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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: openthoughts_100k_32B
+  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. -->
+
+# openthoughts_100k_32B
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the mlfoundations-dev/openthoughts_100k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 512
+- total_train_batch_size: 512
+- total_eval_batch_size: 4096
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.281478037700608e+16,
+    "train_loss": 0.36058994583141657,
+    "train_runtime": 22607.6598,
+    "train_samples_per_second": 9.116,
+    "train_steps_per_second": 0.018
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345036e334e04267fbe3f0a2f361ffad5365d424171404ac56483f8fc6d0a346
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d4f3c779e03af2ddeb307452468f2a7e58292b3fcc6541388d2b7399e482b4
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042c57108d962aeea391d020eabe2c77f130d6d4a672f574d379dc8c643a98d7
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccca46e3f4e6740b3b286840a41af7c531aca1045a76954efa1f4834b6669b9
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fcc72fa9b12e8f5893d84f2ffa8c2cbf4573c4e9b01df28f40677c854d1066
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5aba3f63c6c26a457b72e4ce6ac1217f0cea358c6e469ee1fb9d1cc66184a7
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12eb931ee0f149e2e686fad611f0fd99d619dd96bbc85bd5fadee81cb1d6c698
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8414f334f3d8edcb6d548aac865879fd8031c2df2c808033f4f7d578f349dbff
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5617a82e6006443278bad4b706b73f1036754928cfea974141a2a90d5d31a8
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c04a4db68a36d9776ca63aa734bb5be0fabc7dba5806c15ace168c6705bf49
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48070d19a2b47ef5a35f59c140b1b5fee9d725131a59d172d745ae34ad5ee52a
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:888bf8bcb1291e0d37bed193431ccd9fe3fcea5810b0c4bf0ec08088df6d000b
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb379709eae707347ea8ad5da2cbae67c5eb3b2c8d1d2dcb18ba32dcd88652a
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63068e7d297a20d09e3524b7f253ad188ee4ca62ec41983d230b085135732a6
+size 2123397800

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-30 18:55:36", "end_time": "2025-05-01 01:18:23"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.281478037700608e+16,
+    "train_loss": 0.36058994583141657,
+    "train_runtime": 22607.6598,
+    "train_samples_per_second": 9.116,
+    "train_steps_per_second": 0.018
+}

trainer_log.jsonl

@@ -0,0 +1,406 @@
+{"current_steps": 1, "total_steps": 405, "loss": 0.753, "lr": 1.951219512195122e-06, "epoch": 0.012345679012345678, "percentage": 0.25, "elapsed_time": "0:04:03", "remaining_time": "1 day, 3:17:09"}
+{"current_steps": 2, "total_steps": 405, "loss": 0.7445, "lr": 3.902439024390244e-06, "epoch": 0.024691358024691357, "percentage": 0.49, "elapsed_time": "0:04:49", "remaining_time": "16:12:21"}
+{"current_steps": 3, "total_steps": 405, "loss": 0.7446, "lr": 5.853658536585366e-06, "epoch": 0.037037037037037035, "percentage": 0.74, "elapsed_time": "0:05:34", "remaining_time": "12:27:26"}
+{"current_steps": 4, "total_steps": 405, "loss": 0.7323, "lr": 7.804878048780489e-06, "epoch": 0.04938271604938271, "percentage": 0.99, "elapsed_time": "0:06:19", "remaining_time": "10:33:36"}
+{"current_steps": 5, "total_steps": 405, "loss": 0.6942, "lr": 9.756097560975611e-06, "epoch": 0.06172839506172839, "percentage": 1.23, "elapsed_time": "0:07:08", "remaining_time": "9:31:58"}
+{"current_steps": 6, "total_steps": 405, "loss": 0.6725, "lr": 1.1707317073170731e-05, "epoch": 0.07407407407407407, "percentage": 1.48, "elapsed_time": "0:07:56", "remaining_time": "8:48:07"}
+{"current_steps": 7, "total_steps": 405, "loss": 0.6619, "lr": 1.3658536585365855e-05, "epoch": 0.08641975308641975, "percentage": 1.73, "elapsed_time": "0:08:42", "remaining_time": "8:15:28"}
+{"current_steps": 8, "total_steps": 405, "loss": 0.6237, "lr": 1.5609756097560978e-05, "epoch": 0.09876543209876543, "percentage": 1.98, "elapsed_time": "0:09:28", "remaining_time": "7:50:08"}
+{"current_steps": 9, "total_steps": 405, "loss": 0.6065, "lr": 1.75609756097561e-05, "epoch": 0.1111111111111111, "percentage": 2.22, "elapsed_time": "0:10:15", "remaining_time": "7:31:17"}
+{"current_steps": 10, "total_steps": 405, "loss": 0.5767, "lr": 1.9512195121951222e-05, "epoch": 0.12345679012345678, "percentage": 2.47, "elapsed_time": "0:10:59", "remaining_time": "7:14:10"}
+{"current_steps": 11, "total_steps": 405, "loss": 0.5716, "lr": 2.1463414634146344e-05, "epoch": 0.13580246913580246, "percentage": 2.72, "elapsed_time": "0:11:43", "remaining_time": "7:00:01"}
+{"current_steps": 12, "total_steps": 405, "loss": 0.5503, "lr": 2.3414634146341463e-05, "epoch": 0.14814814814814814, "percentage": 2.96, "elapsed_time": "0:12:29", "remaining_time": "6:49:04"}
+{"current_steps": 13, "total_steps": 405, "loss": 0.5403, "lr": 2.536585365853659e-05, "epoch": 0.16049382716049382, "percentage": 3.21, "elapsed_time": "0:13:15", "remaining_time": "6:39:40"}
+{"current_steps": 14, "total_steps": 405, "loss": 0.527, "lr": 2.731707317073171e-05, "epoch": 0.1728395061728395, "percentage": 3.46, "elapsed_time": "0:14:00", "remaining_time": "6:31:14"}
+{"current_steps": 15, "total_steps": 405, "loss": 0.5249, "lr": 2.926829268292683e-05, "epoch": 0.18518518518518517, "percentage": 3.7, "elapsed_time": "0:14:45", "remaining_time": "6:23:40"}
+{"current_steps": 16, "total_steps": 405, "loss": 0.5204, "lr": 3.1219512195121955e-05, "epoch": 0.19753086419753085, "percentage": 3.95, "elapsed_time": "0:15:35", "remaining_time": "6:19:06"}
+{"current_steps": 17, "total_steps": 405, "loss": 0.5107, "lr": 3.3170731707317074e-05, "epoch": 0.20987654320987653, "percentage": 4.2, "elapsed_time": "0:16:23", "remaining_time": "6:14:14"}
+{"current_steps": 18, "total_steps": 405, "loss": 0.4979, "lr": 3.51219512195122e-05, "epoch": 0.2222222222222222, "percentage": 4.44, "elapsed_time": "0:17:07", "remaining_time": "6:08:01"}
+{"current_steps": 19, "total_steps": 405, "loss": 0.5002, "lr": 3.7073170731707325e-05, "epoch": 0.2345679012345679, "percentage": 4.69, "elapsed_time": "0:17:52", "remaining_time": "6:03:06"}
+{"current_steps": 20, "total_steps": 405, "loss": 0.4975, "lr": 3.9024390243902444e-05, "epoch": 0.24691358024691357, "percentage": 4.94, "elapsed_time": "0:18:39", "remaining_time": "5:59:17"}
+{"current_steps": 21, "total_steps": 405, "loss": 0.4866, "lr": 4.097560975609756e-05, "epoch": 0.25925925925925924, "percentage": 5.19, "elapsed_time": "0:19:27", "remaining_time": "5:55:44"}
+{"current_steps": 22, "total_steps": 405, "loss": 0.4881, "lr": 4.292682926829269e-05, "epoch": 0.2716049382716049, "percentage": 5.43, "elapsed_time": "0:20:12", "remaining_time": "5:51:42"}
+{"current_steps": 23, "total_steps": 405, "loss": 0.4687, "lr": 4.4878048780487814e-05, "epoch": 0.2839506172839506, "percentage": 5.68, "elapsed_time": "0:20:56", "remaining_time": "5:47:44"}
+{"current_steps": 24, "total_steps": 405, "loss": 0.4722, "lr": 4.6829268292682926e-05, "epoch": 0.2962962962962963, "percentage": 5.93, "elapsed_time": "0:21:43", "remaining_time": "5:44:54"}
+{"current_steps": 25, "total_steps": 405, "loss": 0.4663, "lr": 4.878048780487805e-05, "epoch": 0.30864197530864196, "percentage": 6.17, "elapsed_time": "0:22:27", "remaining_time": "5:41:26"}
+{"current_steps": 26, "total_steps": 405, "loss": 0.4669, "lr": 5.073170731707318e-05, "epoch": 0.32098765432098764, "percentage": 6.42, "elapsed_time": "0:23:14", "remaining_time": "5:38:40"}
+{"current_steps": 27, "total_steps": 405, "loss": 0.4658, "lr": 5.26829268292683e-05, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:24:00", "remaining_time": "5:36:05"}
+{"current_steps": 28, "total_steps": 405, "loss": 0.4666, "lr": 5.463414634146342e-05, "epoch": 0.345679012345679, "percentage": 6.91, "elapsed_time": "0:24:50", "remaining_time": "5:34:33"}
+{"current_steps": 29, "total_steps": 405, "loss": 0.4553, "lr": 5.658536585365854e-05, "epoch": 0.35802469135802467, "percentage": 7.16, "elapsed_time": "0:25:36", "remaining_time": "5:32:05"}
+{"current_steps": 30, "total_steps": 405, "loss": 0.4585, "lr": 5.853658536585366e-05, "epoch": 0.37037037037037035, "percentage": 7.41, "elapsed_time": "0:26:22", "remaining_time": "5:29:39"}
+{"current_steps": 31, "total_steps": 405, "loss": 0.4504, "lr": 6.0487804878048785e-05, "epoch": 0.38271604938271603, "percentage": 7.65, "elapsed_time": "0:27:11", "remaining_time": "5:27:58"}
+{"current_steps": 32, "total_steps": 405, "loss": 0.4567, "lr": 6.243902439024391e-05, "epoch": 0.3950617283950617, "percentage": 7.9, "elapsed_time": "0:27:57", "remaining_time": "5:25:58"}
+{"current_steps": 33, "total_steps": 405, "loss": 0.4542, "lr": 6.439024390243903e-05, "epoch": 0.4074074074074074, "percentage": 8.15, "elapsed_time": "0:28:42", "remaining_time": "5:23:32"}
+{"current_steps": 34, "total_steps": 405, "loss": 0.4535, "lr": 6.634146341463415e-05, "epoch": 0.41975308641975306, "percentage": 8.4, "elapsed_time": "0:29:25", "remaining_time": "5:21:07"}
+{"current_steps": 35, "total_steps": 405, "loss": 0.4571, "lr": 6.829268292682927e-05, "epoch": 0.43209876543209874, "percentage": 8.64, "elapsed_time": "0:30:11", "remaining_time": "5:19:13"}
+{"current_steps": 36, "total_steps": 405, "loss": 0.4567, "lr": 7.02439024390244e-05, "epoch": 0.4444444444444444, "percentage": 8.89, "elapsed_time": "0:30:55", "remaining_time": "5:16:59"}
+{"current_steps": 37, "total_steps": 405, "loss": 0.4569, "lr": 7.219512195121952e-05, "epoch": 0.4567901234567901, "percentage": 9.14, "elapsed_time": "0:31:40", "remaining_time": "5:15:04"}
+{"current_steps": 38, "total_steps": 405, "loss": 0.4492, "lr": 7.414634146341465e-05, "epoch": 0.4691358024691358, "percentage": 9.38, "elapsed_time": "0:32:28", "remaining_time": "5:13:40"}
+{"current_steps": 39, "total_steps": 405, "loss": 0.4463, "lr": 7.609756097560976e-05, "epoch": 0.48148148148148145, "percentage": 9.63, "elapsed_time": "0:33:18", "remaining_time": "5:12:34"}
+{"current_steps": 40, "total_steps": 405, "loss": 0.4461, "lr": 7.804878048780489e-05, "epoch": 0.49382716049382713, "percentage": 9.88, "elapsed_time": "0:34:04", "remaining_time": "5:10:55"}
+{"current_steps": 41, "total_steps": 405, "loss": 0.4379, "lr": 8e-05, "epoch": 0.5061728395061729, "percentage": 10.12, "elapsed_time": "0:34:50", "remaining_time": "5:09:15"}
+{"current_steps": 42, "total_steps": 405, "loss": 0.4348, "lr": 7.999851021266518e-05, "epoch": 0.5185185185185185, "percentage": 10.37, "elapsed_time": "0:35:39", "remaining_time": "5:08:14"}
+{"current_steps": 43, "total_steps": 405, "loss": 0.4332, "lr": 7.999404096163398e-05, "epoch": 0.5308641975308642, "percentage": 10.62, "elapsed_time": "0:36:26", "remaining_time": "5:06:47"}
+{"current_steps": 44, "total_steps": 405, "loss": 0.4303, "lr": 7.998659257981813e-05, "epoch": 0.5432098765432098, "percentage": 10.86, "elapsed_time": "0:37:10", "remaining_time": "5:05:02"}
+{"current_steps": 45, "total_steps": 405, "loss": 0.43, "lr": 7.997616562204282e-05, "epoch": 0.5555555555555556, "percentage": 11.11, "elapsed_time": "0:37:54", "remaining_time": "5:03:16"}
+{"current_steps": 46, "total_steps": 405, "loss": 0.434, "lr": 7.996276086500558e-05, "epoch": 0.5679012345679012, "percentage": 11.36, "elapsed_time": "0:38:41", "remaining_time": "5:01:59"}
+{"current_steps": 47, "total_steps": 405, "loss": 0.4248, "lr": 7.994637930721825e-05, "epoch": 0.5802469135802469, "percentage": 11.6, "elapsed_time": "0:39:27", "remaining_time": "5:00:33"}
+{"current_steps": 48, "total_steps": 405, "loss": 0.4312, "lr": 7.99270221689327e-05, "epoch": 0.5925925925925926, "percentage": 11.85, "elapsed_time": "0:40:15", "remaining_time": "4:59:23"}
+{"current_steps": 49, "total_steps": 405, "loss": 0.4167, "lr": 7.990469089204992e-05, "epoch": 0.6049382716049383, "percentage": 12.1, "elapsed_time": "0:41:02", "remaining_time": "4:58:13"}
+{"current_steps": 50, "total_steps": 405, "loss": 0.4199, "lr": 7.987938714001254e-05, "epoch": 0.6172839506172839, "percentage": 12.35, "elapsed_time": "0:41:53", "remaining_time": "4:57:28"}
+{"current_steps": 51, "total_steps": 405, "loss": 0.4287, "lr": 7.985111279768106e-05, "epoch": 0.6296296296296297, "percentage": 12.59, "elapsed_time": "0:42:42", "remaining_time": "4:56:27"}
+{"current_steps": 52, "total_steps": 405, "loss": 0.4176, "lr": 7.981986997119334e-05, "epoch": 0.6419753086419753, "percentage": 12.84, "elapsed_time": "0:43:29", "remaining_time": "4:55:15"}
+{"current_steps": 53, "total_steps": 405, "loss": 0.4175, "lr": 7.978566098780771e-05, "epoch": 0.654320987654321, "percentage": 13.09, "elapsed_time": "0:44:16", "remaining_time": "4:54:05"}
+{"current_steps": 54, "total_steps": 405, "loss": 0.4129, "lr": 7.974848839572971e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:45:05", "remaining_time": "4:53:03"}
+{"current_steps": 55, "total_steps": 405, "loss": 0.4218, "lr": 7.970835496392216e-05, "epoch": 0.6790123456790124, "percentage": 13.58, "elapsed_time": "0:45:51", "remaining_time": "4:51:49"}
+{"current_steps": 56, "total_steps": 405, "loss": 0.4091, "lr": 7.9665263681899e-05, "epoch": 0.691358024691358, "percentage": 13.83, "elapsed_time": "0:46:38", "remaining_time": "4:50:38"}
+{"current_steps": 57, "total_steps": 405, "loss": 0.418, "lr": 7.961921775950254e-05, "epoch": 0.7037037037037037, "percentage": 14.07, "elapsed_time": "0:47:24", "remaining_time": "4:49:23"}
+{"current_steps": 58, "total_steps": 405, "loss": 0.4196, "lr": 7.957022062666436e-05, "epoch": 0.7160493827160493, "percentage": 14.32, "elapsed_time": "0:48:10", "remaining_time": "4:48:16"}
+{"current_steps": 59, "total_steps": 405, "loss": 0.4187, "lr": 7.951827593314987e-05, "epoch": 0.7283950617283951, "percentage": 14.57, "elapsed_time": "0:48:58", "remaining_time": "4:47:12"}
+{"current_steps": 60, "total_steps": 405, "loss": 0.4198, "lr": 7.946338754828639e-05, "epoch": 0.7407407407407407, "percentage": 14.81, "elapsed_time": "0:49:46", "remaining_time": "4:46:10"}
+{"current_steps": 61, "total_steps": 405, "loss": 0.4158, "lr": 7.940555956067495e-05, "epoch": 0.7530864197530864, "percentage": 15.06, "elapsed_time": "0:50:34", "remaining_time": "4:45:14"}
+{"current_steps": 62, "total_steps": 405, "loss": 0.4217, "lr": 7.934479627788576e-05, "epoch": 0.7654320987654321, "percentage": 15.31, "elapsed_time": "0:51:27", "remaining_time": "4:44:41"}
+{"current_steps": 63, "total_steps": 405, "loss": 0.4133, "lr": 7.928110222613723e-05, "epoch": 0.7777777777777778, "percentage": 15.56, "elapsed_time": "0:52:35", "remaining_time": "4:45:28"}
+{"current_steps": 64, "total_steps": 405, "loss": 0.4129, "lr": 7.921448214995895e-05, "epoch": 0.7901234567901234, "percentage": 15.8, "elapsed_time": "0:53:21", "remaining_time": "4:44:19"}
+{"current_steps": 65, "total_steps": 405, "loss": 0.4188, "lr": 7.914494101183822e-05, "epoch": 0.8024691358024691, "percentage": 16.05, "elapsed_time": "0:54:08", "remaining_time": "4:43:12"}
+{"current_steps": 66, "total_steps": 405, "loss": 0.4211, "lr": 7.907248399185037e-05, "epoch": 0.8148148148148148, "percentage": 16.3, "elapsed_time": "0:54:53", "remaining_time": "4:41:57"}
+{"current_steps": 67, "total_steps": 405, "loss": 0.4121, "lr": 7.899711648727294e-05, "epoch": 0.8271604938271605, "percentage": 16.54, "elapsed_time": "0:55:41", "remaining_time": "4:40:55"}
+{"current_steps": 68, "total_steps": 405, "loss": 0.4047, "lr": 7.891884411218364e-05, "epoch": 0.8395061728395061, "percentage": 16.79, "elapsed_time": "0:56:26", "remaining_time": "4:39:40"}
+{"current_steps": 69, "total_steps": 405, "loss": 0.4066, "lr": 7.883767269704209e-05, "epoch": 0.8518518518518519, "percentage": 17.04, "elapsed_time": "0:57:13", "remaining_time": "4:38:38"}
+{"current_steps": 70, "total_steps": 405, "loss": 0.4081, "lr": 7.875360828825562e-05, "epoch": 0.8641975308641975, "percentage": 17.28, "elapsed_time": "0:58:00", "remaining_time": "4:37:37"}
+{"current_steps": 71, "total_steps": 405, "loss": 0.4125, "lr": 7.866665714772879e-05, "epoch": 0.8765432098765432, "percentage": 17.53, "elapsed_time": "0:58:54", "remaining_time": "4:37:06"}
+{"current_steps": 72, "total_steps": 405, "loss": 0.4045, "lr": 7.8576825752397e-05, "epoch": 0.8888888888888888, "percentage": 17.78, "elapsed_time": "0:59:43", "remaining_time": "4:36:15"}
+{"current_steps": 73, "total_steps": 405, "loss": 0.4099, "lr": 7.848412079374403e-05, "epoch": 0.9012345679012346, "percentage": 18.02, "elapsed_time": "1:00:31", "remaining_time": "4:35:17"}
+{"current_steps": 74, "total_steps": 405, "loss": 0.4093, "lr": 7.838854917730351e-05, "epoch": 0.9135802469135802, "percentage": 18.27, "elapsed_time": "1:01:18", "remaining_time": "4:34:13"}
+{"current_steps": 75, "total_steps": 405, "loss": 0.4095, "lr": 7.829011802214464e-05, "epoch": 0.9259259259259259, "percentage": 18.52, "elapsed_time": "1:02:06", "remaining_time": "4:33:16"}
+{"current_steps": 76, "total_steps": 405, "loss": 0.4177, "lr": 7.818883466034184e-05, "epoch": 0.9382716049382716, "percentage": 18.77, "elapsed_time": "1:03:03", "remaining_time": "4:33:00"}
+{"current_steps": 77, "total_steps": 405, "loss": 0.4081, "lr": 7.808470663642856e-05, "epoch": 0.9506172839506173, "percentage": 19.01, "elapsed_time": "1:04:14", "remaining_time": "4:33:38"}
+{"current_steps": 78, "total_steps": 405, "loss": 0.4037, "lr": 7.797774170683542e-05, "epoch": 0.9629629629629629, "percentage": 19.26, "elapsed_time": "1:05:38", "remaining_time": "4:35:10"}
+{"current_steps": 79, "total_steps": 405, "loss": 0.4012, "lr": 7.786794783931225e-05, "epoch": 0.9753086419753086, "percentage": 19.51, "elapsed_time": "1:06:51", "remaining_time": "4:35:53"}
+{"current_steps": 80, "total_steps": 405, "loss": 0.404, "lr": 7.775533321233471e-05, "epoch": 0.9876543209876543, "percentage": 19.75, "elapsed_time": "1:08:00", "remaining_time": "4:36:18"}
+{"current_steps": 81, "total_steps": 405, "loss": 0.404, "lr": 7.763990621449507e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:09:00", "remaining_time": "4:36:02"}
+{"current_steps": 82, "total_steps": 405, "loss": 0.3873, "lr": 7.752167544387728e-05, "epoch": 1.0123456790123457, "percentage": 20.25, "elapsed_time": "1:12:55", "remaining_time": "4:47:14"}
+{"current_steps": 83, "total_steps": 405, "loss": 0.3814, "lr": 7.740064970741661e-05, "epoch": 1.0246913580246915, "percentage": 20.49, "elapsed_time": "1:14:15", "remaining_time": "4:48:05"}
+{"current_steps": 84, "total_steps": 405, "loss": 0.3883, "lr": 7.727683802024347e-05, "epoch": 1.037037037037037, "percentage": 20.74, "elapsed_time": "1:15:28", "remaining_time": "4:48:26"}
+{"current_steps": 85, "total_steps": 405, "loss": 0.3821, "lr": 7.715024960501209e-05, "epoch": 1.0493827160493827, "percentage": 20.99, "elapsed_time": "1:16:36", "remaining_time": "4:48:24"}
+{"current_steps": 86, "total_steps": 405, "loss": 0.3883, "lr": 7.702089389121335e-05, "epoch": 1.0617283950617284, "percentage": 21.23, "elapsed_time": "1:17:34", "remaining_time": "4:47:46"}
+{"current_steps": 87, "total_steps": 405, "loss": 0.3844, "lr": 7.688878051447243e-05, "epoch": 1.074074074074074, "percentage": 21.48, "elapsed_time": "1:18:33", "remaining_time": "4:47:08"}
+{"current_steps": 88, "total_steps": 405, "loss": 0.3894, "lr": 7.675391931583109e-05, "epoch": 1.0864197530864197, "percentage": 21.73, "elapsed_time": "1:19:36", "remaining_time": "4:46:44"}
+{"current_steps": 89, "total_steps": 405, "loss": 0.3868, "lr": 7.661632034101466e-05, "epoch": 1.0987654320987654, "percentage": 21.98, "elapsed_time": "1:20:45", "remaining_time": "4:46:42"}
+{"current_steps": 90, "total_steps": 405, "loss": 0.3835, "lr": 7.64759938396836e-05, "epoch": 1.1111111111111112, "percentage": 22.22, "elapsed_time": "1:22:05", "remaining_time": "4:47:17"}
+{"current_steps": 91, "total_steps": 405, "loss": 0.3771, "lr": 7.633295026467016e-05, "epoch": 1.123456790123457, "percentage": 22.47, "elapsed_time": "1:23:18", "remaining_time": "4:47:29"}
+{"current_steps": 92, "total_steps": 405, "loss": 0.3808, "lr": 7.618720027119966e-05, "epoch": 1.1358024691358024, "percentage": 22.72, "elapsed_time": "1:24:17", "remaining_time": "4:46:48"}
+{"current_steps": 93, "total_steps": 405, "loss": 0.3812, "lr": 7.603875471609677e-05, "epoch": 1.1481481481481481, "percentage": 22.96, "elapsed_time": "1:25:17", "remaining_time": "4:46:08"}
+{"current_steps": 94, "total_steps": 405, "loss": 0.3839, "lr": 7.588762465697693e-05, "epoch": 1.1604938271604939, "percentage": 23.21, "elapsed_time": "1:26:19", "remaining_time": "4:45:35"}
+{"current_steps": 95, "total_steps": 405, "loss": 0.3857, "lr": 7.573382135142253e-05, "epoch": 1.1728395061728394, "percentage": 23.46, "elapsed_time": "1:27:20", "remaining_time": "4:44:59"}
+{"current_steps": 96, "total_steps": 405, "loss": 0.3737, "lr": 7.55773562561444e-05, "epoch": 1.1851851851851851, "percentage": 23.7, "elapsed_time": "1:28:24", "remaining_time": "4:44:34"}
+{"current_steps": 97, "total_steps": 405, "loss": 0.3816, "lr": 7.541824102612839e-05, "epoch": 1.1975308641975309, "percentage": 23.95, "elapsed_time": "1:29:43", "remaining_time": "4:44:54"}
+{"current_steps": 98, "total_steps": 405, "loss": 0.3788, "lr": 7.525648751376726e-05, "epoch": 1.2098765432098766, "percentage": 24.2, "elapsed_time": "1:30:54", "remaining_time": "4:44:46"}
+{"current_steps": 99, "total_steps": 405, "loss": 0.381, "lr": 7.509210776797768e-05, "epoch": 1.2222222222222223, "percentage": 24.44, "elapsed_time": "1:32:00", "remaining_time": "4:44:23"}
+{"current_steps": 100, "total_steps": 405, "loss": 0.379, "lr": 7.492511403330284e-05, "epoch": 1.2345679012345678, "percentage": 24.69, "elapsed_time": "1:33:00", "remaining_time": "4:43:39"}
+{"current_steps": 101, "total_steps": 405, "loss": 0.3795, "lr": 7.475551874900027e-05, "epoch": 1.2469135802469136, "percentage": 24.94, "elapsed_time": "1:33:57", "remaining_time": "4:42:47"}
+{"current_steps": 102, "total_steps": 405, "loss": 0.3811, "lr": 7.458333454811531e-05, "epoch": 1.2592592592592593, "percentage": 25.19, "elapsed_time": "1:34:50", "remaining_time": "4:41:42"}
+{"current_steps": 103, "total_steps": 405, "loss": 0.375, "lr": 7.440857425654004e-05, "epoch": 1.2716049382716048, "percentage": 25.43, "elapsed_time": "1:35:53", "remaining_time": "4:41:09"}
+{"current_steps": 104, "total_steps": 405, "loss": 0.3754, "lr": 7.42312508920579e-05, "epoch": 1.2839506172839505, "percentage": 25.68, "elapsed_time": "1:36:55", "remaining_time": "4:40:31"}
+{"current_steps": 105, "total_steps": 405, "loss": 0.3811, "lr": 7.405137766337406e-05, "epoch": 1.2962962962962963, "percentage": 25.93, "elapsed_time": "1:37:54", "remaining_time": "4:39:44"}
+{"current_steps": 106, "total_steps": 405, "loss": 0.3805, "lr": 7.386896796913137e-05, "epoch": 1.308641975308642, "percentage": 26.17, "elapsed_time": "1:38:53", "remaining_time": "4:38:56"}
+{"current_steps": 107, "total_steps": 405, "loss": 0.3785, "lr": 7.368403539691247e-05, "epoch": 1.3209876543209877, "percentage": 26.42, "elapsed_time": "1:39:56", "remaining_time": "4:38:19"}
+{"current_steps": 108, "total_steps": 405, "loss": 0.3751, "lr": 7.349659372222755e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "1:40:52", "remaining_time": "4:37:25"}
+{"current_steps": 109, "total_steps": 405, "loss": 0.3815, "lr": 7.330665690748825e-05, "epoch": 1.345679012345679, "percentage": 26.91, "elapsed_time": "1:41:58", "remaining_time": "4:36:55"}
+{"current_steps": 110, "total_steps": 405, "loss": 0.3779, "lr": 7.311423910096764e-05, "epoch": 1.3580246913580247, "percentage": 27.16, "elapsed_time": "1:43:06", "remaining_time": "4:36:30"}
+{"current_steps": 111, "total_steps": 405, "loss": 0.3738, "lr": 7.291935463574626e-05, "epoch": 1.3703703703703702, "percentage": 27.41, "elapsed_time": "1:44:20", "remaining_time": "4:36:20"}
+{"current_steps": 112, "total_steps": 405, "loss": 0.3764, "lr": 7.272201802864452e-05, "epoch": 1.382716049382716, "percentage": 27.65, "elapsed_time": "1:45:30", "remaining_time": "4:36:01"}
+{"current_steps": 113, "total_steps": 405, "loss": 0.3777, "lr": 7.25222439791413e-05, "epoch": 1.3950617283950617, "percentage": 27.9, "elapsed_time": "1:46:36", "remaining_time": "4:35:29"}
+{"current_steps": 114, "total_steps": 405, "loss": 0.3857, "lr": 7.232004736827907e-05, "epoch": 1.4074074074074074, "percentage": 28.15, "elapsed_time": "1:47:32", "remaining_time": "4:34:31"}
+{"current_steps": 115, "total_steps": 405, "loss": 0.3786, "lr": 7.21154432575553e-05, "epoch": 1.4197530864197532, "percentage": 28.4, "elapsed_time": "1:48:35", "remaining_time": "4:33:50"}
+{"current_steps": 116, "total_steps": 405, "loss": 0.3796, "lr": 7.190844688780065e-05, "epoch": 1.4320987654320987, "percentage": 28.64, "elapsed_time": "1:49:35", "remaining_time": "4:33:02"}
+{"current_steps": 117, "total_steps": 405, "loss": 0.3872, "lr": 7.169907367804363e-05, "epoch": 1.4444444444444444, "percentage": 28.89, "elapsed_time": "1:50:37", "remaining_time": "4:32:17"}
+{"current_steps": 118, "total_steps": 405, "loss": 0.3877, "lr": 7.148733922436201e-05, "epoch": 1.4567901234567902, "percentage": 29.14, "elapsed_time": "1:51:46", "remaining_time": "4:31:51"}
+{"current_steps": 119, "total_steps": 405, "loss": 0.3841, "lr": 7.12732592987212e-05, "epoch": 1.4691358024691357, "percentage": 29.38, "elapsed_time": "1:52:52", "remaining_time": "4:31:17"}
+{"current_steps": 120, "total_steps": 405, "loss": 0.3774, "lr": 7.105684984779928e-05, "epoch": 1.4814814814814814, "percentage": 29.63, "elapsed_time": "1:54:04", "remaining_time": "4:30:55"}
+{"current_steps": 121, "total_steps": 405, "loss": 0.3833, "lr": 7.083812699179919e-05, "epoch": 1.4938271604938271, "percentage": 29.88, "elapsed_time": "1:55:13", "remaining_time": "4:30:25"}
+{"current_steps": 122, "total_steps": 405, "loss": 0.384, "lr": 7.061710702324799e-05, "epoch": 1.5061728395061729, "percentage": 30.12, "elapsed_time": "1:56:17", "remaining_time": "4:29:46"}
+{"current_steps": 123, "total_steps": 405, "loss": 0.3798, "lr": 7.039380640578316e-05, "epoch": 1.5185185185185186, "percentage": 30.37, "elapsed_time": "1:57:21", "remaining_time": "4:29:04"}
+{"current_steps": 124, "total_steps": 405, "loss": 0.3815, "lr": 7.016824177292629e-05, "epoch": 1.5308641975308643, "percentage": 30.62, "elapsed_time": "1:58:21", "remaining_time": "4:28:12"}
+{"current_steps": 125, "total_steps": 405, "loss": 0.3751, "lr": 6.994042992684406e-05, "epoch": 1.5432098765432098, "percentage": 30.86, "elapsed_time": "1:59:22", "remaining_time": "4:27:24"}
+{"current_steps": 126, "total_steps": 405, "loss": 0.3822, "lr": 6.971038783709658e-05, "epoch": 1.5555555555555556, "percentage": 31.11, "elapsed_time": "2:00:29", "remaining_time": "4:26:47"}
+{"current_steps": 127, "total_steps": 405, "loss": 0.3909, "lr": 6.947813263937347e-05, "epoch": 1.567901234567901, "percentage": 31.36, "elapsed_time": "2:01:39", "remaining_time": "4:26:18"}
+{"current_steps": 128, "total_steps": 405, "loss": 0.3776, "lr": 6.924368163421733e-05, "epoch": 1.5802469135802468, "percentage": 31.6, "elapsed_time": "2:02:49", "remaining_time": "4:25:48"}
+{"current_steps": 129, "total_steps": 405, "loss": 0.3818, "lr": 6.900705228573507e-05, "epoch": 1.5925925925925926, "percentage": 31.85, "elapsed_time": "2:03:50", "remaining_time": "4:24:56"}
+{"current_steps": 130, "total_steps": 405, "loss": 0.3814, "lr": 6.876826222029699e-05, "epoch": 1.6049382716049383, "percentage": 32.1, "elapsed_time": "2:04:48", "remaining_time": "4:24:01"}
+{"current_steps": 131, "total_steps": 405, "loss": 0.3773, "lr": 6.852732922522385e-05, "epoch": 1.617283950617284, "percentage": 32.35, "elapsed_time": "2:05:50", "remaining_time": "4:23:13"}
+{"current_steps": 132, "total_steps": 405, "loss": 0.3819, "lr": 6.828427124746191e-05, "epoch": 1.6296296296296298, "percentage": 32.59, "elapsed_time": "2:06:50", "remaining_time": "4:22:18"}
+{"current_steps": 133, "total_steps": 405, "loss": 0.3785, "lr": 6.803910639224598e-05, "epoch": 1.6419753086419753, "percentage": 32.84, "elapsed_time": "2:07:50", "remaining_time": "4:21:27"}
+{"current_steps": 134, "total_steps": 405, "loss": 0.3794, "lr": 6.77918529217509e-05, "epoch": 1.654320987654321, "percentage": 33.09, "elapsed_time": "2:08:49", "remaining_time": "4:20:33"}
+{"current_steps": 135, "total_steps": 405, "loss": 0.3703, "lr": 6.754252925373109e-05, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "2:09:46", "remaining_time": "4:19:33"}
+{"current_steps": 136, "total_steps": 405, "loss": 0.3719, "lr": 6.729115396014871e-05, "epoch": 1.6790123456790123, "percentage": 33.58, "elapsed_time": "2:10:44", "remaining_time": "4:18:36"}
+{"current_steps": 137, "total_steps": 405, "loss": 0.3775, "lr": 6.703774576579018e-05, "epoch": 1.691358024691358, "percentage": 33.83, "elapsed_time": "2:11:37", "remaining_time": "4:17:28"}
+{"current_steps": 138, "total_steps": 405, "loss": 0.3776, "lr": 6.678232354687144e-05, "epoch": 1.7037037037037037, "percentage": 34.07, "elapsed_time": "2:12:25", "remaining_time": "4:16:13"}
+{"current_steps": 139, "total_steps": 405, "loss": 0.372, "lr": 6.652490632963182e-05, "epoch": 1.7160493827160495, "percentage": 34.32, "elapsed_time": "2:13:11", "remaining_time": "4:14:52"}
+{"current_steps": 140, "total_steps": 405, "loss": 0.3731, "lr": 6.626551328891681e-05, "epoch": 1.7283950617283952, "percentage": 34.57, "elapsed_time": "2:13:57", "remaining_time": "4:13:33"}
+{"current_steps": 141, "total_steps": 405, "loss": 0.3754, "lr": 6.600416374674978e-05, "epoch": 1.7407407407407407, "percentage": 34.81, "elapsed_time": "2:14:43", "remaining_time": "4:12:15"}
+{"current_steps": 142, "total_steps": 405, "loss": 0.3753, "lr": 6.57408771708926e-05, "epoch": 1.7530864197530864, "percentage": 35.06, "elapsed_time": "2:15:30", "remaining_time": "4:10:59"}
+{"current_steps": 143, "total_steps": 405, "loss": 0.3729, "lr": 6.547567317339557e-05, "epoch": 1.765432098765432, "percentage": 35.31, "elapsed_time": "2:16:16", "remaining_time": "4:09:40"}
+{"current_steps": 144, "total_steps": 405, "loss": 0.3788, "lr": 6.520857150913655e-05, "epoch": 1.7777777777777777, "percentage": 35.56, "elapsed_time": "2:17:03", "remaining_time": "4:08:25"}
+{"current_steps": 145, "total_steps": 405, "loss": 0.3727, "lr": 6.493959207434934e-05, "epoch": 1.7901234567901234, "percentage": 35.8, "elapsed_time": "2:17:51", "remaining_time": "4:07:12"}
+{"current_steps": 146, "total_steps": 405, "loss": 0.376, "lr": 6.466875490514173e-05, "epoch": 1.8024691358024691, "percentage": 36.05, "elapsed_time": "2:18:41", "remaining_time": "4:06:01"}
+{"current_steps": 147, "total_steps": 405, "loss": 0.3696, "lr": 6.439608017600292e-05, "epoch": 1.8148148148148149, "percentage": 36.3, "elapsed_time": "2:19:29", "remaining_time": "4:04:49"}
+{"current_steps": 148, "total_steps": 405, "loss": 0.3707, "lr": 6.412158819830082e-05, "epoch": 1.8271604938271606, "percentage": 36.54, "elapsed_time": "2:20:16", "remaining_time": "4:03:35"}
+{"current_steps": 149, "total_steps": 405, "loss": 0.3762, "lr": 6.384529941876902e-05, "epoch": 1.8395061728395061, "percentage": 36.79, "elapsed_time": "2:21:02", "remaining_time": "4:02:19"}
+{"current_steps": 150, "total_steps": 405, "loss": 0.3676, "lr": 6.356723441798375e-05, "epoch": 1.8518518518518519, "percentage": 37.04, "elapsed_time": "2:21:48", "remaining_time": "4:01:04"}
+{"current_steps": 151, "total_steps": 405, "loss": 0.3687, "lr": 6.328741390883084e-05, "epoch": 1.8641975308641974, "percentage": 37.28, "elapsed_time": "2:22:36", "remaining_time": "3:59:53"}
+{"current_steps": 152, "total_steps": 405, "loss": 0.3752, "lr": 6.300585873496279e-05, "epoch": 1.876543209876543, "percentage": 37.53, "elapsed_time": "2:23:22", "remaining_time": "3:58:38"}
+{"current_steps": 153, "total_steps": 405, "loss": 0.3683, "lr": 6.272258986924624e-05, "epoch": 1.8888888888888888, "percentage": 37.78, "elapsed_time": "2:24:09", "remaining_time": "3:57:25"}
+{"current_steps": 154, "total_steps": 405, "loss": 0.3734, "lr": 6.243762841219958e-05, "epoch": 1.9012345679012346, "percentage": 38.02, "elapsed_time": "2:24:55", "remaining_time": "3:56:13"}
+{"current_steps": 155, "total_steps": 405, "loss": 0.3763, "lr": 6.215099559042132e-05, "epoch": 1.9135802469135803, "percentage": 38.27, "elapsed_time": "2:25:45", "remaining_time": "3:55:05"}
+{"current_steps": 156, "total_steps": 405, "loss": 0.3762, "lr": 6.186271275500885e-05, "epoch": 1.925925925925926, "percentage": 38.52, "elapsed_time": "2:26:31", "remaining_time": "3:53:52"}
+{"current_steps": 157, "total_steps": 405, "loss": 0.3802, "lr": 6.157280137996797e-05, "epoch": 1.9382716049382716, "percentage": 38.77, "elapsed_time": "2:27:36", "remaining_time": "3:53:10"}
+{"current_steps": 158, "total_steps": 405, "loss": 0.3727, "lr": 6.128128306061347e-05, "epoch": 1.9506172839506173, "percentage": 39.01, "elapsed_time": "2:28:22", "remaining_time": "3:51:57"}
+{"current_steps": 159, "total_steps": 405, "loss": 0.375, "lr": 6.098817951196032e-05, "epoch": 1.9629629629629628, "percentage": 39.26, "elapsed_time": "2:29:09", "remaining_time": "3:50:45"}
+{"current_steps": 160, "total_steps": 405, "loss": 0.3725, "lr": 6.0693512567106275e-05, "epoch": 1.9753086419753085, "percentage": 39.51, "elapsed_time": "2:29:55", "remaining_time": "3:49:34"}
+{"current_steps": 161, "total_steps": 405, "loss": 0.3732, "lr": 6.0397304175605444e-05, "epoch": 1.9876543209876543, "percentage": 39.75, "elapsed_time": "2:30:43", "remaining_time": "3:48:26"}
+{"current_steps": 162, "total_steps": 405, "loss": 0.3656, "lr": 6.009957640183333e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:31:29", "remaining_time": "3:47:14"}
+{"current_steps": 163, "total_steps": 405, "loss": 0.3415, "lr": 5.980035142334326e-05, "epoch": 2.0123456790123457, "percentage": 40.25, "elapsed_time": "2:34:38", "remaining_time": "3:49:34"}
+{"current_steps": 164, "total_steps": 405, "loss": 0.3457, "lr": 5.94996515292144e-05, "epoch": 2.0246913580246915, "percentage": 40.49, "elapsed_time": "2:35:26", "remaining_time": "3:48:25"}
+{"current_steps": 165, "total_steps": 405, "loss": 0.3439, "lr": 5.919749911839146e-05, "epoch": 2.037037037037037, "percentage": 40.74, "elapsed_time": "2:36:12", "remaining_time": "3:47:12"}
+{"current_steps": 166, "total_steps": 405, "loss": 0.3473, "lr": 5.8893916698016154e-05, "epoch": 2.049382716049383, "percentage": 40.99, "elapsed_time": "2:37:01", "remaining_time": "3:46:04"}
+{"current_steps": 167, "total_steps": 405, "loss": 0.3447, "lr": 5.858892688175075e-05, "epoch": 2.0617283950617282, "percentage": 41.23, "elapsed_time": "2:37:47", "remaining_time": "3:44:51"}
+{"current_steps": 168, "total_steps": 405, "loss": 0.3512, "lr": 5.828255238809352e-05, "epoch": 2.074074074074074, "percentage": 41.48, "elapsed_time": "2:38:32", "remaining_time": "3:43:39"}
+{"current_steps": 169, "total_steps": 405, "loss": 0.3508, "lr": 5.797481603868646e-05, "epoch": 2.0864197530864197, "percentage": 41.73, "elapsed_time": "2:39:18", "remaining_time": "3:42:27"}
+{"current_steps": 170, "total_steps": 405, "loss": 0.3469, "lr": 5.766574075661538e-05, "epoch": 2.0987654320987654, "percentage": 41.98, "elapsed_time": "2:40:05", "remaining_time": "3:41:17"}
+{"current_steps": 171, "total_steps": 405, "loss": 0.3422, "lr": 5.735534956470233e-05, "epoch": 2.111111111111111, "percentage": 42.22, "elapsed_time": "2:40:51", "remaining_time": "3:40:07"}
+{"current_steps": 172, "total_steps": 405, "loss": 0.345, "lr": 5.7043665583790627e-05, "epoch": 2.123456790123457, "percentage": 42.47, "elapsed_time": "2:41:38", "remaining_time": "3:38:57"}
+{"current_steps": 173, "total_steps": 405, "loss": 0.341, "lr": 5.673071203102261e-05, "epoch": 2.1358024691358026, "percentage": 42.72, "elapsed_time": "2:42:25", "remaining_time": "3:37:48"}
+{"current_steps": 174, "total_steps": 405, "loss": 0.3463, "lr": 5.641651221811028e-05, "epoch": 2.148148148148148, "percentage": 42.96, "elapsed_time": "2:43:12", "remaining_time": "3:36:40"}
+{"current_steps": 175, "total_steps": 405, "loss": 0.3417, "lr": 5.6101089549598704e-05, "epoch": 2.1604938271604937, "percentage": 43.21, "elapsed_time": "2:44:02", "remaining_time": "3:35:35"}
+{"current_steps": 176, "total_steps": 405, "loss": 0.3414, "lr": 5.578446752112273e-05, "epoch": 2.1728395061728394, "percentage": 43.46, "elapsed_time": "2:44:49", "remaining_time": "3:34:27"}
+{"current_steps": 177, "total_steps": 405, "loss": 0.3431, "lr": 5.546666971765675e-05, "epoch": 2.185185185185185, "percentage": 43.7, "elapsed_time": "2:45:35", "remaining_time": "3:33:18"}
+{"current_steps": 178, "total_steps": 405, "loss": 0.3428, "lr": 5.5147719811757914e-05, "epoch": 2.197530864197531, "percentage": 43.95, "elapsed_time": "2:46:21", "remaining_time": "3:32:09"}
+{"current_steps": 179, "total_steps": 405, "loss": 0.3442, "lr": 5.4827641561802716e-05, "epoch": 2.2098765432098766, "percentage": 44.2, "elapsed_time": "2:47:08", "remaining_time": "3:31:01"}
+{"current_steps": 180, "total_steps": 405, "loss": 0.3489, "lr": 5.4506458810217286e-05, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "2:47:55", "remaining_time": "3:29:54"}
+{"current_steps": 181, "total_steps": 405, "loss": 0.3395, "lr": 5.4184195481701425e-05, "epoch": 2.234567901234568, "percentage": 44.69, "elapsed_time": "2:48:42", "remaining_time": "3:28:46"}
+{"current_steps": 182, "total_steps": 405, "loss": 0.341, "lr": 5.38608755814464e-05, "epoch": 2.246913580246914, "percentage": 44.94, "elapsed_time": "2:49:28", "remaining_time": "3:27:39"}
+{"current_steps": 183, "total_steps": 405, "loss": 0.3437, "lr": 5.353652319334682e-05, "epoch": 2.259259259259259, "percentage": 45.19, "elapsed_time": "2:50:16", "remaining_time": "3:26:34"}
+{"current_steps": 184, "total_steps": 405, "loss": 0.3495, "lr": 5.321116247820669e-05, "epoch": 2.271604938271605, "percentage": 45.43, "elapsed_time": "2:51:05", "remaining_time": "3:25:30"}
+{"current_steps": 185, "total_steps": 405, "loss": 0.3408, "lr": 5.288481767193963e-05, "epoch": 2.2839506172839505, "percentage": 45.68, "elapsed_time": "2:51:53", "remaining_time": "3:24:24"}
+{"current_steps": 186, "total_steps": 405, "loss": 0.3506, "lr": 5.2557513083763605e-05, "epoch": 2.2962962962962963, "percentage": 45.93, "elapsed_time": "2:52:40", "remaining_time": "3:23:19"}
+{"current_steps": 187, "total_steps": 405, "loss": 0.3369, "lr": 5.2229273094390124e-05, "epoch": 2.308641975308642, "percentage": 46.17, "elapsed_time": "2:53:26", "remaining_time": "3:22:11"}
+{"current_steps": 188, "total_steps": 405, "loss": 0.3377, "lr": 5.190012215420812e-05, "epoch": 2.3209876543209877, "percentage": 46.42, "elapsed_time": "2:54:14", "remaining_time": "3:21:06"}
+{"current_steps": 189, "total_steps": 405, "loss": 0.3426, "lr": 5.1570084781462716e-05, "epoch": 2.3333333333333335, "percentage": 46.67, "elapsed_time": "2:55:01", "remaining_time": "3:20:01"}
+{"current_steps": 190, "total_steps": 405, "loss": 0.3409, "lr": 5.123918556042878e-05, "epoch": 2.3456790123456788, "percentage": 46.91, "elapsed_time": "2:55:47", "remaining_time": "3:18:55"}
+{"current_steps": 191, "total_steps": 405, "loss": 0.3476, "lr": 5.0907449139579755e-05, "epoch": 2.3580246913580245, "percentage": 47.16, "elapsed_time": "2:56:34", "remaining_time": "3:17:49"}
+{"current_steps": 192, "total_steps": 405, "loss": 0.3469, "lr": 5.057490022975156e-05, "epoch": 2.3703703703703702, "percentage": 47.41, "elapsed_time": "2:57:21", "remaining_time": "3:16:45"}
+{"current_steps": 193, "total_steps": 405, "loss": 0.3482, "lr": 5.024156360230189e-05, "epoch": 2.382716049382716, "percentage": 47.65, "elapsed_time": "2:58:09", "remaining_time": "3:15:41"}
+{"current_steps": 194, "total_steps": 405, "loss": 0.3449, "lr": 4.9907464087265045e-05, "epoch": 2.3950617283950617, "percentage": 47.9, "elapsed_time": "2:58:56", "remaining_time": "3:14:36"}
+{"current_steps": 195, "total_steps": 405, "loss": 0.3508, "lr": 4.9572626571502316e-05, "epoch": 2.4074074074074074, "percentage": 48.15, "elapsed_time": "2:59:43", "remaining_time": "3:13:33"}
+{"current_steps": 196, "total_steps": 405, "loss": 0.3421, "lr": 4.9237075996848235e-05, "epoch": 2.419753086419753, "percentage": 48.4, "elapsed_time": "3:00:32", "remaining_time": "3:12:31"}
+{"current_steps": 197, "total_steps": 405, "loss": 0.3432, "lr": 4.890083735825258e-05, "epoch": 2.432098765432099, "percentage": 48.64, "elapsed_time": "3:01:22", "remaining_time": "3:11:30"}
+{"current_steps": 198, "total_steps": 405, "loss": 0.3421, "lr": 4.8563935701918646e-05, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "3:02:09", "remaining_time": "3:10:26"}
+{"current_steps": 199, "total_steps": 405, "loss": 0.344, "lr": 4.8226396123437466e-05, "epoch": 2.45679012345679, "percentage": 49.14, "elapsed_time": "3:02:55", "remaining_time": "3:09:21"}
+{"current_steps": 200, "total_steps": 405, "loss": 0.3364, "lr": 4.788824376591849e-05, "epoch": 2.4691358024691357, "percentage": 49.38, "elapsed_time": "3:03:41", "remaining_time": "3:08:17"}
+{"current_steps": 201, "total_steps": 405, "loss": 0.3497, "lr": 4.754950381811667e-05, "epoch": 2.4814814814814814, "percentage": 49.63, "elapsed_time": "3:04:28", "remaining_time": "3:07:14"}
+{"current_steps": 202, "total_steps": 405, "loss": 0.3415, "lr": 4.721020151255624e-05, "epoch": 2.493827160493827, "percentage": 49.88, "elapsed_time": "3:05:16", "remaining_time": "3:06:11"}
+{"current_steps": 203, "total_steps": 405, "loss": 0.3377, "lr": 4.6870362123651056e-05, "epoch": 2.506172839506173, "percentage": 50.12, "elapsed_time": "3:06:04", "remaining_time": "3:05:09"}
+{"current_steps": 204, "total_steps": 405, "loss": 0.3357, "lr": 4.6530010965821984e-05, "epoch": 2.5185185185185186, "percentage": 50.37, "elapsed_time": "3:06:51", "remaining_time": "3:04:06"}
+{"current_steps": 205, "total_steps": 405, "loss": 0.3391, "lr": 4.618917339161125e-05, "epoch": 2.5308641975308643, "percentage": 50.62, "elapsed_time": "3:07:39", "remaining_time": "3:03:04"}
+{"current_steps": 206, "total_steps": 405, "loss": 0.3422, "lr": 4.584787478979394e-05, "epoch": 2.5432098765432096, "percentage": 50.86, "elapsed_time": "3:08:30", "remaining_time": "3:02:06"}
+{"current_steps": 207, "total_steps": 405, "loss": 0.3361, "lr": 4.550614058348674e-05, "epoch": 2.5555555555555554, "percentage": 51.11, "elapsed_time": "3:09:19", "remaining_time": "3:01:05"}
+{"current_steps": 208, "total_steps": 405, "loss": 0.3428, "lr": 4.516399622825428e-05, "epoch": 2.567901234567901, "percentage": 51.36, "elapsed_time": "3:10:05", "remaining_time": "3:00:02"}
+{"current_steps": 209, "total_steps": 405, "loss": 0.3406, "lr": 4.4821467210212924e-05, "epoch": 2.580246913580247, "percentage": 51.6, "elapsed_time": "3:10:52", "remaining_time": "2:58:59"}
+{"current_steps": 210, "total_steps": 405, "loss": 0.3402, "lr": 4.4478579044132314e-05, "epoch": 2.5925925925925926, "percentage": 51.85, "elapsed_time": "3:11:38", "remaining_time": "2:57:57"}
+{"current_steps": 211, "total_steps": 405, "loss": 0.3485, "lr": 4.41353572715348e-05, "epoch": 2.6049382716049383, "percentage": 52.1, "elapsed_time": "3:12:26", "remaining_time": "2:56:56"}
+{"current_steps": 212, "total_steps": 405, "loss": 0.3417, "lr": 4.379182745879289e-05, "epoch": 2.617283950617284, "percentage": 52.35, "elapsed_time": "3:13:13", "remaining_time": "2:55:54"}
+{"current_steps": 213, "total_steps": 405, "loss": 0.3396, "lr": 4.344801519522478e-05, "epoch": 2.6296296296296298, "percentage": 52.59, "elapsed_time": "3:14:00", "remaining_time": "2:54:52"}
+{"current_steps": 214, "total_steps": 405, "loss": 0.351, "lr": 4.310394609118826e-05, "epoch": 2.6419753086419755, "percentage": 52.84, "elapsed_time": "3:14:47", "remaining_time": "2:53:51"}
+{"current_steps": 215, "total_steps": 405, "loss": 0.3478, "lr": 4.2759645776172996e-05, "epoch": 2.6543209876543212, "percentage": 53.09, "elapsed_time": "3:15:36", "remaining_time": "2:52:51"}
+{"current_steps": 216, "total_steps": 405, "loss": 0.3429, "lr": 4.241513989689145e-05, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "3:16:26", "remaining_time": "2:51:52"}
+{"current_steps": 217, "total_steps": 405, "loss": 0.3392, "lr": 4.2070454115368385e-05, "epoch": 2.6790123456790123, "percentage": 53.58, "elapsed_time": "3:17:13", "remaining_time": "2:50:51"}
+{"current_steps": 218, "total_steps": 405, "loss": 0.342, "lr": 4.1725614107029387e-05, "epoch": 2.691358024691358, "percentage": 53.83, "elapsed_time": "3:18:00", "remaining_time": "2:49:51"}
+{"current_steps": 219, "total_steps": 405, "loss": 0.3401, "lr": 4.138064555878833e-05, "epoch": 2.7037037037037037, "percentage": 54.07, "elapsed_time": "3:18:47", "remaining_time": "2:48:49"}
+{"current_steps": 220, "total_steps": 405, "loss": 0.3432, "lr": 4.1035574167133905e-05, "epoch": 2.7160493827160495, "percentage": 54.32, "elapsed_time": "3:19:35", "remaining_time": "2:47:49"}
+{"current_steps": 221, "total_steps": 405, "loss": 0.3482, "lr": 4.069042563621555e-05, "epoch": 2.728395061728395, "percentage": 54.57, "elapsed_time": "3:20:22", "remaining_time": "2:46:49"}
+{"current_steps": 222, "total_steps": 405, "loss": 0.348, "lr": 4.034522567592876e-05, "epoch": 2.7407407407407405, "percentage": 54.81, "elapsed_time": "3:21:09", "remaining_time": "2:45:48"}
+{"current_steps": 223, "total_steps": 405, "loss": 0.3394, "lr": 4e-05, "epoch": 2.753086419753086, "percentage": 55.06, "elapsed_time": "3:21:56", "remaining_time": "2:44:48"}
+{"current_steps": 224, "total_steps": 405, "loss": 0.3445, "lr": 3.965477432407125e-05, "epoch": 2.765432098765432, "percentage": 55.31, "elapsed_time": "3:22:45", "remaining_time": "2:43:49"}
+{"current_steps": 225, "total_steps": 405, "loss": 0.3397, "lr": 3.9309574363784465e-05, "epoch": 2.7777777777777777, "percentage": 55.56, "elapsed_time": "3:23:34", "remaining_time": "2:42:51"}
+{"current_steps": 226, "total_steps": 405, "loss": 0.3406, "lr": 3.8964425832866115e-05, "epoch": 2.7901234567901234, "percentage": 55.8, "elapsed_time": "3:24:20", "remaining_time": "2:41:51"}
+{"current_steps": 227, "total_steps": 405, "loss": 0.3449, "lr": 3.861935444121169e-05, "epoch": 2.802469135802469, "percentage": 56.05, "elapsed_time": "3:25:10", "remaining_time": "2:40:53"}
+{"current_steps": 228, "total_steps": 405, "loss": 0.342, "lr": 3.827438589297062e-05, "epoch": 2.814814814814815, "percentage": 56.3, "elapsed_time": "3:25:56", "remaining_time": "2:39:52"}
+{"current_steps": 229, "total_steps": 405, "loss": 0.3361, "lr": 3.792954588463162e-05, "epoch": 2.8271604938271606, "percentage": 56.54, "elapsed_time": "3:26:43", "remaining_time": "2:38:52"}
+{"current_steps": 230, "total_steps": 405, "loss": 0.3452, "lr": 3.758486010310856e-05, "epoch": 2.8395061728395063, "percentage": 56.79, "elapsed_time": "3:27:30", "remaining_time": "2:37:53"}
+{"current_steps": 231, "total_steps": 405, "loss": 0.3366, "lr": 3.7240354223827004e-05, "epoch": 2.851851851851852, "percentage": 57.04, "elapsed_time": "3:28:15", "remaining_time": "2:36:52"}
+{"current_steps": 232, "total_steps": 405, "loss": 0.3421, "lr": 3.6896053908811755e-05, "epoch": 2.8641975308641974, "percentage": 57.28, "elapsed_time": "3:29:01", "remaining_time": "2:35:52"}
+{"current_steps": 233, "total_steps": 405, "loss": 0.3385, "lr": 3.655198480477523e-05, "epoch": 2.876543209876543, "percentage": 57.53, "elapsed_time": "3:29:48", "remaining_time": "2:34:52"}
+{"current_steps": 234, "total_steps": 405, "loss": 0.3439, "lr": 3.6208172541207114e-05, "epoch": 2.888888888888889, "percentage": 57.78, "elapsed_time": "3:30:37", "remaining_time": "2:33:55"}
+{"current_steps": 235, "total_steps": 405, "loss": 0.344, "lr": 3.5864642728465205e-05, "epoch": 2.9012345679012346, "percentage": 58.02, "elapsed_time": "3:31:24", "remaining_time": "2:32:56"}
+{"current_steps": 236, "total_steps": 405, "loss": 0.3372, "lr": 3.552142095586769e-05, "epoch": 2.9135802469135803, "percentage": 58.27, "elapsed_time": "3:32:11", "remaining_time": "2:31:57"}
+{"current_steps": 237, "total_steps": 405, "loss": 0.3442, "lr": 3.517853278978708e-05, "epoch": 2.925925925925926, "percentage": 58.52, "elapsed_time": "3:32:59", "remaining_time": "2:30:59"}
+{"current_steps": 238, "total_steps": 405, "loss": 0.347, "lr": 3.4836003771745736e-05, "epoch": 2.9382716049382713, "percentage": 58.77, "elapsed_time": "3:33:49", "remaining_time": "2:30:02"}
+{"current_steps": 239, "total_steps": 405, "loss": 0.344, "lr": 3.449385941651328e-05, "epoch": 2.950617283950617, "percentage": 59.01, "elapsed_time": "3:34:36", "remaining_time": "2:29:03"}
+{"current_steps": 240, "total_steps": 405, "loss": 0.3421, "lr": 3.415212521020609e-05, "epoch": 2.962962962962963, "percentage": 59.26, "elapsed_time": "3:35:22", "remaining_time": "2:28:04"}
+{"current_steps": 241, "total_steps": 405, "loss": 0.341, "lr": 3.381082660838875e-05, "epoch": 2.9753086419753085, "percentage": 59.51, "elapsed_time": "3:36:08", "remaining_time": "2:27:05"}
+{"current_steps": 242, "total_steps": 405, "loss": 0.3379, "lr": 3.346998903417803e-05, "epoch": 2.9876543209876543, "percentage": 59.75, "elapsed_time": "3:36:54", "remaining_time": "2:26:06"}
+{"current_steps": 243, "total_steps": 405, "loss": 0.3255, "lr": 3.312963787634896e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:37:42", "remaining_time": "2:25:08"}
+{"current_steps": 244, "total_steps": 405, "loss": 0.3131, "lr": 3.2789798487443775e-05, "epoch": 3.0123456790123457, "percentage": 60.25, "elapsed_time": "3:40:57", "remaining_time": "2:25:47"}
+{"current_steps": 245, "total_steps": 405, "loss": 0.3174, "lr": 3.245049618188334e-05, "epoch": 3.0246913580246915, "percentage": 60.49, "elapsed_time": "3:41:46", "remaining_time": "2:24:49"}
+{"current_steps": 246, "total_steps": 405, "loss": 0.3156, "lr": 3.2111756234081525e-05, "epoch": 3.037037037037037, "percentage": 60.74, "elapsed_time": "3:42:34", "remaining_time": "2:23:51"}
+{"current_steps": 247, "total_steps": 405, "loss": 0.3165, "lr": 3.177360387656254e-05, "epoch": 3.049382716049383, "percentage": 60.99, "elapsed_time": "3:43:20", "remaining_time": "2:22:52"}
+{"current_steps": 248, "total_steps": 405, "loss": 0.3166, "lr": 3.143606429808136e-05, "epoch": 3.0617283950617282, "percentage": 61.23, "elapsed_time": "3:44:06", "remaining_time": "2:21:52"}
+{"current_steps": 249, "total_steps": 405, "loss": 0.3176, "lr": 3.109916264174743e-05, "epoch": 3.074074074074074, "percentage": 61.48, "elapsed_time": "3:44:54", "remaining_time": "2:20:54"}
+{"current_steps": 250, "total_steps": 405, "loss": 0.3194, "lr": 3.076292400315179e-05, "epoch": 3.0864197530864197, "percentage": 61.73, "elapsed_time": "3:45:40", "remaining_time": "2:19:54"}
+{"current_steps": 251, "total_steps": 405, "loss": 0.3153, "lr": 3.0427373428497704e-05, "epoch": 3.0987654320987654, "percentage": 61.98, "elapsed_time": "3:46:27", "remaining_time": "2:18:56"}
+{"current_steps": 252, "total_steps": 405, "loss": 0.3137, "lr": 3.0092535912734965e-05, "epoch": 3.111111111111111, "percentage": 62.22, "elapsed_time": "3:47:15", "remaining_time": "2:17:58"}
+{"current_steps": 253, "total_steps": 405, "loss": 0.3132, "lr": 2.9758436397698118e-05, "epoch": 3.123456790123457, "percentage": 62.47, "elapsed_time": "3:48:03", "remaining_time": "2:17:01"}
+{"current_steps": 254, "total_steps": 405, "loss": 0.3183, "lr": 2.9425099770248446e-05, "epoch": 3.1358024691358026, "percentage": 62.72, "elapsed_time": "3:48:52", "remaining_time": "2:16:03"}
+{"current_steps": 255, "total_steps": 405, "loss": 0.3108, "lr": 2.9092550860420252e-05, "epoch": 3.148148148148148, "percentage": 62.96, "elapsed_time": "3:49:39", "remaining_time": "2:15:05"}
+{"current_steps": 256, "total_steps": 405, "loss": 0.316, "lr": 2.8760814439571233e-05, "epoch": 3.1604938271604937, "percentage": 63.21, "elapsed_time": "3:50:24", "remaining_time": "2:14:06"}
+{"current_steps": 257, "total_steps": 405, "loss": 0.3149, "lr": 2.8429915218537297e-05, "epoch": 3.1728395061728394, "percentage": 63.46, "elapsed_time": "3:51:11", "remaining_time": "2:13:08"}
+{"current_steps": 258, "total_steps": 405, "loss": 0.309, "lr": 2.809987784579189e-05, "epoch": 3.185185185185185, "percentage": 63.7, "elapsed_time": "3:51:59", "remaining_time": "2:12:10"}
+{"current_steps": 259, "total_steps": 405, "loss": 0.3104, "lr": 2.7770726905609896e-05, "epoch": 3.197530864197531, "percentage": 63.95, "elapsed_time": "3:52:45", "remaining_time": "2:11:12"}
+{"current_steps": 260, "total_steps": 405, "loss": 0.3055, "lr": 2.74424869162364e-05, "epoch": 3.2098765432098766, "percentage": 64.2, "elapsed_time": "3:53:30", "remaining_time": "2:10:13"}
+{"current_steps": 261, "total_steps": 405, "loss": 0.315, "lr": 2.7115182328060385e-05, "epoch": 3.2222222222222223, "percentage": 64.44, "elapsed_time": "3:54:17", "remaining_time": "2:09:15"}
+{"current_steps": 262, "total_steps": 405, "loss": 0.31, "lr": 2.678883752179333e-05, "epoch": 3.234567901234568, "percentage": 64.69, "elapsed_time": "3:55:02", "remaining_time": "2:08:17"}
+{"current_steps": 263, "total_steps": 405, "loss": 0.3067, "lr": 2.6463476806653185e-05, "epoch": 3.246913580246914, "percentage": 64.94, "elapsed_time": "3:55:47", "remaining_time": "2:07:18"}
+{"current_steps": 264, "total_steps": 405, "loss": 0.3086, "lr": 2.61391244185536e-05, "epoch": 3.259259259259259, "percentage": 65.19, "elapsed_time": "3:56:33", "remaining_time": "2:06:20"}
+{"current_steps": 265, "total_steps": 405, "loss": 0.3152, "lr": 2.5815804518298575e-05, "epoch": 3.271604938271605, "percentage": 65.43, "elapsed_time": "3:57:17", "remaining_time": "2:05:21"}
+{"current_steps": 266, "total_steps": 405, "loss": 0.315, "lr": 2.549354118978272e-05, "epoch": 3.2839506172839505, "percentage": 65.68, "elapsed_time": "3:58:02", "remaining_time": "2:04:23"}
+{"current_steps": 267, "total_steps": 405, "loss": 0.3085, "lr": 2.51723584381973e-05, "epoch": 3.2962962962962963, "percentage": 65.93, "elapsed_time": "3:58:47", "remaining_time": "2:03:24"}
+{"current_steps": 268, "total_steps": 405, "loss": 0.3147, "lr": 2.4852280188242096e-05, "epoch": 3.308641975308642, "percentage": 66.17, "elapsed_time": "3:59:32", "remaining_time": "2:02:27"}
+{"current_steps": 269, "total_steps": 405, "loss": 0.3124, "lr": 2.453333028234325e-05, "epoch": 3.3209876543209877, "percentage": 66.42, "elapsed_time": "4:00:17", "remaining_time": "2:01:29"}
+{"current_steps": 270, "total_steps": 405, "loss": 0.308, "lr": 2.4215532478877283e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "4:01:02", "remaining_time": "2:00:31"}
+{"current_steps": 271, "total_steps": 405, "loss": 0.3143, "lr": 2.3898910450401306e-05, "epoch": 3.3456790123456788, "percentage": 66.91, "elapsed_time": "4:01:47", "remaining_time": "1:59:33"}
+{"current_steps": 272, "total_steps": 405, "loss": 0.317, "lr": 2.3583487781889737e-05, "epoch": 3.3580246913580245, "percentage": 67.16, "elapsed_time": "4:02:33", "remaining_time": "1:58:36"}
+{"current_steps": 273, "total_steps": 405, "loss": 0.3108, "lr": 2.3269287968977406e-05, "epoch": 3.3703703703703702, "percentage": 67.41, "elapsed_time": "4:03:17", "remaining_time": "1:57:38"}
+{"current_steps": 274, "total_steps": 405, "loss": 0.3197, "lr": 2.2956334416209404e-05, "epoch": 3.382716049382716, "percentage": 67.65, "elapsed_time": "4:04:03", "remaining_time": "1:56:41"}
+{"current_steps": 275, "total_steps": 405, "loss": 0.3096, "lr": 2.264465043529768e-05, "epoch": 3.3950617283950617, "percentage": 67.9, "elapsed_time": "4:04:49", "remaining_time": "1:55:44"}
+{"current_steps": 276, "total_steps": 405, "loss": 0.3111, "lr": 2.233425924338463e-05, "epoch": 3.4074074074074074, "percentage": 68.15, "elapsed_time": "4:05:34", "remaining_time": "1:54:46"}
+{"current_steps": 277, "total_steps": 405, "loss": 0.315, "lr": 2.2025183961313542e-05, "epoch": 3.419753086419753, "percentage": 68.4, "elapsed_time": "4:06:19", "remaining_time": "1:53:49"}
+{"current_steps": 278, "total_steps": 405, "loss": 0.3128, "lr": 2.1717447611906496e-05, "epoch": 3.432098765432099, "percentage": 68.64, "elapsed_time": "4:07:04", "remaining_time": "1:52:52"}
+{"current_steps": 279, "total_steps": 405, "loss": 0.3156, "lr": 2.141107311824926e-05, "epoch": 3.4444444444444446, "percentage": 68.89, "elapsed_time": "4:07:50", "remaining_time": "1:51:55"}
+{"current_steps": 280, "total_steps": 405, "loss": 0.3095, "lr": 2.1106083301983852e-05, "epoch": 3.45679012345679, "percentage": 69.14, "elapsed_time": "4:08:44", "remaining_time": "1:51:02"}
+{"current_steps": 281, "total_steps": 405, "loss": 0.3184, "lr": 2.0802500881608557e-05, "epoch": 3.4691358024691357, "percentage": 69.38, "elapsed_time": "4:09:45", "remaining_time": "1:50:12"}
+{"current_steps": 282, "total_steps": 405, "loss": 0.3161, "lr": 2.0500348470785614e-05, "epoch": 3.4814814814814814, "percentage": 69.63, "elapsed_time": "4:10:41", "remaining_time": "1:49:20"}
+{"current_steps": 283, "total_steps": 405, "loss": 0.3106, "lr": 2.0199648576656744e-05, "epoch": 3.493827160493827, "percentage": 69.88, "elapsed_time": "4:11:42", "remaining_time": "1:48:30"}
+{"current_steps": 284, "total_steps": 405, "loss": 0.3126, "lr": 1.9900423598166685e-05, "epoch": 3.506172839506173, "percentage": 70.12, "elapsed_time": "4:12:38", "remaining_time": "1:47:38"}
+{"current_steps": 285, "total_steps": 405, "loss": 0.3119, "lr": 1.9602695824394576e-05, "epoch": 3.5185185185185186, "percentage": 70.37, "elapsed_time": "4:13:35", "remaining_time": "1:46:46"}
+{"current_steps": 286, "total_steps": 405, "loss": 0.3129, "lr": 1.9306487432893725e-05, "epoch": 3.5308641975308643, "percentage": 70.62, "elapsed_time": "4:14:21", "remaining_time": "1:45:49"}
+{"current_steps": 287, "total_steps": 405, "loss": 0.3121, "lr": 1.901182048803968e-05, "epoch": 3.5432098765432096, "percentage": 70.86, "elapsed_time": "4:15:06", "remaining_time": "1:44:53"}
+{"current_steps": 288, "total_steps": 405, "loss": 0.3169, "lr": 1.8718716939386543e-05, "epoch": 3.5555555555555554, "percentage": 71.11, "elapsed_time": "4:15:54", "remaining_time": "1:43:57"}
+{"current_steps": 289, "total_steps": 405, "loss": 0.3134, "lr": 1.8427198620032037e-05, "epoch": 3.567901234567901, "percentage": 71.36, "elapsed_time": "4:16:53", "remaining_time": "1:43:06"}
+{"current_steps": 290, "total_steps": 405, "loss": 0.3169, "lr": 1.8137287244991162e-05, "epoch": 3.580246913580247, "percentage": 71.6, "elapsed_time": "4:18:00", "remaining_time": "1:42:18"}
+{"current_steps": 291, "total_steps": 405, "loss": 0.3164, "lr": 1.7849004409578678e-05, "epoch": 3.5925925925925926, "percentage": 71.85, "elapsed_time": "4:19:12", "remaining_time": "1:41:32"}
+{"current_steps": 292, "total_steps": 405, "loss": 0.3103, "lr": 1.7562371587800422e-05, "epoch": 3.6049382716049383, "percentage": 72.1, "elapsed_time": "4:20:20", "remaining_time": "1:40:45"}
+{"current_steps": 293, "total_steps": 405, "loss": 0.3172, "lr": 1.7277410130753775e-05, "epoch": 3.617283950617284, "percentage": 72.35, "elapsed_time": "4:21:25", "remaining_time": "1:39:55"}
+{"current_steps": 294, "total_steps": 405, "loss": 0.3074, "lr": 1.6994141265037222e-05, "epoch": 3.6296296296296298, "percentage": 72.59, "elapsed_time": "4:22:19", "remaining_time": "1:39:02"}
+{"current_steps": 295, "total_steps": 405, "loss": 0.3167, "lr": 1.6712586091169183e-05, "epoch": 3.6419753086419755, "percentage": 72.84, "elapsed_time": "4:23:14", "remaining_time": "1:38:09"}
+{"current_steps": 296, "total_steps": 405, "loss": 0.3103, "lr": 1.6432765582016257e-05, "epoch": 3.6543209876543212, "percentage": 73.09, "elapsed_time": "4:24:08", "remaining_time": "1:37:16"}
+{"current_steps": 297, "total_steps": 405, "loss": 0.3156, "lr": 1.615470058123099e-05, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "4:25:08", "remaining_time": "1:36:24"}
+{"current_steps": 298, "total_steps": 405, "loss": 0.3141, "lr": 1.5878411801699182e-05, "epoch": 3.6790123456790123, "percentage": 73.58, "elapsed_time": "4:26:14", "remaining_time": "1:35:35"}
+{"current_steps": 299, "total_steps": 405, "loss": 0.3188, "lr": 1.5603919823997083e-05, "epoch": 3.691358024691358, "percentage": 73.83, "elapsed_time": "4:27:22", "remaining_time": "1:34:47"}
+{"current_steps": 300, "total_steps": 405, "loss": 0.3105, "lr": 1.5331245094858277e-05, "epoch": 3.7037037037037037, "percentage": 74.07, "elapsed_time": "4:28:34", "remaining_time": "1:34:00"}
+{"current_steps": 301, "total_steps": 405, "loss": 0.3111, "lr": 1.5060407925650662e-05, "epoch": 3.7160493827160495, "percentage": 74.32, "elapsed_time": "4:29:36", "remaining_time": "1:33:09"}
+{"current_steps": 302, "total_steps": 405, "loss": 0.3117, "lr": 1.4791428490863462e-05, "epoch": 3.728395061728395, "percentage": 74.57, "elapsed_time": "4:30:31", "remaining_time": "1:32:15"}
+{"current_steps": 303, "total_steps": 405, "loss": 0.3128, "lr": 1.4524326826604442e-05, "epoch": 3.7407407407407405, "percentage": 74.81, "elapsed_time": "4:31:26", "remaining_time": "1:31:22"}
+{"current_steps": 304, "total_steps": 405, "loss": 0.3087, "lr": 1.425912282910741e-05, "epoch": 3.753086419753086, "percentage": 75.06, "elapsed_time": "4:32:25", "remaining_time": "1:30:30"}
+{"current_steps": 305, "total_steps": 405, "loss": 0.3105, "lr": 1.3995836253250233e-05, "epoch": 3.765432098765432, "percentage": 75.31, "elapsed_time": "4:33:32", "remaining_time": "1:29:41"}
+{"current_steps": 306, "total_steps": 405, "loss": 0.313, "lr": 1.3734486711083199e-05, "epoch": 3.7777777777777777, "percentage": 75.56, "elapsed_time": "4:34:52", "remaining_time": "1:28:55"}
+{"current_steps": 307, "total_steps": 405, "loss": 0.3103, "lr": 1.3475093670368202e-05, "epoch": 3.7901234567901234, "percentage": 75.8, "elapsed_time": "4:36:13", "remaining_time": "1:28:10"}
+{"current_steps": 308, "total_steps": 405, "loss": 0.315, "lr": 1.3217676453128583e-05, "epoch": 3.802469135802469, "percentage": 76.05, "elapsed_time": "4:37:32", "remaining_time": "1:27:24"}
+{"current_steps": 309, "total_steps": 405, "loss": 0.3172, "lr": 1.2962254234209826e-05, "epoch": 3.814814814814815, "percentage": 76.3, "elapsed_time": "4:38:46", "remaining_time": "1:26:36"}
+{"current_steps": 310, "total_steps": 405, "loss": 0.3082, "lr": 1.2708846039851306e-05, "epoch": 3.8271604938271606, "percentage": 76.54, "elapsed_time": "4:39:41", "remaining_time": "1:25:42"}
+{"current_steps": 311, "total_steps": 405, "loss": 0.308, "lr": 1.2457470746268912e-05, "epoch": 3.8395061728395063, "percentage": 76.79, "elapsed_time": "4:40:25", "remaining_time": "1:24:45"}
+{"current_steps": 312, "total_steps": 405, "loss": 0.3165, "lr": 1.2208147078249106e-05, "epoch": 3.851851851851852, "percentage": 77.04, "elapsed_time": "4:41:12", "remaining_time": "1:23:49"}
+{"current_steps": 313, "total_steps": 405, "loss": 0.3243, "lr": 1.1960893607754022e-05, "epoch": 3.8641975308641974, "percentage": 77.28, "elapsed_time": "4:42:20", "remaining_time": "1:22:59"}
+{"current_steps": 314, "total_steps": 405, "loss": 0.3167, "lr": 1.1715728752538103e-05, "epoch": 3.876543209876543, "percentage": 77.53, "elapsed_time": "4:43:31", "remaining_time": "1:22:10"}
+{"current_steps": 315, "total_steps": 405, "loss": 0.3187, "lr": 1.1472670774776159e-05, "epoch": 3.888888888888889, "percentage": 77.78, "elapsed_time": "4:44:47", "remaining_time": "1:21:22"}
+{"current_steps": 316, "total_steps": 405, "loss": 0.3124, "lr": 1.123173777970303e-05, "epoch": 3.9012345679012346, "percentage": 78.02, "elapsed_time": "4:45:58", "remaining_time": "1:20:32"}
+{"current_steps": 317, "total_steps": 405, "loss": 0.3118, "lr": 1.0992947714264952e-05, "epoch": 3.9135802469135803, "percentage": 78.27, "elapsed_time": "4:47:03", "remaining_time": "1:19:41"}
+{"current_steps": 318, "total_steps": 405, "loss": 0.3173, "lr": 1.0756318365782672e-05, "epoch": 3.925925925925926, "percentage": 78.52, "elapsed_time": "4:47:48", "remaining_time": "1:18:44"}
+{"current_steps": 319, "total_steps": 405, "loss": 0.3123, "lr": 1.0521867360626534e-05, "epoch": 3.9382716049382713, "percentage": 78.77, "elapsed_time": "4:48:33", "remaining_time": "1:17:47"}
+{"current_steps": 320, "total_steps": 405, "loss": 0.3168, "lr": 1.028961216290342e-05, "epoch": 3.950617283950617, "percentage": 79.01, "elapsed_time": "4:49:30", "remaining_time": "1:16:54"}
+{"current_steps": 321, "total_steps": 405, "loss": 0.3156, "lr": 1.0059570073155953e-05, "epoch": 3.962962962962963, "percentage": 79.26, "elapsed_time": "4:50:34", "remaining_time": "1:16:02"}
+{"current_steps": 322, "total_steps": 405, "loss": 0.3102, "lr": 9.831758227073714e-06, "epoch": 3.9753086419753085, "percentage": 79.51, "elapsed_time": "4:51:42", "remaining_time": "1:15:11"}
+{"current_steps": 323, "total_steps": 405, "loss": 0.3129, "lr": 9.606193594216852e-06, "epoch": 3.9876543209876543, "percentage": 79.75, "elapsed_time": "4:52:57", "remaining_time": "1:14:22"}
+{"current_steps": 324, "total_steps": 405, "loss": 0.3, "lr": 9.382892976752024e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "4:54:29", "remaining_time": "1:13:37"}
+{"current_steps": 325, "total_steps": 405, "loss": 0.2946, "lr": 9.161873008200816e-06, "epoch": 4.012345679012346, "percentage": 80.25, "elapsed_time": "4:58:38", "remaining_time": "1:13:30"}
+{"current_steps": 326, "total_steps": 405, "loss": 0.3046, "lr": 8.943150152200734e-06, "epoch": 4.0246913580246915, "percentage": 80.49, "elapsed_time": "4:59:50", "remaining_time": "1:12:39"}
+{"current_steps": 327, "total_steps": 405, "loss": 0.2911, "lr": 8.72674070127881e-06, "epoch": 4.037037037037037, "percentage": 80.74, "elapsed_time": "5:01:08", "remaining_time": "1:11:49"}
+{"current_steps": 328, "total_steps": 405, "loss": 0.2936, "lr": 8.512660775637998e-06, "epoch": 4.049382716049383, "percentage": 80.99, "elapsed_time": "5:02:17", "remaining_time": "1:10:57"}
+{"current_steps": 329, "total_steps": 405, "loss": 0.2916, "lr": 8.300926321956391e-06, "epoch": 4.061728395061729, "percentage": 81.23, "elapsed_time": "5:03:46", "remaining_time": "1:10:10"}
+{"current_steps": 330, "total_steps": 405, "loss": 0.3004, "lr": 8.091553112199362e-06, "epoch": 4.074074074074074, "percentage": 81.48, "elapsed_time": "5:05:13", "remaining_time": "1:09:22"}
+{"current_steps": 331, "total_steps": 405, "loss": 0.2947, "lr": 7.884556742444704e-06, "epoch": 4.08641975308642, "percentage": 81.73, "elapsed_time": "5:06:35", "remaining_time": "1:08:32"}
+{"current_steps": 332, "total_steps": 405, "loss": 0.2959, "lr": 7.679952631720944e-06, "epoch": 4.098765432098766, "percentage": 81.98, "elapsed_time": "5:07:45", "remaining_time": "1:07:40"}
+{"current_steps": 333, "total_steps": 405, "loss": 0.3035, "lr": 7.477756020858695e-06, "epoch": 4.111111111111111, "percentage": 82.22, "elapsed_time": "5:08:53", "remaining_time": "1:06:47"}
+{"current_steps": 334, "total_steps": 405, "loss": 0.2937, "lr": 7.277981971355487e-06, "epoch": 4.1234567901234565, "percentage": 82.47, "elapsed_time": "5:09:58", "remaining_time": "1:05:53"}
+{"current_steps": 335, "total_steps": 405, "loss": 0.2946, "lr": 7.080645364253747e-06, "epoch": 4.135802469135802, "percentage": 82.72, "elapsed_time": "5:11:00", "remaining_time": "1:04:59"}
+{"current_steps": 336, "total_steps": 405, "loss": 0.2951, "lr": 6.885760899032368e-06, "epoch": 4.148148148148148, "percentage": 82.96, "elapsed_time": "5:12:14", "remaining_time": "1:04:07"}
+{"current_steps": 337, "total_steps": 405, "loss": 0.2966, "lr": 6.69334309251175e-06, "epoch": 4.160493827160494, "percentage": 83.21, "elapsed_time": "5:13:30", "remaining_time": "1:03:15"}
+{"current_steps": 338, "total_steps": 405, "loss": 0.2941, "lr": 6.503406277772457e-06, "epoch": 4.172839506172839, "percentage": 83.46, "elapsed_time": "5:14:54", "remaining_time": "1:02:25"}
+{"current_steps": 339, "total_steps": 405, "loss": 0.2935, "lr": 6.31596460308753e-06, "epoch": 4.185185185185185, "percentage": 83.7, "elapsed_time": "5:16:10", "remaining_time": "1:01:33"}
+{"current_steps": 340, "total_steps": 405, "loss": 0.2986, "lr": 6.1310320308686354e-06, "epoch": 4.197530864197531, "percentage": 83.95, "elapsed_time": "5:17:21", "remaining_time": "1:00:40"}
+{"current_steps": 341, "total_steps": 405, "loss": 0.2903, "lr": 5.9486223366259555e-06, "epoch": 4.209876543209877, "percentage": 84.2, "elapsed_time": "5:18:27", "remaining_time": "0:59:46"}
+{"current_steps": 342, "total_steps": 405, "loss": 0.2953, "lr": 5.768749107942105e-06, "epoch": 4.222222222222222, "percentage": 84.44, "elapsed_time": "5:19:39", "remaining_time": "0:58:53"}
+{"current_steps": 343, "total_steps": 405, "loss": 0.293, "lr": 5.5914257434599705e-06, "epoch": 4.234567901234568, "percentage": 84.69, "elapsed_time": "5:20:45", "remaining_time": "0:57:58"}
+{"current_steps": 344, "total_steps": 405, "loss": 0.2967, "lr": 5.416665451884706e-06, "epoch": 4.246913580246914, "percentage": 84.94, "elapsed_time": "5:22:00", "remaining_time": "0:57:05"}
+{"current_steps": 345, "total_steps": 405, "loss": 0.3078, "lr": 5.24448125099974e-06, "epoch": 4.2592592592592595, "percentage": 85.19, "elapsed_time": "5:23:15", "remaining_time": "0:56:13"}
+{"current_steps": 346, "total_steps": 405, "loss": 0.2939, "lr": 5.074885966697167e-06, "epoch": 4.271604938271605, "percentage": 85.43, "elapsed_time": "5:24:38", "remaining_time": "0:55:21"}
+{"current_steps": 347, "total_steps": 405, "loss": 0.2891, "lr": 4.9078922320223225e-06, "epoch": 4.283950617283951, "percentage": 85.68, "elapsed_time": "5:25:49", "remaining_time": "0:54:27"}
+{"current_steps": 348, "total_steps": 405, "loss": 0.2951, "lr": 4.7435124862327445e-06, "epoch": 4.296296296296296, "percentage": 85.93, "elapsed_time": "5:26:56", "remaining_time": "0:53:33"}
+{"current_steps": 349, "total_steps": 405, "loss": 0.2937, "lr": 4.581758973871609e-06, "epoch": 4.308641975308642, "percentage": 86.17, "elapsed_time": "5:27:53", "remaining_time": "0:52:36"}
+{"current_steps": 350, "total_steps": 405, "loss": 0.2891, "lr": 4.422643743855611e-06, "epoch": 4.320987654320987, "percentage": 86.42, "elapsed_time": "5:28:49", "remaining_time": "0:51:40"}
+{"current_steps": 351, "total_steps": 405, "loss": 0.2961, "lr": 4.266178648577484e-06, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "5:29:36", "remaining_time": "0:50:42"}
+{"current_steps": 352, "total_steps": 405, "loss": 0.2906, "lr": 4.112375343023076e-06, "epoch": 4.345679012345679, "percentage": 86.91, "elapsed_time": "5:30:22", "remaining_time": "0:49:44"}
+{"current_steps": 353, "total_steps": 405, "loss": 0.2923, "lr": 3.961245283903239e-06, "epoch": 4.3580246913580245, "percentage": 87.16, "elapsed_time": "5:31:10", "remaining_time": "0:48:47"}
+{"current_steps": 354, "total_steps": 405, "loss": 0.2984, "lr": 3.812799728800354e-06, "epoch": 4.37037037037037, "percentage": 87.41, "elapsed_time": "5:32:10", "remaining_time": "0:47:51"}
+{"current_steps": 355, "total_steps": 405, "loss": 0.2977, "lr": 3.6670497353298396e-06, "epoch": 4.382716049382716, "percentage": 87.65, "elapsed_time": "5:33:12", "remaining_time": "0:46:55"}
+{"current_steps": 356, "total_steps": 405, "loss": 0.2943, "lr": 3.5240061603163977e-06, "epoch": 4.395061728395062, "percentage": 87.9, "elapsed_time": "5:34:10", "remaining_time": "0:45:59"}
+{"current_steps": 357, "total_steps": 405, "loss": 0.2903, "lr": 3.3836796589853484e-06, "epoch": 4.407407407407407, "percentage": 88.15, "elapsed_time": "5:35:03", "remaining_time": "0:45:03"}
+{"current_steps": 358, "total_steps": 405, "loss": 0.2881, "lr": 3.246080684168913e-06, "epoch": 4.419753086419753, "percentage": 88.4, "elapsed_time": "5:36:02", "remaining_time": "0:44:07"}
+{"current_steps": 359, "total_steps": 405, "loss": 0.2963, "lr": 3.11121948552759e-06, "epoch": 4.432098765432099, "percentage": 88.64, "elapsed_time": "5:36:55", "remaining_time": "0:43:10"}
+{"current_steps": 360, "total_steps": 405, "loss": 0.2997, "lr": 2.9791061087866625e-06, "epoch": 4.444444444444445, "percentage": 88.89, "elapsed_time": "5:37:41", "remaining_time": "0:42:12"}
+{"current_steps": 361, "total_steps": 405, "loss": 0.2993, "lr": 2.849750394987907e-06, "epoch": 4.45679012345679, "percentage": 89.14, "elapsed_time": "5:38:27", "remaining_time": "0:41:15"}
+{"current_steps": 362, "total_steps": 405, "loss": 0.2956, "lr": 2.7231619797565278e-06, "epoch": 4.469135802469136, "percentage": 89.38, "elapsed_time": "5:39:13", "remaining_time": "0:40:17"}
+{"current_steps": 363, "total_steps": 405, "loss": 0.2969, "lr": 2.5993502925834115e-06, "epoch": 4.481481481481482, "percentage": 89.63, "elapsed_time": "5:39:59", "remaining_time": "0:39:20"}
+{"current_steps": 364, "total_steps": 405, "loss": 0.2942, "lr": 2.4783245561227264e-06, "epoch": 4.493827160493828, "percentage": 89.88, "elapsed_time": "5:40:45", "remaining_time": "0:38:22"}
+{"current_steps": 365, "total_steps": 405, "loss": 0.298, "lr": 2.3600937855049467e-06, "epoch": 4.506172839506172, "percentage": 90.12, "elapsed_time": "5:41:31", "remaining_time": "0:37:25"}
+{"current_steps": 366, "total_steps": 405, "loss": 0.2982, "lr": 2.244666787665297e-06, "epoch": 4.518518518518518, "percentage": 90.37, "elapsed_time": "5:42:16", "remaining_time": "0:36:28"}
+{"current_steps": 367, "total_steps": 405, "loss": 0.2987, "lr": 2.1320521606877653e-06, "epoch": 4.530864197530864, "percentage": 90.62, "elapsed_time": "5:43:02", "remaining_time": "0:35:31"}
+{"current_steps": 368, "total_steps": 405, "loss": 0.2936, "lr": 2.022258293164585e-06, "epoch": 4.54320987654321, "percentage": 90.86, "elapsed_time": "5:43:48", "remaining_time": "0:34:34"}
+{"current_steps": 369, "total_steps": 405, "loss": 0.2914, "lr": 1.9152933635714354e-06, "epoch": 4.555555555555555, "percentage": 91.11, "elapsed_time": "5:44:33", "remaining_time": "0:33:36"}
+{"current_steps": 370, "total_steps": 405, "loss": 0.2987, "lr": 1.8111653396581762e-06, "epoch": 4.567901234567901, "percentage": 91.36, "elapsed_time": "5:45:19", "remaining_time": "0:32:39"}
+{"current_steps": 371, "total_steps": 405, "loss": 0.295, "lr": 1.709881977855372e-06, "epoch": 4.580246913580247, "percentage": 91.6, "elapsed_time": "5:46:05", "remaining_time": "0:31:43"}
+{"current_steps": 372, "total_steps": 405, "loss": 0.2941, "lr": 1.6114508226965009e-06, "epoch": 4.592592592592593, "percentage": 91.85, "elapsed_time": "5:46:51", "remaining_time": "0:30:46"}
+{"current_steps": 373, "total_steps": 405, "loss": 0.2964, "lr": 1.5158792062559813e-06, "epoch": 4.604938271604938, "percentage": 92.1, "elapsed_time": "5:47:37", "remaining_time": "0:29:49"}
+{"current_steps": 374, "total_steps": 405, "loss": 0.2961, "lr": 1.4231742476029965e-06, "epoch": 4.617283950617284, "percentage": 92.35, "elapsed_time": "5:48:22", "remaining_time": "0:28:52"}
+{"current_steps": 375, "total_steps": 405, "loss": 0.2953, "lr": 1.33334285227122e-06, "epoch": 4.62962962962963, "percentage": 92.59, "elapsed_time": "5:49:09", "remaining_time": "0:27:55"}
+{"current_steps": 376, "total_steps": 405, "loss": 0.2972, "lr": 1.2463917117443968e-06, "epoch": 4.6419753086419755, "percentage": 92.84, "elapsed_time": "5:49:54", "remaining_time": "0:26:59"}
+{"current_steps": 377, "total_steps": 405, "loss": 0.296, "lr": 1.1623273029579195e-06, "epoch": 4.654320987654321, "percentage": 93.09, "elapsed_time": "5:50:39", "remaining_time": "0:26:02"}
+{"current_steps": 378, "total_steps": 405, "loss": 0.2946, "lr": 1.0811558878163698e-06, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "5:51:24", "remaining_time": "0:25:06"}
+{"current_steps": 379, "total_steps": 405, "loss": 0.2924, "lr": 1.0028835127270553e-06, "epoch": 4.679012345679013, "percentage": 93.58, "elapsed_time": "5:52:10", "remaining_time": "0:24:09"}
+{"current_steps": 380, "total_steps": 405, "loss": 0.2955, "lr": 9.275160081496337e-07, "epoch": 4.6913580246913575, "percentage": 93.83, "elapsed_time": "5:52:56", "remaining_time": "0:23:13"}
+{"current_steps": 381, "total_steps": 405, "loss": 0.2923, "lr": 8.550589881617877e-07, "epoch": 4.703703703703704, "percentage": 94.07, "elapsed_time": "5:53:41", "remaining_time": "0:22:16"}
+{"current_steps": 382, "total_steps": 405, "loss": 0.2894, "lr": 7.85517850041062e-07, "epoch": 4.716049382716049, "percentage": 94.32, "elapsed_time": "5:54:26", "remaining_time": "0:21:20"}
+{"current_steps": 383, "total_steps": 405, "loss": 0.2952, "lr": 7.188977738627901e-07, "epoch": 4.728395061728395, "percentage": 94.57, "elapsed_time": "5:55:29", "remaining_time": "0:20:25"}
+{"current_steps": 384, "total_steps": 405, "loss": 0.2899, "lr": 6.552037221142593e-07, "epoch": 4.7407407407407405, "percentage": 94.81, "elapsed_time": "5:56:15", "remaining_time": "0:19:28"}
+{"current_steps": 385, "total_steps": 405, "loss": 0.2914, "lr": 5.944404393250481e-07, "epoch": 4.753086419753086, "percentage": 95.06, "elapsed_time": "5:57:00", "remaining_time": "0:18:32"}
+{"current_steps": 386, "total_steps": 405, "loss": 0.292, "lr": 5.366124517136184e-07, "epoch": 4.765432098765432, "percentage": 95.31, "elapsed_time": "5:57:46", "remaining_time": "0:17:36"}
+{"current_steps": 387, "total_steps": 405, "loss": 0.2911, "lr": 4.817240668501421e-07, "epoch": 4.777777777777778, "percentage": 95.56, "elapsed_time": "5:58:31", "remaining_time": "0:16:40"}
+{"current_steps": 388, "total_steps": 405, "loss": 0.2926, "lr": 4.297793733356548e-07, "epoch": 4.790123456790123, "percentage": 95.8, "elapsed_time": "5:59:16", "remaining_time": "0:15:44"}
+{"current_steps": 389, "total_steps": 405, "loss": 0.2983, "lr": 3.807822404974726e-07, "epoch": 4.802469135802469, "percentage": 96.05, "elapsed_time": "6:00:04", "remaining_time": "0:14:48"}
+{"current_steps": 390, "total_steps": 405, "loss": 0.2843, "lr": 3.3473631810100103e-07, "epoch": 4.814814814814815, "percentage": 96.3, "elapsed_time": "6:00:51", "remaining_time": "0:13:52"}
+{"current_steps": 391, "total_steps": 405, "loss": 0.2865, "lr": 2.916450360778411e-07, "epoch": 4.827160493827161, "percentage": 96.54, "elapsed_time": "6:01:39", "remaining_time": "0:12:56"}
+{"current_steps": 392, "total_steps": 405, "loss": 0.2965, "lr": 2.5151160427029584e-07, "epoch": 4.839506172839506, "percentage": 96.79, "elapsed_time": "6:02:26", "remaining_time": "0:12:01"}
+{"current_steps": 393, "total_steps": 405, "loss": 0.2962, "lr": 2.1433901219229502e-07, "epoch": 4.851851851851852, "percentage": 97.04, "elapsed_time": "6:03:12", "remaining_time": "0:11:05"}
+{"current_steps": 394, "total_steps": 405, "loss": 0.2942, "lr": 1.8013002880667096e-07, "epoch": 4.864197530864198, "percentage": 97.28, "elapsed_time": "6:03:58", "remaining_time": "0:10:09"}
+{"current_steps": 395, "total_steps": 405, "loss": 0.2984, "lr": 1.4888720231894138e-07, "epoch": 4.8765432098765435, "percentage": 97.53, "elapsed_time": "6:04:43", "remaining_time": "0:09:14"}
+{"current_steps": 396, "total_steps": 405, "loss": 0.2966, "lr": 1.2061285998746562e-07, "epoch": 4.888888888888889, "percentage": 97.78, "elapsed_time": "6:05:28", "remaining_time": "0:08:18"}
+{"current_steps": 397, "total_steps": 405, "loss": 0.2944, "lr": 9.530910795009895e-08, "epoch": 4.901234567901234, "percentage": 98.02, "elapsed_time": "6:06:14", "remaining_time": "0:07:22"}
+{"current_steps": 398, "total_steps": 405, "loss": 0.2911, "lr": 7.297783106730016e-08, "epoch": 4.91358024691358, "percentage": 98.27, "elapsed_time": "6:06:59", "remaining_time": "0:06:27"}
+{"current_steps": 399, "total_steps": 405, "loss": 0.2959, "lr": 5.362069278175508e-08, "epoch": 4.925925925925926, "percentage": 98.52, "elapsed_time": "6:07:44", "remaining_time": "0:05:31"}
+{"current_steps": 400, "total_steps": 405, "loss": 0.2893, "lr": 3.7239134994426775e-08, "epoch": 4.938271604938271, "percentage": 98.77, "elapsed_time": "6:08:30", "remaining_time": "0:04:36"}
+{"current_steps": 401, "total_steps": 405, "loss": 0.2871, "lr": 2.3834377957183684e-08, "epoch": 4.950617283950617, "percentage": 99.01, "elapsed_time": "6:09:15", "remaining_time": "0:03:41"}
+{"current_steps": 402, "total_steps": 405, "loss": 0.2903, "lr": 1.3407420181885678e-08, "epoch": 4.962962962962963, "percentage": 99.26, "elapsed_time": "6:10:01", "remaining_time": "0:02:45"}
+{"current_steps": 403, "total_steps": 405, "loss": 0.2965, "lr": 5.959038366021297e-09, "epoch": 4.9753086419753085, "percentage": 99.51, "elapsed_time": "6:10:49", "remaining_time": "0:01:50"}
+{"current_steps": 404, "total_steps": 405, "loss": 0.2937, "lr": 1.4897873348340697e-09, "epoch": 4.987654320987654, "percentage": 99.75, "elapsed_time": "6:11:37", "remaining_time": "0:00:55"}
+{"current_steps": 405, "total_steps": 405, "loss": 0.2918, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:12:24", "remaining_time": "0:00:00"}
+{"current_steps": 405, "total_steps": 405, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:16:39", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2877 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 405,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012345679012345678,
+      "grad_norm": 2.3641861999816807,
+      "learning_rate": 1.951219512195122e-06,
+      "loss": 0.753,
+      "step": 1
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 2.356503301807238,
+      "learning_rate": 3.902439024390244e-06,
+      "loss": 0.7445,
+      "step": 2
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 2.2234803569377406,
+      "learning_rate": 5.853658536585366e-06,
+      "loss": 0.7446,
+      "step": 3
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 1.7703804403466514,
+      "learning_rate": 7.804878048780489e-06,
+      "loss": 0.7323,
+      "step": 4
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 1.1963527791360251,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 0.6942,
+      "step": 5
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 1.3516452600340108,
+      "learning_rate": 1.1707317073170731e-05,
+      "loss": 0.6725,
+      "step": 6
+    },
+    {
+      "epoch": 0.08641975308641975,
+      "grad_norm": 1.2102032816047636,
+      "learning_rate": 1.3658536585365855e-05,
+      "loss": 0.6619,
+      "step": 7
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 1.4932103040926035,
+      "learning_rate": 1.5609756097560978e-05,
+      "loss": 0.6237,
+      "step": 8
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.1357188851467106,
+      "learning_rate": 1.75609756097561e-05,
+      "loss": 0.6065,
+      "step": 9
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 1.1490820971226716,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 0.5767,
+      "step": 10
+    },
+    {
+      "epoch": 0.13580246913580246,
+      "grad_norm": 1.081067984530428,
+      "learning_rate": 2.1463414634146344e-05,
+      "loss": 0.5716,
+      "step": 11
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.6455345973200298,
+      "learning_rate": 2.3414634146341463e-05,
+      "loss": 0.5503,
+      "step": 12
+    },
+    {
+      "epoch": 0.16049382716049382,
+      "grad_norm": 0.7885415139181559,
+      "learning_rate": 2.536585365853659e-05,
+      "loss": 0.5403,
+      "step": 13
+    },
+    {
+      "epoch": 0.1728395061728395,
+      "grad_norm": 0.8234239814877424,
+      "learning_rate": 2.731707317073171e-05,
+      "loss": 0.527,
+      "step": 14
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.5196730757242491,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.5249,
+      "step": 15
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.7094387110081807,
+      "learning_rate": 3.1219512195121955e-05,
+      "loss": 0.5204,
+      "step": 16
+    },
+    {
+      "epoch": 0.20987654320987653,
+      "grad_norm": 0.5913229373005716,
+      "learning_rate": 3.3170731707317074e-05,
+      "loss": 0.5107,
+      "step": 17
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4036869055130918,
+      "learning_rate": 3.51219512195122e-05,
+      "loss": 0.4979,
+      "step": 18
+    },
+    {
+      "epoch": 0.2345679012345679,
+      "grad_norm": 0.5182698590385874,
+      "learning_rate": 3.7073170731707325e-05,
+      "loss": 0.5002,
+      "step": 19
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.40307576563013764,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 0.4975,
+      "step": 20
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.3892755712805291,
+      "learning_rate": 4.097560975609756e-05,
+      "loss": 0.4866,
+      "step": 21
+    },
+    {
+      "epoch": 0.2716049382716049,
+      "grad_norm": 0.41166237657961224,
+      "learning_rate": 4.292682926829269e-05,
+      "loss": 0.4881,
+      "step": 22
+    },
+    {
+      "epoch": 0.2839506172839506,
+      "grad_norm": 0.2852254116646358,
+      "learning_rate": 4.4878048780487814e-05,
+      "loss": 0.4687,
+      "step": 23
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.40947971386328313,
+      "learning_rate": 4.6829268292682926e-05,
+      "loss": 0.4722,
+      "step": 24
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.30010628779625415,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 0.4663,
+      "step": 25
+    },
+    {
+      "epoch": 0.32098765432098764,
+      "grad_norm": 0.2846821550956248,
+      "learning_rate": 5.073170731707318e-05,
+      "loss": 0.4669,
+      "step": 26
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.30303915404191006,
+      "learning_rate": 5.26829268292683e-05,
+      "loss": 0.4658,
+      "step": 27
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 0.3385048236473295,
+      "learning_rate": 5.463414634146342e-05,
+      "loss": 0.4666,
+      "step": 28
+    },
+    {
+      "epoch": 0.35802469135802467,
+      "grad_norm": 0.26505633123869665,
+      "learning_rate": 5.658536585365854e-05,
+      "loss": 0.4553,
+      "step": 29
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.32251699210244655,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 0.4585,
+      "step": 30
+    },
+    {
+      "epoch": 0.38271604938271603,
+      "grad_norm": 0.39911813658563333,
+      "learning_rate": 6.0487804878048785e-05,
+      "loss": 0.4504,
+      "step": 31
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.550266908481255,
+      "learning_rate": 6.243902439024391e-05,
+      "loss": 0.4567,
+      "step": 32
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.7558742259025343,
+      "learning_rate": 6.439024390243903e-05,
+      "loss": 0.4542,
+      "step": 33
+    },
+    {
+      "epoch": 0.41975308641975306,
+      "grad_norm": 0.7668829949225733,
+      "learning_rate": 6.634146341463415e-05,
+      "loss": 0.4535,
+      "step": 34
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.8356174741713307,
+      "learning_rate": 6.829268292682927e-05,
+      "loss": 0.4571,
+      "step": 35
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.9519575129169183,
+      "learning_rate": 7.02439024390244e-05,
+      "loss": 0.4567,
+      "step": 36
+    },
+    {
+      "epoch": 0.4567901234567901,
+      "grad_norm": 0.669293130953804,
+      "learning_rate": 7.219512195121952e-05,
+      "loss": 0.4569,
+      "step": 37
+    },
+    {
+      "epoch": 0.4691358024691358,
+      "grad_norm": 0.5312525567869633,
+      "learning_rate": 7.414634146341465e-05,
+      "loss": 0.4492,
+      "step": 38
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.7236182728346602,
+      "learning_rate": 7.609756097560976e-05,
+      "loss": 0.4463,
+      "step": 39
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.694469685863173,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.4461,
+      "step": 40
+    },
+    {
+      "epoch": 0.5061728395061729,
+      "grad_norm": 0.6055663719699068,
+      "learning_rate": 8e-05,
+      "loss": 0.4379,
+      "step": 41
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.5605285463176353,
+      "learning_rate": 7.999851021266518e-05,
+      "loss": 0.4348,
+      "step": 42
+    },
+    {
+      "epoch": 0.5308641975308642,
+      "grad_norm": 0.44648228668215406,
+      "learning_rate": 7.999404096163398e-05,
+      "loss": 0.4332,
+      "step": 43
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.6320764806874656,
+      "learning_rate": 7.998659257981813e-05,
+      "loss": 0.4303,
+      "step": 44
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.4637476053296809,
+      "learning_rate": 7.997616562204282e-05,
+      "loss": 0.43,
+      "step": 45
+    },
+    {
+      "epoch": 0.5679012345679012,
+      "grad_norm": 0.48174151021334227,
+      "learning_rate": 7.996276086500558e-05,
+      "loss": 0.434,
+      "step": 46
+    },
+    {
+      "epoch": 0.5802469135802469,
+      "grad_norm": 0.32250929239831827,
+      "learning_rate": 7.994637930721825e-05,
+      "loss": 0.4248,
+      "step": 47
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.4362490481280333,
+      "learning_rate": 7.99270221689327e-05,
+      "loss": 0.4312,
+      "step": 48
+    },
+    {
+      "epoch": 0.6049382716049383,
+      "grad_norm": 0.33745194839324855,
+      "learning_rate": 7.990469089204992e-05,
+      "loss": 0.4167,
+      "step": 49
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.36155344233989684,
+      "learning_rate": 7.987938714001254e-05,
+      "loss": 0.4199,
+      "step": 50
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.33591305334353816,
+      "learning_rate": 7.985111279768106e-05,
+      "loss": 0.4287,
+      "step": 51
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.33172670837286455,
+      "learning_rate": 7.981986997119334e-05,
+      "loss": 0.4176,
+      "step": 52
+    },
+    {
+      "epoch": 0.654320987654321,
+      "grad_norm": 0.29170146703251837,
+      "learning_rate": 7.978566098780771e-05,
+      "loss": 0.4175,
+      "step": 53
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2976426252745893,
+      "learning_rate": 7.974848839572971e-05,
+      "loss": 0.4129,
+      "step": 54
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.34950158528102804,
+      "learning_rate": 7.970835496392216e-05,
+      "loss": 0.4218,
+      "step": 55
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.3914250704266441,
+      "learning_rate": 7.9665263681899e-05,
+      "loss": 0.4091,
+      "step": 56
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.37808792302444477,
+      "learning_rate": 7.961921775950254e-05,
+      "loss": 0.418,
+      "step": 57
+    },
+    {
+      "epoch": 0.7160493827160493,
+      "grad_norm": 0.4269790342577099,
+      "learning_rate": 7.957022062666436e-05,
+      "loss": 0.4196,
+      "step": 58
+    },
+    {
+      "epoch": 0.7283950617283951,
+      "grad_norm": 0.5485430875445669,
+      "learning_rate": 7.951827593314987e-05,
+      "loss": 0.4187,
+      "step": 59
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.6036979168446722,
+      "learning_rate": 7.946338754828639e-05,
+      "loss": 0.4198,
+      "step": 60
+    },
+    {
+      "epoch": 0.7530864197530864,
+      "grad_norm": 0.5661146721756646,
+      "learning_rate": 7.940555956067495e-05,
+      "loss": 0.4158,
+      "step": 61
+    },
+    {
+      "epoch": 0.7654320987654321,
+      "grad_norm": 0.5386904877883265,
+      "learning_rate": 7.934479627788576e-05,
+      "loss": 0.4217,
+      "step": 62
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.43759284695679806,
+      "learning_rate": 7.928110222613723e-05,
+      "loss": 0.4133,
+      "step": 63
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.41167742730002344,
+      "learning_rate": 7.921448214995895e-05,
+      "loss": 0.4129,
+      "step": 64
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.584192459482168,
+      "learning_rate": 7.914494101183822e-05,
+      "loss": 0.4188,
+      "step": 65
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.6167861651110604,
+      "learning_rate": 7.907248399185037e-05,
+      "loss": 0.4211,
+      "step": 66
+    },
+    {
+      "epoch": 0.8271604938271605,
+      "grad_norm": 0.4764107138941137,
+      "learning_rate": 7.899711648727294e-05,
+      "loss": 0.4121,
+      "step": 67
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 0.50441349423777,
+      "learning_rate": 7.891884411218364e-05,
+      "loss": 0.4047,
+      "step": 68
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.4636658055731566,
+      "learning_rate": 7.883767269704209e-05,
+      "loss": 0.4066,
+      "step": 69
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.31884275898458864,
+      "learning_rate": 7.875360828825562e-05,
+      "loss": 0.4081,
+      "step": 70
+    },
+    {
+      "epoch": 0.8765432098765432,
+      "grad_norm": 0.3178857716738372,
+      "learning_rate": 7.866665714772879e-05,
+      "loss": 0.4125,
+      "step": 71
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.4126901350672691,
+      "learning_rate": 7.8576825752397e-05,
+      "loss": 0.4045,
+      "step": 72
+    },
+    {
+      "epoch": 0.9012345679012346,
+      "grad_norm": 0.3718391683194117,
+      "learning_rate": 7.848412079374403e-05,
+      "loss": 0.4099,
+      "step": 73
+    },
+    {
+      "epoch": 0.9135802469135802,
+      "grad_norm": 0.2261943900191593,
+      "learning_rate": 7.838854917730351e-05,
+      "loss": 0.4093,
+      "step": 74
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.302566760403374,
+      "learning_rate": 7.829011802214464e-05,
+      "loss": 0.4095,
+      "step": 75
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.36760200643543206,
+      "learning_rate": 7.818883466034184e-05,
+      "loss": 0.4177,
+      "step": 76
+    },
+    {
+      "epoch": 0.9506172839506173,
+      "grad_norm": 0.27688395344036465,
+      "learning_rate": 7.808470663642856e-05,
+      "loss": 0.4081,
+      "step": 77
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.30935394438459235,
+      "learning_rate": 7.797774170683542e-05,
+      "loss": 0.4037,
+      "step": 78
+    },
+    {
+      "epoch": 0.9753086419753086,
+      "grad_norm": 0.324715968062959,
+      "learning_rate": 7.786794783931225e-05,
+      "loss": 0.4012,
+      "step": 79
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.28468072941202355,
+      "learning_rate": 7.775533321233471e-05,
+      "loss": 0.404,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.31053252672382625,
+      "learning_rate": 7.763990621449507e-05,
+      "loss": 0.404,
+      "step": 81
+    },
+    {
+      "epoch": 1.0123456790123457,
+      "grad_norm": 0.34382181797112316,
+      "learning_rate": 7.752167544387728e-05,
+      "loss": 0.3873,
+      "step": 82
+    },
+    {
+      "epoch": 1.0246913580246915,
+      "grad_norm": 0.3603797149441549,
+      "learning_rate": 7.740064970741661e-05,
+      "loss": 0.3814,
+      "step": 83
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.41152393308462365,
+      "learning_rate": 7.727683802024347e-05,
+      "loss": 0.3883,
+      "step": 84
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.526555038729764,
+      "learning_rate": 7.715024960501209e-05,
+      "loss": 0.3821,
+      "step": 85
+    },
+    {
+      "epoch": 1.0617283950617284,
+      "grad_norm": 0.6132897309361413,
+      "learning_rate": 7.702089389121335e-05,
+      "loss": 0.3883,
+      "step": 86
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.5768252940402074,
+      "learning_rate": 7.688878051447243e-05,
+      "loss": 0.3844,
+      "step": 87
+    },
+    {
+      "epoch": 1.0864197530864197,
+      "grad_norm": 0.49324807323863507,
+      "learning_rate": 7.675391931583109e-05,
+      "loss": 0.3894,
+      "step": 88
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.36966304689615836,
+      "learning_rate": 7.661632034101466e-05,
+      "loss": 0.3868,
+      "step": 89
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.2899882870704448,
+      "learning_rate": 7.64759938396836e-05,
+      "loss": 0.3835,
+      "step": 90
+    },
+    {
+      "epoch": 1.123456790123457,
+      "grad_norm": 0.41018425563529043,
+      "learning_rate": 7.633295026467016e-05,
+      "loss": 0.3771,
+      "step": 91
+    },
+    {
+      "epoch": 1.1358024691358024,
+      "grad_norm": 0.39381709714591767,
+      "learning_rate": 7.618720027119966e-05,
+      "loss": 0.3808,
+      "step": 92
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.30402938826618775,
+      "learning_rate": 7.603875471609677e-05,
+      "loss": 0.3812,
+      "step": 93
+    },
+    {
+      "epoch": 1.1604938271604939,
+      "grad_norm": 0.3296700127757976,
+      "learning_rate": 7.588762465697693e-05,
+      "loss": 0.3839,
+      "step": 94
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.3004783677387976,
+      "learning_rate": 7.573382135142253e-05,
+      "loss": 0.3857,
+      "step": 95
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.29756197424587133,
+      "learning_rate": 7.55773562561444e-05,
+      "loss": 0.3737,
+      "step": 96
+    },
+    {
+      "epoch": 1.1975308641975309,
+      "grad_norm": 0.2963119894104844,
+      "learning_rate": 7.541824102612839e-05,
+      "loss": 0.3816,
+      "step": 97
+    },
+    {
+      "epoch": 1.2098765432098766,
+      "grad_norm": 0.3221272302911747,
+      "learning_rate": 7.525648751376726e-05,
+      "loss": 0.3788,
+      "step": 98
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.3505516006882623,
+      "learning_rate": 7.509210776797768e-05,
+      "loss": 0.381,
+      "step": 99
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.4131467868924798,
+      "learning_rate": 7.492511403330284e-05,
+      "loss": 0.379,
+      "step": 100
+    },
+    {
+      "epoch": 1.2469135802469136,
+      "grad_norm": 0.4994755665018677,
+      "learning_rate": 7.475551874900027e-05,
+      "loss": 0.3795,
+      "step": 101
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.42404205710027576,
+      "learning_rate": 7.458333454811531e-05,
+      "loss": 0.3811,
+      "step": 102
+    },
+    {
+      "epoch": 1.2716049382716048,
+      "grad_norm": 0.371508914950139,
+      "learning_rate": 7.440857425654004e-05,
+      "loss": 0.375,
+      "step": 103
+    },
+    {
+      "epoch": 1.2839506172839505,
+      "grad_norm": 0.3289815043177092,
+      "learning_rate": 7.42312508920579e-05,
+      "loss": 0.3754,
+      "step": 104
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.267787451991178,
+      "learning_rate": 7.405137766337406e-05,
+      "loss": 0.3811,
+      "step": 105
+    },
+    {
+      "epoch": 1.308641975308642,
+      "grad_norm": 0.3148567202371999,
+      "learning_rate": 7.386896796913137e-05,
+      "loss": 0.3805,
+      "step": 106
+    },
+    {
+      "epoch": 1.3209876543209877,
+      "grad_norm": 0.3024182886172311,
+      "learning_rate": 7.368403539691247e-05,
+      "loss": 0.3785,
+      "step": 107
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.2611655169990854,
+      "learning_rate": 7.349659372222755e-05,
+      "loss": 0.3751,
+      "step": 108
+    },
+    {
+      "epoch": 1.345679012345679,
+      "grad_norm": 0.227199795047311,
+      "learning_rate": 7.330665690748825e-05,
+      "loss": 0.3815,
+      "step": 109
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.24032579689583877,
+      "learning_rate": 7.311423910096764e-05,
+      "loss": 0.3779,
+      "step": 110
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.23305281609551937,
+      "learning_rate": 7.291935463574626e-05,
+      "loss": 0.3738,
+      "step": 111
+    },
+    {
+      "epoch": 1.382716049382716,
+      "grad_norm": 0.2238048785936102,
+      "learning_rate": 7.272201802864452e-05,
+      "loss": 0.3764,
+      "step": 112
+    },
+    {
+      "epoch": 1.3950617283950617,
+      "grad_norm": 0.22235447537632988,
+      "learning_rate": 7.25222439791413e-05,
+      "loss": 0.3777,
+      "step": 113
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.24285179141339513,
+      "learning_rate": 7.232004736827907e-05,
+      "loss": 0.3857,
+      "step": 114
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.35028383740615804,
+      "learning_rate": 7.21154432575553e-05,
+      "loss": 0.3786,
+      "step": 115
+    },
+    {
+      "epoch": 1.4320987654320987,
+      "grad_norm": 0.5011913441877963,
+      "learning_rate": 7.190844688780065e-05,
+      "loss": 0.3796,
+      "step": 116
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.7234012591025516,
+      "learning_rate": 7.169907367804363e-05,
+      "loss": 0.3872,
+      "step": 117
+    },
+    {
+      "epoch": 1.4567901234567902,
+      "grad_norm": 0.8736773825961814,
+      "learning_rate": 7.148733922436201e-05,
+      "loss": 0.3877,
+      "step": 118
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "grad_norm": 0.647652343475919,
+      "learning_rate": 7.12732592987212e-05,
+      "loss": 0.3841,
+      "step": 119
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.44259716517269754,
+      "learning_rate": 7.105684984779928e-05,
+      "loss": 0.3774,
+      "step": 120
+    },
+    {
+      "epoch": 1.4938271604938271,
+      "grad_norm": 0.6375380239448176,
+      "learning_rate": 7.083812699179919e-05,
+      "loss": 0.3833,
+      "step": 121
+    },
+    {
+      "epoch": 1.5061728395061729,
+      "grad_norm": 0.4446422701768727,
+      "learning_rate": 7.061710702324799e-05,
+      "loss": 0.384,
+      "step": 122
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.5377629836537741,
+      "learning_rate": 7.039380640578316e-05,
+      "loss": 0.3798,
+      "step": 123
+    },
+    {
+      "epoch": 1.5308641975308643,
+      "grad_norm": 0.39911966953844114,
+      "learning_rate": 7.016824177292629e-05,
+      "loss": 0.3815,
+      "step": 124
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.47614759620805847,
+      "learning_rate": 6.994042992684406e-05,
+      "loss": 0.3751,
+      "step": 125
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.3902881801554934,
+      "learning_rate": 6.971038783709658e-05,
+      "loss": 0.3822,
+      "step": 126
+    },
+    {
+      "epoch": 1.567901234567901,
+      "grad_norm": 0.3950707973102776,
+      "learning_rate": 6.947813263937347e-05,
+      "loss": 0.3909,
+      "step": 127
+    },
+    {
+      "epoch": 1.5802469135802468,
+      "grad_norm": 0.39065242782769266,
+      "learning_rate": 6.924368163421733e-05,
+      "loss": 0.3776,
+      "step": 128
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.3845188280321808,
+      "learning_rate": 6.900705228573507e-05,
+      "loss": 0.3818,
+      "step": 129
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.3666651030223992,
+      "learning_rate": 6.876826222029699e-05,
+      "loss": 0.3814,
+      "step": 130
+    },
+    {
+      "epoch": 1.617283950617284,
+      "grad_norm": 0.3977610094713467,
+      "learning_rate": 6.852732922522385e-05,
+      "loss": 0.3773,
+      "step": 131
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.35768048059685736,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.3819,
+      "step": 132
+    },
+    {
+      "epoch": 1.6419753086419753,
+      "grad_norm": 0.4156966736319398,
+      "learning_rate": 6.803910639224598e-05,
+      "loss": 0.3785,
+      "step": 133
+    },
+    {
+      "epoch": 1.654320987654321,
+      "grad_norm": 0.4383124623240888,
+      "learning_rate": 6.77918529217509e-05,
+      "loss": 0.3794,
+      "step": 134
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2662806997278085,
+      "learning_rate": 6.754252925373109e-05,
+      "loss": 0.3703,
+      "step": 135
+    },
+    {
+      "epoch": 1.6790123456790123,
+      "grad_norm": 0.4520625145932699,
+      "learning_rate": 6.729115396014871e-05,
+      "loss": 0.3719,
+      "step": 136
+    },
+    {
+      "epoch": 1.691358024691358,
+      "grad_norm": 0.2070090676920595,
+      "learning_rate": 6.703774576579018e-05,
+      "loss": 0.3775,
+      "step": 137
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.3239752000666446,
+      "learning_rate": 6.678232354687144e-05,
+      "loss": 0.3776,
+      "step": 138
+    },
+    {
+      "epoch": 1.7160493827160495,
+      "grad_norm": 0.21453923956199625,
+      "learning_rate": 6.652490632963182e-05,
+      "loss": 0.372,
+      "step": 139
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.28425061897851517,
+      "learning_rate": 6.626551328891681e-05,
+      "loss": 0.3731,
+      "step": 140
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.20289767375505124,
+      "learning_rate": 6.600416374674978e-05,
+      "loss": 0.3754,
+      "step": 141
+    },
+    {
+      "epoch": 1.7530864197530864,
+      "grad_norm": 0.2941601676983556,
+      "learning_rate": 6.57408771708926e-05,
+      "loss": 0.3753,
+      "step": 142
+    },
+    {
+      "epoch": 1.765432098765432,
+      "grad_norm": 0.2531605241778047,
+      "learning_rate": 6.547567317339557e-05,
+      "loss": 0.3729,
+      "step": 143
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.24030402783919833,
+      "learning_rate": 6.520857150913655e-05,
+      "loss": 0.3788,
+      "step": 144
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.2257077979823743,
+      "learning_rate": 6.493959207434934e-05,
+      "loss": 0.3727,
+      "step": 145
+    },
+    {
+      "epoch": 1.8024691358024691,
+      "grad_norm": 0.19399386160203091,
+      "learning_rate": 6.466875490514173e-05,
+      "loss": 0.376,
+      "step": 146
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 0.16682730893329648,
+      "learning_rate": 6.439608017600292e-05,
+      "loss": 0.3696,
+      "step": 147
+    },
+    {
+      "epoch": 1.8271604938271606,
+      "grad_norm": 0.19271882851675304,
+      "learning_rate": 6.412158819830082e-05,
+      "loss": 0.3707,
+      "step": 148
+    },
+    {
+      "epoch": 1.8395061728395061,
+      "grad_norm": 0.17669418563092693,
+      "learning_rate": 6.384529941876902e-05,
+      "loss": 0.3762,
+      "step": 149
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.1925875289442905,
+      "learning_rate": 6.356723441798375e-05,
+      "loss": 0.3676,
+      "step": 150
+    },
+    {
+      "epoch": 1.8641975308641974,
+      "grad_norm": 0.1408862149542848,
+      "learning_rate": 6.328741390883084e-05,
+      "loss": 0.3687,
+      "step": 151
+    },
+    {
+      "epoch": 1.876543209876543,
+      "grad_norm": 0.14546720452245734,
+      "learning_rate": 6.300585873496279e-05,
+      "loss": 0.3752,
+      "step": 152
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.13890661536975604,
+      "learning_rate": 6.272258986924624e-05,
+      "loss": 0.3683,
+      "step": 153
+    },
+    {
+      "epoch": 1.9012345679012346,
+      "grad_norm": 0.1467003606071226,
+      "learning_rate": 6.243762841219958e-05,
+      "loss": 0.3734,
+      "step": 154
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.12949834841576283,
+      "learning_rate": 6.215099559042132e-05,
+      "loss": 0.3763,
+      "step": 155
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.15998910215440382,
+      "learning_rate": 6.186271275500885e-05,
+      "loss": 0.3762,
+      "step": 156
+    },
+    {
+      "epoch": 1.9382716049382716,
+      "grad_norm": 0.15419137375229935,
+      "learning_rate": 6.157280137996797e-05,
+      "loss": 0.3802,
+      "step": 157
+    },
+    {
+      "epoch": 1.9506172839506173,
+      "grad_norm": 0.15401839913036416,
+      "learning_rate": 6.128128306061347e-05,
+      "loss": 0.3727,
+      "step": 158
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.1591328932264097,
+      "learning_rate": 6.098817951196032e-05,
+      "loss": 0.375,
+      "step": 159
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.16611360643777526,
+      "learning_rate": 6.0693512567106275e-05,
+      "loss": 0.3725,
+      "step": 160
+    },
+    {
+      "epoch": 1.9876543209876543,
+      "grad_norm": 0.12833523499381977,
+      "learning_rate": 6.0397304175605444e-05,
+      "loss": 0.3732,
+      "step": 161
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.14903958253361047,
+      "learning_rate": 6.009957640183333e-05,
+      "loss": 0.3656,
+      "step": 162
+    },
+    {
+      "epoch": 2.0123456790123457,
+      "grad_norm": 0.18181721170148502,
+      "learning_rate": 5.980035142334326e-05,
+      "loss": 0.3415,
+      "step": 163
+    },
+    {
+      "epoch": 2.0246913580246915,
+      "grad_norm": 0.2423707518127179,
+      "learning_rate": 5.94996515292144e-05,
+      "loss": 0.3457,
+      "step": 164
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.28805844834958094,
+      "learning_rate": 5.919749911839146e-05,
+      "loss": 0.3439,
+      "step": 165
+    },
+    {
+      "epoch": 2.049382716049383,
+      "grad_norm": 0.338041968881525,
+      "learning_rate": 5.8893916698016154e-05,
+      "loss": 0.3473,
+      "step": 166
+    },
+    {
+      "epoch": 2.0617283950617282,
+      "grad_norm": 0.3702979968407714,
+      "learning_rate": 5.858892688175075e-05,
+      "loss": 0.3447,
+      "step": 167
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.4121949019126149,
+      "learning_rate": 5.828255238809352e-05,
+      "loss": 0.3512,
+      "step": 168
+    },
+    {
+      "epoch": 2.0864197530864197,
+      "grad_norm": 0.45776885604634626,
+      "learning_rate": 5.797481603868646e-05,
+      "loss": 0.3508,
+      "step": 169
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.3430185376275583,
+      "learning_rate": 5.766574075661538e-05,
+      "loss": 0.3469,
+      "step": 170
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.22264426177393448,
+      "learning_rate": 5.735534956470233e-05,
+      "loss": 0.3422,
+      "step": 171
+    },
+    {
+      "epoch": 2.123456790123457,
+      "grad_norm": 0.3217552555364519,
+      "learning_rate": 5.7043665583790627e-05,
+      "loss": 0.345,
+      "step": 172
+    },
+    {
+      "epoch": 2.1358024691358026,
+      "grad_norm": 0.38877231245171023,
+      "learning_rate": 5.673071203102261e-05,
+      "loss": 0.341,
+      "step": 173
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.3123168778869936,
+      "learning_rate": 5.641651221811028e-05,
+      "loss": 0.3463,
+      "step": 174
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.20501267062539852,
+      "learning_rate": 5.6101089549598704e-05,
+      "loss": 0.3417,
+      "step": 175
+    },
+    {
+      "epoch": 2.1728395061728394,
+      "grad_norm": 0.28330486285341644,
+      "learning_rate": 5.578446752112273e-05,
+      "loss": 0.3414,
+      "step": 176
+    },
+    {
+      "epoch": 2.185185185185185,
+      "grad_norm": 0.32274136835662276,
+      "learning_rate": 5.546666971765675e-05,
+      "loss": 0.3431,
+      "step": 177
+    },
+    {
+      "epoch": 2.197530864197531,
+      "grad_norm": 0.25213392309250476,
+      "learning_rate": 5.5147719811757914e-05,
+      "loss": 0.3428,
+      "step": 178
+    },
+    {
+      "epoch": 2.2098765432098766,
+      "grad_norm": 0.24516118069133921,
+      "learning_rate": 5.4827641561802716e-05,
+      "loss": 0.3442,
+      "step": 179
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.2979271066921269,
+      "learning_rate": 5.4506458810217286e-05,
+      "loss": 0.3489,
+      "step": 180
+    },
+    {
+      "epoch": 2.234567901234568,
+      "grad_norm": 0.22402128672002253,
+      "learning_rate": 5.4184195481701425e-05,
+      "loss": 0.3395,
+      "step": 181
+    },
+    {
+      "epoch": 2.246913580246914,
+      "grad_norm": 0.22724740290770673,
+      "learning_rate": 5.38608755814464e-05,
+      "loss": 0.341,
+      "step": 182
+    },
+    {
+      "epoch": 2.259259259259259,
+      "grad_norm": 0.24878280226655755,
+      "learning_rate": 5.353652319334682e-05,
+      "loss": 0.3437,
+      "step": 183
+    },
+    {
+      "epoch": 2.271604938271605,
+      "grad_norm": 0.22863573984816668,
+      "learning_rate": 5.321116247820669e-05,
+      "loss": 0.3495,
+      "step": 184
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.22727359773726635,
+      "learning_rate": 5.288481767193963e-05,
+      "loss": 0.3408,
+      "step": 185
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.22274370262509133,
+      "learning_rate": 5.2557513083763605e-05,
+      "loss": 0.3506,
+      "step": 186
+    },
+    {
+      "epoch": 2.308641975308642,
+      "grad_norm": 0.2025663838014498,
+      "learning_rate": 5.2229273094390124e-05,
+      "loss": 0.3369,
+      "step": 187
+    },
+    {
+      "epoch": 2.3209876543209877,
+      "grad_norm": 0.16546511202510056,
+      "learning_rate": 5.190012215420812e-05,
+      "loss": 0.3377,
+      "step": 188
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.21647345354334316,
+      "learning_rate": 5.1570084781462716e-05,
+      "loss": 0.3426,
+      "step": 189
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.2034697235358243,
+      "learning_rate": 5.123918556042878e-05,
+      "loss": 0.3409,
+      "step": 190
+    },
+    {
+      "epoch": 2.3580246913580245,
+      "grad_norm": 0.163754934265929,
+      "learning_rate": 5.0907449139579755e-05,
+      "loss": 0.3476,
+      "step": 191
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.22046531921346055,
+      "learning_rate": 5.057490022975156e-05,
+      "loss": 0.3469,
+      "step": 192
+    },
+    {
+      "epoch": 2.382716049382716,
+      "grad_norm": 0.15716283519185711,
+      "learning_rate": 5.024156360230189e-05,
+      "loss": 0.3482,
+      "step": 193
+    },
+    {
+      "epoch": 2.3950617283950617,
+      "grad_norm": 0.15090786156455027,
+      "learning_rate": 4.9907464087265045e-05,
+      "loss": 0.3449,
+      "step": 194
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.19096227798652976,
+      "learning_rate": 4.9572626571502316e-05,
+      "loss": 0.3508,
+      "step": 195
+    },
+    {
+      "epoch": 2.419753086419753,
+      "grad_norm": 0.15474696831726198,
+      "learning_rate": 4.9237075996848235e-05,
+      "loss": 0.3421,
+      "step": 196
+    },
+    {
+      "epoch": 2.432098765432099,
+      "grad_norm": 0.16453226815038777,
+      "learning_rate": 4.890083735825258e-05,
+      "loss": 0.3432,
+      "step": 197
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.16148345062693617,
+      "learning_rate": 4.8563935701918646e-05,
+      "loss": 0.3421,
+      "step": 198
+    },
+    {
+      "epoch": 2.45679012345679,
+      "grad_norm": 0.15169952631015304,
+      "learning_rate": 4.8226396123437466e-05,
+      "loss": 0.344,
+      "step": 199
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.17716383254585324,
+      "learning_rate": 4.788824376591849e-05,
+      "loss": 0.3364,
+      "step": 200
+    },
+    {
+      "epoch": 2.4814814814814814,
+      "grad_norm": 0.16454308719566607,
+      "learning_rate": 4.754950381811667e-05,
+      "loss": 0.3497,
+      "step": 201
+    },
+    {
+      "epoch": 2.493827160493827,
+      "grad_norm": 0.1371523158400062,
+      "learning_rate": 4.721020151255624e-05,
+      "loss": 0.3415,
+      "step": 202
+    },
+    {
+      "epoch": 2.506172839506173,
+      "grad_norm": 0.16398706421546627,
+      "learning_rate": 4.6870362123651056e-05,
+      "loss": 0.3377,
+      "step": 203
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.1192805903348546,
+      "learning_rate": 4.6530010965821984e-05,
+      "loss": 0.3357,
+      "step": 204
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.12674994582592325,
+      "learning_rate": 4.618917339161125e-05,
+      "loss": 0.3391,
+      "step": 205
+    },
+    {
+      "epoch": 2.5432098765432096,
+      "grad_norm": 0.13417868147022113,
+      "learning_rate": 4.584787478979394e-05,
+      "loss": 0.3422,
+      "step": 206
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.11770941337583052,
+      "learning_rate": 4.550614058348674e-05,
+      "loss": 0.3361,
+      "step": 207
+    },
+    {
+      "epoch": 2.567901234567901,
+      "grad_norm": 0.12502193046755677,
+      "learning_rate": 4.516399622825428e-05,
+      "loss": 0.3428,
+      "step": 208
+    },
+    {
+      "epoch": 2.580246913580247,
+      "grad_norm": 0.1252094791466198,
+      "learning_rate": 4.4821467210212924e-05,
+      "loss": 0.3406,
+      "step": 209
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.14201504969341056,
+      "learning_rate": 4.4478579044132314e-05,
+      "loss": 0.3402,
+      "step": 210
+    },
+    {
+      "epoch": 2.6049382716049383,
+      "grad_norm": 0.10401512308427016,
+      "learning_rate": 4.41353572715348e-05,
+      "loss": 0.3485,
+      "step": 211
+    },
+    {
+      "epoch": 2.617283950617284,
+      "grad_norm": 0.109741465703448,
+      "learning_rate": 4.379182745879289e-05,
+      "loss": 0.3417,
+      "step": 212
+    },
+    {
+      "epoch": 2.6296296296296298,
+      "grad_norm": 0.10920450482797511,
+      "learning_rate": 4.344801519522478e-05,
+      "loss": 0.3396,
+      "step": 213
+    },
+    {
+      "epoch": 2.6419753086419755,
+      "grad_norm": 0.10983132997933204,
+      "learning_rate": 4.310394609118826e-05,
+      "loss": 0.351,
+      "step": 214
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.10480987516458594,
+      "learning_rate": 4.2759645776172996e-05,
+      "loss": 0.3478,
+      "step": 215
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.10510713775685178,
+      "learning_rate": 4.241513989689145e-05,
+      "loss": 0.3429,
+      "step": 216
+    },
+    {
+      "epoch": 2.6790123456790123,
+      "grad_norm": 0.10799679683280532,
+      "learning_rate": 4.2070454115368385e-05,
+      "loss": 0.3392,
+      "step": 217
+    },
+    {
+      "epoch": 2.691358024691358,
+      "grad_norm": 0.10761700962826581,
+      "learning_rate": 4.1725614107029387e-05,
+      "loss": 0.342,
+      "step": 218
+    },
+    {
+      "epoch": 2.7037037037037037,
+      "grad_norm": 0.11160386327206023,
+      "learning_rate": 4.138064555878833e-05,
+      "loss": 0.3401,
+      "step": 219
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.08955846422356055,
+      "learning_rate": 4.1035574167133905e-05,
+      "loss": 0.3432,
+      "step": 220
+    },
+    {
+      "epoch": 2.728395061728395,
+      "grad_norm": 0.10069141576333207,
+      "learning_rate": 4.069042563621555e-05,
+      "loss": 0.3482,
+      "step": 221
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.1013563575882113,
+      "learning_rate": 4.034522567592876e-05,
+      "loss": 0.348,
+      "step": 222
+    },
+    {
+      "epoch": 2.753086419753086,
+      "grad_norm": 0.08374836578591716,
+      "learning_rate": 4e-05,
+      "loss": 0.3394,
+      "step": 223
+    },
+    {
+      "epoch": 2.765432098765432,
+      "grad_norm": 0.11355478685898833,
+      "learning_rate": 3.965477432407125e-05,
+      "loss": 0.3445,
+      "step": 224
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.09624818214040735,
+      "learning_rate": 3.9309574363784465e-05,
+      "loss": 0.3397,
+      "step": 225
+    },
+    {
+      "epoch": 2.7901234567901234,
+      "grad_norm": 0.10745228303359741,
+      "learning_rate": 3.8964425832866115e-05,
+      "loss": 0.3406,
+      "step": 226
+    },
+    {
+      "epoch": 2.802469135802469,
+      "grad_norm": 0.10944141418443391,
+      "learning_rate": 3.861935444121169e-05,
+      "loss": 0.3449,
+      "step": 227
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.09476918334115324,
+      "learning_rate": 3.827438589297062e-05,
+      "loss": 0.342,
+      "step": 228
+    },
+    {
+      "epoch": 2.8271604938271606,
+      "grad_norm": 0.10273438061210496,
+      "learning_rate": 3.792954588463162e-05,
+      "loss": 0.3361,
+      "step": 229
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.11607415931602874,
+      "learning_rate": 3.758486010310856e-05,
+      "loss": 0.3452,
+      "step": 230
+    },
+    {
+      "epoch": 2.851851851851852,
+      "grad_norm": 0.09907111449232464,
+      "learning_rate": 3.7240354223827004e-05,
+      "loss": 0.3366,
+      "step": 231
+    },
+    {
+      "epoch": 2.8641975308641974,
+      "grad_norm": 0.10759891603562133,
+      "learning_rate": 3.6896053908811755e-05,
+      "loss": 0.3421,
+      "step": 232
+    },
+    {
+      "epoch": 2.876543209876543,
+      "grad_norm": 0.11265861580398358,
+      "learning_rate": 3.655198480477523e-05,
+      "loss": 0.3385,
+      "step": 233
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.08786520347014656,
+      "learning_rate": 3.6208172541207114e-05,
+      "loss": 0.3439,
+      "step": 234
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.10356235192852613,
+      "learning_rate": 3.5864642728465205e-05,
+      "loss": 0.344,
+      "step": 235
+    },
+    {
+      "epoch": 2.9135802469135803,
+      "grad_norm": 0.08646764717063034,
+      "learning_rate": 3.552142095586769e-05,
+      "loss": 0.3372,
+      "step": 236
+    },
+    {
+      "epoch": 2.925925925925926,
+      "grad_norm": 0.08728680364650734,
+      "learning_rate": 3.517853278978708e-05,
+      "loss": 0.3442,
+      "step": 237
+    },
+    {
+      "epoch": 2.9382716049382713,
+      "grad_norm": 0.08641508464694472,
+      "learning_rate": 3.4836003771745736e-05,
+      "loss": 0.347,
+      "step": 238
+    },
+    {
+      "epoch": 2.950617283950617,
+      "grad_norm": 0.08026941583492263,
+      "learning_rate": 3.449385941651328e-05,
+      "loss": 0.344,
+      "step": 239
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.07970349647437662,
+      "learning_rate": 3.415212521020609e-05,
+      "loss": 0.3421,
+      "step": 240
+    },
+    {
+      "epoch": 2.9753086419753085,
+      "grad_norm": 0.08418686616391638,
+      "learning_rate": 3.381082660838875e-05,
+      "loss": 0.341,
+      "step": 241
+    },
+    {
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.08406309903078657,
+      "learning_rate": 3.346998903417803e-05,
+      "loss": 0.3379,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10584099386673017,
+      "learning_rate": 3.312963787634896e-05,
+      "loss": 0.3255,
+      "step": 243
+    },
+    {
+      "epoch": 3.0123456790123457,
+      "grad_norm": 0.11668930835793952,
+      "learning_rate": 3.2789798487443775e-05,
+      "loss": 0.3131,
+      "step": 244
+    },
+    {
+      "epoch": 3.0246913580246915,
+      "grad_norm": 0.1669388515245804,
+      "learning_rate": 3.245049618188334e-05,
+      "loss": 0.3174,
+      "step": 245
+    },
+    {
+      "epoch": 3.037037037037037,
+      "grad_norm": 0.18369659931677468,
+      "learning_rate": 3.2111756234081525e-05,
+      "loss": 0.3156,
+      "step": 246
+    },
+    {
+      "epoch": 3.049382716049383,
+      "grad_norm": 0.13629944699104346,
+      "learning_rate": 3.177360387656254e-05,
+      "loss": 0.3165,
+      "step": 247
+    },
+    {
+      "epoch": 3.0617283950617282,
+      "grad_norm": 0.17142135547324663,
+      "learning_rate": 3.143606429808136e-05,
+      "loss": 0.3166,
+      "step": 248
+    },
+    {
+      "epoch": 3.074074074074074,
+      "grad_norm": 0.15149427007225624,
+      "learning_rate": 3.109916264174743e-05,
+      "loss": 0.3176,
+      "step": 249
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 0.15396745309510165,
+      "learning_rate": 3.076292400315179e-05,
+      "loss": 0.3194,
+      "step": 250
+    },
+    {
+      "epoch": 3.0987654320987654,
+      "grad_norm": 0.1504374833609666,
+      "learning_rate": 3.0427373428497704e-05,
+      "loss": 0.3153,
+      "step": 251
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 0.1447891435817236,
+      "learning_rate": 3.0092535912734965e-05,
+      "loss": 0.3137,
+      "step": 252
+    },
+    {
+      "epoch": 3.123456790123457,
+      "grad_norm": 0.1240945569621049,
+      "learning_rate": 2.9758436397698118e-05,
+      "loss": 0.3132,
+      "step": 253
+    },
+    {
+      "epoch": 3.1358024691358026,
+      "grad_norm": 0.14110355949415496,
+      "learning_rate": 2.9425099770248446e-05,
+      "loss": 0.3183,
+      "step": 254
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.1159630707653213,
+      "learning_rate": 2.9092550860420252e-05,
+      "loss": 0.3108,
+      "step": 255
+    },
+    {
+      "epoch": 3.1604938271604937,
+      "grad_norm": 0.13700102924862842,
+      "learning_rate": 2.8760814439571233e-05,
+      "loss": 0.316,
+      "step": 256
+    },
+    {
+      "epoch": 3.1728395061728394,
+      "grad_norm": 0.13265375633512722,
+      "learning_rate": 2.8429915218537297e-05,
+      "loss": 0.3149,
+      "step": 257
+    },
+    {
+      "epoch": 3.185185185185185,
+      "grad_norm": 0.11236640820635488,
+      "learning_rate": 2.809987784579189e-05,
+      "loss": 0.309,
+      "step": 258
+    },
+    {
+      "epoch": 3.197530864197531,
+      "grad_norm": 0.12315582646249258,
+      "learning_rate": 2.7770726905609896e-05,
+      "loss": 0.3104,
+      "step": 259
+    },
+    {
+      "epoch": 3.2098765432098766,
+      "grad_norm": 0.11157133087921481,
+      "learning_rate": 2.74424869162364e-05,
+      "loss": 0.3055,
+      "step": 260
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.11197743979607111,
+      "learning_rate": 2.7115182328060385e-05,
+      "loss": 0.315,
+      "step": 261
+    },
+    {
+      "epoch": 3.234567901234568,
+      "grad_norm": 0.10682756116310503,
+      "learning_rate": 2.678883752179333e-05,
+      "loss": 0.31,
+      "step": 262
+    },
+    {
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.11399631314683994,
+      "learning_rate": 2.6463476806653185e-05,
+      "loss": 0.3067,
+      "step": 263
+    },
+    {
+      "epoch": 3.259259259259259,
+      "grad_norm": 0.1094411958729708,
+      "learning_rate": 2.61391244185536e-05,
+      "loss": 0.3086,
+      "step": 264
+    },
+    {
+      "epoch": 3.271604938271605,
+      "grad_norm": 0.1116792255496454,
+      "learning_rate": 2.5815804518298575e-05,
+      "loss": 0.3152,
+      "step": 265
+    },
+    {
+      "epoch": 3.2839506172839505,
+      "grad_norm": 0.1015555941802624,
+      "learning_rate": 2.549354118978272e-05,
+      "loss": 0.315,
+      "step": 266
+    },
+    {
+      "epoch": 3.2962962962962963,
+      "grad_norm": 0.1021182964174851,
+      "learning_rate": 2.51723584381973e-05,
+      "loss": 0.3085,
+      "step": 267
+    },
+    {
+      "epoch": 3.308641975308642,
+      "grad_norm": 0.09147707821939131,
+      "learning_rate": 2.4852280188242096e-05,
+      "loss": 0.3147,
+      "step": 268
+    },
+    {
+      "epoch": 3.3209876543209877,
+      "grad_norm": 0.09480770266216229,
+      "learning_rate": 2.453333028234325e-05,
+      "loss": 0.3124,
+      "step": 269
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.08987330341410524,
+      "learning_rate": 2.4215532478877283e-05,
+      "loss": 0.308,
+      "step": 270
+    },
+    {
+      "epoch": 3.3456790123456788,
+      "grad_norm": 0.09222775174353676,
+      "learning_rate": 2.3898910450401306e-05,
+      "loss": 0.3143,
+      "step": 271
+    },
+    {
+      "epoch": 3.3580246913580245,
+      "grad_norm": 0.10164501511096202,
+      "learning_rate": 2.3583487781889737e-05,
+      "loss": 0.317,
+      "step": 272
+    },
+    {
+      "epoch": 3.3703703703703702,
+      "grad_norm": 0.08550554614390403,
+      "learning_rate": 2.3269287968977406e-05,
+      "loss": 0.3108,
+      "step": 273
+    },
+    {
+      "epoch": 3.382716049382716,
+      "grad_norm": 0.09689757113186731,
+      "learning_rate": 2.2956334416209404e-05,
+      "loss": 0.3197,
+      "step": 274
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 0.08249938204150917,
+      "learning_rate": 2.264465043529768e-05,
+      "loss": 0.3096,
+      "step": 275
+    },
+    {
+      "epoch": 3.4074074074074074,
+      "grad_norm": 0.09810559172282965,
+      "learning_rate": 2.233425924338463e-05,
+      "loss": 0.3111,
+      "step": 276
+    },
+    {
+      "epoch": 3.419753086419753,
+      "grad_norm": 0.07443521516241665,
+      "learning_rate": 2.2025183961313542e-05,
+      "loss": 0.315,
+      "step": 277
+    },
+    {
+      "epoch": 3.432098765432099,
+      "grad_norm": 0.08895358180851759,
+      "learning_rate": 2.1717447611906496e-05,
+      "loss": 0.3128,
+      "step": 278
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.0723164660244269,
+      "learning_rate": 2.141107311824926e-05,
+      "loss": 0.3156,
+      "step": 279
+    },
+    {
+      "epoch": 3.45679012345679,
+      "grad_norm": 0.08324855026015407,
+      "learning_rate": 2.1106083301983852e-05,
+      "loss": 0.3095,
+      "step": 280
+    },
+    {
+      "epoch": 3.4691358024691357,
+      "grad_norm": 0.08211120229034059,
+      "learning_rate": 2.0802500881608557e-05,
+      "loss": 0.3184,
+      "step": 281
+    },
+    {
+      "epoch": 3.4814814814814814,
+      "grad_norm": 0.07867376241345962,
+      "learning_rate": 2.0500348470785614e-05,
+      "loss": 0.3161,
+      "step": 282
+    },
+    {
+      "epoch": 3.493827160493827,
+      "grad_norm": 0.08703763648921135,
+      "learning_rate": 2.0199648576656744e-05,
+      "loss": 0.3106,
+      "step": 283
+    },
+    {
+      "epoch": 3.506172839506173,
+      "grad_norm": 0.08128658381823438,
+      "learning_rate": 1.9900423598166685e-05,
+      "loss": 0.3126,
+      "step": 284
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.07190025711087338,
+      "learning_rate": 1.9602695824394576e-05,
+      "loss": 0.3119,
+      "step": 285
+    },
+    {
+      "epoch": 3.5308641975308643,
+      "grad_norm": 0.07811310190032812,
+      "learning_rate": 1.9306487432893725e-05,
+      "loss": 0.3129,
+      "step": 286
+    },
+    {
+      "epoch": 3.5432098765432096,
+      "grad_norm": 0.0821659921480485,
+      "learning_rate": 1.901182048803968e-05,
+      "loss": 0.3121,
+      "step": 287
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.07295261076429908,
+      "learning_rate": 1.8718716939386543e-05,
+      "loss": 0.3169,
+      "step": 288
+    },
+    {
+      "epoch": 3.567901234567901,
+      "grad_norm": 0.07696770378293614,
+      "learning_rate": 1.8427198620032037e-05,
+      "loss": 0.3134,
+      "step": 289
+    },
+    {
+      "epoch": 3.580246913580247,
+      "grad_norm": 0.08046401496743873,
+      "learning_rate": 1.8137287244991162e-05,
+      "loss": 0.3169,
+      "step": 290
+    },
+    {
+      "epoch": 3.5925925925925926,
+      "grad_norm": 0.0703214404667131,
+      "learning_rate": 1.7849004409578678e-05,
+      "loss": 0.3164,
+      "step": 291
+    },
+    {
+      "epoch": 3.6049382716049383,
+      "grad_norm": 0.08453860273391918,
+      "learning_rate": 1.7562371587800422e-05,
+      "loss": 0.3103,
+      "step": 292
+    },
+    {
+      "epoch": 3.617283950617284,
+      "grad_norm": 0.07396275334428812,
+      "learning_rate": 1.7277410130753775e-05,
+      "loss": 0.3172,
+      "step": 293
+    },
+    {
+      "epoch": 3.6296296296296298,
+      "grad_norm": 0.07182941981821332,
+      "learning_rate": 1.6994141265037222e-05,
+      "loss": 0.3074,
+      "step": 294
+    },
+    {
+      "epoch": 3.6419753086419755,
+      "grad_norm": 0.07171764168131682,
+      "learning_rate": 1.6712586091169183e-05,
+      "loss": 0.3167,
+      "step": 295
+    },
+    {
+      "epoch": 3.6543209876543212,
+      "grad_norm": 0.07648822160728858,
+      "learning_rate": 1.6432765582016257e-05,
+      "loss": 0.3103,
+      "step": 296
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.06883670504886352,
+      "learning_rate": 1.615470058123099e-05,
+      "loss": 0.3156,
+      "step": 297
+    },
+    {
+      "epoch": 3.6790123456790123,
+      "grad_norm": 0.0755381972249872,
+      "learning_rate": 1.5878411801699182e-05,
+      "loss": 0.3141,
+      "step": 298
+    },
+    {
+      "epoch": 3.691358024691358,
+      "grad_norm": 0.07809497050574539,
+      "learning_rate": 1.5603919823997083e-05,
+      "loss": 0.3188,
+      "step": 299
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.07202964272659307,
+      "learning_rate": 1.5331245094858277e-05,
+      "loss": 0.3105,
+      "step": 300
+    },
+    {
+      "epoch": 3.7160493827160495,
+      "grad_norm": 0.07302156601924886,
+      "learning_rate": 1.5060407925650662e-05,
+      "loss": 0.3111,
+      "step": 301
+    },
+    {
+      "epoch": 3.728395061728395,
+      "grad_norm": 0.06617657477839962,
+      "learning_rate": 1.4791428490863462e-05,
+      "loss": 0.3117,
+      "step": 302
+    },
+    {
+      "epoch": 3.7407407407407405,
+      "grad_norm": 0.06562020275625721,
+      "learning_rate": 1.4524326826604442e-05,
+      "loss": 0.3128,
+      "step": 303
+    },
+    {
+      "epoch": 3.753086419753086,
+      "grad_norm": 0.07392186219428895,
+      "learning_rate": 1.425912282910741e-05,
+      "loss": 0.3087,
+      "step": 304
+    },
+    {
+      "epoch": 3.765432098765432,
+      "grad_norm": 0.0686839130861847,
+      "learning_rate": 1.3995836253250233e-05,
+      "loss": 0.3105,
+      "step": 305
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 0.06439567039390182,
+      "learning_rate": 1.3734486711083199e-05,
+      "loss": 0.313,
+      "step": 306
+    },
+    {
+      "epoch": 3.7901234567901234,
+      "grad_norm": 0.06797256136784066,
+      "learning_rate": 1.3475093670368202e-05,
+      "loss": 0.3103,
+      "step": 307
+    },
+    {
+      "epoch": 3.802469135802469,
+      "grad_norm": 0.0689077346771484,
+      "learning_rate": 1.3217676453128583e-05,
+      "loss": 0.315,
+      "step": 308
+    },
+    {
+      "epoch": 3.814814814814815,
+      "grad_norm": 0.07471804083765593,
+      "learning_rate": 1.2962254234209826e-05,
+      "loss": 0.3172,
+      "step": 309
+    },
+    {
+      "epoch": 3.8271604938271606,
+      "grad_norm": 0.06692556046893039,
+      "learning_rate": 1.2708846039851306e-05,
+      "loss": 0.3082,
+      "step": 310
+    },
+    {
+      "epoch": 3.8395061728395063,
+      "grad_norm": 0.06464047114296656,
+      "learning_rate": 1.2457470746268912e-05,
+      "loss": 0.308,
+      "step": 311
+    },
+    {
+      "epoch": 3.851851851851852,
+      "grad_norm": 0.06835815828286365,
+      "learning_rate": 1.2208147078249106e-05,
+      "loss": 0.3165,
+      "step": 312
+    },
+    {
+      "epoch": 3.8641975308641974,
+      "grad_norm": 0.06949252295767612,
+      "learning_rate": 1.1960893607754022e-05,
+      "loss": 0.3243,
+      "step": 313
+    },
+    {
+      "epoch": 3.876543209876543,
+      "grad_norm": 0.06761430757610919,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.3167,
+      "step": 314
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.06926674108977166,
+      "learning_rate": 1.1472670774776159e-05,
+      "loss": 0.3187,
+      "step": 315
+    },
+    {
+      "epoch": 3.9012345679012346,
+      "grad_norm": 0.07065191859435709,
+      "learning_rate": 1.123173777970303e-05,
+      "loss": 0.3124,
+      "step": 316
+    },
+    {
+      "epoch": 3.9135802469135803,
+      "grad_norm": 0.07201016021529724,
+      "learning_rate": 1.0992947714264952e-05,
+      "loss": 0.3118,
+      "step": 317
+    },
+    {
+      "epoch": 3.925925925925926,
+      "grad_norm": 0.06487401702864597,
+      "learning_rate": 1.0756318365782672e-05,
+      "loss": 0.3173,
+      "step": 318
+    },
+    {
+      "epoch": 3.9382716049382713,
+      "grad_norm": 0.06482783090109683,
+      "learning_rate": 1.0521867360626534e-05,
+      "loss": 0.3123,
+      "step": 319
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.06411169699315523,
+      "learning_rate": 1.028961216290342e-05,
+      "loss": 0.3168,
+      "step": 320
+    },
+    {
+      "epoch": 3.962962962962963,
+      "grad_norm": 0.05749606874053444,
+      "learning_rate": 1.0059570073155953e-05,
+      "loss": 0.3156,
+      "step": 321
+    },
+    {
+      "epoch": 3.9753086419753085,
+      "grad_norm": 0.05934029266147272,
+      "learning_rate": 9.831758227073714e-06,
+      "loss": 0.3102,
+      "step": 322
+    },
+    {
+      "epoch": 3.9876543209876543,
+      "grad_norm": 0.06223708967415169,
+      "learning_rate": 9.606193594216852e-06,
+      "loss": 0.3129,
+      "step": 323
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.08646442342493,
+      "learning_rate": 9.382892976752024e-06,
+      "loss": 0.3,
+      "step": 324
+    },
+    {
+      "epoch": 4.012345679012346,
+      "grad_norm": 0.10656911821190412,
+      "learning_rate": 9.161873008200816e-06,
+      "loss": 0.2946,
+      "step": 325
+    },
+    {
+      "epoch": 4.0246913580246915,
+      "grad_norm": 0.07444562732268245,
+      "learning_rate": 8.943150152200734e-06,
+      "loss": 0.3046,
+      "step": 326
+    },
+    {
+      "epoch": 4.037037037037037,
+      "grad_norm": 0.0908823770206481,
+      "learning_rate": 8.72674070127881e-06,
+      "loss": 0.2911,
+      "step": 327
+    },
+    {
+      "epoch": 4.049382716049383,
+      "grad_norm": 0.10134902478493782,
+      "learning_rate": 8.512660775637998e-06,
+      "loss": 0.2936,
+      "step": 328
+    },
+    {
+      "epoch": 4.061728395061729,
+      "grad_norm": 0.08350119892969536,
+      "learning_rate": 8.300926321956391e-06,
+      "loss": 0.2916,
+      "step": 329
+    },
+    {
+      "epoch": 4.074074074074074,
+      "grad_norm": 0.08908038161816212,
+      "learning_rate": 8.091553112199362e-06,
+      "loss": 0.3004,
+      "step": 330
+    },
+    {
+      "epoch": 4.08641975308642,
+      "grad_norm": 0.07915758860894596,
+      "learning_rate": 7.884556742444704e-06,
+      "loss": 0.2947,
+      "step": 331
+    },
+    {
+      "epoch": 4.098765432098766,
+      "grad_norm": 0.0831504083984309,
+      "learning_rate": 7.679952631720944e-06,
+      "loss": 0.2959,
+      "step": 332
+    },
+    {
+      "epoch": 4.111111111111111,
+      "grad_norm": 0.09029271980378631,
+      "learning_rate": 7.477756020858695e-06,
+      "loss": 0.3035,
+      "step": 333
+    },
+    {
+      "epoch": 4.1234567901234565,
+      "grad_norm": 0.07759118928477404,
+      "learning_rate": 7.277981971355487e-06,
+      "loss": 0.2937,
+      "step": 334
+    },
+    {
+      "epoch": 4.135802469135802,
+      "grad_norm": 0.07326193477975727,
+      "learning_rate": 7.080645364253747e-06,
+      "loss": 0.2946,
+      "step": 335
+    },
+    {
+      "epoch": 4.148148148148148,
+      "grad_norm": 0.07400163858434072,
+      "learning_rate": 6.885760899032368e-06,
+      "loss": 0.2951,
+      "step": 336
+    },
+    {
+      "epoch": 4.160493827160494,
+      "grad_norm": 0.07049936261378838,
+      "learning_rate": 6.69334309251175e-06,
+      "loss": 0.2966,
+      "step": 337
+    },
+    {
+      "epoch": 4.172839506172839,
+      "grad_norm": 0.07182120870973077,
+      "learning_rate": 6.503406277772457e-06,
+      "loss": 0.2941,
+      "step": 338
+    },
+    {
+      "epoch": 4.185185185185185,
+      "grad_norm": 0.0737852972425236,
+      "learning_rate": 6.31596460308753e-06,
+      "loss": 0.2935,
+      "step": 339
+    },
+    {
+      "epoch": 4.197530864197531,
+      "grad_norm": 0.07163115112180748,
+      "learning_rate": 6.1310320308686354e-06,
+      "loss": 0.2986,
+      "step": 340
+    },
+    {
+      "epoch": 4.209876543209877,
+      "grad_norm": 0.06473383702882682,
+      "learning_rate": 5.9486223366259555e-06,
+      "loss": 0.2903,
+      "step": 341
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.06669412046842975,
+      "learning_rate": 5.768749107942105e-06,
+      "loss": 0.2953,
+      "step": 342
+    },
+    {
+      "epoch": 4.234567901234568,
+      "grad_norm": 0.06248965360789027,
+      "learning_rate": 5.5914257434599705e-06,
+      "loss": 0.293,
+      "step": 343
+    },
+    {
+      "epoch": 4.246913580246914,
+      "grad_norm": 0.06437693433750728,
+      "learning_rate": 5.416665451884706e-06,
+      "loss": 0.2967,
+      "step": 344
+    },
+    {
+      "epoch": 4.2592592592592595,
+      "grad_norm": 0.06588940439973648,
+      "learning_rate": 5.24448125099974e-06,
+      "loss": 0.3078,
+      "step": 345
+    },
+    {
+      "epoch": 4.271604938271605,
+      "grad_norm": 0.06569061357683663,
+      "learning_rate": 5.074885966697167e-06,
+      "loss": 0.2939,
+      "step": 346
+    },
+    {
+      "epoch": 4.283950617283951,
+      "grad_norm": 0.055605185400721784,
+      "learning_rate": 4.9078922320223225e-06,
+      "loss": 0.2891,
+      "step": 347
+    },
+    {
+      "epoch": 4.296296296296296,
+      "grad_norm": 0.060637458853606094,
+      "learning_rate": 4.7435124862327445e-06,
+      "loss": 0.2951,
+      "step": 348
+    },
+    {
+      "epoch": 4.308641975308642,
+      "grad_norm": 0.06126670478207391,
+      "learning_rate": 4.581758973871609e-06,
+      "loss": 0.2937,
+      "step": 349
+    },
+    {
+      "epoch": 4.320987654320987,
+      "grad_norm": 0.06233815735956439,
+      "learning_rate": 4.422643743855611e-06,
+      "loss": 0.2891,
+      "step": 350
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.059207770207222475,
+      "learning_rate": 4.266178648577484e-06,
+      "loss": 0.2961,
+      "step": 351
+    },
+    {
+      "epoch": 4.345679012345679,
+      "grad_norm": 0.052435668089758795,
+      "learning_rate": 4.112375343023076e-06,
+      "loss": 0.2906,
+      "step": 352
+    },
+    {
+      "epoch": 4.3580246913580245,
+      "grad_norm": 0.05513316882730981,
+      "learning_rate": 3.961245283903239e-06,
+      "loss": 0.2923,
+      "step": 353
+    },
+    {
+      "epoch": 4.37037037037037,
+      "grad_norm": 0.06415306302147575,
+      "learning_rate": 3.812799728800354e-06,
+      "loss": 0.2984,
+      "step": 354
+    },
+    {
+      "epoch": 4.382716049382716,
+      "grad_norm": 0.060016760391854884,
+      "learning_rate": 3.6670497353298396e-06,
+      "loss": 0.2977,
+      "step": 355
+    },
+    {
+      "epoch": 4.395061728395062,
+      "grad_norm": 0.05343746604593776,
+      "learning_rate": 3.5240061603163977e-06,
+      "loss": 0.2943,
+      "step": 356
+    },
+    {
+      "epoch": 4.407407407407407,
+      "grad_norm": 0.055019505974751165,
+      "learning_rate": 3.3836796589853484e-06,
+      "loss": 0.2903,
+      "step": 357
+    },
+    {
+      "epoch": 4.419753086419753,
+      "grad_norm": 0.055567188008123394,
+      "learning_rate": 3.246080684168913e-06,
+      "loss": 0.2881,
+      "step": 358
+    },
+    {
+      "epoch": 4.432098765432099,
+      "grad_norm": 0.05507390642960094,
+      "learning_rate": 3.11121948552759e-06,
+      "loss": 0.2963,
+      "step": 359
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.06057331966915183,
+      "learning_rate": 2.9791061087866625e-06,
+      "loss": 0.2997,
+      "step": 360
+    },
+    {
+      "epoch": 4.45679012345679,
+      "grad_norm": 0.05546235973182725,
+      "learning_rate": 2.849750394987907e-06,
+      "loss": 0.2993,
+      "step": 361
+    },
+    {
+      "epoch": 4.469135802469136,
+      "grad_norm": 0.05313511928559259,
+      "learning_rate": 2.7231619797565278e-06,
+      "loss": 0.2956,
+      "step": 362
+    },
+    {
+      "epoch": 4.481481481481482,
+      "grad_norm": 0.05217573548352385,
+      "learning_rate": 2.5993502925834115e-06,
+      "loss": 0.2969,
+      "step": 363
+    },
+    {
+      "epoch": 4.493827160493828,
+      "grad_norm": 0.05158690799767976,
+      "learning_rate": 2.4783245561227264e-06,
+      "loss": 0.2942,
+      "step": 364
+    },
+    {
+      "epoch": 4.506172839506172,
+      "grad_norm": 0.05365265639701058,
+      "learning_rate": 2.3600937855049467e-06,
+      "loss": 0.298,
+      "step": 365
+    },
+    {
+      "epoch": 4.518518518518518,
+      "grad_norm": 0.051193805971302644,
+      "learning_rate": 2.244666787665297e-06,
+      "loss": 0.2982,
+      "step": 366
+    },
+    {
+      "epoch": 4.530864197530864,
+      "grad_norm": 0.051166369631722206,
+      "learning_rate": 2.1320521606877653e-06,
+      "loss": 0.2987,
+      "step": 367
+    },
+    {
+      "epoch": 4.54320987654321,
+      "grad_norm": 0.04849255198472993,
+      "learning_rate": 2.022258293164585e-06,
+      "loss": 0.2936,
+      "step": 368
+    },
+    {
+      "epoch": 4.555555555555555,
+      "grad_norm": 0.04886701621858151,
+      "learning_rate": 1.9152933635714354e-06,
+      "loss": 0.2914,
+      "step": 369
+    },
+    {
+      "epoch": 4.567901234567901,
+      "grad_norm": 0.04876004337558675,
+      "learning_rate": 1.8111653396581762e-06,
+      "loss": 0.2987,
+      "step": 370
+    },
+    {
+      "epoch": 4.580246913580247,
+      "grad_norm": 0.047529937586621676,
+      "learning_rate": 1.709881977855372e-06,
+      "loss": 0.295,
+      "step": 371
+    },
+    {
+      "epoch": 4.592592592592593,
+      "grad_norm": 0.0464429073575302,
+      "learning_rate": 1.6114508226965009e-06,
+      "loss": 0.2941,
+      "step": 372
+    },
+    {
+      "epoch": 4.604938271604938,
+      "grad_norm": 0.04694601432015816,
+      "learning_rate": 1.5158792062559813e-06,
+      "loss": 0.2964,
+      "step": 373
+    },
+    {
+      "epoch": 4.617283950617284,
+      "grad_norm": 0.04778132421437688,
+      "learning_rate": 1.4231742476029965e-06,
+      "loss": 0.2961,
+      "step": 374
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 0.0484788311311817,
+      "learning_rate": 1.33334285227122e-06,
+      "loss": 0.2953,
+      "step": 375
+    },
+    {
+      "epoch": 4.6419753086419755,
+      "grad_norm": 0.04856431073439481,
+      "learning_rate": 1.2463917117443968e-06,
+      "loss": 0.2972,
+      "step": 376
+    },
+    {
+      "epoch": 4.654320987654321,
+      "grad_norm": 0.046366250941292986,
+      "learning_rate": 1.1623273029579195e-06,
+      "loss": 0.296,
+      "step": 377
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.046904184432256205,
+      "learning_rate": 1.0811558878163698e-06,
+      "loss": 0.2946,
+      "step": 378
+    },
+    {
+      "epoch": 4.679012345679013,
+      "grad_norm": 0.04826575156192067,
+      "learning_rate": 1.0028835127270553e-06,
+      "loss": 0.2924,
+      "step": 379
+    },
+    {
+      "epoch": 4.6913580246913575,
+      "grad_norm": 0.04817519998342948,
+      "learning_rate": 9.275160081496337e-07,
+      "loss": 0.2955,
+      "step": 380
+    },
+    {
+      "epoch": 4.703703703703704,
+      "grad_norm": 0.04699537004045298,
+      "learning_rate": 8.550589881617877e-07,
+      "loss": 0.2923,
+      "step": 381
+    },
+    {
+      "epoch": 4.716049382716049,
+      "grad_norm": 0.04674530957240808,
+      "learning_rate": 7.85517850041062e-07,
+      "loss": 0.2894,
+      "step": 382
+    },
+    {
+      "epoch": 4.728395061728395,
+      "grad_norm": 0.04800057098440756,
+      "learning_rate": 7.188977738627901e-07,
+      "loss": 0.2952,
+      "step": 383
+    },
+    {
+      "epoch": 4.7407407407407405,
+      "grad_norm": 0.04455578535257919,
+      "learning_rate": 6.552037221142593e-07,
+      "loss": 0.2899,
+      "step": 384
+    },
+    {
+      "epoch": 4.753086419753086,
+      "grad_norm": 0.04726225822781275,
+      "learning_rate": 5.944404393250481e-07,
+      "loss": 0.2914,
+      "step": 385
+    },
+    {
+      "epoch": 4.765432098765432,
+      "grad_norm": 0.04512333606857293,
+      "learning_rate": 5.366124517136184e-07,
+      "loss": 0.292,
+      "step": 386
+    },
+    {
+      "epoch": 4.777777777777778,
+      "grad_norm": 0.04524097094131603,
+      "learning_rate": 4.817240668501421e-07,
+      "loss": 0.2911,
+      "step": 387
+    },
+    {
+      "epoch": 4.790123456790123,
+      "grad_norm": 0.04623557314958941,
+      "learning_rate": 4.297793733356548e-07,
+      "loss": 0.2926,
+      "step": 388
+    },
+    {
+      "epoch": 4.802469135802469,
+      "grad_norm": 0.04837753601413586,
+      "learning_rate": 3.807822404974726e-07,
+      "loss": 0.2983,
+      "step": 389
+    },
+    {
+      "epoch": 4.814814814814815,
+      "grad_norm": 0.04505375863457343,
+      "learning_rate": 3.3473631810100103e-07,
+      "loss": 0.2843,
+      "step": 390
+    },
+    {
+      "epoch": 4.827160493827161,
+      "grad_norm": 0.04759033447599698,
+      "learning_rate": 2.916450360778411e-07,
+      "loss": 0.2865,
+      "step": 391
+    },
+    {
+      "epoch": 4.839506172839506,
+      "grad_norm": 0.04823373809171462,
+      "learning_rate": 2.5151160427029584e-07,
+      "loss": 0.2965,
+      "step": 392
+    },
+    {
+      "epoch": 4.851851851851852,
+      "grad_norm": 0.04807801540319918,
+      "learning_rate": 2.1433901219229502e-07,
+      "loss": 0.2962,
+      "step": 393
+    },
+    {
+      "epoch": 4.864197530864198,
+      "grad_norm": 0.04524128866243309,
+      "learning_rate": 1.8013002880667096e-07,
+      "loss": 0.2942,
+      "step": 394
+    },
+    {
+      "epoch": 4.8765432098765435,
+      "grad_norm": 0.04869810769094954,
+      "learning_rate": 1.4888720231894138e-07,
+      "loss": 0.2984,
+      "step": 395
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.04566244073826472,
+      "learning_rate": 1.2061285998746562e-07,
+      "loss": 0.2966,
+      "step": 396
+    },
+    {
+      "epoch": 4.901234567901234,
+      "grad_norm": 0.04787695828649585,
+      "learning_rate": 9.530910795009895e-08,
+      "loss": 0.2944,
+      "step": 397
+    },
+    {
+      "epoch": 4.91358024691358,
+      "grad_norm": 0.04511010894218573,
+      "learning_rate": 7.297783106730016e-08,
+      "loss": 0.2911,
+      "step": 398
+    },
+    {
+      "epoch": 4.925925925925926,
+      "grad_norm": 0.04513978521503107,
+      "learning_rate": 5.362069278175508e-08,
+      "loss": 0.2959,
+      "step": 399
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.04748198730494815,
+      "learning_rate": 3.7239134994426775e-08,
+      "loss": 0.2893,
+      "step": 400
+    },
+    {
+      "epoch": 4.950617283950617,
+      "grad_norm": 0.04564396773873473,
+      "learning_rate": 2.3834377957183684e-08,
+      "loss": 0.2871,
+      "step": 401
+    },
+    {
+      "epoch": 4.962962962962963,
+      "grad_norm": 0.04597730125665465,
+      "learning_rate": 1.3407420181885678e-08,
+      "loss": 0.2903,
+      "step": 402
+    },
+    {
+      "epoch": 4.9753086419753085,
+      "grad_norm": 0.045086142214784956,
+      "learning_rate": 5.959038366021297e-09,
+      "loss": 0.2965,
+      "step": 403
+    },
+    {
+      "epoch": 4.987654320987654,
+      "grad_norm": 0.044012981743185825,
+      "learning_rate": 1.4897873348340697e-09,
+      "loss": 0.2937,
+      "step": 404
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.053513400662439016,
+      "learning_rate": 0.0,
+      "loss": 0.2918,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "step": 405,
+      "total_flos": 2.281478037700608e+16,
+      "train_loss": 0.36058994583141657,
+      "train_runtime": 22607.6598,
+      "train_samples_per_second": 9.116,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 405,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.281478037700608e+16,
+  "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 sha256:04e26927f6c2e0541c572db0922978018a604a449b3548468656529206e1035c
+size 7352