Upload model

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: b2_code_fasttext_pos_codeforces_neg_codereview_3k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# b2_code_fasttext_pos_codeforces_neg_codereview_3k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_code_fasttext_pos_codeforces_neg_codereview_3k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 96
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 6.474382962841354e+17,
+    "train_loss": 0.5183511296392003,
+    "train_runtime": 8671.5363,
+    "train_samples_per_second": 2.551,
+    "train_steps_per_second": 0.027
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e6376cb5eb5d46df7ce6674979d554646b16e1b21288ca9952138739a455e5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007aee784864b98e9af29b6165f18ce02520578e98ea54116a00bc2b1ac62ed3
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4559d30d8fc5c9ecdf43d830714ef488ec90c0eec9192349fcab204cdd896989
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91af70f851f2bbe783c4a1d72c88bb34f5a66f5361f46c09159a76fe4b7a75ff
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/Apr26_19-21-51_jpbot-001-38.jupiter.internal/events.out.tfevents.1745688148.jpbot-001-38.jupiter.internal.1458951.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cab4d0217117542a6e5e3bf0cfb14554fab6cd6199902b685b492a2c61f55d6
+size 54233

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-26 19:21:51", "end_time": "2025-04-26 21:47:07"}

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": 7.0,
+    "total_flos": 6.474382962841354e+17,
+    "train_loss": 0.5183511296392003,
+    "train_runtime": 8671.5363,
+    "train_samples_per_second": 2.551,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,232 @@
+{"current_steps": 1, "total_steps": 231, "loss": 1.0115, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:01:09", "remaining_time": "4:24:31"}
+{"current_steps": 2, "total_steps": 231, "loss": 1.0286, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:01:58", "remaining_time": "3:45:52"}
+{"current_steps": 3, "total_steps": 231, "loss": 1.0389, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:02:36", "remaining_time": "3:17:46"}
+{"current_steps": 4, "total_steps": 231, "loss": 1.0259, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:03:11", "remaining_time": "3:00:43"}
+{"current_steps": 5, "total_steps": 231, "loss": 0.9918, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:03:48", "remaining_time": "2:52:03"}
+{"current_steps": 6, "total_steps": 231, "loss": 0.9379, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:04:27", "remaining_time": "2:47:13"}
+{"current_steps": 7, "total_steps": 231, "loss": 0.9482, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:05:05", "remaining_time": "2:43:04"}
+{"current_steps": 8, "total_steps": 231, "loss": 0.9188, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:05:41", "remaining_time": "2:38:38"}
+{"current_steps": 9, "total_steps": 231, "loss": 0.9283, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:06:20", "remaining_time": "2:36:31"}
+{"current_steps": 10, "total_steps": 231, "loss": 0.9153, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:06:57", "remaining_time": "2:33:50"}
+{"current_steps": 11, "total_steps": 231, "loss": 0.8984, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:07:34", "remaining_time": "2:31:25"}
+{"current_steps": 12, "total_steps": 231, "loss": 0.8745, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:08:10", "remaining_time": "2:29:07"}
+{"current_steps": 13, "total_steps": 231, "loss": 0.8407, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:08:47", "remaining_time": "2:27:21"}
+{"current_steps": 14, "total_steps": 231, "loss": 0.8072, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:09:25", "remaining_time": "2:26:10"}
+{"current_steps": 15, "total_steps": 231, "loss": 0.8059, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:10:02", "remaining_time": "2:24:32"}
+{"current_steps": 16, "total_steps": 231, "loss": 0.7992, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:10:36", "remaining_time": "2:22:39"}
+{"current_steps": 17, "total_steps": 231, "loss": 0.781, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:11:13", "remaining_time": "2:21:22"}
+{"current_steps": 18, "total_steps": 231, "loss": 0.7467, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:11:45", "remaining_time": "2:19:13"}
+{"current_steps": 19, "total_steps": 231, "loss": 0.7772, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:12:22", "remaining_time": "2:18:09"}
+{"current_steps": 20, "total_steps": 231, "loss": 0.7322, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:12:59", "remaining_time": "2:16:59"}
+{"current_steps": 21, "total_steps": 231, "loss": 0.7542, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:13:38", "remaining_time": "2:16:21"}
+{"current_steps": 22, "total_steps": 231, "loss": 0.7272, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:14:15", "remaining_time": "2:15:27"}
+{"current_steps": 23, "total_steps": 231, "loss": 0.7264, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:14:51", "remaining_time": "2:14:25"}
+{"current_steps": 24, "total_steps": 231, "loss": 0.7198, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:15:26", "remaining_time": "2:13:15"}
+{"current_steps": 25, "total_steps": 231, "loss": 0.7314, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:16:05", "remaining_time": "2:12:37"}
+{"current_steps": 26, "total_steps": 231, "loss": 0.7092, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:16:43", "remaining_time": "2:11:55"}
+{"current_steps": 27, "total_steps": 231, "loss": 0.7022, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:17:23", "remaining_time": "2:11:21"}
+{"current_steps": 28, "total_steps": 231, "loss": 0.7131, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:18:01", "remaining_time": "2:10:37"}
+{"current_steps": 29, "total_steps": 231, "loss": 0.7071, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:18:37", "remaining_time": "2:09:40"}
+{"current_steps": 30, "total_steps": 231, "loss": 0.696, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:19:15", "remaining_time": "2:09:01"}
+{"current_steps": 31, "total_steps": 231, "loss": 0.6941, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:19:51", "remaining_time": "2:08:09"}
+{"current_steps": 32, "total_steps": 231, "loss": 0.6933, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:20:29", "remaining_time": "2:07:23"}
+{"current_steps": 33, "total_steps": 231, "loss": 0.6915, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:21:07", "remaining_time": "2:06:44"}
+{"current_steps": 34, "total_steps": 231, "loss": 0.6447, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:22:04", "remaining_time": "2:07:56"}
+{"current_steps": 35, "total_steps": 231, "loss": 0.6683, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:22:41", "remaining_time": "2:07:07"}
+{"current_steps": 36, "total_steps": 231, "loss": 0.6472, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:23:19", "remaining_time": "2:06:23"}
+{"current_steps": 37, "total_steps": 231, "loss": 0.6632, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:23:58", "remaining_time": "2:05:42"}
+{"current_steps": 38, "total_steps": 231, "loss": 0.6554, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:24:37", "remaining_time": "2:05:03"}
+{"current_steps": 39, "total_steps": 231, "loss": 0.6336, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:25:12", "remaining_time": "2:04:05"}
+{"current_steps": 40, "total_steps": 231, "loss": 0.6408, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:25:45", "remaining_time": "2:03:00"}
+{"current_steps": 41, "total_steps": 231, "loss": 0.6303, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:26:23", "remaining_time": "2:02:16"}
+{"current_steps": 42, "total_steps": 231, "loss": 0.6398, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:26:58", "remaining_time": "2:01:24"}
+{"current_steps": 43, "total_steps": 231, "loss": 0.6286, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:27:35", "remaining_time": "2:00:40"}
+{"current_steps": 44, "total_steps": 231, "loss": 0.6402, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:28:14", "remaining_time": "2:00:03"}
+{"current_steps": 45, "total_steps": 231, "loss": 0.6241, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:28:49", "remaining_time": "1:59:10"}
+{"current_steps": 46, "total_steps": 231, "loss": 0.6293, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:29:28", "remaining_time": "1:58:32"}
+{"current_steps": 47, "total_steps": 231, "loss": 0.6316, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:30:06", "remaining_time": "1:57:53"}
+{"current_steps": 48, "total_steps": 231, "loss": 0.6256, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:30:41", "remaining_time": "1:56:59"}
+{"current_steps": 49, "total_steps": 231, "loss": 0.6123, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:31:16", "remaining_time": "1:56:08"}
+{"current_steps": 50, "total_steps": 231, "loss": 0.6221, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:31:54", "remaining_time": "1:55:31"}
+{"current_steps": 51, "total_steps": 231, "loss": 0.6248, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:32:30", "remaining_time": "1:54:43"}
+{"current_steps": 52, "total_steps": 231, "loss": 0.6407, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:33:06", "remaining_time": "1:53:56"}
+{"current_steps": 53, "total_steps": 231, "loss": 0.6184, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:33:44", "remaining_time": "1:53:18"}
+{"current_steps": 54, "total_steps": 231, "loss": 0.6129, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:34:20", "remaining_time": "1:52:35"}
+{"current_steps": 55, "total_steps": 231, "loss": 0.6179, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:34:54", "remaining_time": "1:51:43"}
+{"current_steps": 56, "total_steps": 231, "loss": 0.6113, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:35:31", "remaining_time": "1:51:00"}
+{"current_steps": 57, "total_steps": 231, "loss": 0.6173, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:36:06", "remaining_time": "1:50:14"}
+{"current_steps": 58, "total_steps": 231, "loss": 0.617, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:36:43", "remaining_time": "1:49:31"}
+{"current_steps": 59, "total_steps": 231, "loss": 0.6085, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:37:20", "remaining_time": "1:48:51"}
+{"current_steps": 60, "total_steps": 231, "loss": 0.6203, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:37:57", "remaining_time": "1:48:10"}
+{"current_steps": 61, "total_steps": 231, "loss": 0.6146, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:38:32", "remaining_time": "1:47:24"}
+{"current_steps": 62, "total_steps": 231, "loss": 0.6063, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:39:09", "remaining_time": "1:46:44"}
+{"current_steps": 63, "total_steps": 231, "loss": 0.6301, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:39:44", "remaining_time": "1:45:59"}
+{"current_steps": 64, "total_steps": 231, "loss": 0.6001, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:40:21", "remaining_time": "1:45:17"}
+{"current_steps": 65, "total_steps": 231, "loss": 0.6119, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:40:57", "remaining_time": "1:44:35"}
+{"current_steps": 66, "total_steps": 231, "loss": 0.6099, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:41:35", "remaining_time": "1:43:58"}
+{"current_steps": 67, "total_steps": 231, "loss": 0.5596, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:42:38", "remaining_time": "1:44:23"}
+{"current_steps": 68, "total_steps": 231, "loss": 0.5585, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:43:12", "remaining_time": "1:43:35"}
+{"current_steps": 69, "total_steps": 231, "loss": 0.56, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:43:50", "remaining_time": "1:42:56"}
+{"current_steps": 70, "total_steps": 231, "loss": 0.5631, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:44:23", "remaining_time": "1:42:05"}
+{"current_steps": 71, "total_steps": 231, "loss": 0.5491, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:45:12", "remaining_time": "1:41:51"}
+{"current_steps": 72, "total_steps": 231, "loss": 0.5528, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:45:47", "remaining_time": "1:41:08"}
+{"current_steps": 73, "total_steps": 231, "loss": 0.545, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:46:25", "remaining_time": "1:40:29"}
+{"current_steps": 74, "total_steps": 231, "loss": 0.547, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:47:03", "remaining_time": "1:39:49"}
+{"current_steps": 75, "total_steps": 231, "loss": 0.5488, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:47:39", "remaining_time": "1:39:07"}
+{"current_steps": 76, "total_steps": 231, "loss": 0.5519, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:48:12", "remaining_time": "1:38:18"}
+{"current_steps": 77, "total_steps": 231, "loss": 0.5499, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:48:50", "remaining_time": "1:37:40"}
+{"current_steps": 78, "total_steps": 231, "loss": 0.5317, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:49:27", "remaining_time": "1:37:00"}
+{"current_steps": 79, "total_steps": 231, "loss": 0.5524, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:50:01", "remaining_time": "1:36:14"}
+{"current_steps": 80, "total_steps": 231, "loss": 0.5426, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:50:37", "remaining_time": "1:35:32"}
+{"current_steps": 81, "total_steps": 231, "loss": 0.5494, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:51:11", "remaining_time": "1:34:47"}
+{"current_steps": 82, "total_steps": 231, "loss": 0.5382, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:51:46", "remaining_time": "1:34:04"}
+{"current_steps": 83, "total_steps": 231, "loss": 0.5564, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:52:23", "remaining_time": "1:33:26"}
+{"current_steps": 84, "total_steps": 231, "loss": 0.5504, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:53:00", "remaining_time": "1:32:45"}
+{"current_steps": 85, "total_steps": 231, "loss": 0.5366, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:53:37", "remaining_time": "1:32:05"}
+{"current_steps": 86, "total_steps": 231, "loss": 0.5382, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:54:13", "remaining_time": "1:31:26"}
+{"current_steps": 87, "total_steps": 231, "loss": 0.5491, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:54:49", "remaining_time": "1:30:43"}
+{"current_steps": 88, "total_steps": 231, "loss": 0.5387, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:55:28", "remaining_time": "1:30:09"}
+{"current_steps": 89, "total_steps": 231, "loss": 0.5374, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:56:04", "remaining_time": "1:29:28"}
+{"current_steps": 90, "total_steps": 231, "loss": 0.539, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:56:42", "remaining_time": "1:28:51"}
+{"current_steps": 91, "total_steps": 231, "loss": 0.5483, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:57:20", "remaining_time": "1:28:12"}
+{"current_steps": 92, "total_steps": 231, "loss": 0.524, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:57:58", "remaining_time": "1:27:35"}
+{"current_steps": 93, "total_steps": 231, "loss": 0.5512, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "0:58:34", "remaining_time": "1:26:54"}
+{"current_steps": 94, "total_steps": 231, "loss": 0.5448, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "0:59:12", "remaining_time": "1:26:18"}
+{"current_steps": 95, "total_steps": 231, "loss": 0.541, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:59:48", "remaining_time": "1:25:36"}
+{"current_steps": 96, "total_steps": 231, "loss": 0.5473, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "1:00:23", "remaining_time": "1:24:56"}
+{"current_steps": 97, "total_steps": 231, "loss": 0.5615, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "1:01:02", "remaining_time": "1:24:19"}
+{"current_steps": 98, "total_steps": 231, "loss": 0.535, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "1:01:37", "remaining_time": "1:23:37"}
+{"current_steps": 99, "total_steps": 231, "loss": 0.5424, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "1:02:16", "remaining_time": "1:23:01"}
+{"current_steps": 100, "total_steps": 231, "loss": 0.4838, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "1:03:06", "remaining_time": "1:22:39"}
+{"current_steps": 101, "total_steps": 231, "loss": 0.4822, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "1:03:42", "remaining_time": "1:22:00"}
+{"current_steps": 102, "total_steps": 231, "loss": 0.4866, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "1:04:20", "remaining_time": "1:21:22"}
+{"current_steps": 103, "total_steps": 231, "loss": 0.4875, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "1:04:59", "remaining_time": "1:20:46"}
+{"current_steps": 104, "total_steps": 231, "loss": 0.4973, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "1:05:36", "remaining_time": "1:20:07"}
+{"current_steps": 105, "total_steps": 231, "loss": 0.4838, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "1:06:12", "remaining_time": "1:19:27"}
+{"current_steps": 106, "total_steps": 231, "loss": 0.4742, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "1:06:48", "remaining_time": "1:18:46"}
+{"current_steps": 107, "total_steps": 231, "loss": 0.4888, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "1:07:25", "remaining_time": "1:18:08"}
+{"current_steps": 108, "total_steps": 231, "loss": 0.491, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "1:07:57", "remaining_time": "1:17:24"}
+{"current_steps": 109, "total_steps": 231, "loss": 0.4843, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "1:08:34", "remaining_time": "1:16:45"}
+{"current_steps": 110, "total_steps": 231, "loss": 0.4916, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "1:09:10", "remaining_time": "1:16:05"}
+{"current_steps": 111, "total_steps": 231, "loss": 0.4855, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "1:09:46", "remaining_time": "1:15:25"}
+{"current_steps": 112, "total_steps": 231, "loss": 0.4858, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "1:10:23", "remaining_time": "1:14:47"}
+{"current_steps": 113, "total_steps": 231, "loss": 0.4755, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "1:11:02", "remaining_time": "1:14:10"}
+{"current_steps": 114, "total_steps": 231, "loss": 0.4803, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "1:11:40", "remaining_time": "1:13:33"}
+{"current_steps": 115, "total_steps": 231, "loss": 0.4859, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "1:12:17", "remaining_time": "1:12:55"}
+{"current_steps": 116, "total_steps": 231, "loss": 0.4758, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "1:12:52", "remaining_time": "1:12:14"}
+{"current_steps": 117, "total_steps": 231, "loss": 0.4733, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "1:13:28", "remaining_time": "1:11:35"}
+{"current_steps": 118, "total_steps": 231, "loss": 0.4843, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "1:14:07", "remaining_time": "1:10:58"}
+{"current_steps": 119, "total_steps": 231, "loss": 0.4752, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "1:14:46", "remaining_time": "1:10:22"}
+{"current_steps": 120, "total_steps": 231, "loss": 0.4642, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "1:15:19", "remaining_time": "1:09:40"}
+{"current_steps": 121, "total_steps": 231, "loss": 0.475, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "1:15:56", "remaining_time": "1:09:02"}
+{"current_steps": 122, "total_steps": 231, "loss": 0.487, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "1:16:35", "remaining_time": "1:08:25"}
+{"current_steps": 123, "total_steps": 231, "loss": 0.4728, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "1:17:13", "remaining_time": "1:07:48"}
+{"current_steps": 124, "total_steps": 231, "loss": 0.4822, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "1:17:51", "remaining_time": "1:07:10"}
+{"current_steps": 125, "total_steps": 231, "loss": 0.4814, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "1:18:26", "remaining_time": "1:06:31"}
+{"current_steps": 126, "total_steps": 231, "loss": 0.4752, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "1:19:02", "remaining_time": "1:05:51"}
+{"current_steps": 127, "total_steps": 231, "loss": 0.4589, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "1:19:39", "remaining_time": "1:05:13"}
+{"current_steps": 128, "total_steps": 231, "loss": 0.4797, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "1:20:15", "remaining_time": "1:04:35"}
+{"current_steps": 129, "total_steps": 231, "loss": 0.4855, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "1:20:51", "remaining_time": "1:03:56"}
+{"current_steps": 130, "total_steps": 231, "loss": 0.4701, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:21:25", "remaining_time": "1:03:16"}
+{"current_steps": 131, "total_steps": 231, "loss": 0.4669, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "1:22:00", "remaining_time": "1:02:35"}
+{"current_steps": 132, "total_steps": 231, "loss": 0.4694, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:22:36", "remaining_time": "1:01:57"}
+{"current_steps": 133, "total_steps": 231, "loss": 0.4278, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:23:32", "remaining_time": "1:01:33"}
+{"current_steps": 134, "total_steps": 231, "loss": 0.4199, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:24:08", "remaining_time": "1:00:54"}
+{"current_steps": 135, "total_steps": 231, "loss": 0.4233, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:24:47", "remaining_time": "1:00:17"}
+{"current_steps": 136, "total_steps": 231, "loss": 0.4134, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:25:25", "remaining_time": "0:59:40"}
+{"current_steps": 137, "total_steps": 231, "loss": 0.4153, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:26:00", "remaining_time": "0:59:01"}
+{"current_steps": 138, "total_steps": 231, "loss": 0.4245, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:26:36", "remaining_time": "0:58:22"}
+{"current_steps": 139, "total_steps": 231, "loss": 0.4163, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:27:13", "remaining_time": "0:57:43"}
+{"current_steps": 140, "total_steps": 231, "loss": 0.4219, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:27:50", "remaining_time": "0:57:06"}
+{"current_steps": 141, "total_steps": 231, "loss": 0.4252, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:28:23", "remaining_time": "0:56:25"}
+{"current_steps": 142, "total_steps": 231, "loss": 0.4275, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:29:02", "remaining_time": "0:55:48"}
+{"current_steps": 143, "total_steps": 231, "loss": 0.4293, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:29:37", "remaining_time": "0:55:08"}
+{"current_steps": 144, "total_steps": 231, "loss": 0.4331, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:30:14", "remaining_time": "0:54:31"}
+{"current_steps": 145, "total_steps": 231, "loss": 0.408, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:30:48", "remaining_time": "0:53:51"}
+{"current_steps": 146, "total_steps": 231, "loss": 0.4241, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:31:24", "remaining_time": "0:53:13"}
+{"current_steps": 147, "total_steps": 231, "loss": 0.4199, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:32:01", "remaining_time": "0:52:35"}
+{"current_steps": 148, "total_steps": 231, "loss": 0.414, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:32:36", "remaining_time": "0:51:56"}
+{"current_steps": 149, "total_steps": 231, "loss": 0.4142, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:33:13", "remaining_time": "0:51:18"}
+{"current_steps": 150, "total_steps": 231, "loss": 0.4199, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:33:47", "remaining_time": "0:50:38"}
+{"current_steps": 151, "total_steps": 231, "loss": 0.4392, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:34:23", "remaining_time": "0:50:00"}
+{"current_steps": 152, "total_steps": 231, "loss": 0.429, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:34:58", "remaining_time": "0:49:21"}
+{"current_steps": 153, "total_steps": 231, "loss": 0.4245, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:35:36", "remaining_time": "0:48:44"}
+{"current_steps": 154, "total_steps": 231, "loss": 0.4339, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:36:11", "remaining_time": "0:48:05"}
+{"current_steps": 155, "total_steps": 231, "loss": 0.4195, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:36:47", "remaining_time": "0:47:27"}
+{"current_steps": 156, "total_steps": 231, "loss": 0.4257, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:37:26", "remaining_time": "0:46:50"}
+{"current_steps": 157, "total_steps": 231, "loss": 0.4105, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:38:04", "remaining_time": "0:46:13"}
+{"current_steps": 158, "total_steps": 231, "loss": 0.4161, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:38:39", "remaining_time": "0:45:34"}
+{"current_steps": 159, "total_steps": 231, "loss": 0.4274, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:39:18", "remaining_time": "0:44:58"}
+{"current_steps": 160, "total_steps": 231, "loss": 0.4093, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:39:57", "remaining_time": "0:44:21"}
+{"current_steps": 161, "total_steps": 231, "loss": 0.4117, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:40:33", "remaining_time": "0:43:43"}
+{"current_steps": 162, "total_steps": 231, "loss": 0.4244, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:41:12", "remaining_time": "0:43:06"}
+{"current_steps": 163, "total_steps": 231, "loss": 0.4103, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:41:47", "remaining_time": "0:42:28"}
+{"current_steps": 164, "total_steps": 231, "loss": 0.413, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:42:23", "remaining_time": "0:41:49"}
+{"current_steps": 165, "total_steps": 231, "loss": 0.4165, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:42:59", "remaining_time": "0:41:11"}
+{"current_steps": 166, "total_steps": 231, "loss": 0.3721, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:43:49", "remaining_time": "0:40:39"}
+{"current_steps": 167, "total_steps": 231, "loss": 0.3834, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:44:25", "remaining_time": "0:40:01"}
+{"current_steps": 168, "total_steps": 231, "loss": 0.3911, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:45:01", "remaining_time": "0:39:23"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.379, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:45:39", "remaining_time": "0:38:45"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.3838, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:46:18", "remaining_time": "0:38:08"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.3806, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:46:51", "remaining_time": "0:37:29"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.3716, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:47:29", "remaining_time": "0:36:52"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.3894, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:48:06", "remaining_time": "0:36:14"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.3814, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:48:43", "remaining_time": "0:35:36"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.3742, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:49:21", "remaining_time": "0:34:59"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.3725, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:49:59", "remaining_time": "0:34:22"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.376, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:50:35", "remaining_time": "0:33:44"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.3776, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:51:13", "remaining_time": "0:33:07"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.3796, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:51:50", "remaining_time": "0:32:29"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.3724, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:52:29", "remaining_time": "0:31:52"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.3768, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:53:03", "remaining_time": "0:31:13"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.3718, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:53:40", "remaining_time": "0:30:36"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.374, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:54:15", "remaining_time": "0:29:58"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.365, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:54:50", "remaining_time": "0:29:20"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.3728, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:55:26", "remaining_time": "0:28:42"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.3696, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:56:04", "remaining_time": "0:28:04"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.3688, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:56:40", "remaining_time": "0:27:27"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.3743, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:57:18", "remaining_time": "0:26:49"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.3771, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:57:54", "remaining_time": "0:26:12"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.3713, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:58:30", "remaining_time": "0:25:34"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.3735, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:59:08", "remaining_time": "0:24:57"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.3792, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:59:45", "remaining_time": "0:24:19"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.3746, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "2:00:23", "remaining_time": "0:23:42"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.386, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "2:00:57", "remaining_time": "0:23:04"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.3787, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "2:01:34", "remaining_time": "0:22:26"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.3801, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "2:02:11", "remaining_time": "0:21:49"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.3907, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "2:02:47", "remaining_time": "0:21:11"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.3755, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:03:22", "remaining_time": "0:20:33"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.3658, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "2:04:21", "remaining_time": "0:19:59"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.3603, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "2:04:56", "remaining_time": "0:19:21"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.3529, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "2:05:32", "remaining_time": "0:18:44"}
+{"current_steps": 202, "total_steps": 231, "loss": 0.359, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "2:06:09", "remaining_time": "0:18:06"}
+{"current_steps": 203, "total_steps": 231, "loss": 0.3641, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "2:06:44", "remaining_time": "0:17:28"}
+{"current_steps": 204, "total_steps": 231, "loss": 0.3479, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "2:07:19", "remaining_time": "0:16:51"}
+{"current_steps": 205, "total_steps": 231, "loss": 0.3661, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "2:07:56", "remaining_time": "0:16:13"}
+{"current_steps": 206, "total_steps": 231, "loss": 0.3638, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "2:08:32", "remaining_time": "0:15:35"}
+{"current_steps": 207, "total_steps": 231, "loss": 0.3585, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "2:09:07", "remaining_time": "0:14:58"}
+{"current_steps": 208, "total_steps": 231, "loss": 0.3523, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "2:09:46", "remaining_time": "0:14:21"}
+{"current_steps": 209, "total_steps": 231, "loss": 0.3562, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "2:10:23", "remaining_time": "0:13:43"}
+{"current_steps": 210, "total_steps": 231, "loss": 0.3558, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "2:11:01", "remaining_time": "0:13:06"}
+{"current_steps": 211, "total_steps": 231, "loss": 0.3598, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "2:11:39", "remaining_time": "0:12:28"}
+{"current_steps": 212, "total_steps": 231, "loss": 0.3521, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "2:12:16", "remaining_time": "0:11:51"}
+{"current_steps": 213, "total_steps": 231, "loss": 0.349, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "2:12:52", "remaining_time": "0:11:13"}
+{"current_steps": 214, "total_steps": 231, "loss": 0.3649, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "2:13:27", "remaining_time": "0:10:36"}
+{"current_steps": 215, "total_steps": 231, "loss": 0.3576, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "2:14:06", "remaining_time": "0:09:58"}
+{"current_steps": 216, "total_steps": 231, "loss": 0.3602, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "2:14:41", "remaining_time": "0:09:21"}
+{"current_steps": 217, "total_steps": 231, "loss": 0.3573, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "2:15:16", "remaining_time": "0:08:43"}
+{"current_steps": 218, "total_steps": 231, "loss": 0.3546, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "2:15:54", "remaining_time": "0:08:06"}
+{"current_steps": 219, "total_steps": 231, "loss": 0.3578, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "2:16:31", "remaining_time": "0:07:28"}
+{"current_steps": 220, "total_steps": 231, "loss": 0.3449, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "2:17:09", "remaining_time": "0:06:51"}
+{"current_steps": 221, "total_steps": 231, "loss": 0.3513, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "2:17:44", "remaining_time": "0:06:13"}
+{"current_steps": 222, "total_steps": 231, "loss": 0.3638, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "2:18:21", "remaining_time": "0:05:36"}
+{"current_steps": 223, "total_steps": 231, "loss": 0.3538, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "2:19:00", "remaining_time": "0:04:59"}
+{"current_steps": 224, "total_steps": 231, "loss": 0.3525, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "2:19:36", "remaining_time": "0:04:21"}
+{"current_steps": 225, "total_steps": 231, "loss": 0.352, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "2:20:12", "remaining_time": "0:03:44"}
+{"current_steps": 226, "total_steps": 231, "loss": 0.3573, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "2:20:49", "remaining_time": "0:03:06"}
+{"current_steps": 227, "total_steps": 231, "loss": 0.3513, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "2:21:27", "remaining_time": "0:02:29"}
+{"current_steps": 228, "total_steps": 231, "loss": 0.3506, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "2:22:01", "remaining_time": "0:01:52"}
+{"current_steps": 229, "total_steps": 231, "loss": 0.3495, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "2:22:38", "remaining_time": "0:01:14"}
+{"current_steps": 230, "total_steps": 231, "loss": 0.3507, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "2:23:15", "remaining_time": "0:00:37"}
+{"current_steps": 231, "total_steps": 231, "loss": 0.357, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:23:54", "remaining_time": "0:00:00"}
+{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:24:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1659 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 6.312150870591461,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.0115,
+      "step": 1
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 6.475694856091368,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0286,
+      "step": 2
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 6.510110526436135,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0389,
+      "step": 3
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 5.981791395592498,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0259,
+      "step": 4
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 4.53026982334595,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9918,
+      "step": 5
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.8104793581280285,
+      "learning_rate": 5e-06,
+      "loss": 0.9379,
+      "step": 6
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.567100887895647,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9482,
+      "step": 7
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 3.892397384715512,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9188,
+      "step": 8
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 4.142874339222047,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9283,
+      "step": 9
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 4.138619036300646,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9153,
+      "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.373497058955061,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.8984,
+      "step": 11
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.8583835585294537,
+      "learning_rate": 1e-05,
+      "loss": 0.8745,
+      "step": 12
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 2.0867771671497706,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.8407,
+      "step": 13
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 1.4253099021132698,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8072,
+      "step": 14
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.5431649525602196,
+      "learning_rate": 1.25e-05,
+      "loss": 0.8059,
+      "step": 15
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 1.2817611290592914,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7992,
+      "step": 16
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 1.1356040619726908,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 0.781,
+      "step": 17
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.1421250437266164,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7467,
+      "step": 18
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 1.0425455417206984,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7772,
+      "step": 19
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.9574395482369085,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7322,
+      "step": 20
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.0470442958944162,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.7542,
+      "step": 21
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.0529632063486736,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7272,
+      "step": 22
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 1.169220818599545,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.7264,
+      "step": 23
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.9407356437242442,
+      "learning_rate": 2e-05,
+      "loss": 0.7198,
+      "step": 24
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 1.0131670420617127,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.7314,
+      "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.9558934157548457,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.7092,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.7862337023546967,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.7022,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.8015449395501483,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.7131,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.8604817636158697,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.7071,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7854145700441739,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.696,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.6225530941896312,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.6941,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.7778316880329571,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.6933,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5277454875573591,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.6915,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.5805460635972389,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.6447,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.6019817869943789,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.6683,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.5088210340957223,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.6472,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.5962209257067279,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.6632,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.5831832792689964,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.6554,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.5817683452118627,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.6336,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.5669925733078411,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.6408,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.6105774979030593,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.6303,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.6142577901965711,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.6398,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.5337799657097911,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.6286,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.5572020819014635,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.6402,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.4872837857719787,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.6241,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.5181010202053239,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.6293,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.5967191523625646,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6316,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.5703718513429342,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.6256,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.6541547573166652,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.6123,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.6609780061398919,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.6221,
+      "step": 50
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.6894966357223148,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.6248,
+      "step": 51
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.5939539044353149,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.6407,
+      "step": 52
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.7038110533728202,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.6184,
+      "step": 53
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.62732059189463,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.6129,
+      "step": 54
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5427046281169445,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.6179,
+      "step": 55
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.6194003921539317,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.6113,
+      "step": 56
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.6410974021298932,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.6173,
+      "step": 57
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.5779009695922482,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.617,
+      "step": 58
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.5147582250315594,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.6085,
+      "step": 59
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5671710300061014,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.6203,
+      "step": 60
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.7941211783306206,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.6146,
+      "step": 61
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.7506842382530591,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.6063,
+      "step": 62
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.5258601890372588,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.6301,
+      "step": 63
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.8268877793831794,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.6001,
+      "step": 64
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.5581536666536359,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.6119,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.600234570523279,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.6099,
+      "step": 66
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.7265544201056052,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.5596,
+      "step": 67
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.5248402931161873,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.5585,
+      "step": 68
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.585676191853421,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.56,
+      "step": 69
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.7015489638418316,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5631,
+      "step": 70
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.5842445543540288,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.5491,
+      "step": 71
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.51243844443462,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.5528,
+      "step": 72
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.7150352543491989,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.545,
+      "step": 73
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.5141968817426051,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.547,
+      "step": 74
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.585858728549435,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.5488,
+      "step": 75
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.7866792966684663,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.5519,
+      "step": 76
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.5061107670338666,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.5499,
+      "step": 77
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.6469169079163084,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.5317,
+      "step": 78
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.6060546083978395,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.5524,
+      "step": 79
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.4696097237633282,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.5426,
+      "step": 80
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.5399242385302314,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.5494,
+      "step": 81
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.48245852694053143,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.5382,
+      "step": 82
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.47001514713374226,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.5564,
+      "step": 83
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.5618528608673509,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.5504,
+      "step": 84
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.525585513155995,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.5366,
+      "step": 85
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.47441334531625917,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.5382,
+      "step": 86
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.6093467259870757,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.5491,
+      "step": 87
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.561336046190135,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.5387,
+      "step": 88
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 0.49872044831217777,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.5374,
+      "step": 89
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.45268268638401327,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.539,
+      "step": 90
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 0.49399347923936493,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.5483,
+      "step": 91
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.5051110919057764,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.524,
+      "step": 92
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.5378366080363427,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5512,
+      "step": 93
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.46256558272521914,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.5448,
+      "step": 94
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.5939458305415402,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.541,
+      "step": 95
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.48938531706905364,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.5473,
+      "step": 96
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 0.5012717641433172,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.5615,
+      "step": 97
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.534292141394524,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.535,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.534314937899243,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.5424,
+      "step": 99
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 0.5582906692438339,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.4838,
+      "step": 100
+    },
+    {
+      "epoch": 3.0606060606060606,
+      "grad_norm": 0.6022338728928069,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.4822,
+      "step": 101
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.6062975278971561,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.4866,
+      "step": 102
+    },
+    {
+      "epoch": 3.121212121212121,
+      "grad_norm": 0.6965168962135356,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.4875,
+      "step": 103
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 0.5740971337746343,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.4973,
+      "step": 104
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.6037151795891081,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.4838,
+      "step": 105
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 0.5209861578836725,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.4742,
+      "step": 106
+    },
+    {
+      "epoch": 3.242424242424242,
+      "grad_norm": 0.5456291719112359,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.4888,
+      "step": 107
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.48032197533105836,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.491,
+      "step": 108
+    },
+    {
+      "epoch": 3.303030303030303,
+      "grad_norm": 0.4580756881783694,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.4843,
+      "step": 109
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.46235698412068515,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.4916,
+      "step": 110
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 0.4489151537798375,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.4855,
+      "step": 111
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.4383101762947854,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.4858,
+      "step": 112
+    },
+    {
+      "epoch": 3.4242424242424243,
+      "grad_norm": 0.45451185564173385,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.4755,
+      "step": 113
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.42050469812801256,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.4803,
+      "step": 114
+    },
+    {
+      "epoch": 3.484848484848485,
+      "grad_norm": 0.45831672585375605,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.4859,
+      "step": 115
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 0.4798493173213465,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4758,
+      "step": 116
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 0.5047184645263595,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.4733,
+      "step": 117
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 0.43050751564999873,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.4843,
+      "step": 118
+    },
+    {
+      "epoch": 3.606060606060606,
+      "grad_norm": 0.507474061745988,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.4752,
+      "step": 119
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.5027468266837049,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.4642,
+      "step": 120
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.5002534033302283,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.475,
+      "step": 121
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 0.5099369195818414,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.487,
+      "step": 122
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.48144394820768416,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.4728,
+      "step": 123
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 0.48509841581231067,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.4822,
+      "step": 124
+    },
+    {
+      "epoch": 3.787878787878788,
+      "grad_norm": 0.5232355102786402,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.4814,
+      "step": 125
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 0.4522597876855734,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.4752,
+      "step": 126
+    },
+    {
+      "epoch": 3.8484848484848486,
+      "grad_norm": 0.48608519066110173,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.4589,
+      "step": 127
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.4175574940160927,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.4797,
+      "step": 128
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 0.4081235310325298,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.4855,
+      "step": 129
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 0.4672381986062692,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.4701,
+      "step": 130
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.4013104550104878,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.4669,
+      "step": 131
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.40311810148872756,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.4694,
+      "step": 132
+    },
+    {
+      "epoch": 4.03030303030303,
+      "grad_norm": 0.5253103516174084,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.4278,
+      "step": 133
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 0.4229995957542638,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.4199,
+      "step": 134
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.4834993887824011,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.4233,
+      "step": 135
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 0.5083836778846227,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.4134,
+      "step": 136
+    },
+    {
+      "epoch": 4.151515151515151,
+      "grad_norm": 0.4629826983464886,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.4153,
+      "step": 137
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.4262442369411264,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.4245,
+      "step": 138
+    },
+    {
+      "epoch": 4.212121212121212,
+      "grad_norm": 0.48584922213655163,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4163,
+      "step": 139
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 0.43099027346452917,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.4219,
+      "step": 140
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.45792891092025656,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.4252,
+      "step": 141
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 0.45821297586471343,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.4275,
+      "step": 142
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.4440069719961142,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.4293,
+      "step": 143
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.4061400289189544,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.4331,
+      "step": 144
+    },
+    {
+      "epoch": 4.393939393939394,
+      "grad_norm": 0.37815756277205015,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.408,
+      "step": 145
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 0.4742561168827842,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.4241,
+      "step": 146
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.3850909440657431,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.4199,
+      "step": 147
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.3850307914357772,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.414,
+      "step": 148
+    },
+    {
+      "epoch": 4.515151515151516,
+      "grad_norm": 0.37628212538187894,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.4142,
+      "step": 149
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.3697164917421783,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.4199,
+      "step": 150
+    },
+    {
+      "epoch": 4.575757575757576,
+      "grad_norm": 0.3936732478606088,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.4392,
+      "step": 151
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 0.36979958098093274,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.429,
+      "step": 152
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.4120222499856573,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.4245,
+      "step": 153
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.37901191700407694,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.4339,
+      "step": 154
+    },
+    {
+      "epoch": 4.696969696969697,
+      "grad_norm": 0.34436938180267346,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.4195,
+      "step": 155
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.3954985824584074,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.4257,
+      "step": 156
+    },
+    {
+      "epoch": 4.757575757575758,
+      "grad_norm": 0.3847038911028595,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.4105,
+      "step": 157
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 0.35182897006844766,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.4161,
+      "step": 158
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.3395768604052704,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.4274,
+      "step": 159
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.37610765942404767,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.4093,
+      "step": 160
+    },
+    {
+      "epoch": 4.878787878787879,
+      "grad_norm": 0.34369090240001643,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.4117,
+      "step": 161
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.3193574933254639,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4244,
+      "step": 162
+    },
+    {
+      "epoch": 4.9393939393939394,
+      "grad_norm": 0.3223949271599354,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.4103,
+      "step": 163
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 0.3244127700665561,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.413,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.32409787537740004,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.4165,
+      "step": 165
+    },
+    {
+      "epoch": 5.03030303030303,
+      "grad_norm": 0.4575500171903933,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.3721,
+      "step": 166
+    },
+    {
+      "epoch": 5.0606060606060606,
+      "grad_norm": 0.36883989819661467,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.3834,
+      "step": 167
+    },
+    {
+      "epoch": 5.090909090909091,
+      "grad_norm": 0.33445890390189614,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.3911,
+      "step": 168
+    },
+    {
+      "epoch": 5.121212121212121,
+      "grad_norm": 0.41535879066134074,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.379,
+      "step": 169
+    },
+    {
+      "epoch": 5.151515151515151,
+      "grad_norm": 0.4967611991379499,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.3838,
+      "step": 170
+    },
+    {
+      "epoch": 5.181818181818182,
+      "grad_norm": 0.4117803449507636,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.3806,
+      "step": 171
+    },
+    {
+      "epoch": 5.212121212121212,
+      "grad_norm": 0.3805214746037457,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.3716,
+      "step": 172
+    },
+    {
+      "epoch": 5.242424242424242,
+      "grad_norm": 0.3538575739009125,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.3894,
+      "step": 173
+    },
+    {
+      "epoch": 5.2727272727272725,
+      "grad_norm": 0.4055868044908981,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.3814,
+      "step": 174
+    },
+    {
+      "epoch": 5.303030303030303,
+      "grad_norm": 0.4047775213330113,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.3742,
+      "step": 175
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.351123670955561,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.3725,
+      "step": 176
+    },
+    {
+      "epoch": 5.363636363636363,
+      "grad_norm": 0.3587210333393083,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.376,
+      "step": 177
+    },
+    {
+      "epoch": 5.393939393939394,
+      "grad_norm": 0.38060043226029316,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.3776,
+      "step": 178
+    },
+    {
+      "epoch": 5.424242424242424,
+      "grad_norm": 0.33805978166739914,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.3796,
+      "step": 179
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.3221363257994335,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.3724,
+      "step": 180
+    },
+    {
+      "epoch": 5.484848484848484,
+      "grad_norm": 0.3248118221029093,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.3768,
+      "step": 181
+    },
+    {
+      "epoch": 5.515151515151516,
+      "grad_norm": 0.3571193688032367,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.3718,
+      "step": 182
+    },
+    {
+      "epoch": 5.545454545454545,
+      "grad_norm": 0.325622710888302,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.374,
+      "step": 183
+    },
+    {
+      "epoch": 5.575757575757576,
+      "grad_norm": 0.30970994937371304,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.365,
+      "step": 184
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 0.2939098855993905,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3728,
+      "step": 185
+    },
+    {
+      "epoch": 5.636363636363637,
+      "grad_norm": 0.3327725237141841,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.3696,
+      "step": 186
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.33733530820889834,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.3688,
+      "step": 187
+    },
+    {
+      "epoch": 5.696969696969697,
+      "grad_norm": 0.3267723664611921,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.3743,
+      "step": 188
+    },
+    {
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.30477416794739226,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.3771,
+      "step": 189
+    },
+    {
+      "epoch": 5.757575757575758,
+      "grad_norm": 0.31237110797322104,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.3713,
+      "step": 190
+    },
+    {
+      "epoch": 5.787878787878788,
+      "grad_norm": 0.3270216603267311,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.3735,
+      "step": 191
+    },
+    {
+      "epoch": 5.818181818181818,
+      "grad_norm": 0.3086374044328664,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.3792,
+      "step": 192
+    },
+    {
+      "epoch": 5.848484848484849,
+      "grad_norm": 0.3154329043876322,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.3746,
+      "step": 193
+    },
+    {
+      "epoch": 5.878787878787879,
+      "grad_norm": 0.3186084501919431,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.386,
+      "step": 194
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.3129459155979679,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.3787,
+      "step": 195
+    },
+    {
+      "epoch": 5.9393939393939394,
+      "grad_norm": 0.2849812085273699,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.3801,
+      "step": 196
+    },
+    {
+      "epoch": 5.96969696969697,
+      "grad_norm": 0.29770863297104755,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.3907,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.29769942695520835,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.3755,
+      "step": 198
+    },
+    {
+      "epoch": 6.03030303030303,
+      "grad_norm": 0.37028292991289424,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.3658,
+      "step": 199
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.3640687593367054,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.3603,
+      "step": 200
+    },
+    {
+      "epoch": 6.090909090909091,
+      "grad_norm": 0.34956891428811765,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.3529,
+      "step": 201
+    },
+    {
+      "epoch": 6.121212121212121,
+      "grad_norm": 0.31208168864820524,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.359,
+      "step": 202
+    },
+    {
+      "epoch": 6.151515151515151,
+      "grad_norm": 0.2985599079997785,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.3641,
+      "step": 203
+    },
+    {
+      "epoch": 6.181818181818182,
+      "grad_norm": 0.3045681297282551,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.3479,
+      "step": 204
+    },
+    {
+      "epoch": 6.212121212121212,
+      "grad_norm": 0.3337677361693306,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.3661,
+      "step": 205
+    },
+    {
+      "epoch": 6.242424242424242,
+      "grad_norm": 0.330091275503482,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.3638,
+      "step": 206
+    },
+    {
+      "epoch": 6.2727272727272725,
+      "grad_norm": 0.33236530374834883,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.3585,
+      "step": 207
+    },
+    {
+      "epoch": 6.303030303030303,
+      "grad_norm": 0.33403382077537863,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3523,
+      "step": 208
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.3076896715478002,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.3562,
+      "step": 209
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.2892632966187589,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.3558,
+      "step": 210
+    },
+    {
+      "epoch": 6.393939393939394,
+      "grad_norm": 0.3006521646154084,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.3598,
+      "step": 211
+    },
+    {
+      "epoch": 6.424242424242424,
+      "grad_norm": 0.29904963807062096,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.3521,
+      "step": 212
+    },
+    {
+      "epoch": 6.454545454545454,
+      "grad_norm": 0.29793493646756863,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.349,
+      "step": 213
+    },
+    {
+      "epoch": 6.484848484848484,
+      "grad_norm": 0.2935354245570347,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.3649,
+      "step": 214
+    },
+    {
+      "epoch": 6.515151515151516,
+      "grad_norm": 0.27964737258039646,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.3576,
+      "step": 215
+    },
+    {
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.301582739448306,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.3602,
+      "step": 216
+    },
+    {
+      "epoch": 6.575757575757576,
+      "grad_norm": 0.2936742547927523,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.3573,
+      "step": 217
+    },
+    {
+      "epoch": 6.606060606060606,
+      "grad_norm": 0.29954291916250736,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.3546,
+      "step": 218
+    },
+    {
+      "epoch": 6.636363636363637,
+      "grad_norm": 0.27606871733537713,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.3578,
+      "step": 219
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.30802643125453266,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.3449,
+      "step": 220
+    },
+    {
+      "epoch": 6.696969696969697,
+      "grad_norm": 0.2962737721620968,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.3513,
+      "step": 221
+    },
+    {
+      "epoch": 6.7272727272727275,
+      "grad_norm": 0.2747413575856551,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.3638,
+      "step": 222
+    },
+    {
+      "epoch": 6.757575757575758,
+      "grad_norm": 0.2854609348497825,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.3538,
+      "step": 223
+    },
+    {
+      "epoch": 6.787878787878788,
+      "grad_norm": 0.28835820053227823,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.3525,
+      "step": 224
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.2912380841058537,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.352,
+      "step": 225
+    },
+    {
+      "epoch": 6.848484848484849,
+      "grad_norm": 0.2752077854667188,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.3573,
+      "step": 226
+    },
+    {
+      "epoch": 6.878787878787879,
+      "grad_norm": 0.2879200632137298,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.3513,
+      "step": 227
+    },
+    {
+      "epoch": 6.909090909090909,
+      "grad_norm": 0.2906879499875626,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.3506,
+      "step": 228
+    },
+    {
+      "epoch": 6.9393939393939394,
+      "grad_norm": 0.2787965911550042,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.3495,
+      "step": 229
+    },
+    {
+      "epoch": 6.96969696969697,
+      "grad_norm": 0.27756524800483817,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.3507,
+      "step": 230
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.2770002873936819,
+      "learning_rate": 0.0,
+      "loss": 0.357,
+      "step": 231
+    },
+    {
+      "epoch": 7.0,
+      "step": 231,
+      "total_flos": 6.474382962841354e+17,
+      "train_loss": 0.5183511296392003,
+      "train_runtime": 8671.5363,
+      "train_samples_per_second": 2.551,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 231,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.474382962841354e+17,
+  "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 sha256:1d790148c0d98b237107a7c7311490d0903996728f0c0457120bec2fbe612977
+size 7416