Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qos_boost_qos_bprod_fig1_math_openr1_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. -->
+
+# qos_boost_qos_bprod_fig1_math_openr1_32B
+
+This model is a fine-tuned version of [/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd](https://huggingface.co//leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd) on the mlfoundations-dev/fig1_math_openr1 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 0.20.0

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": 1.915314895847424e+16,
+    "train_loss": 0.3188589934040518,
+    "train_runtime": 19815.4609,
+    "train_samples_per_second": 8.67,
+    "train_steps_per_second": 0.017
+}

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 sha256:75fe77745efba154bd5e0fd7ff3b2963b50fba1c13e36d06fa784cba8a0d11da
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403e7ba72a905eabea963f213e7209a60fb31b4fdafa397e259ba63516789700
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e36fd2539c0c9bd45ebe823068b48e6c3ef8f0f8b3d5f9f8e53824ac96c5f0
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4587d0fda1637cee36d50f366f0f502be2b6bcd9f83f222ecf14d3824275355c
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119a1885361bdf690fb21df12c481c0865cbd3e720e88d76a3ecc26175dee84b
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf79fa914bd95c58cdcbebfc8c905f397c2bd4dc008f44a4452c0e26f73aa8f
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe48dc4dd0584bd8cca931a8c750a6dbde7c76930b132de0d3fd20953e82d8a
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26815e58965a2d8546ca8929d4e016f87c19c7dacbc19e4e8ad74665ce879536
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbf12ce7460b3ac160f002417d9ee2178dad938fb1c5e925edb8e438d4c3236
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3e67626f960325a2f9a072344592cd35ba9d56f336d33819819372eaf4d99a
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f604fb0ef566448760c8b9be99ca1d93d7e40e132bdd92e3cbce51e023e9db
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6a871e6749d21bb0154ae0bd7f8b602acaf9f44b0dce5523a24b5888cc320a
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd185831769a3cd7708ba9c233611147757dea3e9109d04907cf6f1b66b9c12e
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386e2a95a0c5874eb62e8c53ae31e0c41892c470ecb0e39e70e2a6bdcaf9d3bc
+size 2123397800

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.915314895847424e+16,
+    "train_loss": 0.3188589934040518,
+    "train_runtime": 19815.4609,
+    "train_samples_per_second": 8.67,
+    "train_steps_per_second": 0.017
+}

trainer_log.jsonl

@@ -0,0 +1,341 @@
+{"current_steps": 1, "total_steps": 340, "loss": 0.693, "lr": 2.3529411764705885e-06, "epoch": 0.014705882352941176, "percentage": 0.29, "elapsed_time": "0:02:04", "remaining_time": "11:44:28"}
+{"current_steps": 2, "total_steps": 340, "loss": 0.6892, "lr": 4.705882352941177e-06, "epoch": 0.029411764705882353, "percentage": 0.59, "elapsed_time": "0:03:00", "remaining_time": "8:28:29"}
+{"current_steps": 3, "total_steps": 340, "loss": 0.6851, "lr": 7.058823529411766e-06, "epoch": 0.04411764705882353, "percentage": 0.88, "elapsed_time": "0:03:56", "remaining_time": "7:23:00"}
+{"current_steps": 4, "total_steps": 340, "loss": 0.6513, "lr": 9.411764705882354e-06, "epoch": 0.058823529411764705, "percentage": 1.18, "elapsed_time": "0:04:52", "remaining_time": "6:49:23"}
+{"current_steps": 5, "total_steps": 340, "loss": 0.6231, "lr": 1.1764705882352942e-05, "epoch": 0.07352941176470588, "percentage": 1.47, "elapsed_time": "0:05:48", "remaining_time": "6:29:32"}
+{"current_steps": 6, "total_steps": 340, "loss": 0.6169, "lr": 1.4117647058823532e-05, "epoch": 0.08823529411764706, "percentage": 1.76, "elapsed_time": "0:06:45", "remaining_time": "6:15:55"}
+{"current_steps": 7, "total_steps": 340, "loss": 0.5687, "lr": 1.647058823529412e-05, "epoch": 0.10294117647058823, "percentage": 2.06, "elapsed_time": "0:07:41", "remaining_time": "6:05:41"}
+{"current_steps": 8, "total_steps": 340, "loss": 0.5586, "lr": 1.8823529411764708e-05, "epoch": 0.11764705882352941, "percentage": 2.35, "elapsed_time": "0:08:36", "remaining_time": "5:57:18"}
+{"current_steps": 9, "total_steps": 340, "loss": 0.5208, "lr": 2.1176470588235296e-05, "epoch": 0.1323529411764706, "percentage": 2.65, "elapsed_time": "0:09:33", "remaining_time": "5:51:20"}
+{"current_steps": 10, "total_steps": 340, "loss": 0.5086, "lr": 2.3529411764705884e-05, "epoch": 0.14705882352941177, "percentage": 2.94, "elapsed_time": "0:10:30", "remaining_time": "5:46:33"}
+{"current_steps": 11, "total_steps": 340, "loss": 0.4903, "lr": 2.5882352941176475e-05, "epoch": 0.16176470588235295, "percentage": 3.24, "elapsed_time": "0:11:26", "remaining_time": "5:42:15"}
+{"current_steps": 12, "total_steps": 340, "loss": 0.4841, "lr": 2.8235294117647063e-05, "epoch": 0.17647058823529413, "percentage": 3.53, "elapsed_time": "0:12:22", "remaining_time": "5:38:07"}
+{"current_steps": 13, "total_steps": 340, "loss": 0.4711, "lr": 3.0588235294117644e-05, "epoch": 0.19117647058823528, "percentage": 3.82, "elapsed_time": "0:13:17", "remaining_time": "5:34:30"}
+{"current_steps": 14, "total_steps": 340, "loss": 0.4567, "lr": 3.294117647058824e-05, "epoch": 0.20588235294117646, "percentage": 4.12, "elapsed_time": "0:14:14", "remaining_time": "5:31:44"}
+{"current_steps": 15, "total_steps": 340, "loss": 0.4522, "lr": 3.529411764705883e-05, "epoch": 0.22058823529411764, "percentage": 4.41, "elapsed_time": "0:15:09", "remaining_time": "5:28:36"}
+{"current_steps": 16, "total_steps": 340, "loss": 0.4415, "lr": 3.7647058823529415e-05, "epoch": 0.23529411764705882, "percentage": 4.71, "elapsed_time": "0:16:06", "remaining_time": "5:26:08"}
+{"current_steps": 17, "total_steps": 340, "loss": 0.4327, "lr": 4e-05, "epoch": 0.25, "percentage": 5.0, "elapsed_time": "0:17:03", "remaining_time": "5:24:04"}
+{"current_steps": 18, "total_steps": 340, "loss": 0.43, "lr": 4.235294117647059e-05, "epoch": 0.2647058823529412, "percentage": 5.29, "elapsed_time": "0:18:00", "remaining_time": "5:22:10"}
+{"current_steps": 19, "total_steps": 340, "loss": 0.4317, "lr": 4.470588235294118e-05, "epoch": 0.27941176470588236, "percentage": 5.59, "elapsed_time": "0:18:55", "remaining_time": "5:19:48"}
+{"current_steps": 20, "total_steps": 340, "loss": 0.43, "lr": 4.705882352941177e-05, "epoch": 0.29411764705882354, "percentage": 5.88, "elapsed_time": "0:19:53", "remaining_time": "5:18:11"}
+{"current_steps": 21, "total_steps": 340, "loss": 0.4199, "lr": 4.941176470588236e-05, "epoch": 0.3088235294117647, "percentage": 6.18, "elapsed_time": "0:20:50", "remaining_time": "5:16:33"}
+{"current_steps": 22, "total_steps": 340, "loss": 0.4185, "lr": 5.176470588235295e-05, "epoch": 0.3235294117647059, "percentage": 6.47, "elapsed_time": "0:21:46", "remaining_time": "5:14:44"}
+{"current_steps": 23, "total_steps": 340, "loss": 0.4128, "lr": 5.411764705882354e-05, "epoch": 0.3382352941176471, "percentage": 6.76, "elapsed_time": "0:22:42", "remaining_time": "5:13:01"}
+{"current_steps": 24, "total_steps": 340, "loss": 0.4043, "lr": 5.6470588235294126e-05, "epoch": 0.35294117647058826, "percentage": 7.06, "elapsed_time": "0:23:35", "remaining_time": "5:10:42"}
+{"current_steps": 25, "total_steps": 340, "loss": 0.4089, "lr": 5.8823529411764714e-05, "epoch": 0.36764705882352944, "percentage": 7.35, "elapsed_time": "0:24:21", "remaining_time": "5:06:57"}
+{"current_steps": 26, "total_steps": 340, "loss": 0.4017, "lr": 6.117647058823529e-05, "epoch": 0.38235294117647056, "percentage": 7.65, "elapsed_time": "0:25:09", "remaining_time": "5:03:44"}
+{"current_steps": 27, "total_steps": 340, "loss": 0.4011, "lr": 6.352941176470589e-05, "epoch": 0.39705882352941174, "percentage": 7.94, "elapsed_time": "0:26:05", "remaining_time": "5:02:23"}
+{"current_steps": 28, "total_steps": 340, "loss": 0.3989, "lr": 6.588235294117648e-05, "epoch": 0.4117647058823529, "percentage": 8.24, "elapsed_time": "0:27:01", "remaining_time": "5:01:05"}
+{"current_steps": 29, "total_steps": 340, "loss": 0.4051, "lr": 6.823529411764707e-05, "epoch": 0.4264705882352941, "percentage": 8.53, "elapsed_time": "0:27:57", "remaining_time": "4:59:45"}
+{"current_steps": 30, "total_steps": 340, "loss": 0.406, "lr": 7.058823529411765e-05, "epoch": 0.4411764705882353, "percentage": 8.82, "elapsed_time": "0:28:54", "remaining_time": "4:58:38"}
+{"current_steps": 31, "total_steps": 340, "loss": 0.3959, "lr": 7.294117647058824e-05, "epoch": 0.45588235294117646, "percentage": 9.12, "elapsed_time": "0:29:50", "remaining_time": "4:57:23"}
+{"current_steps": 32, "total_steps": 340, "loss": 0.3979, "lr": 7.529411764705883e-05, "epoch": 0.47058823529411764, "percentage": 9.41, "elapsed_time": "0:30:46", "remaining_time": "4:56:17"}
+{"current_steps": 33, "total_steps": 340, "loss": 0.4037, "lr": 7.764705882352942e-05, "epoch": 0.4852941176470588, "percentage": 9.71, "elapsed_time": "0:31:43", "remaining_time": "4:55:04"}
+{"current_steps": 34, "total_steps": 340, "loss": 0.3981, "lr": 8e-05, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:32:38", "remaining_time": "4:53:45"}
+{"current_steps": 35, "total_steps": 340, "loss": 0.3899, "lr": 7.999789193948694e-05, "epoch": 0.5147058823529411, "percentage": 10.29, "elapsed_time": "0:33:34", "remaining_time": "4:52:35"}
+{"current_steps": 36, "total_steps": 340, "loss": 0.3919, "lr": 7.999156798014366e-05, "epoch": 0.5294117647058824, "percentage": 10.59, "elapsed_time": "0:34:30", "remaining_time": "4:51:26"}
+{"current_steps": 37, "total_steps": 340, "loss": 0.3842, "lr": 7.998102878853464e-05, "epoch": 0.5441176470588235, "percentage": 10.88, "elapsed_time": "0:35:26", "remaining_time": "4:50:16"}
+{"current_steps": 38, "total_steps": 340, "loss": 0.3887, "lr": 7.996627547552256e-05, "epoch": 0.5588235294117647, "percentage": 11.18, "elapsed_time": "0:36:22", "remaining_time": "4:49:06"}
+{"current_steps": 39, "total_steps": 340, "loss": 0.3801, "lr": 7.994730959615125e-05, "epoch": 0.5735294117647058, "percentage": 11.47, "elapsed_time": "0:37:19", "remaining_time": "4:48:04"}
+{"current_steps": 40, "total_steps": 340, "loss": 0.3872, "lr": 7.992413314948177e-05, "epoch": 0.5882352941176471, "percentage": 11.76, "elapsed_time": "0:38:16", "remaining_time": "4:47:02"}
+{"current_steps": 41, "total_steps": 340, "loss": 0.3799, "lr": 7.989674857838173e-05, "epoch": 0.6029411764705882, "percentage": 12.06, "elapsed_time": "0:39:12", "remaining_time": "4:45:57"}
+{"current_steps": 42, "total_steps": 340, "loss": 0.3795, "lr": 7.986515876926777e-05, "epoch": 0.6176470588235294, "percentage": 12.35, "elapsed_time": "0:40:09", "remaining_time": "4:44:53"}
+{"current_steps": 43, "total_steps": 340, "loss": 0.3797, "lr": 7.982936705180139e-05, "epoch": 0.6323529411764706, "percentage": 12.65, "elapsed_time": "0:41:02", "remaining_time": "4:43:28"}
+{"current_steps": 44, "total_steps": 340, "loss": 0.3713, "lr": 7.978937719853786e-05, "epoch": 0.6470588235294118, "percentage": 12.94, "elapsed_time": "0:41:57", "remaining_time": "4:42:13"}
+{"current_steps": 45, "total_steps": 340, "loss": 0.37, "lr": 7.974519342452872e-05, "epoch": 0.6617647058823529, "percentage": 13.24, "elapsed_time": "0:42:51", "remaining_time": "4:40:59"}
+{"current_steps": 46, "total_steps": 340, "loss": 0.3706, "lr": 7.969682038687744e-05, "epoch": 0.6764705882352942, "percentage": 13.53, "elapsed_time": "0:43:48", "remaining_time": "4:40:00"}
+{"current_steps": 47, "total_steps": 340, "loss": 0.3717, "lr": 7.964426318424855e-05, "epoch": 0.6911764705882353, "percentage": 13.82, "elapsed_time": "0:44:45", "remaining_time": "4:39:00"}
+{"current_steps": 48, "total_steps": 340, "loss": 0.3678, "lr": 7.958752735633022e-05, "epoch": 0.7058823529411765, "percentage": 14.12, "elapsed_time": "0:45:41", "remaining_time": "4:37:59"}
+{"current_steps": 49, "total_steps": 340, "loss": 0.3667, "lr": 7.952661888325038e-05, "epoch": 0.7205882352941176, "percentage": 14.41, "elapsed_time": "0:46:38", "remaining_time": "4:36:57"}
+{"current_steps": 50, "total_steps": 340, "loss": 0.3658, "lr": 7.946154418494639e-05, "epoch": 0.7352941176470589, "percentage": 14.71, "elapsed_time": "0:47:34", "remaining_time": "4:35:53"}
+{"current_steps": 51, "total_steps": 340, "loss": 0.366, "lr": 7.939231012048833e-05, "epoch": 0.75, "percentage": 15.0, "elapsed_time": "0:48:32", "remaining_time": "4:35:01"}
+{"current_steps": 52, "total_steps": 340, "loss": 0.364, "lr": 7.931892398735608e-05, "epoch": 0.7647058823529411, "percentage": 15.29, "elapsed_time": "0:49:28", "remaining_time": "4:34:01"}
+{"current_steps": 53, "total_steps": 340, "loss": 0.36, "lr": 7.92413935206701e-05, "epoch": 0.7794117647058824, "percentage": 15.59, "elapsed_time": "0:50:25", "remaining_time": "4:33:00"}
+{"current_steps": 54, "total_steps": 340, "loss": 0.3629, "lr": 7.915972689237618e-05, "epoch": 0.7941176470588235, "percentage": 15.88, "elapsed_time": "0:51:21", "remaining_time": "4:32:00"}
+{"current_steps": 55, "total_steps": 340, "loss": 0.3548, "lr": 7.907393271038403e-05, "epoch": 0.8088235294117647, "percentage": 16.18, "elapsed_time": "0:52:17", "remaining_time": "4:30:59"}
+{"current_steps": 56, "total_steps": 340, "loss": 0.364, "lr": 7.898402001766002e-05, "epoch": 0.8235294117647058, "percentage": 16.47, "elapsed_time": "0:53:14", "remaining_time": "4:30:02"}
+{"current_steps": 57, "total_steps": 340, "loss": 0.3578, "lr": 7.888999829127398e-05, "epoch": 0.8382352941176471, "percentage": 16.76, "elapsed_time": "0:54:11", "remaining_time": "4:29:02"}
+{"current_steps": 58, "total_steps": 340, "loss": 0.3607, "lr": 7.879187744140039e-05, "epoch": 0.8529411764705882, "percentage": 17.06, "elapsed_time": "0:55:06", "remaining_time": "4:27:57"}
+{"current_steps": 59, "total_steps": 340, "loss": 0.3592, "lr": 7.868966781027367e-05, "epoch": 0.8676470588235294, "percentage": 17.35, "elapsed_time": "0:56:03", "remaining_time": "4:26:57"}
+{"current_steps": 60, "total_steps": 340, "loss": 0.3657, "lr": 7.858338017109822e-05, "epoch": 0.8823529411764706, "percentage": 17.65, "elapsed_time": "0:57:00", "remaining_time": "4:26:03"}
+{"current_steps": 61, "total_steps": 340, "loss": 0.3625, "lr": 7.847302572691277e-05, "epoch": 0.8970588235294118, "percentage": 17.94, "elapsed_time": "0:57:56", "remaining_time": "4:25:01"}
+{"current_steps": 62, "total_steps": 340, "loss": 0.3613, "lr": 7.835861610940965e-05, "epoch": 0.9117647058823529, "percentage": 18.24, "elapsed_time": "0:58:52", "remaining_time": "4:24:00"}
+{"current_steps": 63, "total_steps": 340, "loss": 0.3573, "lr": 7.824016337770872e-05, "epoch": 0.9264705882352942, "percentage": 18.53, "elapsed_time": "0:59:49", "remaining_time": "4:23:00"}
+{"current_steps": 64, "total_steps": 340, "loss": 0.362, "lr": 7.811768001708627e-05, "epoch": 0.9411764705882353, "percentage": 18.82, "elapsed_time": "1:00:44", "remaining_time": "4:21:57"}
+{"current_steps": 65, "total_steps": 340, "loss": 0.3557, "lr": 7.799117893765913e-05, "epoch": 0.9558823529411765, "percentage": 19.12, "elapsed_time": "1:01:40", "remaining_time": "4:20:55"}
+{"current_steps": 66, "total_steps": 340, "loss": 0.3545, "lr": 7.786067347302379e-05, "epoch": 0.9705882352941176, "percentage": 19.41, "elapsed_time": "1:02:34", "remaining_time": "4:19:46"}
+{"current_steps": 67, "total_steps": 340, "loss": 0.353, "lr": 7.77261773788511e-05, "epoch": 0.9852941176470589, "percentage": 19.71, "elapsed_time": "1:03:23", "remaining_time": "4:18:18"}
+{"current_steps": 68, "total_steps": 340, "loss": 0.3545, "lr": 7.758770483143634e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:04:18", "remaining_time": "4:17:14"}
+{"current_steps": 69, "total_steps": 340, "loss": 0.3419, "lr": 7.744527042620496e-05, "epoch": 1.0147058823529411, "percentage": 20.29, "elapsed_time": "1:07:48", "remaining_time": "4:26:18"}
+{"current_steps": 70, "total_steps": 340, "loss": 0.3471, "lr": 7.729888917617424e-05, "epoch": 1.0294117647058822, "percentage": 20.59, "elapsed_time": "1:08:44", "remaining_time": "4:25:09"}
+{"current_steps": 71, "total_steps": 340, "loss": 0.3412, "lr": 7.714857651037081e-05, "epoch": 1.0441176470588236, "percentage": 20.88, "elapsed_time": "1:09:40", "remaining_time": "4:23:57"}
+{"current_steps": 72, "total_steps": 340, "loss": 0.3428, "lr": 7.699434827220448e-05, "epoch": 1.0588235294117647, "percentage": 21.18, "elapsed_time": "1:10:35", "remaining_time": "4:22:46"}
+{"current_steps": 73, "total_steps": 340, "loss": 0.3364, "lr": 7.683622071779816e-05, "epoch": 1.0735294117647058, "percentage": 21.47, "elapsed_time": "1:11:31", "remaining_time": "4:21:38"}
+{"current_steps": 74, "total_steps": 340, "loss": 0.3389, "lr": 7.667421051427453e-05, "epoch": 1.088235294117647, "percentage": 21.76, "elapsed_time": "1:12:28", "remaining_time": "4:20:30"}
+{"current_steps": 75, "total_steps": 340, "loss": 0.3312, "lr": 7.650833473799922e-05, "epoch": 1.1029411764705883, "percentage": 22.06, "elapsed_time": "1:13:25", "remaining_time": "4:19:25"}
+{"current_steps": 76, "total_steps": 340, "loss": 0.3293, "lr": 7.633861087278095e-05, "epoch": 1.1176470588235294, "percentage": 22.35, "elapsed_time": "1:14:21", "remaining_time": "4:18:16"}
+{"current_steps": 77, "total_steps": 340, "loss": 0.3375, "lr": 7.616505680802863e-05, "epoch": 1.1323529411764706, "percentage": 22.65, "elapsed_time": "1:15:17", "remaining_time": "4:17:10"}
+{"current_steps": 78, "total_steps": 340, "loss": 0.3405, "lr": 7.598769083686582e-05, "epoch": 1.1470588235294117, "percentage": 22.94, "elapsed_time": "1:16:14", "remaining_time": "4:16:05"}
+{"current_steps": 79, "total_steps": 340, "loss": 0.3351, "lr": 7.58065316542025e-05, "epoch": 1.161764705882353, "percentage": 23.24, "elapsed_time": "1:17:11", "remaining_time": "4:15:00"}
+{"current_steps": 80, "total_steps": 340, "loss": 0.3389, "lr": 7.562159835476466e-05, "epoch": 1.1764705882352942, "percentage": 23.53, "elapsed_time": "1:18:07", "remaining_time": "4:13:55"}
+{"current_steps": 81, "total_steps": 340, "loss": 0.3378, "lr": 7.543291043108159e-05, "epoch": 1.1911764705882353, "percentage": 23.82, "elapsed_time": "1:19:03", "remaining_time": "4:12:48"}
+{"current_steps": 82, "total_steps": 340, "loss": 0.3387, "lr": 7.524048777143139e-05, "epoch": 1.2058823529411764, "percentage": 24.12, "elapsed_time": "1:19:59", "remaining_time": "4:11:41"}
+{"current_steps": 83, "total_steps": 340, "loss": 0.3306, "lr": 7.504435065774455e-05, "epoch": 1.2205882352941178, "percentage": 24.41, "elapsed_time": "1:20:55", "remaining_time": "4:10:35"}
+{"current_steps": 84, "total_steps": 340, "loss": 0.3349, "lr": 7.48445197634663e-05, "epoch": 1.2352941176470589, "percentage": 24.71, "elapsed_time": "1:21:52", "remaining_time": "4:09:30"}
+{"current_steps": 85, "total_steps": 340, "loss": 0.3324, "lr": 7.464101615137756e-05, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "1:22:48", "remaining_time": "4:08:26"}
+{"current_steps": 86, "total_steps": 340, "loss": 0.3317, "lr": 7.443386127137472e-05, "epoch": 1.2647058823529411, "percentage": 25.29, "elapsed_time": "1:23:45", "remaining_time": "4:07:22"}
+{"current_steps": 87, "total_steps": 340, "loss": 0.3346, "lr": 7.422307695820893e-05, "epoch": 1.2794117647058822, "percentage": 25.59, "elapsed_time": "1:24:42", "remaining_time": "4:06:19"}
+{"current_steps": 88, "total_steps": 340, "loss": 0.3303, "lr": 7.400868542918457e-05, "epoch": 1.2941176470588236, "percentage": 25.88, "elapsed_time": "1:25:37", "remaining_time": "4:05:11"}
+{"current_steps": 89, "total_steps": 340, "loss": 0.3351, "lr": 7.379070928181747e-05, "epoch": 1.3088235294117647, "percentage": 26.18, "elapsed_time": "1:26:34", "remaining_time": "4:04:09"}
+{"current_steps": 90, "total_steps": 340, "loss": 0.3353, "lr": 7.356917149145308e-05, "epoch": 1.3235294117647058, "percentage": 26.47, "elapsed_time": "1:27:29", "remaining_time": "4:03:02"}
+{"current_steps": 91, "total_steps": 340, "loss": 0.3294, "lr": 7.334409540884479e-05, "epoch": 1.3382352941176472, "percentage": 26.76, "elapsed_time": "1:28:27", "remaining_time": "4:02:01"}
+{"current_steps": 92, "total_steps": 340, "loss": 0.3248, "lr": 7.311550475769272e-05, "epoch": 1.3529411764705883, "percentage": 27.06, "elapsed_time": "1:29:24", "remaining_time": "4:01:00"}
+{"current_steps": 93, "total_steps": 340, "loss": 0.3328, "lr": 7.288342363214313e-05, "epoch": 1.3676470588235294, "percentage": 27.35, "elapsed_time": "1:30:20", "remaining_time": "3:59:55"}
+{"current_steps": 94, "total_steps": 340, "loss": 0.3312, "lr": 7.264787649424888e-05, "epoch": 1.3823529411764706, "percentage": 27.65, "elapsed_time": "1:31:17", "remaining_time": "3:58:53"}
+{"current_steps": 95, "total_steps": 340, "loss": 0.3348, "lr": 7.240888817139094e-05, "epoch": 1.3970588235294117, "percentage": 27.94, "elapsed_time": "1:32:13", "remaining_time": "3:57:49"}
+{"current_steps": 96, "total_steps": 340, "loss": 0.3395, "lr": 7.216648385366167e-05, "epoch": 1.4117647058823528, "percentage": 28.24, "elapsed_time": "1:33:08", "remaining_time": "3:56:45"}
+{"current_steps": 97, "total_steps": 340, "loss": 0.3306, "lr": 7.192068909120959e-05, "epoch": 1.4264705882352942, "percentage": 28.53, "elapsed_time": "1:34:05", "remaining_time": "3:55:43"}
+{"current_steps": 98, "total_steps": 340, "loss": 0.3334, "lr": 7.167152979154634e-05, "epoch": 1.4411764705882353, "percentage": 28.82, "elapsed_time": "1:35:02", "remaining_time": "3:54:42"}
+{"current_steps": 99, "total_steps": 340, "loss": 0.3404, "lr": 7.141903221681595e-05, "epoch": 1.4558823529411764, "percentage": 29.12, "elapsed_time": "1:35:58", "remaining_time": "3:53:38"}
+{"current_steps": 100, "total_steps": 340, "loss": 0.3332, "lr": 7.116322298102681e-05, "epoch": 1.4705882352941178, "percentage": 29.41, "elapsed_time": "1:36:55", "remaining_time": "3:52:38"}
+{"current_steps": 101, "total_steps": 340, "loss": 0.3313, "lr": 7.090412904724636e-05, "epoch": 1.4852941176470589, "percentage": 29.71, "elapsed_time": "1:37:52", "remaining_time": "3:51:35"}
+{"current_steps": 102, "total_steps": 340, "loss": 0.3285, "lr": 7.064177772475912e-05, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "1:38:48", "remaining_time": "3:50:32"}
+{"current_steps": 103, "total_steps": 340, "loss": 0.3361, "lr": 7.037619666618829e-05, "epoch": 1.5147058823529411, "percentage": 30.29, "elapsed_time": "1:39:44", "remaining_time": "3:49:30"}
+{"current_steps": 104, "total_steps": 340, "loss": 0.3388, "lr": 7.010741386458099e-05, "epoch": 1.5294117647058822, "percentage": 30.59, "elapsed_time": "1:40:39", "remaining_time": "3:48:24"}
+{"current_steps": 105, "total_steps": 340, "loss": 0.3311, "lr": 6.983545765045774e-05, "epoch": 1.5441176470588234, "percentage": 30.88, "elapsed_time": "1:41:25", "remaining_time": "3:46:59"}
+{"current_steps": 106, "total_steps": 340, "loss": 0.3297, "lr": 6.956035668882637e-05, "epoch": 1.5588235294117647, "percentage": 31.18, "elapsed_time": "1:42:12", "remaining_time": "3:45:37"}
+{"current_steps": 107, "total_steps": 340, "loss": 0.3318, "lr": 6.928213997616059e-05, "epoch": 1.5735294117647058, "percentage": 31.47, "elapsed_time": "1:43:07", "remaining_time": "3:44:33"}
+{"current_steps": 108, "total_steps": 340, "loss": 0.3304, "lr": 6.900083683734372e-05, "epoch": 1.5882352941176472, "percentage": 31.76, "elapsed_time": "1:44:03", "remaining_time": "3:43:31"}
+{"current_steps": 109, "total_steps": 340, "loss": 0.3276, "lr": 6.871647692257768e-05, "epoch": 1.6029411764705883, "percentage": 32.06, "elapsed_time": "1:44:59", "remaining_time": "3:42:29"}
+{"current_steps": 110, "total_steps": 340, "loss": 0.334, "lr": 6.842909020425789e-05, "epoch": 1.6176470588235294, "percentage": 32.35, "elapsed_time": "1:45:55", "remaining_time": "3:41:28"}
+{"current_steps": 111, "total_steps": 340, "loss": 0.3286, "lr": 6.8138706973814e-05, "epoch": 1.6323529411764706, "percentage": 32.65, "elapsed_time": "1:46:52", "remaining_time": "3:40:28"}
+{"current_steps": 112, "total_steps": 340, "loss": 0.3266, "lr": 6.784535783851708e-05, "epoch": 1.6470588235294117, "percentage": 32.94, "elapsed_time": "1:47:47", "remaining_time": "3:39:26"}
+{"current_steps": 113, "total_steps": 340, "loss": 0.3262, "lr": 6.754907371825355e-05, "epoch": 1.6617647058823528, "percentage": 33.24, "elapsed_time": "1:48:42", "remaining_time": "3:38:21"}
+{"current_steps": 114, "total_steps": 340, "loss": 0.3279, "lr": 6.724988584226616e-05, "epoch": 1.6764705882352942, "percentage": 33.53, "elapsed_time": "1:49:36", "remaining_time": "3:37:17"}
+{"current_steps": 115, "total_steps": 340, "loss": 0.3281, "lr": 6.69478257458623e-05, "epoch": 1.6911764705882353, "percentage": 33.82, "elapsed_time": "1:50:30", "remaining_time": "3:36:13"}
+{"current_steps": 116, "total_steps": 340, "loss": 0.3313, "lr": 6.664292526709001e-05, "epoch": 1.7058823529411766, "percentage": 34.12, "elapsed_time": "1:51:27", "remaining_time": "3:35:13"}
+{"current_steps": 117, "total_steps": 340, "loss": 0.3334, "lr": 6.633521654338233e-05, "epoch": 1.7205882352941178, "percentage": 34.41, "elapsed_time": "1:52:24", "remaining_time": "3:34:13"}
+{"current_steps": 118, "total_steps": 340, "loss": 0.3267, "lr": 6.602473200816969e-05, "epoch": 1.7352941176470589, "percentage": 34.71, "elapsed_time": "1:53:19", "remaining_time": "3:33:13"}
+{"current_steps": 119, "total_steps": 340, "loss": 0.3242, "lr": 6.571150438746157e-05, "epoch": 1.75, "percentage": 35.0, "elapsed_time": "1:54:16", "remaining_time": "3:32:13"}
+{"current_steps": 120, "total_steps": 340, "loss": 0.3244, "lr": 6.539556669639691e-05, "epoch": 1.7647058823529411, "percentage": 35.29, "elapsed_time": "1:55:13", "remaining_time": "3:31:15"}
+{"current_steps": 121, "total_steps": 340, "loss": 0.3229, "lr": 6.507695223576428e-05, "epoch": 1.7794117647058822, "percentage": 35.59, "elapsed_time": "1:56:09", "remaining_time": "3:30:14"}
+{"current_steps": 122, "total_steps": 340, "loss": 0.331, "lr": 6.475569458849178e-05, "epoch": 1.7941176470588234, "percentage": 35.88, "elapsed_time": "1:57:06", "remaining_time": "3:29:15"}
+{"current_steps": 123, "total_steps": 340, "loss": 0.3321, "lr": 6.443182761610752e-05, "epoch": 1.8088235294117647, "percentage": 36.18, "elapsed_time": "1:58:02", "remaining_time": "3:28:14"}
+{"current_steps": 124, "total_steps": 340, "loss": 0.3288, "lr": 6.410538545517026e-05, "epoch": 1.8235294117647058, "percentage": 36.47, "elapsed_time": "1:58:58", "remaining_time": "3:27:14"}
+{"current_steps": 125, "total_steps": 340, "loss": 0.3285, "lr": 6.377640251367148e-05, "epoch": 1.8382352941176472, "percentage": 36.76, "elapsed_time": "1:59:53", "remaining_time": "3:26:13"}
+{"current_steps": 126, "total_steps": 340, "loss": 0.3265, "lr": 6.344491346740859e-05, "epoch": 1.8529411764705883, "percentage": 37.06, "elapsed_time": "2:00:50", "remaining_time": "3:25:15"}
+{"current_steps": 127, "total_steps": 340, "loss": 0.3287, "lr": 6.311095325633006e-05, "epoch": 1.8676470588235294, "percentage": 37.35, "elapsed_time": "2:01:46", "remaining_time": "3:24:14"}
+{"current_steps": 128, "total_steps": 340, "loss": 0.3193, "lr": 6.277455708085255e-05, "epoch": 1.8823529411764706, "percentage": 37.65, "elapsed_time": "2:02:43", "remaining_time": "3:23:15"}
+{"current_steps": 129, "total_steps": 340, "loss": 0.3218, "lr": 6.24357603981508e-05, "epoch": 1.8970588235294117, "percentage": 37.94, "elapsed_time": "2:03:40", "remaining_time": "3:22:17"}
+{"current_steps": 130, "total_steps": 340, "loss": 0.3232, "lr": 6.209459891842023e-05, "epoch": 1.9117647058823528, "percentage": 38.24, "elapsed_time": "2:04:36", "remaining_time": "3:21:17"}
+{"current_steps": 131, "total_steps": 340, "loss": 0.3291, "lr": 6.175110860111307e-05, "epoch": 1.9264705882352942, "percentage": 38.53, "elapsed_time": "2:05:31", "remaining_time": "3:20:16"}
+{"current_steps": 132, "total_steps": 340, "loss": 0.3255, "lr": 6.140532565114801e-05, "epoch": 1.9411764705882353, "percentage": 38.82, "elapsed_time": "2:06:25", "remaining_time": "3:19:13"}
+{"current_steps": 133, "total_steps": 340, "loss": 0.3254, "lr": 6.105728651509424e-05, "epoch": 1.9558823529411766, "percentage": 39.12, "elapsed_time": "2:07:21", "remaining_time": "3:18:13"}
+{"current_steps": 134, "total_steps": 340, "loss": 0.3249, "lr": 6.070702787732971e-05, "epoch": 1.9705882352941178, "percentage": 39.41, "elapsed_time": "2:08:17", "remaining_time": "3:17:12"}
+{"current_steps": 135, "total_steps": 340, "loss": 0.3288, "lr": 6.0354586656174606e-05, "epoch": 1.9852941176470589, "percentage": 39.71, "elapsed_time": "2:09:12", "remaining_time": "3:16:12"}
+{"current_steps": 136, "total_steps": 340, "loss": 0.3099, "lr": 6.000000000000001e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:10:08", "remaining_time": "3:15:12"}
+{"current_steps": 137, "total_steps": 340, "loss": 0.3056, "lr": 5.964330528331234e-05, "epoch": 2.014705882352941, "percentage": 40.29, "elapsed_time": "2:13:42", "remaining_time": "3:18:07"}
+{"current_steps": 138, "total_steps": 340, "loss": 0.3, "lr": 5.9284540102813964e-05, "epoch": 2.0294117647058822, "percentage": 40.59, "elapsed_time": "2:14:38", "remaining_time": "3:17:05"}
+{"current_steps": 139, "total_steps": 340, "loss": 0.308, "lr": 5.892374227344041e-05, "epoch": 2.0441176470588234, "percentage": 40.88, "elapsed_time": "2:15:35", "remaining_time": "3:16:03"}
+{"current_steps": 140, "total_steps": 340, "loss": 0.3067, "lr": 5.856094982437454e-05, "epoch": 2.0588235294117645, "percentage": 41.18, "elapsed_time": "2:16:32", "remaining_time": "3:15:03"}
+{"current_steps": 141, "total_steps": 340, "loss": 0.3101, "lr": 5.819620099503818e-05, "epoch": 2.073529411764706, "percentage": 41.47, "elapsed_time": "2:17:28", "remaining_time": "3:14:01"}
+{"current_steps": 142, "total_steps": 340, "loss": 0.3046, "lr": 5.782953423106154e-05, "epoch": 2.088235294117647, "percentage": 41.76, "elapsed_time": "2:18:24", "remaining_time": "3:12:59"}
+{"current_steps": 143, "total_steps": 340, "loss": 0.2988, "lr": 5.746098818023093e-05, "epoch": 2.1029411764705883, "percentage": 42.06, "elapsed_time": "2:19:20", "remaining_time": "3:11:57"}
+{"current_steps": 144, "total_steps": 340, "loss": 0.3033, "lr": 5.709060168841524e-05, "epoch": 2.1176470588235294, "percentage": 42.35, "elapsed_time": "2:20:08", "remaining_time": "3:10:45"}
+{"current_steps": 145, "total_steps": 340, "loss": 0.3028, "lr": 5.6718413795471346e-05, "epoch": 2.1323529411764706, "percentage": 42.65, "elapsed_time": "2:21:05", "remaining_time": "3:09:44"}
+{"current_steps": 146, "total_steps": 340, "loss": 0.3035, "lr": 5.634446373112926e-05, "epoch": 2.1470588235294117, "percentage": 42.94, "elapsed_time": "2:22:02", "remaining_time": "3:08:44"}
+{"current_steps": 147, "total_steps": 340, "loss": 0.3001, "lr": 5.596879091085724e-05, "epoch": 2.161764705882353, "percentage": 43.24, "elapsed_time": "2:22:58", "remaining_time": "3:07:42"}
+{"current_steps": 148, "total_steps": 340, "loss": 0.3005, "lr": 5.5591434931707176e-05, "epoch": 2.176470588235294, "percentage": 43.53, "elapsed_time": "2:23:54", "remaining_time": "3:06:42"}
+{"current_steps": 149, "total_steps": 340, "loss": 0.3045, "lr": 5.5212435568141036e-05, "epoch": 2.1911764705882355, "percentage": 43.82, "elapsed_time": "2:24:50", "remaining_time": "3:05:40"}
+{"current_steps": 150, "total_steps": 340, "loss": 0.2993, "lr": 5.4831832767838436e-05, "epoch": 2.2058823529411766, "percentage": 44.12, "elapsed_time": "2:25:46", "remaining_time": "3:04:38"}
+{"current_steps": 151, "total_steps": 340, "loss": 0.2967, "lr": 5.444966664748613e-05, "epoch": 2.2205882352941178, "percentage": 44.41, "elapsed_time": "2:26:42", "remaining_time": "3:03:38"}
+{"current_steps": 152, "total_steps": 340, "loss": 0.2993, "lr": 5.406597748854947e-05, "epoch": 2.235294117647059, "percentage": 44.71, "elapsed_time": "2:27:38", "remaining_time": "3:02:36"}
+{"current_steps": 153, "total_steps": 340, "loss": 0.3044, "lr": 5.368080573302676e-05, "epoch": 2.25, "percentage": 45.0, "elapsed_time": "2:28:35", "remaining_time": "3:01:36"}
+{"current_steps": 154, "total_steps": 340, "loss": 0.3062, "lr": 5.329419197918639e-05, "epoch": 2.264705882352941, "percentage": 45.29, "elapsed_time": "2:29:30", "remaining_time": "3:00:34"}
+{"current_steps": 155, "total_steps": 340, "loss": 0.2995, "lr": 5.29061769772878e-05, "epoch": 2.2794117647058822, "percentage": 45.59, "elapsed_time": "2:30:26", "remaining_time": "2:59:33"}
+{"current_steps": 156, "total_steps": 340, "loss": 0.3013, "lr": 5.251680162528618e-05, "epoch": 2.2941176470588234, "percentage": 45.88, "elapsed_time": "2:31:23", "remaining_time": "2:58:33"}
+{"current_steps": 157, "total_steps": 340, "loss": 0.3036, "lr": 5.212610696452174e-05, "epoch": 2.3088235294117645, "percentage": 46.18, "elapsed_time": "2:32:20", "remaining_time": "2:57:33"}
+{"current_steps": 158, "total_steps": 340, "loss": 0.3029, "lr": 5.173413417539385e-05, "epoch": 2.323529411764706, "percentage": 46.47, "elapsed_time": "2:33:16", "remaining_time": "2:56:33"}
+{"current_steps": 159, "total_steps": 340, "loss": 0.3024, "lr": 5.134092457302044e-05, "epoch": 2.338235294117647, "percentage": 46.76, "elapsed_time": "2:34:12", "remaining_time": "2:55:32"}
+{"current_steps": 160, "total_steps": 340, "loss": 0.3037, "lr": 5.0946519602883326e-05, "epoch": 2.3529411764705883, "percentage": 47.06, "elapsed_time": "2:35:06", "remaining_time": "2:54:29"}
+{"current_steps": 161, "total_steps": 340, "loss": 0.3044, "lr": 5.0550960836459674e-05, "epoch": 2.3676470588235294, "percentage": 47.35, "elapsed_time": "2:36:00", "remaining_time": "2:53:26"}
+{"current_steps": 162, "total_steps": 340, "loss": 0.2954, "lr": 5.0154289966840315e-05, "epoch": 2.3823529411764706, "percentage": 47.65, "elapsed_time": "2:36:55", "remaining_time": "2:52:25"}
+{"current_steps": 163, "total_steps": 340, "loss": 0.2991, "lr": 4.975654880433509e-05, "epoch": 2.3970588235294117, "percentage": 47.94, "elapsed_time": "2:37:49", "remaining_time": "2:51:23"}
+{"current_steps": 164, "total_steps": 340, "loss": 0.301, "lr": 4.935777927206595e-05, "epoch": 2.411764705882353, "percentage": 48.24, "elapsed_time": "2:38:44", "remaining_time": "2:50:21"}
+{"current_steps": 165, "total_steps": 340, "loss": 0.3038, "lr": 4.895802340154813e-05, "epoch": 2.426470588235294, "percentage": 48.53, "elapsed_time": "2:39:37", "remaining_time": "2:49:17"}
+{"current_steps": 166, "total_steps": 340, "loss": 0.3022, "lr": 4.85573233282599e-05, "epoch": 2.4411764705882355, "percentage": 48.82, "elapsed_time": "2:40:31", "remaining_time": "2:48:16"}
+{"current_steps": 167, "total_steps": 340, "loss": 0.3049, "lr": 4.815572128720138e-05, "epoch": 2.4558823529411766, "percentage": 49.12, "elapsed_time": "2:41:26", "remaining_time": "2:47:14"}
+{"current_steps": 168, "total_steps": 340, "loss": 0.2998, "lr": 4.7753259608442804e-05, "epoch": 2.4705882352941178, "percentage": 49.41, "elapsed_time": "2:42:20", "remaining_time": "2:46:12"}
+{"current_steps": 169, "total_steps": 340, "loss": 0.298, "lr": 4.734998071266282e-05, "epoch": 2.485294117647059, "percentage": 49.71, "elapsed_time": "2:43:12", "remaining_time": "2:45:08"}
+{"current_steps": 170, "total_steps": 340, "loss": 0.3068, "lr": 4.694592710667723e-05, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "2:44:07", "remaining_time": "2:44:07"}
+{"current_steps": 171, "total_steps": 340, "loss": 0.3005, "lr": 4.65411413789586e-05, "epoch": 2.514705882352941, "percentage": 50.29, "elapsed_time": "2:45:01", "remaining_time": "2:43:05"}
+{"current_steps": 172, "total_steps": 340, "loss": 0.2994, "lr": 4.6135666195147426e-05, "epoch": 2.5294117647058822, "percentage": 50.59, "elapsed_time": "2:45:55", "remaining_time": "2:42:04"}
+{"current_steps": 173, "total_steps": 340, "loss": 0.3026, "lr": 4.572954429355487e-05, "epoch": 2.5441176470588234, "percentage": 50.88, "elapsed_time": "2:46:50", "remaining_time": "2:41:03"}
+{"current_steps": 174, "total_steps": 340, "loss": 0.3014, "lr": 4.532281848065816e-05, "epoch": 2.5588235294117645, "percentage": 51.18, "elapsed_time": "2:47:45", "remaining_time": "2:40:02"}
+{"current_steps": 175, "total_steps": 340, "loss": 0.3044, "lr": 4.491553162658857e-05, "epoch": 2.5735294117647056, "percentage": 51.47, "elapsed_time": "2:48:40", "remaining_time": "2:39:01"}
+{"current_steps": 176, "total_steps": 340, "loss": 0.301, "lr": 4.450772666061285e-05, "epoch": 2.588235294117647, "percentage": 51.76, "elapsed_time": "2:49:34", "remaining_time": "2:38:00"}
+{"current_steps": 177, "total_steps": 340, "loss": 0.2965, "lr": 4.409944656660828e-05, "epoch": 2.6029411764705883, "percentage": 52.06, "elapsed_time": "2:50:27", "remaining_time": "2:36:58"}
+{"current_steps": 178, "total_steps": 340, "loss": 0.3009, "lr": 4.369073437853208e-05, "epoch": 2.6176470588235294, "percentage": 52.35, "elapsed_time": "2:51:21", "remaining_time": "2:35:57"}
+{"current_steps": 179, "total_steps": 340, "loss": 0.298, "lr": 4.328163317588552e-05, "epoch": 2.6323529411764706, "percentage": 52.65, "elapsed_time": "2:52:15", "remaining_time": "2:34:56"}
+{"current_steps": 180, "total_steps": 340, "loss": 0.3013, "lr": 4.2872186079173106e-05, "epoch": 2.6470588235294117, "percentage": 52.94, "elapsed_time": "2:53:09", "remaining_time": "2:33:55"}
+{"current_steps": 181, "total_steps": 340, "loss": 0.3, "lr": 4.2462436245357724e-05, "epoch": 2.661764705882353, "percentage": 53.24, "elapsed_time": "2:54:04", "remaining_time": "2:32:54"}
+{"current_steps": 182, "total_steps": 340, "loss": 0.3029, "lr": 4.205242686331159e-05, "epoch": 2.6764705882352944, "percentage": 53.53, "elapsed_time": "2:54:59", "remaining_time": "2:31:54"}
+{"current_steps": 183, "total_steps": 340, "loss": 0.2978, "lr": 4.164220114926414e-05, "epoch": 2.6911764705882355, "percentage": 53.82, "elapsed_time": "2:55:53", "remaining_time": "2:30:53"}
+{"current_steps": 184, "total_steps": 340, "loss": 0.2998, "lr": 4.123180234224682e-05, "epoch": 2.7058823529411766, "percentage": 54.12, "elapsed_time": "2:56:46", "remaining_time": "2:29:52"}
+{"current_steps": 185, "total_steps": 340, "loss": 0.3013, "lr": 4.0821273699535625e-05, "epoch": 2.7205882352941178, "percentage": 54.41, "elapsed_time": "2:57:39", "remaining_time": "2:28:50"}
+{"current_steps": 186, "total_steps": 340, "loss": 0.3006, "lr": 4.04106584920916e-05, "epoch": 2.735294117647059, "percentage": 54.71, "elapsed_time": "2:58:23", "remaining_time": "2:27:41"}
+{"current_steps": 187, "total_steps": 340, "loss": 0.3031, "lr": 4e-05, "epoch": 2.75, "percentage": 55.0, "elapsed_time": "2:59:08", "remaining_time": "2:26:33"}
+{"current_steps": 188, "total_steps": 340, "loss": 0.3037, "lr": 3.9589341507908415e-05, "epoch": 2.764705882352941, "percentage": 55.29, "elapsed_time": "3:00:01", "remaining_time": "2:25:33"}
+{"current_steps": 189, "total_steps": 340, "loss": 0.3032, "lr": 3.917872630046439e-05, "epoch": 2.7794117647058822, "percentage": 55.59, "elapsed_time": "3:00:55", "remaining_time": "2:24:33"}
+{"current_steps": 190, "total_steps": 340, "loss": 0.3035, "lr": 3.8768197657753194e-05, "epoch": 2.7941176470588234, "percentage": 55.88, "elapsed_time": "3:01:50", "remaining_time": "2:23:33"}
+{"current_steps": 191, "total_steps": 340, "loss": 0.2985, "lr": 3.835779885073588e-05, "epoch": 2.8088235294117645, "percentage": 56.18, "elapsed_time": "3:02:44", "remaining_time": "2:22:33"}
+{"current_steps": 192, "total_steps": 340, "loss": 0.3025, "lr": 3.794757313668841e-05, "epoch": 2.8235294117647056, "percentage": 56.47, "elapsed_time": "3:03:38", "remaining_time": "2:21:33"}
+{"current_steps": 193, "total_steps": 340, "loss": 0.2964, "lr": 3.753756375464229e-05, "epoch": 2.838235294117647, "percentage": 56.76, "elapsed_time": "3:04:31", "remaining_time": "2:20:32"}
+{"current_steps": 194, "total_steps": 340, "loss": 0.2983, "lr": 3.71278139208269e-05, "epoch": 2.8529411764705883, "percentage": 57.06, "elapsed_time": "3:05:25", "remaining_time": "2:19:32"}
+{"current_steps": 195, "total_steps": 340, "loss": 0.303, "lr": 3.67183668241145e-05, "epoch": 2.8676470588235294, "percentage": 57.35, "elapsed_time": "3:06:18", "remaining_time": "2:18:32"}
+{"current_steps": 196, "total_steps": 340, "loss": 0.2977, "lr": 3.630926562146792e-05, "epoch": 2.8823529411764706, "percentage": 57.65, "elapsed_time": "3:07:11", "remaining_time": "2:17:31"}
+{"current_steps": 197, "total_steps": 340, "loss": 0.2987, "lr": 3.5900553433391724e-05, "epoch": 2.8970588235294117, "percentage": 57.94, "elapsed_time": "3:08:05", "remaining_time": "2:16:31"}
+{"current_steps": 198, "total_steps": 340, "loss": 0.2986, "lr": 3.549227333938716e-05, "epoch": 2.911764705882353, "percentage": 58.24, "elapsed_time": "3:08:59", "remaining_time": "2:15:32"}
+{"current_steps": 199, "total_steps": 340, "loss": 0.3013, "lr": 3.5084468373411444e-05, "epoch": 2.9264705882352944, "percentage": 58.53, "elapsed_time": "3:09:54", "remaining_time": "2:14:33"}
+{"current_steps": 200, "total_steps": 340, "loss": 0.2972, "lr": 3.467718151934187e-05, "epoch": 2.9411764705882355, "percentage": 58.82, "elapsed_time": "3:10:48", "remaining_time": "2:13:34"}
+{"current_steps": 201, "total_steps": 340, "loss": 0.2979, "lr": 3.427045570644515e-05, "epoch": 2.9558823529411766, "percentage": 59.12, "elapsed_time": "3:11:43", "remaining_time": "2:12:35"}
+{"current_steps": 202, "total_steps": 340, "loss": 0.2992, "lr": 3.386433380485258e-05, "epoch": 2.9705882352941178, "percentage": 59.41, "elapsed_time": "3:12:39", "remaining_time": "2:11:37"}
+{"current_steps": 203, "total_steps": 340, "loss": 0.3011, "lr": 3.34588586210414e-05, "epoch": 2.985294117647059, "percentage": 59.71, "elapsed_time": "3:13:34", "remaining_time": "2:10:38"}
+{"current_steps": 204, "total_steps": 340, "loss": 0.2806, "lr": 3.305407289332279e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:14:28", "remaining_time": "2:09:39"}
+{"current_steps": 205, "total_steps": 340, "loss": 0.2799, "lr": 3.2650019287337184e-05, "epoch": 3.014705882352941, "percentage": 60.29, "elapsed_time": "3:18:02", "remaining_time": "2:10:25"}
+{"current_steps": 206, "total_steps": 340, "loss": 0.2781, "lr": 3.22467403915572e-05, "epoch": 3.0294117647058822, "percentage": 60.59, "elapsed_time": "3:18:58", "remaining_time": "2:09:25"}
+{"current_steps": 207, "total_steps": 340, "loss": 0.282, "lr": 3.184427871279863e-05, "epoch": 3.0441176470588234, "percentage": 60.88, "elapsed_time": "3:19:52", "remaining_time": "2:08:25"}
+{"current_steps": 208, "total_steps": 340, "loss": 0.2776, "lr": 3.144267667174011e-05, "epoch": 3.0588235294117645, "percentage": 61.18, "elapsed_time": "3:20:47", "remaining_time": "2:07:25"}
+{"current_steps": 209, "total_steps": 340, "loss": 0.2781, "lr": 3.1041976598451884e-05, "epoch": 3.073529411764706, "percentage": 61.47, "elapsed_time": "3:21:41", "remaining_time": "2:06:24"}
+{"current_steps": 210, "total_steps": 340, "loss": 0.2765, "lr": 3.064222072793407e-05, "epoch": 3.088235294117647, "percentage": 61.76, "elapsed_time": "3:22:36", "remaining_time": "2:05:25"}
+{"current_steps": 211, "total_steps": 340, "loss": 0.2783, "lr": 3.0243451195664914e-05, "epoch": 3.1029411764705883, "percentage": 62.06, "elapsed_time": "3:23:32", "remaining_time": "2:04:26"}
+{"current_steps": 212, "total_steps": 340, "loss": 0.2781, "lr": 2.984571003315969e-05, "epoch": 3.1176470588235294, "percentage": 62.35, "elapsed_time": "3:24:27", "remaining_time": "2:03:26"}
+{"current_steps": 213, "total_steps": 340, "loss": 0.2795, "lr": 2.944903916354032e-05, "epoch": 3.1323529411764706, "percentage": 62.65, "elapsed_time": "3:25:22", "remaining_time": "2:02:26"}
+{"current_steps": 214, "total_steps": 340, "loss": 0.2784, "lr": 2.905348039711669e-05, "epoch": 3.1470588235294117, "percentage": 62.94, "elapsed_time": "3:26:17", "remaining_time": "2:01:27"}
+{"current_steps": 215, "total_steps": 340, "loss": 0.2758, "lr": 2.865907542697957e-05, "epoch": 3.161764705882353, "percentage": 63.24, "elapsed_time": "3:27:12", "remaining_time": "2:00:28"}
+{"current_steps": 216, "total_steps": 340, "loss": 0.2758, "lr": 2.8265865824606165e-05, "epoch": 3.176470588235294, "percentage": 63.53, "elapsed_time": "3:28:07", "remaining_time": "1:59:28"}
+{"current_steps": 217, "total_steps": 340, "loss": 0.2748, "lr": 2.7873893035478265e-05, "epoch": 3.1911764705882355, "percentage": 63.82, "elapsed_time": "3:29:01", "remaining_time": "1:58:28"}
+{"current_steps": 218, "total_steps": 340, "loss": 0.2746, "lr": 2.7483198374713836e-05, "epoch": 3.2058823529411766, "percentage": 64.12, "elapsed_time": "3:29:56", "remaining_time": "1:57:29"}
+{"current_steps": 219, "total_steps": 340, "loss": 0.2739, "lr": 2.7093823022712217e-05, "epoch": 3.2205882352941178, "percentage": 64.41, "elapsed_time": "3:30:52", "remaining_time": "1:56:30"}
+{"current_steps": 220, "total_steps": 340, "loss": 0.2832, "lr": 2.6705808020813622e-05, "epoch": 3.235294117647059, "percentage": 64.71, "elapsed_time": "3:31:46", "remaining_time": "1:55:31"}
+{"current_steps": 221, "total_steps": 340, "loss": 0.2743, "lr": 2.6319194266973256e-05, "epoch": 3.25, "percentage": 65.0, "elapsed_time": "3:32:41", "remaining_time": "1:54:31"}
+{"current_steps": 222, "total_steps": 340, "loss": 0.2762, "lr": 2.5934022511450528e-05, "epoch": 3.264705882352941, "percentage": 65.29, "elapsed_time": "3:33:36", "remaining_time": "1:53:32"}
+{"current_steps": 223, "total_steps": 340, "loss": 0.2782, "lr": 2.5550333352513885e-05, "epoch": 3.2794117647058822, "percentage": 65.59, "elapsed_time": "3:34:31", "remaining_time": "1:52:33"}
+{"current_steps": 224, "total_steps": 340, "loss": 0.2748, "lr": 2.5168167232161574e-05, "epoch": 3.2941176470588234, "percentage": 65.88, "elapsed_time": "3:35:27", "remaining_time": "1:51:34"}
+{"current_steps": 225, "total_steps": 340, "loss": 0.2753, "lr": 2.4787564431858977e-05, "epoch": 3.3088235294117645, "percentage": 66.18, "elapsed_time": "3:36:21", "remaining_time": "1:50:34"}
+{"current_steps": 226, "total_steps": 340, "loss": 0.2751, "lr": 2.4408565068292827e-05, "epoch": 3.323529411764706, "percentage": 66.47, "elapsed_time": "3:37:09", "remaining_time": "1:49:32"}
+{"current_steps": 227, "total_steps": 340, "loss": 0.2773, "lr": 2.4031209089142773e-05, "epoch": 3.338235294117647, "percentage": 66.76, "elapsed_time": "3:38:05", "remaining_time": "1:48:34"}
+{"current_steps": 228, "total_steps": 340, "loss": 0.2752, "lr": 2.3655536268870744e-05, "epoch": 3.3529411764705883, "percentage": 67.06, "elapsed_time": "3:38:59", "remaining_time": "1:47:34"}
+{"current_steps": 229, "total_steps": 340, "loss": 0.2729, "lr": 2.328158620452868e-05, "epoch": 3.3676470588235294, "percentage": 67.35, "elapsed_time": "3:39:53", "remaining_time": "1:46:34"}
+{"current_steps": 230, "total_steps": 340, "loss": 0.2731, "lr": 2.2909398311584775e-05, "epoch": 3.3823529411764706, "percentage": 67.65, "elapsed_time": "3:40:47", "remaining_time": "1:45:35"}
+{"current_steps": 231, "total_steps": 340, "loss": 0.2782, "lr": 2.2539011819769056e-05, "epoch": 3.3970588235294117, "percentage": 67.94, "elapsed_time": "3:41:42", "remaining_time": "1:44:36"}
+{"current_steps": 232, "total_steps": 340, "loss": 0.275, "lr": 2.2170465768938473e-05, "epoch": 3.411764705882353, "percentage": 68.24, "elapsed_time": "3:42:37", "remaining_time": "1:43:38"}
+{"current_steps": 233, "total_steps": 340, "loss": 0.2766, "lr": 2.1803799004961824e-05, "epoch": 3.426470588235294, "percentage": 68.53, "elapsed_time": "3:43:31", "remaining_time": "1:42:38"}
+{"current_steps": 234, "total_steps": 340, "loss": 0.2759, "lr": 2.1439050175625474e-05, "epoch": 3.4411764705882355, "percentage": 68.82, "elapsed_time": "3:44:26", "remaining_time": "1:41:40"}
+{"current_steps": 235, "total_steps": 340, "loss": 0.2795, "lr": 2.1076257726559603e-05, "epoch": 3.4558823529411766, "percentage": 69.12, "elapsed_time": "3:45:21", "remaining_time": "1:40:41"}
+{"current_steps": 236, "total_steps": 340, "loss": 0.2767, "lr": 2.0715459897186046e-05, "epoch": 3.4705882352941178, "percentage": 69.41, "elapsed_time": "3:46:16", "remaining_time": "1:39:43"}
+{"current_steps": 237, "total_steps": 340, "loss": 0.2785, "lr": 2.0356694716687687e-05, "epoch": 3.485294117647059, "percentage": 69.71, "elapsed_time": "3:47:11", "remaining_time": "1:38:44"}
+{"current_steps": 238, "total_steps": 340, "loss": 0.2739, "lr": 2.0000000000000012e-05, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "3:48:06", "remaining_time": "1:37:45"}
+{"current_steps": 239, "total_steps": 340, "loss": 0.2729, "lr": 1.964541334382541e-05, "epoch": 3.514705882352941, "percentage": 70.29, "elapsed_time": "3:49:00", "remaining_time": "1:36:46"}
+{"current_steps": 240, "total_steps": 340, "loss": 0.2752, "lr": 1.9292972122670303e-05, "epoch": 3.5294117647058822, "percentage": 70.59, "elapsed_time": "3:49:54", "remaining_time": "1:35:47"}
+{"current_steps": 241, "total_steps": 340, "loss": 0.2801, "lr": 1.8942713484905762e-05, "epoch": 3.5441176470588234, "percentage": 70.88, "elapsed_time": "3:50:49", "remaining_time": "1:34:49"}
+{"current_steps": 242, "total_steps": 340, "loss": 0.2767, "lr": 1.8594674348851992e-05, "epoch": 3.5588235294117645, "percentage": 71.18, "elapsed_time": "3:51:43", "remaining_time": "1:33:50"}
+{"current_steps": 243, "total_steps": 340, "loss": 0.2773, "lr": 1.824889139888694e-05, "epoch": 3.5735294117647056, "percentage": 71.47, "elapsed_time": "3:52:38", "remaining_time": "1:32:51"}
+{"current_steps": 244, "total_steps": 340, "loss": 0.2763, "lr": 1.790540108157977e-05, "epoch": 3.588235294117647, "percentage": 71.76, "elapsed_time": "3:53:31", "remaining_time": "1:31:52"}
+{"current_steps": 245, "total_steps": 340, "loss": 0.2781, "lr": 1.756423960184922e-05, "epoch": 3.6029411764705883, "percentage": 72.06, "elapsed_time": "3:54:26", "remaining_time": "1:30:54"}
+{"current_steps": 246, "total_steps": 340, "loss": 0.2757, "lr": 1.7225442919147467e-05, "epoch": 3.6176470588235294, "percentage": 72.35, "elapsed_time": "3:55:21", "remaining_time": "1:29:56"}
+{"current_steps": 247, "total_steps": 340, "loss": 0.2776, "lr": 1.6889046743669957e-05, "epoch": 3.6323529411764706, "percentage": 72.65, "elapsed_time": "3:56:15", "remaining_time": "1:28:57"}
+{"current_steps": 248, "total_steps": 340, "loss": 0.2781, "lr": 1.6555086532591425e-05, "epoch": 3.6470588235294117, "percentage": 72.94, "elapsed_time": "3:57:11", "remaining_time": "1:27:59"}
+{"current_steps": 249, "total_steps": 340, "loss": 0.279, "lr": 1.6223597486328534e-05, "epoch": 3.661764705882353, "percentage": 73.24, "elapsed_time": "3:58:05", "remaining_time": "1:27:00"}
+{"current_steps": 250, "total_steps": 340, "loss": 0.2802, "lr": 1.589461454482975e-05, "epoch": 3.6764705882352944, "percentage": 73.53, "elapsed_time": "3:59:01", "remaining_time": "1:26:02"}
+{"current_steps": 251, "total_steps": 340, "loss": 0.2781, "lr": 1.556817238389249e-05, "epoch": 3.6911764705882355, "percentage": 73.82, "elapsed_time": "3:59:55", "remaining_time": "1:25:04"}
+{"current_steps": 252, "total_steps": 340, "loss": 0.278, "lr": 1.5244305411508217e-05, "epoch": 3.7058823529411766, "percentage": 74.12, "elapsed_time": "4:00:49", "remaining_time": "1:24:05"}
+{"current_steps": 253, "total_steps": 340, "loss": 0.2767, "lr": 1.4923047764235752e-05, "epoch": 3.7205882352941178, "percentage": 74.41, "elapsed_time": "4:01:42", "remaining_time": "1:23:07"}
+{"current_steps": 254, "total_steps": 340, "loss": 0.2732, "lr": 1.4604433303603092e-05, "epoch": 3.735294117647059, "percentage": 74.71, "elapsed_time": "4:02:37", "remaining_time": "1:22:08"}
+{"current_steps": 255, "total_steps": 340, "loss": 0.2743, "lr": 1.4288495612538427e-05, "epoch": 3.75, "percentage": 75.0, "elapsed_time": "4:03:30", "remaining_time": "1:21:10"}
+{"current_steps": 256, "total_steps": 340, "loss": 0.2817, "lr": 1.3975267991830327e-05, "epoch": 3.764705882352941, "percentage": 75.29, "elapsed_time": "4:04:23", "remaining_time": "1:20:11"}
+{"current_steps": 257, "total_steps": 340, "loss": 0.2725, "lr": 1.3664783456617703e-05, "epoch": 3.7794117647058822, "percentage": 75.59, "elapsed_time": "4:05:19", "remaining_time": "1:19:13"}
+{"current_steps": 258, "total_steps": 340, "loss": 0.2775, "lr": 1.3357074732909996e-05, "epoch": 3.7941176470588234, "percentage": 75.88, "elapsed_time": "4:06:16", "remaining_time": "1:18:16"}
+{"current_steps": 259, "total_steps": 340, "loss": 0.2771, "lr": 1.3052174254137713e-05, "epoch": 3.8088235294117645, "percentage": 76.18, "elapsed_time": "4:07:10", "remaining_time": "1:17:18"}
+{"current_steps": 260, "total_steps": 340, "loss": 0.2789, "lr": 1.275011415773383e-05, "epoch": 3.8235294117647056, "percentage": 76.47, "elapsed_time": "4:08:05", "remaining_time": "1:16:20"}
+{"current_steps": 261, "total_steps": 340, "loss": 0.274, "lr": 1.2450926281746458e-05, "epoch": 3.838235294117647, "percentage": 76.76, "elapsed_time": "4:09:00", "remaining_time": "1:15:22"}
+{"current_steps": 262, "total_steps": 340, "loss": 0.2771, "lr": 1.2154642161482939e-05, "epoch": 3.8529411764705883, "percentage": 77.06, "elapsed_time": "4:09:54", "remaining_time": "1:14:23"}
+{"current_steps": 263, "total_steps": 340, "loss": 0.2754, "lr": 1.1861293026186007e-05, "epoch": 3.8676470588235294, "percentage": 77.35, "elapsed_time": "4:10:49", "remaining_time": "1:13:26"}
+{"current_steps": 264, "total_steps": 340, "loss": 0.2732, "lr": 1.1570909795742118e-05, "epoch": 3.8823529411764706, "percentage": 77.65, "elapsed_time": "4:11:44", "remaining_time": "1:12:28"}
+{"current_steps": 265, "total_steps": 340, "loss": 0.2797, "lr": 1.1283523077422327e-05, "epoch": 3.8970588235294117, "percentage": 77.94, "elapsed_time": "4:12:39", "remaining_time": "1:11:30"}
+{"current_steps": 266, "total_steps": 340, "loss": 0.279, "lr": 1.0999163162656296e-05, "epoch": 3.911764705882353, "percentage": 78.24, "elapsed_time": "4:13:34", "remaining_time": "1:10:32"}
+{"current_steps": 267, "total_steps": 340, "loss": 0.276, "lr": 1.0717860023839424e-05, "epoch": 3.9264705882352944, "percentage": 78.53, "elapsed_time": "4:14:28", "remaining_time": "1:09:34"}
+{"current_steps": 268, "total_steps": 340, "loss": 0.2768, "lr": 1.0439643311173642e-05, "epoch": 3.9411764705882355, "percentage": 78.82, "elapsed_time": "4:15:13", "remaining_time": "1:08:34"}
+{"current_steps": 269, "total_steps": 340, "loss": 0.2788, "lr": 1.0164542349542273e-05, "epoch": 3.9558823529411766, "percentage": 79.12, "elapsed_time": "4:16:01", "remaining_time": "1:07:34"}
+{"current_steps": 270, "total_steps": 340, "loss": 0.2777, "lr": 9.892586135419022e-06, "epoch": 3.9705882352941178, "percentage": 79.41, "elapsed_time": "4:16:54", "remaining_time": "1:06:36"}
+{"current_steps": 271, "total_steps": 340, "loss": 0.2771, "lr": 9.623803333811713e-06, "epoch": 3.985294117647059, "percentage": 79.71, "elapsed_time": "4:17:48", "remaining_time": "1:05:38"}
+{"current_steps": 272, "total_steps": 340, "loss": 0.2599, "lr": 9.358222275240884e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "4:18:43", "remaining_time": "1:04:40"}
+{"current_steps": 273, "total_steps": 340, "loss": 0.2593, "lr": 9.095870952753647e-06, "epoch": 4.014705882352941, "percentage": 80.29, "elapsed_time": "4:22:19", "remaining_time": "1:04:22"}
+{"current_steps": 274, "total_steps": 340, "loss": 0.262, "lr": 8.83677701897318e-06, "epoch": 4.029411764705882, "percentage": 80.59, "elapsed_time": "4:23:16", "remaining_time": "1:03:25"}
+{"current_steps": 275, "total_steps": 340, "loss": 0.261, "lr": 8.580967783184055e-06, "epoch": 4.044117647058823, "percentage": 80.88, "elapsed_time": "4:24:12", "remaining_time": "1:02:26"}
+{"current_steps": 276, "total_steps": 340, "loss": 0.2622, "lr": 8.328470208453683e-06, "epoch": 4.0588235294117645, "percentage": 81.18, "elapsed_time": "4:25:09", "remaining_time": "1:01:29"}
+{"current_steps": 277, "total_steps": 340, "loss": 0.2577, "lr": 8.07931090879042e-06, "epoch": 4.073529411764706, "percentage": 81.47, "elapsed_time": "4:26:05", "remaining_time": "1:00:31"}
+{"current_steps": 278, "total_steps": 340, "loss": 0.2617, "lr": 7.833516146338329e-06, "epoch": 4.088235294117647, "percentage": 81.76, "elapsed_time": "4:27:02", "remaining_time": "0:59:33"}
+{"current_steps": 279, "total_steps": 340, "loss": 0.2641, "lr": 7.591111828609059e-06, "epoch": 4.102941176470588, "percentage": 82.06, "elapsed_time": "4:27:57", "remaining_time": "0:58:35"}
+{"current_steps": 280, "total_steps": 340, "loss": 0.2638, "lr": 7.3521235057511364e-06, "epoch": 4.117647058823529, "percentage": 82.35, "elapsed_time": "4:28:53", "remaining_time": "0:57:37"}
+{"current_steps": 281, "total_steps": 340, "loss": 0.2606, "lr": 7.116576367856871e-06, "epoch": 4.132352941176471, "percentage": 82.65, "elapsed_time": "4:29:49", "remaining_time": "0:56:39"}
+{"current_steps": 282, "total_steps": 340, "loss": 0.2613, "lr": 6.884495242307285e-06, "epoch": 4.147058823529412, "percentage": 82.94, "elapsed_time": "4:30:44", "remaining_time": "0:55:41"}
+{"current_steps": 283, "total_steps": 340, "loss": 0.2618, "lr": 6.655904591155224e-06, "epoch": 4.161764705882353, "percentage": 83.24, "elapsed_time": "4:31:38", "remaining_time": "0:54:42"}
+{"current_steps": 284, "total_steps": 340, "loss": 0.2637, "lr": 6.430828508546936e-06, "epoch": 4.176470588235294, "percentage": 83.53, "elapsed_time": "4:32:34", "remaining_time": "0:53:44"}
+{"current_steps": 285, "total_steps": 340, "loss": 0.2615, "lr": 6.209290718182539e-06, "epoch": 4.1911764705882355, "percentage": 83.82, "elapsed_time": "4:33:31", "remaining_time": "0:52:47"}
+{"current_steps": 286, "total_steps": 340, "loss": 0.265, "lr": 5.991314570815441e-06, "epoch": 4.205882352941177, "percentage": 84.12, "elapsed_time": "4:34:29", "remaining_time": "0:51:49"}
+{"current_steps": 287, "total_steps": 340, "loss": 0.2602, "lr": 5.776923041791076e-06, "epoch": 4.220588235294118, "percentage": 84.41, "elapsed_time": "4:35:24", "remaining_time": "0:50:51"}
+{"current_steps": 288, "total_steps": 340, "loss": 0.2575, "lr": 5.566138728625294e-06, "epoch": 4.235294117647059, "percentage": 84.71, "elapsed_time": "4:36:20", "remaining_time": "0:49:53"}
+{"current_steps": 289, "total_steps": 340, "loss": 0.2566, "lr": 5.358983848622452e-06, "epoch": 4.25, "percentage": 85.0, "elapsed_time": "4:37:17", "remaining_time": "0:48:56"}
+{"current_steps": 290, "total_steps": 340, "loss": 0.2595, "lr": 5.15548023653369e-06, "epoch": 4.264705882352941, "percentage": 85.29, "elapsed_time": "4:38:15", "remaining_time": "0:47:58"}
+{"current_steps": 291, "total_steps": 340, "loss": 0.2622, "lr": 4.955649342255462e-06, "epoch": 4.279411764705882, "percentage": 85.59, "elapsed_time": "4:39:09", "remaining_time": "0:47:00"}
+{"current_steps": 292, "total_steps": 340, "loss": 0.2605, "lr": 4.7595122285686215e-06, "epoch": 4.294117647058823, "percentage": 85.88, "elapsed_time": "4:40:05", "remaining_time": "0:46:02"}
+{"current_steps": 293, "total_steps": 340, "loss": 0.262, "lr": 4.567089568918403e-06, "epoch": 4.3088235294117645, "percentage": 86.18, "elapsed_time": "4:41:02", "remaining_time": "0:45:04"}
+{"current_steps": 294, "total_steps": 340, "loss": 0.2577, "lr": 4.3784016452353526e-06, "epoch": 4.323529411764706, "percentage": 86.47, "elapsed_time": "4:41:58", "remaining_time": "0:44:07"}
+{"current_steps": 295, "total_steps": 340, "loss": 0.2626, "lr": 4.193468345797511e-06, "epoch": 4.338235294117647, "percentage": 86.76, "elapsed_time": "4:42:55", "remaining_time": "0:43:09"}
+{"current_steps": 296, "total_steps": 340, "loss": 0.2631, "lr": 4.012309163134194e-06, "epoch": 4.352941176470588, "percentage": 87.06, "elapsed_time": "4:43:51", "remaining_time": "0:42:11"}
+{"current_steps": 297, "total_steps": 340, "loss": 0.2606, "lr": 3.8349431919713655e-06, "epoch": 4.367647058823529, "percentage": 87.35, "elapsed_time": "4:44:48", "remaining_time": "0:41:14"}
+{"current_steps": 298, "total_steps": 340, "loss": 0.2584, "lr": 3.6613891272190506e-06, "epoch": 4.382352941176471, "percentage": 87.65, "elapsed_time": "4:45:44", "remaining_time": "0:40:16"}
+{"current_steps": 299, "total_steps": 340, "loss": 0.2623, "lr": 3.49166526200079e-06, "epoch": 4.397058823529412, "percentage": 87.94, "elapsed_time": "4:46:38", "remaining_time": "0:39:18"}
+{"current_steps": 300, "total_steps": 340, "loss": 0.2607, "lr": 3.325789485725488e-06, "epoch": 4.411764705882353, "percentage": 88.24, "elapsed_time": "4:47:34", "remaining_time": "0:38:20"}
+{"current_steps": 301, "total_steps": 340, "loss": 0.2648, "lr": 3.163779282201853e-06, "epoch": 4.426470588235294, "percentage": 88.53, "elapsed_time": "4:48:31", "remaining_time": "0:37:23"}
+{"current_steps": 302, "total_steps": 340, "loss": 0.2612, "lr": 3.0056517277955357e-06, "epoch": 4.4411764705882355, "percentage": 88.82, "elapsed_time": "4:49:28", "remaining_time": "0:36:25"}
+{"current_steps": 303, "total_steps": 340, "loss": 0.2617, "lr": 2.8514234896291904e-06, "epoch": 4.455882352941177, "percentage": 89.12, "elapsed_time": "4:50:25", "remaining_time": "0:35:27"}
+{"current_steps": 304, "total_steps": 340, "loss": 0.2656, "lr": 2.7011108238257723e-06, "epoch": 4.470588235294118, "percentage": 89.41, "elapsed_time": "4:51:22", "remaining_time": "0:34:30"}
+{"current_steps": 305, "total_steps": 340, "loss": 0.2651, "lr": 2.5547295737950475e-06, "epoch": 4.485294117647059, "percentage": 89.71, "elapsed_time": "4:52:18", "remaining_time": "0:33:32"}
+{"current_steps": 306, "total_steps": 340, "loss": 0.2647, "lr": 2.4122951685636674e-06, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "4:53:15", "remaining_time": "0:32:35"}
+{"current_steps": 307, "total_steps": 340, "loss": 0.2588, "lr": 2.2738226211489024e-06, "epoch": 4.514705882352941, "percentage": 90.29, "elapsed_time": "4:54:06", "remaining_time": "0:31:36"}
+{"current_steps": 308, "total_steps": 340, "loss": 0.2628, "lr": 2.1393265269762197e-06, "epoch": 4.529411764705882, "percentage": 90.59, "elapsed_time": "4:55:06", "remaining_time": "0:30:39"}
+{"current_steps": 309, "total_steps": 340, "loss": 0.2621, "lr": 2.008821062340891e-06, "epoch": 4.544117647058823, "percentage": 90.88, "elapsed_time": "4:56:04", "remaining_time": "0:29:42"}
+{"current_steps": 310, "total_steps": 340, "loss": 0.2604, "lr": 1.8823199829137406e-06, "epoch": 4.5588235294117645, "percentage": 91.18, "elapsed_time": "4:57:01", "remaining_time": "0:28:44"}
+{"current_steps": 311, "total_steps": 340, "loss": 0.2626, "lr": 1.7598366222912933e-06, "epoch": 4.573529411764706, "percentage": 91.47, "elapsed_time": "4:57:57", "remaining_time": "0:27:47"}
+{"current_steps": 312, "total_steps": 340, "loss": 0.2567, "lr": 1.6413838905903556e-06, "epoch": 4.588235294117647, "percentage": 91.76, "elapsed_time": "4:58:52", "remaining_time": "0:26:49"}
+{"current_steps": 313, "total_steps": 340, "loss": 0.2618, "lr": 1.5269742730872384e-06, "epoch": 4.602941176470588, "percentage": 92.06, "elapsed_time": "4:59:47", "remaining_time": "0:25:51"}
+{"current_steps": 314, "total_steps": 340, "loss": 0.2624, "lr": 1.4166198289017952e-06, "epoch": 4.617647058823529, "percentage": 92.35, "elapsed_time": "5:00:44", "remaining_time": "0:24:54"}
+{"current_steps": 315, "total_steps": 340, "loss": 0.2624, "lr": 1.3103321897263421e-06, "epoch": 4.632352941176471, "percentage": 92.65, "elapsed_time": "5:01:39", "remaining_time": "0:23:56"}
+{"current_steps": 316, "total_steps": 340, "loss": 0.2594, "lr": 1.2081225585996248e-06, "epoch": 4.647058823529412, "percentage": 92.94, "elapsed_time": "5:02:34", "remaining_time": "0:22:58"}
+{"current_steps": 317, "total_steps": 340, "loss": 0.2622, "lr": 1.1100017087260205e-06, "epoch": 4.661764705882353, "percentage": 93.24, "elapsed_time": "5:03:29", "remaining_time": "0:22:01"}
+{"current_steps": 318, "total_steps": 340, "loss": 0.2636, "lr": 1.015979982339994e-06, "epoch": 4.676470588235294, "percentage": 93.53, "elapsed_time": "5:04:27", "remaining_time": "0:21:03"}
+{"current_steps": 319, "total_steps": 340, "loss": 0.2603, "lr": 9.260672896159728e-07, "epoch": 4.6911764705882355, "percentage": 93.82, "elapsed_time": "5:05:24", "remaining_time": "0:20:06"}
+{"current_steps": 320, "total_steps": 340, "loss": 0.2606, "lr": 8.402731076238191e-07, "epoch": 4.705882352941177, "percentage": 94.12, "elapsed_time": "5:06:21", "remaining_time": "0:19:08"}
+{"current_steps": 321, "total_steps": 340, "loss": 0.2593, "lr": 7.586064793298998e-07, "epoch": 4.720588235294118, "percentage": 94.41, "elapsed_time": "5:07:18", "remaining_time": "0:18:11"}
+{"current_steps": 322, "total_steps": 340, "loss": 0.2654, "lr": 6.810760126439287e-07, "epoch": 4.735294117647059, "percentage": 94.71, "elapsed_time": "5:08:16", "remaining_time": "0:17:13"}
+{"current_steps": 323, "total_steps": 340, "loss": 0.2621, "lr": 6.076898795116792e-07, "epoch": 4.75, "percentage": 95.0, "elapsed_time": "5:09:13", "remaining_time": "0:16:16"}
+{"current_steps": 324, "total_steps": 340, "loss": 0.2615, "lr": 5.384558150536201e-07, "epoch": 4.764705882352941, "percentage": 95.29, "elapsed_time": "5:10:09", "remaining_time": "0:15:18"}
+{"current_steps": 325, "total_steps": 340, "loss": 0.2606, "lr": 4.7338111674962495e-07, "epoch": 4.779411764705882, "percentage": 95.59, "elapsed_time": "5:11:06", "remaining_time": "0:14:21"}
+{"current_steps": 326, "total_steps": 340, "loss": 0.2621, "lr": 4.124726436697879e-07, "epoch": 4.794117647058823, "percentage": 95.88, "elapsed_time": "5:12:02", "remaining_time": "0:13:24"}
+{"current_steps": 327, "total_steps": 340, "loss": 0.2646, "lr": 3.557368157514596e-07, "epoch": 4.8088235294117645, "percentage": 96.18, "elapsed_time": "5:12:58", "remaining_time": "0:12:26"}
+{"current_steps": 328, "total_steps": 340, "loss": 0.2625, "lr": 3.031796131225706e-07, "epoch": 4.823529411764706, "percentage": 96.47, "elapsed_time": "5:13:54", "remaining_time": "0:11:29"}
+{"current_steps": 329, "total_steps": 340, "loss": 0.2592, "lr": 2.548065754712914e-07, "epoch": 4.838235294117647, "percentage": 96.76, "elapsed_time": "5:14:51", "remaining_time": "0:10:31"}
+{"current_steps": 330, "total_steps": 340, "loss": 0.2625, "lr": 2.1062280146215252e-07, "epoch": 4.852941176470588, "percentage": 97.06, "elapsed_time": "5:15:48", "remaining_time": "0:09:34"}
+{"current_steps": 331, "total_steps": 340, "loss": 0.2635, "lr": 1.706329481986213e-07, "epoch": 4.867647058823529, "percentage": 97.35, "elapsed_time": "5:16:44", "remaining_time": "0:08:36"}
+{"current_steps": 332, "total_steps": 340, "loss": 0.2637, "lr": 1.3484123073222332e-07, "epoch": 4.882352941176471, "percentage": 97.65, "elapsed_time": "5:17:40", "remaining_time": "0:07:39"}
+{"current_steps": 333, "total_steps": 340, "loss": 0.2637, "lr": 1.0325142161827561e-07, "epoch": 4.897058823529412, "percentage": 97.94, "elapsed_time": "5:18:37", "remaining_time": "0:06:41"}
+{"current_steps": 334, "total_steps": 340, "loss": 0.2586, "lr": 7.586685051823584e-08, "epoch": 4.911764705882353, "percentage": 98.24, "elapsed_time": "5:19:35", "remaining_time": "0:05:44"}
+{"current_steps": 335, "total_steps": 340, "loss": 0.2603, "lr": 5.2690403848760785e-08, "epoch": 4.926470588235294, "percentage": 98.53, "elapsed_time": "5:20:32", "remaining_time": "0:04:47"}
+{"current_steps": 336, "total_steps": 340, "loss": 0.2622, "lr": 3.3724524477447564e-08, "epoch": 4.9411764705882355, "percentage": 98.82, "elapsed_time": "5:21:30", "remaining_time": "0:03:49"}
+{"current_steps": 337, "total_steps": 340, "loss": 0.2542, "lr": 1.897121146536396e-08, "epoch": 4.955882352941177, "percentage": 99.12, "elapsed_time": "5:22:28", "remaining_time": "0:02:52"}
+{"current_steps": 338, "total_steps": 340, "loss": 0.2582, "lr": 8.432019856345896e-09, "epoch": 4.970588235294118, "percentage": 99.41, "elapsed_time": "5:23:24", "remaining_time": "0:01:54"}
+{"current_steps": 339, "total_steps": 340, "loss": 0.2564, "lr": 2.1080605130752162e-09, "epoch": 4.985294117647059, "percentage": 99.71, "elapsed_time": "5:24:19", "remaining_time": "0:00:57"}
+{"current_steps": 340, "total_steps": 340, "loss": 0.2511, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:25:15", "remaining_time": "0:00:00"}
+{"current_steps": 340, "total_steps": 340, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:30:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2422 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 2.547836181388219,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.693,
+      "step": 1
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 2.5270813414533366,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.6892,
+      "step": 2
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 2.355483907211656,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.6851,
+      "step": 3
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 1.8130870424308736,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.6513,
+      "step": 4
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 1.2216520407231852,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.6231,
+      "step": 5
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 1.503718312141216,
+      "learning_rate": 1.4117647058823532e-05,
+      "loss": 0.6169,
+      "step": 6
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 1.7964660884238277,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 0.5687,
+      "step": 7
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.7269912533351832,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 0.5586,
+      "step": 8
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 0.7251113424301481,
+      "learning_rate": 2.1176470588235296e-05,
+      "loss": 0.5208,
+      "step": 9
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.1160352667226052,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.5086,
+      "step": 10
+    },
+    {
+      "epoch": 0.16176470588235295,
+      "grad_norm": 0.9015674485810162,
+      "learning_rate": 2.5882352941176475e-05,
+      "loss": 0.4903,
+      "step": 11
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.7153137232697248,
+      "learning_rate": 2.8235294117647063e-05,
+      "loss": 0.4841,
+      "step": 12
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 0.8088993429376143,
+      "learning_rate": 3.0588235294117644e-05,
+      "loss": 0.4711,
+      "step": 13
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 0.5653053624299016,
+      "learning_rate": 3.294117647058824e-05,
+      "loss": 0.4567,
+      "step": 14
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.5534586516972508,
+      "learning_rate": 3.529411764705883e-05,
+      "loss": 0.4522,
+      "step": 15
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.5736228520847013,
+      "learning_rate": 3.7647058823529415e-05,
+      "loss": 0.4415,
+      "step": 16
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.4337208100637674,
+      "learning_rate": 4e-05,
+      "loss": 0.4327,
+      "step": 17
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 0.4876347786470063,
+      "learning_rate": 4.235294117647059e-05,
+      "loss": 0.43,
+      "step": 18
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 0.4061097022997626,
+      "learning_rate": 4.470588235294118e-05,
+      "loss": 0.4317,
+      "step": 19
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.4103637458773689,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.43,
+      "step": 20
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 0.3888995331551954,
+      "learning_rate": 4.941176470588236e-05,
+      "loss": 0.4199,
+      "step": 21
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 0.3268371484433097,
+      "learning_rate": 5.176470588235295e-05,
+      "loss": 0.4185,
+      "step": 22
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 0.39223698739269497,
+      "learning_rate": 5.411764705882354e-05,
+      "loss": 0.4128,
+      "step": 23
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.2779761293219138,
+      "learning_rate": 5.6470588235294126e-05,
+      "loss": 0.4043,
+      "step": 24
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.3989443078505564,
+      "learning_rate": 5.8823529411764714e-05,
+      "loss": 0.4089,
+      "step": 25
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 0.38093200095401203,
+      "learning_rate": 6.117647058823529e-05,
+      "loss": 0.4017,
+      "step": 26
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": 0.4064320796173135,
+      "learning_rate": 6.352941176470589e-05,
+      "loss": 0.4011,
+      "step": 27
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.4971422289820653,
+      "learning_rate": 6.588235294117648e-05,
+      "loss": 0.3989,
+      "step": 28
+    },
+    {
+      "epoch": 0.4264705882352941,
+      "grad_norm": 0.7406572881589351,
+      "learning_rate": 6.823529411764707e-05,
+      "loss": 0.4051,
+      "step": 29
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.8206793701783639,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.406,
+      "step": 30
+    },
+    {
+      "epoch": 0.45588235294117646,
+      "grad_norm": 0.46999206766579715,
+      "learning_rate": 7.294117647058824e-05,
+      "loss": 0.3959,
+      "step": 31
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.7832181937714577,
+      "learning_rate": 7.529411764705883e-05,
+      "loss": 0.3979,
+      "step": 32
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": 0.6729630572440819,
+      "learning_rate": 7.764705882352942e-05,
+      "loss": 0.4037,
+      "step": 33
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5845843059576046,
+      "learning_rate": 8e-05,
+      "loss": 0.3981,
+      "step": 34
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.5179039508771461,
+      "learning_rate": 7.999789193948694e-05,
+      "loss": 0.3899,
+      "step": 35
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.8446247503414208,
+      "learning_rate": 7.999156798014366e-05,
+      "loss": 0.3919,
+      "step": 36
+    },
+    {
+      "epoch": 0.5441176470588235,
+      "grad_norm": 0.5811147704566235,
+      "learning_rate": 7.998102878853464e-05,
+      "loss": 0.3842,
+      "step": 37
+    },
+    {
+      "epoch": 0.5588235294117647,
+      "grad_norm": 0.7042141225204365,
+      "learning_rate": 7.996627547552256e-05,
+      "loss": 0.3887,
+      "step": 38
+    },
+    {
+      "epoch": 0.5735294117647058,
+      "grad_norm": 0.5162453656112366,
+      "learning_rate": 7.994730959615125e-05,
+      "loss": 0.3801,
+      "step": 39
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.6306069956051037,
+      "learning_rate": 7.992413314948177e-05,
+      "loss": 0.3872,
+      "step": 40
+    },
+    {
+      "epoch": 0.6029411764705882,
+      "grad_norm": 0.4954620508512063,
+      "learning_rate": 7.989674857838173e-05,
+      "loss": 0.3799,
+      "step": 41
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "grad_norm": 0.4655956434769946,
+      "learning_rate": 7.986515876926777e-05,
+      "loss": 0.3795,
+      "step": 42
+    },
+    {
+      "epoch": 0.6323529411764706,
+      "grad_norm": 0.4180599863638677,
+      "learning_rate": 7.982936705180139e-05,
+      "loss": 0.3797,
+      "step": 43
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.3370827795593815,
+      "learning_rate": 7.978937719853786e-05,
+      "loss": 0.3713,
+      "step": 44
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.302709681434872,
+      "learning_rate": 7.974519342452872e-05,
+      "loss": 0.37,
+      "step": 45
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 0.35605679848702854,
+      "learning_rate": 7.969682038687744e-05,
+      "loss": 0.3706,
+      "step": 46
+    },
+    {
+      "epoch": 0.6911764705882353,
+      "grad_norm": 0.3386095408702867,
+      "learning_rate": 7.964426318424855e-05,
+      "loss": 0.3717,
+      "step": 47
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.3740443449230433,
+      "learning_rate": 7.958752735633022e-05,
+      "loss": 0.3678,
+      "step": 48
+    },
+    {
+      "epoch": 0.7205882352941176,
+      "grad_norm": 0.291877051555131,
+      "learning_rate": 7.952661888325038e-05,
+      "loss": 0.3667,
+      "step": 49
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.22798970572724098,
+      "learning_rate": 7.946154418494639e-05,
+      "loss": 0.3658,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3017794055631277,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.366,
+      "step": 51
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.2183488887265105,
+      "learning_rate": 7.931892398735608e-05,
+      "loss": 0.364,
+      "step": 52
+    },
+    {
+      "epoch": 0.7794117647058824,
+      "grad_norm": 0.2651745781496878,
+      "learning_rate": 7.92413935206701e-05,
+      "loss": 0.36,
+      "step": 53
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": 0.25030378975718287,
+      "learning_rate": 7.915972689237618e-05,
+      "loss": 0.3629,
+      "step": 54
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.2531618636697317,
+      "learning_rate": 7.907393271038403e-05,
+      "loss": 0.3548,
+      "step": 55
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.33260642234735066,
+      "learning_rate": 7.898402001766002e-05,
+      "loss": 0.364,
+      "step": 56
+    },
+    {
+      "epoch": 0.8382352941176471,
+      "grad_norm": 0.41115101334491694,
+      "learning_rate": 7.888999829127398e-05,
+      "loss": 0.3578,
+      "step": 57
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 0.44590061545961934,
+      "learning_rate": 7.879187744140039e-05,
+      "loss": 0.3607,
+      "step": 58
+    },
+    {
+      "epoch": 0.8676470588235294,
+      "grad_norm": 0.522962751461851,
+      "learning_rate": 7.868966781027367e-05,
+      "loss": 0.3592,
+      "step": 59
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.6601512591505266,
+      "learning_rate": 7.858338017109822e-05,
+      "loss": 0.3657,
+      "step": 60
+    },
+    {
+      "epoch": 0.8970588235294118,
+      "grad_norm": 0.5825651454852345,
+      "learning_rate": 7.847302572691277e-05,
+      "loss": 0.3625,
+      "step": 61
+    },
+    {
+      "epoch": 0.9117647058823529,
+      "grad_norm": 0.42428578770971376,
+      "learning_rate": 7.835861610940965e-05,
+      "loss": 0.3613,
+      "step": 62
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "grad_norm": 0.3717888932030909,
+      "learning_rate": 7.824016337770872e-05,
+      "loss": 0.3573,
+      "step": 63
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.42447915248441553,
+      "learning_rate": 7.811768001708627e-05,
+      "loss": 0.362,
+      "step": 64
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.3876778292466403,
+      "learning_rate": 7.799117893765913e-05,
+      "loss": 0.3557,
+      "step": 65
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 0.26608755562026015,
+      "learning_rate": 7.786067347302379e-05,
+      "loss": 0.3545,
+      "step": 66
+    },
+    {
+      "epoch": 0.9852941176470589,
+      "grad_norm": 0.3434111610187913,
+      "learning_rate": 7.77261773788511e-05,
+      "loss": 0.353,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3497537599784584,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.3545,
+      "step": 68
+    },
+    {
+      "epoch": 1.0147058823529411,
+      "grad_norm": 0.3391085192527439,
+      "learning_rate": 7.744527042620496e-05,
+      "loss": 0.3419,
+      "step": 69
+    },
+    {
+      "epoch": 1.0294117647058822,
+      "grad_norm": 0.5077627087325893,
+      "learning_rate": 7.729888917617424e-05,
+      "loss": 0.3471,
+      "step": 70
+    },
+    {
+      "epoch": 1.0441176470588236,
+      "grad_norm": 0.5532598557050799,
+      "learning_rate": 7.714857651037081e-05,
+      "loss": 0.3412,
+      "step": 71
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.5780960309028261,
+      "learning_rate": 7.699434827220448e-05,
+      "loss": 0.3428,
+      "step": 72
+    },
+    {
+      "epoch": 1.0735294117647058,
+      "grad_norm": 0.49974865026294507,
+      "learning_rate": 7.683622071779816e-05,
+      "loss": 0.3364,
+      "step": 73
+    },
+    {
+      "epoch": 1.088235294117647,
+      "grad_norm": 0.36747177299557693,
+      "learning_rate": 7.667421051427453e-05,
+      "loss": 0.3389,
+      "step": 74
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": 0.3669907335719105,
+      "learning_rate": 7.650833473799922e-05,
+      "loss": 0.3312,
+      "step": 75
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.3922235437218937,
+      "learning_rate": 7.633861087278095e-05,
+      "loss": 0.3293,
+      "step": 76
+    },
+    {
+      "epoch": 1.1323529411764706,
+      "grad_norm": 0.3719011690300337,
+      "learning_rate": 7.616505680802863e-05,
+      "loss": 0.3375,
+      "step": 77
+    },
+    {
+      "epoch": 1.1470588235294117,
+      "grad_norm": 0.3377098123124342,
+      "learning_rate": 7.598769083686582e-05,
+      "loss": 0.3405,
+      "step": 78
+    },
+    {
+      "epoch": 1.161764705882353,
+      "grad_norm": 0.29899552501628507,
+      "learning_rate": 7.58065316542025e-05,
+      "loss": 0.3351,
+      "step": 79
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.32828082894171606,
+      "learning_rate": 7.562159835476466e-05,
+      "loss": 0.3389,
+      "step": 80
+    },
+    {
+      "epoch": 1.1911764705882353,
+      "grad_norm": 0.3445874209931112,
+      "learning_rate": 7.543291043108159e-05,
+      "loss": 0.3378,
+      "step": 81
+    },
+    {
+      "epoch": 1.2058823529411764,
+      "grad_norm": 0.3023978628206444,
+      "learning_rate": 7.524048777143139e-05,
+      "loss": 0.3387,
+      "step": 82
+    },
+    {
+      "epoch": 1.2205882352941178,
+      "grad_norm": 0.25558483521205383,
+      "learning_rate": 7.504435065774455e-05,
+      "loss": 0.3306,
+      "step": 83
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.32953601128265847,
+      "learning_rate": 7.48445197634663e-05,
+      "loss": 0.3349,
+      "step": 84
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.33756326919937646,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.3324,
+      "step": 85
+    },
+    {
+      "epoch": 1.2647058823529411,
+      "grad_norm": 0.24120088917587124,
+      "learning_rate": 7.443386127137472e-05,
+      "loss": 0.3317,
+      "step": 86
+    },
+    {
+      "epoch": 1.2794117647058822,
+      "grad_norm": 0.2914122682482861,
+      "learning_rate": 7.422307695820893e-05,
+      "loss": 0.3346,
+      "step": 87
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.32020365300061576,
+      "learning_rate": 7.400868542918457e-05,
+      "loss": 0.3303,
+      "step": 88
+    },
+    {
+      "epoch": 1.3088235294117647,
+      "grad_norm": 0.2516025057415832,
+      "learning_rate": 7.379070928181747e-05,
+      "loss": 0.3351,
+      "step": 89
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "grad_norm": 0.25001986331755705,
+      "learning_rate": 7.356917149145308e-05,
+      "loss": 0.3353,
+      "step": 90
+    },
+    {
+      "epoch": 1.3382352941176472,
+      "grad_norm": 0.2792197235528977,
+      "learning_rate": 7.334409540884479e-05,
+      "loss": 0.3294,
+      "step": 91
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.28078783596981044,
+      "learning_rate": 7.311550475769272e-05,
+      "loss": 0.3248,
+      "step": 92
+    },
+    {
+      "epoch": 1.3676470588235294,
+      "grad_norm": 0.37967936203746205,
+      "learning_rate": 7.288342363214313e-05,
+      "loss": 0.3328,
+      "step": 93
+    },
+    {
+      "epoch": 1.3823529411764706,
+      "grad_norm": 0.5149190442137033,
+      "learning_rate": 7.264787649424888e-05,
+      "loss": 0.3312,
+      "step": 94
+    },
+    {
+      "epoch": 1.3970588235294117,
+      "grad_norm": 0.6122843221799549,
+      "learning_rate": 7.240888817139094e-05,
+      "loss": 0.3348,
+      "step": 95
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.5886981731078635,
+      "learning_rate": 7.216648385366167e-05,
+      "loss": 0.3395,
+      "step": 96
+    },
+    {
+      "epoch": 1.4264705882352942,
+      "grad_norm": 0.34409848388448383,
+      "learning_rate": 7.192068909120959e-05,
+      "loss": 0.3306,
+      "step": 97
+    },
+    {
+      "epoch": 1.4411764705882353,
+      "grad_norm": 0.2978091494500524,
+      "learning_rate": 7.167152979154634e-05,
+      "loss": 0.3334,
+      "step": 98
+    },
+    {
+      "epoch": 1.4558823529411764,
+      "grad_norm": 0.4400729737039225,
+      "learning_rate": 7.141903221681595e-05,
+      "loss": 0.3404,
+      "step": 99
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3694283042397561,
+      "learning_rate": 7.116322298102681e-05,
+      "loss": 0.3332,
+      "step": 100
+    },
+    {
+      "epoch": 1.4852941176470589,
+      "grad_norm": 0.2639067391873521,
+      "learning_rate": 7.090412904724636e-05,
+      "loss": 0.3313,
+      "step": 101
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.37416820779021187,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.3285,
+      "step": 102
+    },
+    {
+      "epoch": 1.5147058823529411,
+      "grad_norm": 0.33275488946271775,
+      "learning_rate": 7.037619666618829e-05,
+      "loss": 0.3361,
+      "step": 103
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.23894606263596457,
+      "learning_rate": 7.010741386458099e-05,
+      "loss": 0.3388,
+      "step": 104
+    },
+    {
+      "epoch": 1.5441176470588234,
+      "grad_norm": 0.3668325550727754,
+      "learning_rate": 6.983545765045774e-05,
+      "loss": 0.3311,
+      "step": 105
+    },
+    {
+      "epoch": 1.5588235294117647,
+      "grad_norm": 0.2399104316842811,
+      "learning_rate": 6.956035668882637e-05,
+      "loss": 0.3297,
+      "step": 106
+    },
+    {
+      "epoch": 1.5735294117647058,
+      "grad_norm": 0.2357871283562126,
+      "learning_rate": 6.928213997616059e-05,
+      "loss": 0.3318,
+      "step": 107
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.2849131707817035,
+      "learning_rate": 6.900083683734372e-05,
+      "loss": 0.3304,
+      "step": 108
+    },
+    {
+      "epoch": 1.6029411764705883,
+      "grad_norm": 0.17423798370987492,
+      "learning_rate": 6.871647692257768e-05,
+      "loss": 0.3276,
+      "step": 109
+    },
+    {
+      "epoch": 1.6176470588235294,
+      "grad_norm": 0.2548925157793133,
+      "learning_rate": 6.842909020425789e-05,
+      "loss": 0.334,
+      "step": 110
+    },
+    {
+      "epoch": 1.6323529411764706,
+      "grad_norm": 0.24942793454876405,
+      "learning_rate": 6.8138706973814e-05,
+      "loss": 0.3286,
+      "step": 111
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.18689295644396056,
+      "learning_rate": 6.784535783851708e-05,
+      "loss": 0.3266,
+      "step": 112
+    },
+    {
+      "epoch": 1.6617647058823528,
+      "grad_norm": 0.2911151755362797,
+      "learning_rate": 6.754907371825355e-05,
+      "loss": 0.3262,
+      "step": 113
+    },
+    {
+      "epoch": 1.6764705882352942,
+      "grad_norm": 0.27837463790987516,
+      "learning_rate": 6.724988584226616e-05,
+      "loss": 0.3279,
+      "step": 114
+    },
+    {
+      "epoch": 1.6911764705882353,
+      "grad_norm": 0.28908336337027807,
+      "learning_rate": 6.69478257458623e-05,
+      "loss": 0.3281,
+      "step": 115
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.34403162565227147,
+      "learning_rate": 6.664292526709001e-05,
+      "loss": 0.3313,
+      "step": 116
+    },
+    {
+      "epoch": 1.7205882352941178,
+      "grad_norm": 0.29186151217355694,
+      "learning_rate": 6.633521654338233e-05,
+      "loss": 0.3334,
+      "step": 117
+    },
+    {
+      "epoch": 1.7352941176470589,
+      "grad_norm": 0.3213370329801203,
+      "learning_rate": 6.602473200816969e-05,
+      "loss": 0.3267,
+      "step": 118
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.30160846132752556,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.3242,
+      "step": 119
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.26892209589390914,
+      "learning_rate": 6.539556669639691e-05,
+      "loss": 0.3244,
+      "step": 120
+    },
+    {
+      "epoch": 1.7794117647058822,
+      "grad_norm": 0.2440948850515908,
+      "learning_rate": 6.507695223576428e-05,
+      "loss": 0.3229,
+      "step": 121
+    },
+    {
+      "epoch": 1.7941176470588234,
+      "grad_norm": 0.20672290158202897,
+      "learning_rate": 6.475569458849178e-05,
+      "loss": 0.331,
+      "step": 122
+    },
+    {
+      "epoch": 1.8088235294117647,
+      "grad_norm": 0.2459670080944092,
+      "learning_rate": 6.443182761610752e-05,
+      "loss": 0.3321,
+      "step": 123
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.2704407966484609,
+      "learning_rate": 6.410538545517026e-05,
+      "loss": 0.3288,
+      "step": 124
+    },
+    {
+      "epoch": 1.8382352941176472,
+      "grad_norm": 0.23662938749712678,
+      "learning_rate": 6.377640251367148e-05,
+      "loss": 0.3285,
+      "step": 125
+    },
+    {
+      "epoch": 1.8529411764705883,
+      "grad_norm": 0.23508733004486604,
+      "learning_rate": 6.344491346740859e-05,
+      "loss": 0.3265,
+      "step": 126
+    },
+    {
+      "epoch": 1.8676470588235294,
+      "grad_norm": 0.15905797582955938,
+      "learning_rate": 6.311095325633006e-05,
+      "loss": 0.3287,
+      "step": 127
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.16194725388549308,
+      "learning_rate": 6.277455708085255e-05,
+      "loss": 0.3193,
+      "step": 128
+    },
+    {
+      "epoch": 1.8970588235294117,
+      "grad_norm": 0.19431781452308503,
+      "learning_rate": 6.24357603981508e-05,
+      "loss": 0.3218,
+      "step": 129
+    },
+    {
+      "epoch": 1.9117647058823528,
+      "grad_norm": 0.1530375931457355,
+      "learning_rate": 6.209459891842023e-05,
+      "loss": 0.3232,
+      "step": 130
+    },
+    {
+      "epoch": 1.9264705882352942,
+      "grad_norm": 0.20552563428946305,
+      "learning_rate": 6.175110860111307e-05,
+      "loss": 0.3291,
+      "step": 131
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.16800259989430927,
+      "learning_rate": 6.140532565114801e-05,
+      "loss": 0.3255,
+      "step": 132
+    },
+    {
+      "epoch": 1.9558823529411766,
+      "grad_norm": 0.15539283189220082,
+      "learning_rate": 6.105728651509424e-05,
+      "loss": 0.3254,
+      "step": 133
+    },
+    {
+      "epoch": 1.9705882352941178,
+      "grad_norm": 0.16103547056804585,
+      "learning_rate": 6.070702787732971e-05,
+      "loss": 0.3249,
+      "step": 134
+    },
+    {
+      "epoch": 1.9852941176470589,
+      "grad_norm": 0.16239367515131709,
+      "learning_rate": 6.0354586656174606e-05,
+      "loss": 0.3288,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20166055674169706,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.3099,
+      "step": 136
+    },
+    {
+      "epoch": 2.014705882352941,
+      "grad_norm": 0.24260127096827225,
+      "learning_rate": 5.964330528331234e-05,
+      "loss": 0.3056,
+      "step": 137
+    },
+    {
+      "epoch": 2.0294117647058822,
+      "grad_norm": 0.33127332158017103,
+      "learning_rate": 5.9284540102813964e-05,
+      "loss": 0.3,
+      "step": 138
+    },
+    {
+      "epoch": 2.0441176470588234,
+      "grad_norm": 0.43353541229148657,
+      "learning_rate": 5.892374227344041e-05,
+      "loss": 0.308,
+      "step": 139
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.49315921894412995,
+      "learning_rate": 5.856094982437454e-05,
+      "loss": 0.3067,
+      "step": 140
+    },
+    {
+      "epoch": 2.073529411764706,
+      "grad_norm": 0.450512729936066,
+      "learning_rate": 5.819620099503818e-05,
+      "loss": 0.3101,
+      "step": 141
+    },
+    {
+      "epoch": 2.088235294117647,
+      "grad_norm": 0.343920919271517,
+      "learning_rate": 5.782953423106154e-05,
+      "loss": 0.3046,
+      "step": 142
+    },
+    {
+      "epoch": 2.1029411764705883,
+      "grad_norm": 0.2814078808698335,
+      "learning_rate": 5.746098818023093e-05,
+      "loss": 0.2988,
+      "step": 143
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.3529797938787429,
+      "learning_rate": 5.709060168841524e-05,
+      "loss": 0.3033,
+      "step": 144
+    },
+    {
+      "epoch": 2.1323529411764706,
+      "grad_norm": 0.33042737999638,
+      "learning_rate": 5.6718413795471346e-05,
+      "loss": 0.3028,
+      "step": 145
+    },
+    {
+      "epoch": 2.1470588235294117,
+      "grad_norm": 0.16519735683489525,
+      "learning_rate": 5.634446373112926e-05,
+      "loss": 0.3035,
+      "step": 146
+    },
+    {
+      "epoch": 2.161764705882353,
+      "grad_norm": 0.23206099454265375,
+      "learning_rate": 5.596879091085724e-05,
+      "loss": 0.3001,
+      "step": 147
+    },
+    {
+      "epoch": 2.176470588235294,
+      "grad_norm": 0.2771142062084271,
+      "learning_rate": 5.5591434931707176e-05,
+      "loss": 0.3005,
+      "step": 148
+    },
+    {
+      "epoch": 2.1911764705882355,
+      "grad_norm": 0.2431821354495366,
+      "learning_rate": 5.5212435568141036e-05,
+      "loss": 0.3045,
+      "step": 149
+    },
+    {
+      "epoch": 2.2058823529411766,
+      "grad_norm": 0.18676533826823546,
+      "learning_rate": 5.4831832767838436e-05,
+      "loss": 0.2993,
+      "step": 150
+    },
+    {
+      "epoch": 2.2205882352941178,
+      "grad_norm": 0.21179962464182328,
+      "learning_rate": 5.444966664748613e-05,
+      "loss": 0.2967,
+      "step": 151
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.2277766014598405,
+      "learning_rate": 5.406597748854947e-05,
+      "loss": 0.2993,
+      "step": 152
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.19342351829324006,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.3044,
+      "step": 153
+    },
+    {
+      "epoch": 2.264705882352941,
+      "grad_norm": 0.21064512781524572,
+      "learning_rate": 5.329419197918639e-05,
+      "loss": 0.3062,
+      "step": 154
+    },
+    {
+      "epoch": 2.2794117647058822,
+      "grad_norm": 0.15702816077320908,
+      "learning_rate": 5.29061769772878e-05,
+      "loss": 0.2995,
+      "step": 155
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.17947407344934332,
+      "learning_rate": 5.251680162528618e-05,
+      "loss": 0.3013,
+      "step": 156
+    },
+    {
+      "epoch": 2.3088235294117645,
+      "grad_norm": 0.18466536636530687,
+      "learning_rate": 5.212610696452174e-05,
+      "loss": 0.3036,
+      "step": 157
+    },
+    {
+      "epoch": 2.323529411764706,
+      "grad_norm": 0.1680929482668945,
+      "learning_rate": 5.173413417539385e-05,
+      "loss": 0.3029,
+      "step": 158
+    },
+    {
+      "epoch": 2.338235294117647,
+      "grad_norm": 0.1654731382812225,
+      "learning_rate": 5.134092457302044e-05,
+      "loss": 0.3024,
+      "step": 159
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.15258036230353525,
+      "learning_rate": 5.0946519602883326e-05,
+      "loss": 0.3037,
+      "step": 160
+    },
+    {
+      "epoch": 2.3676470588235294,
+      "grad_norm": 0.1491955575134207,
+      "learning_rate": 5.0550960836459674e-05,
+      "loss": 0.3044,
+      "step": 161
+    },
+    {
+      "epoch": 2.3823529411764706,
+      "grad_norm": 0.14545439455177017,
+      "learning_rate": 5.0154289966840315e-05,
+      "loss": 0.2954,
+      "step": 162
+    },
+    {
+      "epoch": 2.3970588235294117,
+      "grad_norm": 0.13499905174566654,
+      "learning_rate": 4.975654880433509e-05,
+      "loss": 0.2991,
+      "step": 163
+    },
+    {
+      "epoch": 2.411764705882353,
+      "grad_norm": 0.13529530394095032,
+      "learning_rate": 4.935777927206595e-05,
+      "loss": 0.301,
+      "step": 164
+    },
+    {
+      "epoch": 2.426470588235294,
+      "grad_norm": 0.14447147193835977,
+      "learning_rate": 4.895802340154813e-05,
+      "loss": 0.3038,
+      "step": 165
+    },
+    {
+      "epoch": 2.4411764705882355,
+      "grad_norm": 0.1368779663418461,
+      "learning_rate": 4.85573233282599e-05,
+      "loss": 0.3022,
+      "step": 166
+    },
+    {
+      "epoch": 2.4558823529411766,
+      "grad_norm": 0.13420641137376216,
+      "learning_rate": 4.815572128720138e-05,
+      "loss": 0.3049,
+      "step": 167
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.12163815573974876,
+      "learning_rate": 4.7753259608442804e-05,
+      "loss": 0.2998,
+      "step": 168
+    },
+    {
+      "epoch": 2.485294117647059,
+      "grad_norm": 0.15356753682422525,
+      "learning_rate": 4.734998071266282e-05,
+      "loss": 0.298,
+      "step": 169
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.11474062387695687,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.3068,
+      "step": 170
+    },
+    {
+      "epoch": 2.514705882352941,
+      "grad_norm": 0.15293267687494932,
+      "learning_rate": 4.65411413789586e-05,
+      "loss": 0.3005,
+      "step": 171
+    },
+    {
+      "epoch": 2.5294117647058822,
+      "grad_norm": 0.13885259280209167,
+      "learning_rate": 4.6135666195147426e-05,
+      "loss": 0.2994,
+      "step": 172
+    },
+    {
+      "epoch": 2.5441176470588234,
+      "grad_norm": 0.11212797930990655,
+      "learning_rate": 4.572954429355487e-05,
+      "loss": 0.3026,
+      "step": 173
+    },
+    {
+      "epoch": 2.5588235294117645,
+      "grad_norm": 0.1441373090862667,
+      "learning_rate": 4.532281848065816e-05,
+      "loss": 0.3014,
+      "step": 174
+    },
+    {
+      "epoch": 2.5735294117647056,
+      "grad_norm": 0.1438877611890079,
+      "learning_rate": 4.491553162658857e-05,
+      "loss": 0.3044,
+      "step": 175
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.12603413712308525,
+      "learning_rate": 4.450772666061285e-05,
+      "loss": 0.301,
+      "step": 176
+    },
+    {
+      "epoch": 2.6029411764705883,
+      "grad_norm": 0.12633770238098366,
+      "learning_rate": 4.409944656660828e-05,
+      "loss": 0.2965,
+      "step": 177
+    },
+    {
+      "epoch": 2.6176470588235294,
+      "grad_norm": 0.13789374969079662,
+      "learning_rate": 4.369073437853208e-05,
+      "loss": 0.3009,
+      "step": 178
+    },
+    {
+      "epoch": 2.6323529411764706,
+      "grad_norm": 0.1402520516162208,
+      "learning_rate": 4.328163317588552e-05,
+      "loss": 0.298,
+      "step": 179
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.09904937633936901,
+      "learning_rate": 4.2872186079173106e-05,
+      "loss": 0.3013,
+      "step": 180
+    },
+    {
+      "epoch": 2.661764705882353,
+      "grad_norm": 0.1312793347901254,
+      "learning_rate": 4.2462436245357724e-05,
+      "loss": 0.3,
+      "step": 181
+    },
+    {
+      "epoch": 2.6764705882352944,
+      "grad_norm": 0.09621059323368814,
+      "learning_rate": 4.205242686331159e-05,
+      "loss": 0.3029,
+      "step": 182
+    },
+    {
+      "epoch": 2.6911764705882355,
+      "grad_norm": 0.10807537972219632,
+      "learning_rate": 4.164220114926414e-05,
+      "loss": 0.2978,
+      "step": 183
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 0.10722934994246927,
+      "learning_rate": 4.123180234224682e-05,
+      "loss": 0.2998,
+      "step": 184
+    },
+    {
+      "epoch": 2.7205882352941178,
+      "grad_norm": 0.1064704662992324,
+      "learning_rate": 4.0821273699535625e-05,
+      "loss": 0.3013,
+      "step": 185
+    },
+    {
+      "epoch": 2.735294117647059,
+      "grad_norm": 0.10969792661155021,
+      "learning_rate": 4.04106584920916e-05,
+      "loss": 0.3006,
+      "step": 186
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.12146189911454472,
+      "learning_rate": 4e-05,
+      "loss": 0.3031,
+      "step": 187
+    },
+    {
+      "epoch": 2.764705882352941,
+      "grad_norm": 0.11305408445478238,
+      "learning_rate": 3.9589341507908415e-05,
+      "loss": 0.3037,
+      "step": 188
+    },
+    {
+      "epoch": 2.7794117647058822,
+      "grad_norm": 0.13033799624199852,
+      "learning_rate": 3.917872630046439e-05,
+      "loss": 0.3032,
+      "step": 189
+    },
+    {
+      "epoch": 2.7941176470588234,
+      "grad_norm": 0.10937208565515465,
+      "learning_rate": 3.8768197657753194e-05,
+      "loss": 0.3035,
+      "step": 190
+    },
+    {
+      "epoch": 2.8088235294117645,
+      "grad_norm": 0.11386446489403948,
+      "learning_rate": 3.835779885073588e-05,
+      "loss": 0.2985,
+      "step": 191
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.10573108090134906,
+      "learning_rate": 3.794757313668841e-05,
+      "loss": 0.3025,
+      "step": 192
+    },
+    {
+      "epoch": 2.838235294117647,
+      "grad_norm": 0.09522893522850687,
+      "learning_rate": 3.753756375464229e-05,
+      "loss": 0.2964,
+      "step": 193
+    },
+    {
+      "epoch": 2.8529411764705883,
+      "grad_norm": 0.10763504421587497,
+      "learning_rate": 3.71278139208269e-05,
+      "loss": 0.2983,
+      "step": 194
+    },
+    {
+      "epoch": 2.8676470588235294,
+      "grad_norm": 0.09673967344497875,
+      "learning_rate": 3.67183668241145e-05,
+      "loss": 0.303,
+      "step": 195
+    },
+    {
+      "epoch": 2.8823529411764706,
+      "grad_norm": 0.11019580337657149,
+      "learning_rate": 3.630926562146792e-05,
+      "loss": 0.2977,
+      "step": 196
+    },
+    {
+      "epoch": 2.8970588235294117,
+      "grad_norm": 0.09457792059050557,
+      "learning_rate": 3.5900553433391724e-05,
+      "loss": 0.2987,
+      "step": 197
+    },
+    {
+      "epoch": 2.911764705882353,
+      "grad_norm": 0.08738325053473636,
+      "learning_rate": 3.549227333938716e-05,
+      "loss": 0.2986,
+      "step": 198
+    },
+    {
+      "epoch": 2.9264705882352944,
+      "grad_norm": 0.09681306300823637,
+      "learning_rate": 3.5084468373411444e-05,
+      "loss": 0.3013,
+      "step": 199
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.09249395424589109,
+      "learning_rate": 3.467718151934187e-05,
+      "loss": 0.2972,
+      "step": 200
+    },
+    {
+      "epoch": 2.9558823529411766,
+      "grad_norm": 0.09703820251292773,
+      "learning_rate": 3.427045570644515e-05,
+      "loss": 0.2979,
+      "step": 201
+    },
+    {
+      "epoch": 2.9705882352941178,
+      "grad_norm": 0.10540258782003765,
+      "learning_rate": 3.386433380485258e-05,
+      "loss": 0.2992,
+      "step": 202
+    },
+    {
+      "epoch": 2.985294117647059,
+      "grad_norm": 0.08015062850340511,
+      "learning_rate": 3.34588586210414e-05,
+      "loss": 0.3011,
+      "step": 203
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.14706722768632058,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.2806,
+      "step": 204
+    },
+    {
+      "epoch": 3.014705882352941,
+      "grad_norm": 0.10603496844146229,
+      "learning_rate": 3.2650019287337184e-05,
+      "loss": 0.2799,
+      "step": 205
+    },
+    {
+      "epoch": 3.0294117647058822,
+      "grad_norm": 0.15530639149269276,
+      "learning_rate": 3.22467403915572e-05,
+      "loss": 0.2781,
+      "step": 206
+    },
+    {
+      "epoch": 3.0441176470588234,
+      "grad_norm": 0.1421223150968687,
+      "learning_rate": 3.184427871279863e-05,
+      "loss": 0.282,
+      "step": 207
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.14419949652005803,
+      "learning_rate": 3.144267667174011e-05,
+      "loss": 0.2776,
+      "step": 208
+    },
+    {
+      "epoch": 3.073529411764706,
+      "grad_norm": 0.12994406412161302,
+      "learning_rate": 3.1041976598451884e-05,
+      "loss": 0.2781,
+      "step": 209
+    },
+    {
+      "epoch": 3.088235294117647,
+      "grad_norm": 0.14614171687593527,
+      "learning_rate": 3.064222072793407e-05,
+      "loss": 0.2765,
+      "step": 210
+    },
+    {
+      "epoch": 3.1029411764705883,
+      "grad_norm": 0.12016869114374024,
+      "learning_rate": 3.0243451195664914e-05,
+      "loss": 0.2783,
+      "step": 211
+    },
+    {
+      "epoch": 3.1176470588235294,
+      "grad_norm": 0.1310851029344073,
+      "learning_rate": 2.984571003315969e-05,
+      "loss": 0.2781,
+      "step": 212
+    },
+    {
+      "epoch": 3.1323529411764706,
+      "grad_norm": 0.11922587006224326,
+      "learning_rate": 2.944903916354032e-05,
+      "loss": 0.2795,
+      "step": 213
+    },
+    {
+      "epoch": 3.1470588235294117,
+      "grad_norm": 0.12710795880675843,
+      "learning_rate": 2.905348039711669e-05,
+      "loss": 0.2784,
+      "step": 214
+    },
+    {
+      "epoch": 3.161764705882353,
+      "grad_norm": 0.11445734817339984,
+      "learning_rate": 2.865907542697957e-05,
+      "loss": 0.2758,
+      "step": 215
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 0.1300689688100464,
+      "learning_rate": 2.8265865824606165e-05,
+      "loss": 0.2758,
+      "step": 216
+    },
+    {
+      "epoch": 3.1911764705882355,
+      "grad_norm": 0.09831374725437492,
+      "learning_rate": 2.7873893035478265e-05,
+      "loss": 0.2748,
+      "step": 217
+    },
+    {
+      "epoch": 3.2058823529411766,
+      "grad_norm": 0.1272913228663667,
+      "learning_rate": 2.7483198374713836e-05,
+      "loss": 0.2746,
+      "step": 218
+    },
+    {
+      "epoch": 3.2205882352941178,
+      "grad_norm": 0.0993483978526809,
+      "learning_rate": 2.7093823022712217e-05,
+      "loss": 0.2739,
+      "step": 219
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.09886695511684795,
+      "learning_rate": 2.6705808020813622e-05,
+      "loss": 0.2832,
+      "step": 220
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.0998986520318052,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.2743,
+      "step": 221
+    },
+    {
+      "epoch": 3.264705882352941,
+      "grad_norm": 0.0964816428580283,
+      "learning_rate": 2.5934022511450528e-05,
+      "loss": 0.2762,
+      "step": 222
+    },
+    {
+      "epoch": 3.2794117647058822,
+      "grad_norm": 0.09255980694012796,
+      "learning_rate": 2.5550333352513885e-05,
+      "loss": 0.2782,
+      "step": 223
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 0.0988289109757557,
+      "learning_rate": 2.5168167232161574e-05,
+      "loss": 0.2748,
+      "step": 224
+    },
+    {
+      "epoch": 3.3088235294117645,
+      "grad_norm": 0.0884234456508421,
+      "learning_rate": 2.4787564431858977e-05,
+      "loss": 0.2753,
+      "step": 225
+    },
+    {
+      "epoch": 3.323529411764706,
+      "grad_norm": 0.09774336930093334,
+      "learning_rate": 2.4408565068292827e-05,
+      "loss": 0.2751,
+      "step": 226
+    },
+    {
+      "epoch": 3.338235294117647,
+      "grad_norm": 0.0883002824327121,
+      "learning_rate": 2.4031209089142773e-05,
+      "loss": 0.2773,
+      "step": 227
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.09215211229010013,
+      "learning_rate": 2.3655536268870744e-05,
+      "loss": 0.2752,
+      "step": 228
+    },
+    {
+      "epoch": 3.3676470588235294,
+      "grad_norm": 0.08094179064778044,
+      "learning_rate": 2.328158620452868e-05,
+      "loss": 0.2729,
+      "step": 229
+    },
+    {
+      "epoch": 3.3823529411764706,
+      "grad_norm": 0.09692135730954927,
+      "learning_rate": 2.2909398311584775e-05,
+      "loss": 0.2731,
+      "step": 230
+    },
+    {
+      "epoch": 3.3970588235294117,
+      "grad_norm": 0.0813183018452283,
+      "learning_rate": 2.2539011819769056e-05,
+      "loss": 0.2782,
+      "step": 231
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 0.08149910156743696,
+      "learning_rate": 2.2170465768938473e-05,
+      "loss": 0.275,
+      "step": 232
+    },
+    {
+      "epoch": 3.426470588235294,
+      "grad_norm": 0.08503586167349093,
+      "learning_rate": 2.1803799004961824e-05,
+      "loss": 0.2766,
+      "step": 233
+    },
+    {
+      "epoch": 3.4411764705882355,
+      "grad_norm": 0.07599564665486494,
+      "learning_rate": 2.1439050175625474e-05,
+      "loss": 0.2759,
+      "step": 234
+    },
+    {
+      "epoch": 3.4558823529411766,
+      "grad_norm": 0.08451424035355402,
+      "learning_rate": 2.1076257726559603e-05,
+      "loss": 0.2795,
+      "step": 235
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 0.07467914550010295,
+      "learning_rate": 2.0715459897186046e-05,
+      "loss": 0.2767,
+      "step": 236
+    },
+    {
+      "epoch": 3.485294117647059,
+      "grad_norm": 0.09085541610657201,
+      "learning_rate": 2.0356694716687687e-05,
+      "loss": 0.2785,
+      "step": 237
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.0734615712405951,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.2739,
+      "step": 238
+    },
+    {
+      "epoch": 3.514705882352941,
+      "grad_norm": 0.07717163991035296,
+      "learning_rate": 1.964541334382541e-05,
+      "loss": 0.2729,
+      "step": 239
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.07496301816518236,
+      "learning_rate": 1.9292972122670303e-05,
+      "loss": 0.2752,
+      "step": 240
+    },
+    {
+      "epoch": 3.5441176470588234,
+      "grad_norm": 0.08080347359960849,
+      "learning_rate": 1.8942713484905762e-05,
+      "loss": 0.2801,
+      "step": 241
+    },
+    {
+      "epoch": 3.5588235294117645,
+      "grad_norm": 0.0738257225960406,
+      "learning_rate": 1.8594674348851992e-05,
+      "loss": 0.2767,
+      "step": 242
+    },
+    {
+      "epoch": 3.5735294117647056,
+      "grad_norm": 0.07389506773645138,
+      "learning_rate": 1.824889139888694e-05,
+      "loss": 0.2773,
+      "step": 243
+    },
+    {
+      "epoch": 3.588235294117647,
+      "grad_norm": 0.070294801390775,
+      "learning_rate": 1.790540108157977e-05,
+      "loss": 0.2763,
+      "step": 244
+    },
+    {
+      "epoch": 3.6029411764705883,
+      "grad_norm": 0.068704655766595,
+      "learning_rate": 1.756423960184922e-05,
+      "loss": 0.2781,
+      "step": 245
+    },
+    {
+      "epoch": 3.6176470588235294,
+      "grad_norm": 0.06594242125553404,
+      "learning_rate": 1.7225442919147467e-05,
+      "loss": 0.2757,
+      "step": 246
+    },
+    {
+      "epoch": 3.6323529411764706,
+      "grad_norm": 0.06969707402390993,
+      "learning_rate": 1.6889046743669957e-05,
+      "loss": 0.2776,
+      "step": 247
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 0.06492677835336866,
+      "learning_rate": 1.6555086532591425e-05,
+      "loss": 0.2781,
+      "step": 248
+    },
+    {
+      "epoch": 3.661764705882353,
+      "grad_norm": 0.06331911499148075,
+      "learning_rate": 1.6223597486328534e-05,
+      "loss": 0.279,
+      "step": 249
+    },
+    {
+      "epoch": 3.6764705882352944,
+      "grad_norm": 0.06722098051730128,
+      "learning_rate": 1.589461454482975e-05,
+      "loss": 0.2802,
+      "step": 250
+    },
+    {
+      "epoch": 3.6911764705882355,
+      "grad_norm": 0.06266474278629547,
+      "learning_rate": 1.556817238389249e-05,
+      "loss": 0.2781,
+      "step": 251
+    },
+    {
+      "epoch": 3.7058823529411766,
+      "grad_norm": 0.07000155789305507,
+      "learning_rate": 1.5244305411508217e-05,
+      "loss": 0.278,
+      "step": 252
+    },
+    {
+      "epoch": 3.7205882352941178,
+      "grad_norm": 0.061574644987438566,
+      "learning_rate": 1.4923047764235752e-05,
+      "loss": 0.2767,
+      "step": 253
+    },
+    {
+      "epoch": 3.735294117647059,
+      "grad_norm": 0.0682684963649869,
+      "learning_rate": 1.4604433303603092e-05,
+      "loss": 0.2732,
+      "step": 254
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.0642818898133848,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.2743,
+      "step": 255
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.06713851434875447,
+      "learning_rate": 1.3975267991830327e-05,
+      "loss": 0.2817,
+      "step": 256
+    },
+    {
+      "epoch": 3.7794117647058822,
+      "grad_norm": 0.06828899506125703,
+      "learning_rate": 1.3664783456617703e-05,
+      "loss": 0.2725,
+      "step": 257
+    },
+    {
+      "epoch": 3.7941176470588234,
+      "grad_norm": 0.07069453573008218,
+      "learning_rate": 1.3357074732909996e-05,
+      "loss": 0.2775,
+      "step": 258
+    },
+    {
+      "epoch": 3.8088235294117645,
+      "grad_norm": 0.06390051742059577,
+      "learning_rate": 1.3052174254137713e-05,
+      "loss": 0.2771,
+      "step": 259
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.06129666220940109,
+      "learning_rate": 1.275011415773383e-05,
+      "loss": 0.2789,
+      "step": 260
+    },
+    {
+      "epoch": 3.838235294117647,
+      "grad_norm": 0.065817213580326,
+      "learning_rate": 1.2450926281746458e-05,
+      "loss": 0.274,
+      "step": 261
+    },
+    {
+      "epoch": 3.8529411764705883,
+      "grad_norm": 0.06519904576862424,
+      "learning_rate": 1.2154642161482939e-05,
+      "loss": 0.2771,
+      "step": 262
+    },
+    {
+      "epoch": 3.8676470588235294,
+      "grad_norm": 0.06313901880567484,
+      "learning_rate": 1.1861293026186007e-05,
+      "loss": 0.2754,
+      "step": 263
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 0.06296057703800705,
+      "learning_rate": 1.1570909795742118e-05,
+      "loss": 0.2732,
+      "step": 264
+    },
+    {
+      "epoch": 3.8970588235294117,
+      "grad_norm": 0.06544715501817833,
+      "learning_rate": 1.1283523077422327e-05,
+      "loss": 0.2797,
+      "step": 265
+    },
+    {
+      "epoch": 3.911764705882353,
+      "grad_norm": 0.0650053871447722,
+      "learning_rate": 1.0999163162656296e-05,
+      "loss": 0.279,
+      "step": 266
+    },
+    {
+      "epoch": 3.9264705882352944,
+      "grad_norm": 0.06600064138970108,
+      "learning_rate": 1.0717860023839424e-05,
+      "loss": 0.276,
+      "step": 267
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.06210716465473454,
+      "learning_rate": 1.0439643311173642e-05,
+      "loss": 0.2768,
+      "step": 268
+    },
+    {
+      "epoch": 3.9558823529411766,
+      "grad_norm": 0.06401894182204264,
+      "learning_rate": 1.0164542349542273e-05,
+      "loss": 0.2788,
+      "step": 269
+    },
+    {
+      "epoch": 3.9705882352941178,
+      "grad_norm": 0.06372281222639016,
+      "learning_rate": 9.892586135419022e-06,
+      "loss": 0.2777,
+      "step": 270
+    },
+    {
+      "epoch": 3.985294117647059,
+      "grad_norm": 0.05892561579737352,
+      "learning_rate": 9.623803333811713e-06,
+      "loss": 0.2771,
+      "step": 271
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12086246389399692,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.2599,
+      "step": 272
+    },
+    {
+      "epoch": 4.014705882352941,
+      "grad_norm": 0.08602389508274347,
+      "learning_rate": 9.095870952753647e-06,
+      "loss": 0.2593,
+      "step": 273
+    },
+    {
+      "epoch": 4.029411764705882,
+      "grad_norm": 0.07197077150088015,
+      "learning_rate": 8.83677701897318e-06,
+      "loss": 0.262,
+      "step": 274
+    },
+    {
+      "epoch": 4.044117647058823,
+      "grad_norm": 0.0968580360252349,
+      "learning_rate": 8.580967783184055e-06,
+      "loss": 0.261,
+      "step": 275
+    },
+    {
+      "epoch": 4.0588235294117645,
+      "grad_norm": 0.09014393537599821,
+      "learning_rate": 8.328470208453683e-06,
+      "loss": 0.2622,
+      "step": 276
+    },
+    {
+      "epoch": 4.073529411764706,
+      "grad_norm": 0.0789945543394142,
+      "learning_rate": 8.07931090879042e-06,
+      "loss": 0.2577,
+      "step": 277
+    },
+    {
+      "epoch": 4.088235294117647,
+      "grad_norm": 0.08815856516590073,
+      "learning_rate": 7.833516146338329e-06,
+      "loss": 0.2617,
+      "step": 278
+    },
+    {
+      "epoch": 4.102941176470588,
+      "grad_norm": 0.08015266822256034,
+      "learning_rate": 7.591111828609059e-06,
+      "loss": 0.2641,
+      "step": 279
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.08154629673882077,
+      "learning_rate": 7.3521235057511364e-06,
+      "loss": 0.2638,
+      "step": 280
+    },
+    {
+      "epoch": 4.132352941176471,
+      "grad_norm": 0.08290035992126818,
+      "learning_rate": 7.116576367856871e-06,
+      "loss": 0.2606,
+      "step": 281
+    },
+    {
+      "epoch": 4.147058823529412,
+      "grad_norm": 0.07674741527367407,
+      "learning_rate": 6.884495242307285e-06,
+      "loss": 0.2613,
+      "step": 282
+    },
+    {
+      "epoch": 4.161764705882353,
+      "grad_norm": 0.07292754427620451,
+      "learning_rate": 6.655904591155224e-06,
+      "loss": 0.2618,
+      "step": 283
+    },
+    {
+      "epoch": 4.176470588235294,
+      "grad_norm": 0.0736899911159241,
+      "learning_rate": 6.430828508546936e-06,
+      "loss": 0.2637,
+      "step": 284
+    },
+    {
+      "epoch": 4.1911764705882355,
+      "grad_norm": 0.07217050587422956,
+      "learning_rate": 6.209290718182539e-06,
+      "loss": 0.2615,
+      "step": 285
+    },
+    {
+      "epoch": 4.205882352941177,
+      "grad_norm": 0.07553232921098052,
+      "learning_rate": 5.991314570815441e-06,
+      "loss": 0.265,
+      "step": 286
+    },
+    {
+      "epoch": 4.220588235294118,
+      "grad_norm": 0.06886285952389541,
+      "learning_rate": 5.776923041791076e-06,
+      "loss": 0.2602,
+      "step": 287
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 0.06173078424810273,
+      "learning_rate": 5.566138728625294e-06,
+      "loss": 0.2575,
+      "step": 288
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.06592763687997258,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.2566,
+      "step": 289
+    },
+    {
+      "epoch": 4.264705882352941,
+      "grad_norm": 0.06767164583052036,
+      "learning_rate": 5.15548023653369e-06,
+      "loss": 0.2595,
+      "step": 290
+    },
+    {
+      "epoch": 4.279411764705882,
+      "grad_norm": 0.06893875689961178,
+      "learning_rate": 4.955649342255462e-06,
+      "loss": 0.2622,
+      "step": 291
+    },
+    {
+      "epoch": 4.294117647058823,
+      "grad_norm": 0.0627731194283305,
+      "learning_rate": 4.7595122285686215e-06,
+      "loss": 0.2605,
+      "step": 292
+    },
+    {
+      "epoch": 4.3088235294117645,
+      "grad_norm": 0.06183425105989223,
+      "learning_rate": 4.567089568918403e-06,
+      "loss": 0.262,
+      "step": 293
+    },
+    {
+      "epoch": 4.323529411764706,
+      "grad_norm": 0.08304190651695828,
+      "learning_rate": 4.3784016452353526e-06,
+      "loss": 0.2577,
+      "step": 294
+    },
+    {
+      "epoch": 4.338235294117647,
+      "grad_norm": 0.06162011756699104,
+      "learning_rate": 4.193468345797511e-06,
+      "loss": 0.2626,
+      "step": 295
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 0.06077784990223975,
+      "learning_rate": 4.012309163134194e-06,
+      "loss": 0.2631,
+      "step": 296
+    },
+    {
+      "epoch": 4.367647058823529,
+      "grad_norm": 0.059344232351091784,
+      "learning_rate": 3.8349431919713655e-06,
+      "loss": 0.2606,
+      "step": 297
+    },
+    {
+      "epoch": 4.382352941176471,
+      "grad_norm": 0.053110563118761965,
+      "learning_rate": 3.6613891272190506e-06,
+      "loss": 0.2584,
+      "step": 298
+    },
+    {
+      "epoch": 4.397058823529412,
+      "grad_norm": 0.0550813714546073,
+      "learning_rate": 3.49166526200079e-06,
+      "loss": 0.2623,
+      "step": 299
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.05497952308193732,
+      "learning_rate": 3.325789485725488e-06,
+      "loss": 0.2607,
+      "step": 300
+    },
+    {
+      "epoch": 4.426470588235294,
+      "grad_norm": 0.056505023992606394,
+      "learning_rate": 3.163779282201853e-06,
+      "loss": 0.2648,
+      "step": 301
+    },
+    {
+      "epoch": 4.4411764705882355,
+      "grad_norm": 0.055167426784272444,
+      "learning_rate": 3.0056517277955357e-06,
+      "loss": 0.2612,
+      "step": 302
+    },
+    {
+      "epoch": 4.455882352941177,
+      "grad_norm": 0.052033455176057224,
+      "learning_rate": 2.8514234896291904e-06,
+      "loss": 0.2617,
+      "step": 303
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.05049118136446942,
+      "learning_rate": 2.7011108238257723e-06,
+      "loss": 0.2656,
+      "step": 304
+    },
+    {
+      "epoch": 4.485294117647059,
+      "grad_norm": 0.04973325645683792,
+      "learning_rate": 2.5547295737950475e-06,
+      "loss": 0.2651,
+      "step": 305
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.05470312702591553,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.2647,
+      "step": 306
+    },
+    {
+      "epoch": 4.514705882352941,
+      "grad_norm": 0.04975562581567009,
+      "learning_rate": 2.2738226211489024e-06,
+      "loss": 0.2588,
+      "step": 307
+    },
+    {
+      "epoch": 4.529411764705882,
+      "grad_norm": 0.04990586736807332,
+      "learning_rate": 2.1393265269762197e-06,
+      "loss": 0.2628,
+      "step": 308
+    },
+    {
+      "epoch": 4.544117647058823,
+      "grad_norm": 0.048763186017272454,
+      "learning_rate": 2.008821062340891e-06,
+      "loss": 0.2621,
+      "step": 309
+    },
+    {
+      "epoch": 4.5588235294117645,
+      "grad_norm": 0.04772811522858683,
+      "learning_rate": 1.8823199829137406e-06,
+      "loss": 0.2604,
+      "step": 310
+    },
+    {
+      "epoch": 4.573529411764706,
+      "grad_norm": 0.04514011191017183,
+      "learning_rate": 1.7598366222912933e-06,
+      "loss": 0.2626,
+      "step": 311
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 0.0447568436808381,
+      "learning_rate": 1.6413838905903556e-06,
+      "loss": 0.2567,
+      "step": 312
+    },
+    {
+      "epoch": 4.602941176470588,
+      "grad_norm": 0.04828872191610463,
+      "learning_rate": 1.5269742730872384e-06,
+      "loss": 0.2618,
+      "step": 313
+    },
+    {
+      "epoch": 4.617647058823529,
+      "grad_norm": 0.048070892531791296,
+      "learning_rate": 1.4166198289017952e-06,
+      "loss": 0.2624,
+      "step": 314
+    },
+    {
+      "epoch": 4.632352941176471,
+      "grad_norm": 0.0481947096054082,
+      "learning_rate": 1.3103321897263421e-06,
+      "loss": 0.2624,
+      "step": 315
+    },
+    {
+      "epoch": 4.647058823529412,
+      "grad_norm": 0.0498006739485343,
+      "learning_rate": 1.2081225585996248e-06,
+      "loss": 0.2594,
+      "step": 316
+    },
+    {
+      "epoch": 4.661764705882353,
+      "grad_norm": 0.046785729335567995,
+      "learning_rate": 1.1100017087260205e-06,
+      "loss": 0.2622,
+      "step": 317
+    },
+    {
+      "epoch": 4.676470588235294,
+      "grad_norm": 0.04518076179941004,
+      "learning_rate": 1.015979982339994e-06,
+      "loss": 0.2636,
+      "step": 318
+    },
+    {
+      "epoch": 4.6911764705882355,
+      "grad_norm": 0.04627910929165888,
+      "learning_rate": 9.260672896159728e-07,
+      "loss": 0.2603,
+      "step": 319
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.04505892744233274,
+      "learning_rate": 8.402731076238191e-07,
+      "loss": 0.2606,
+      "step": 320
+    },
+    {
+      "epoch": 4.720588235294118,
+      "grad_norm": 0.04552316822622753,
+      "learning_rate": 7.586064793298998e-07,
+      "loss": 0.2593,
+      "step": 321
+    },
+    {
+      "epoch": 4.735294117647059,
+      "grad_norm": 0.045512369955118724,
+      "learning_rate": 6.810760126439287e-07,
+      "loss": 0.2654,
+      "step": 322
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.0451772973693403,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.2621,
+      "step": 323
+    },
+    {
+      "epoch": 4.764705882352941,
+      "grad_norm": 0.044079852747311694,
+      "learning_rate": 5.384558150536201e-07,
+      "loss": 0.2615,
+      "step": 324
+    },
+    {
+      "epoch": 4.779411764705882,
+      "grad_norm": 0.04455441736236055,
+      "learning_rate": 4.7338111674962495e-07,
+      "loss": 0.2606,
+      "step": 325
+    },
+    {
+      "epoch": 4.794117647058823,
+      "grad_norm": 0.04405689466623866,
+      "learning_rate": 4.124726436697879e-07,
+      "loss": 0.2621,
+      "step": 326
+    },
+    {
+      "epoch": 4.8088235294117645,
+      "grad_norm": 0.044529538816460816,
+      "learning_rate": 3.557368157514596e-07,
+      "loss": 0.2646,
+      "step": 327
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 0.04553425966459204,
+      "learning_rate": 3.031796131225706e-07,
+      "loss": 0.2625,
+      "step": 328
+    },
+    {
+      "epoch": 4.838235294117647,
+      "grad_norm": 0.04331163075687581,
+      "learning_rate": 2.548065754712914e-07,
+      "loss": 0.2592,
+      "step": 329
+    },
+    {
+      "epoch": 4.852941176470588,
+      "grad_norm": 0.045474788941501976,
+      "learning_rate": 2.1062280146215252e-07,
+      "loss": 0.2625,
+      "step": 330
+    },
+    {
+      "epoch": 4.867647058823529,
+      "grad_norm": 0.04615519000321619,
+      "learning_rate": 1.706329481986213e-07,
+      "loss": 0.2635,
+      "step": 331
+    },
+    {
+      "epoch": 4.882352941176471,
+      "grad_norm": 0.04427563364549322,
+      "learning_rate": 1.3484123073222332e-07,
+      "loss": 0.2637,
+      "step": 332
+    },
+    {
+      "epoch": 4.897058823529412,
+      "grad_norm": 0.04265147614885937,
+      "learning_rate": 1.0325142161827561e-07,
+      "loss": 0.2637,
+      "step": 333
+    },
+    {
+      "epoch": 4.911764705882353,
+      "grad_norm": 0.04295525693989313,
+      "learning_rate": 7.586685051823584e-08,
+      "loss": 0.2586,
+      "step": 334
+    },
+    {
+      "epoch": 4.926470588235294,
+      "grad_norm": 0.04243683788724124,
+      "learning_rate": 5.2690403848760785e-08,
+      "loss": 0.2603,
+      "step": 335
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.043654171470091575,
+      "learning_rate": 3.3724524477447564e-08,
+      "loss": 0.2622,
+      "step": 336
+    },
+    {
+      "epoch": 4.955882352941177,
+      "grad_norm": 0.04272527321797204,
+      "learning_rate": 1.897121146536396e-08,
+      "loss": 0.2542,
+      "step": 337
+    },
+    {
+      "epoch": 4.970588235294118,
+      "grad_norm": 0.04827925979026659,
+      "learning_rate": 8.432019856345896e-09,
+      "loss": 0.2582,
+      "step": 338
+    },
+    {
+      "epoch": 4.985294117647059,
+      "grad_norm": 0.042423900810093146,
+      "learning_rate": 2.1080605130752162e-09,
+      "loss": 0.2564,
+      "step": 339
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.07128915321863381,
+      "learning_rate": 0.0,
+      "loss": 0.2511,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "step": 340,
+      "total_flos": 1.915314895847424e+16,
+      "train_loss": 0.3188589934040518,
+      "train_runtime": 19815.4609,
+      "train_samples_per_second": 8.67,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 340,
+  "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": 1.915314895847424e+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 sha256:9e4e6ebbec20e6da97cfa5b362f71895a16230bf94aed21347f922148665479f
+size 7416