362,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.5082,
+      "step": 165
+    },
+    {
+      "epoch": 5.03030303030303,
+      "grad_norm": 0.6396686995541148,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.4722,
+      "step": 166
+    },
+    {
+      "epoch": 5.0606060606060606,
+      "grad_norm": 0.3423121241028325,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.5007,
+      "step": 167
+    },
+    {
+      "epoch": 5.090909090909091,
+      "grad_norm": 0.4221329439669877,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.4563,
+      "step": 168
+    },
+    {
+      "epoch": 5.121212121212121,
+      "grad_norm": 0.6155289420170268,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.4219,
+      "step": 169
+    },
+    {
+      "epoch": 5.151515151515151,
+      "grad_norm": 0.40123316857880825,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.4222,
+      "step": 170
+    },
+    {
+      "epoch": 5.181818181818182,
+      "grad_norm": 0.3320803102770148,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.4563,
+      "step": 171
+    },
+    {
+      "epoch": 5.212121212121212,
+      "grad_norm": 0.3948023088899153,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.473,
+      "step": 172
+    },
+    {
+      "epoch": 5.242424242424242,
+      "grad_norm": 0.3837070545882063,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.4906,
+      "step": 173
+    },
+    {
+      "epoch": 5.2727272727272725,
+      "grad_norm": 0.33592587876681307,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.4917,
+      "step": 174
+    },
+    {
+      "epoch": 5.303030303030303,
+      "grad_norm": 0.31195103979332,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.4569,
+      "step": 175
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.36728919190444254,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.4635,
+      "step": 176
+    },
+    {
+      "epoch": 5.363636363636363,
+      "grad_norm": 0.3517700737933514,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.4398,
+      "step": 177
+    },
+    {
+      "epoch": 5.393939393939394,
+      "grad_norm": 0.2943168684553675,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.4284,
+      "step": 178
+    },
+    {
+      "epoch": 5.424242424242424,
+      "grad_norm": 0.26739447517561443,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.4225,
+      "step": 179
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.3507665474790921,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.4641,
+      "step": 180
+    },
+    {
+      "epoch": 5.484848484848484,
+      "grad_norm": 0.40200384317116233,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.4357,
+      "step": 181
+    },
+    {
+      "epoch": 5.515151515151516,
+      "grad_norm": 0.2823987694207428,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.4329,
+      "step": 182
+    },
+    {
+      "epoch": 5.545454545454545,
+      "grad_norm": 0.3194011591578307,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.4591,
+      "step": 183
+    },
+    {
+      "epoch": 5.575757575757576,
+      "grad_norm": 12.00665981560085,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.4422,
+      "step": 184
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 0.4054663444384578,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.5145,
+      "step": 185
+    },
+    {
+      "epoch": 5.636363636363637,
+      "grad_norm": 0.3444464352203058,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.4473,
+      "step": 186
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.2630241472106751,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.4549,
+      "step": 187
+    },
+    {
+      "epoch": 5.696969696969697,
+      "grad_norm": 0.26492666361572254,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.5098,
+      "step": 188
+    },
+    {
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.31298591883853255,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.4747,
+      "step": 189
+    },
+    {
+      "epoch": 5.757575757575758,
+      "grad_norm": 0.29755219202050065,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.4705,
+      "step": 190
+    },
+    {
+      "epoch": 5.787878787878788,
+      "grad_norm": 0.31180141240352466,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.4658,
+      "step": 191
+    },
+    {
+      "epoch": 5.818181818181818,
+      "grad_norm": 0.2548757714611652,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.495,
+      "step": 192
+    },
+    {
+      "epoch": 5.848484848484849,
+      "grad_norm": 0.2495894264574609,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.4912,
+      "step": 193
+    },
+    {
+      "epoch": 5.878787878787879,
+      "grad_norm": 0.27525778253407,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.4414,
+      "step": 194
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.2882641006805427,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.4428,
+      "step": 195
+    },
+    {
+      "epoch": 5.9393939393939394,
+      "grad_norm": 0.2707067991284653,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.4501,
+      "step": 196
+    },
+    {
+      "epoch": 5.96969696969697,
+      "grad_norm": 0.27255241451283946,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.4156,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.23902392900936897,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.4772,
+      "step": 198
+    },
+    {
+      "epoch": 6.03030303030303,
+      "grad_norm": 0.59970297576034,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.4291,
+      "step": 199
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.4576800220633988,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.4452,
+      "step": 200
+    },
+    {
+      "epoch": 6.090909090909091,
+      "grad_norm": 0.4274779611887373,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.4869,
+      "step": 201
+    },
+    {
+      "epoch": 6.121212121212121,
+      "grad_norm": 0.2724706245307364,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.4514,
+      "step": 202
+    },
+    {
+      "epoch": 6.151515151515151,
+      "grad_norm": 0.2768126110602979,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.4111,
+      "step": 203
+    },
+    {
+      "epoch": 6.181818181818182,
+      "grad_norm": 0.36175848135934524,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.3967,
+      "step": 204
+    },
+    {
+      "epoch": 6.212121212121212,
+      "grad_norm": 0.3255617649420347,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.4209,
+      "step": 205
+    },
+    {
+      "epoch": 6.242424242424242,
+      "grad_norm": 0.37390031536194934,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.4709,
+      "step": 206
+    },
+    {
+      "epoch": 6.2727272727272725,
+      "grad_norm": 0.2842925028722727,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.4057,
+      "step": 207
+    },
+    {
+      "epoch": 6.303030303030303,
+      "grad_norm": 0.30737010509919,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.4025,
+      "step": 208
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.2774212067126218,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.389,
+      "step": 209
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.24902416809163633,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.4167,
+      "step": 210
+    },
+    {
+      "epoch": 6.393939393939394,
+      "grad_norm": 0.23884345151826672,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.4448,
+      "step": 211
+    },
+    {
+      "epoch": 6.424242424242424,
+      "grad_norm": 0.2433230050086897,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.4279,
+      "step": 212
+    },
+    {
+      "epoch": 6.454545454545454,
+      "grad_norm": 0.23663270669548958,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.4333,
+      "step": 213
+    },
+    {
+      "epoch": 6.484848484848484,
+      "grad_norm": 0.26350115568381516,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.4435,
+      "step": 214
+    },
+    {
+      "epoch": 6.515151515151516,
+      "grad_norm": 0.2523958492422985,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.4058,
+      "step": 215
+    },
+    {
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.4363043626731539,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.4212,
+      "step": 216
+    },
+    {
+      "epoch": 6.575757575757576,
+      "grad_norm": 0.24510225333558835,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.433,
+      "step": 217
+    },
+    {
+      "epoch": 6.606060606060606,
+      "grad_norm": 0.2515502412207173,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.4114,
+      "step": 218
+    },
+    {
+      "epoch": 6.636363636363637,
+      "grad_norm": 0.22642116713616728,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.4208,
+      "step": 219
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.23045976062255522,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.4377,
+      "step": 220
+    },
+    {
+      "epoch": 6.696969696969697,
+      "grad_norm": 0.3273677387615356,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.4335,
+      "step": 221
+    },
+    {
+      "epoch": 6.7272727272727275,
+      "grad_norm": 0.2190561532506803,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.429,
+      "step": 222
+    },
+    {
+      "epoch": 6.757575757575758,
+      "grad_norm": 0.2173262726511028,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.4489,
+      "step": 223
+    },
+    {
+      "epoch": 6.787878787878788,
+      "grad_norm": 0.21008428279486377,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.4455,
+      "step": 224
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.22018538950475083,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.4448,
+      "step": 225
+    },
+    {
+      "epoch": 6.848484848484849,
+      "grad_norm": 0.2150873034352879,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.4125,
+      "step": 226
+    },
+    {
+      "epoch": 6.878787878787879,
+      "grad_norm": 0.2327869206947825,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.4053,
+      "step": 227
+    },
+    {
+      "epoch": 6.909090909090909,
+      "grad_norm": 0.22670408223918043,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.449,
+      "step": 228
+    },
+    {
+      "epoch": 6.9393939393939394,
+      "grad_norm": 0.22376706811314764,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.4298,
+      "step": 229
+    },
+    {
+      "epoch": 6.96969696969697,
+      "grad_norm": 0.21864456226252352,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.4316,
+      "step": 230
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.211507799811681,
+      "learning_rate": 0.0,
+      "loss": 0.443,
+      "step": 231
+    },
+    {
+      "epoch": 7.0,
+      "step": 231,
+      "total_flos": 2229330703810560.0,
+      "train_loss": 0.6009024948010713,
+      "train_runtime": 6779.558,
+      "train_samples_per_second": 3.263,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 231,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 2229330703810560.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958c7f2965c876b503ea05df4bc696269610f0c58059020c6bb9b6dcbef9deb1
+size 7416