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: openmathreasoning_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. -->
+
+# openmathreasoning_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/openmathreasoning_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: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- 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": 6.850632911392405,
+    "total_flos": 5.277578878380933e+17,
+    "train_loss": 0.39017832059679286,
+    "train_runtime": 21047.8381,
+    "train_samples_per_second": 1.051,
+    "train_steps_per_second": 0.011
+}

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 sha256:788aeeefc8850c7635e180975637b2943d632610042febeaa355eedd703c0d39
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f48fdbbeb0f76211d4115383d46bce9b61b10abe744741cff5bd882d732e5b9
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd81793fdc03ab9a9713dad44160368f19a22285e35e40b7e01dcea6cbf6aa6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e278de3904543cd9da912930d9ac60d76f7c81e3efd6a9d9d5a4c0c4cc39f40a
+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/Apr28_08-17-57_jrc0913/events.out.tfevents.1745821125.jrc0913.4147072.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f0839e85678433a494d75189ddc03568451999039098828b4381e7f64705bd
+size 52619

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": "2025-04-28 08:17:57", "end_time": "2025-04-28 14:09:43"}

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": 6.850632911392405,
+    "total_flos": 5.277578878380933e+17,
+    "train_loss": 0.39017832059679286,
+    "train_runtime": 21047.8381,
+    "train_samples_per_second": 1.051,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 0.8419, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:01:38", "remaining_time": "6:05:06"}
+{"current_steps": 2, "total_steps": 224, "loss": 0.8759, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:03:15", "remaining_time": "6:01:58"}
+{"current_steps": 3, "total_steps": 224, "loss": 0.8305, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:04:58", "remaining_time": "6:06:32"}
+{"current_steps": 4, "total_steps": 224, "loss": 0.8242, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:06:32", "remaining_time": "5:59:33"}
+{"current_steps": 5, "total_steps": 224, "loss": 0.7634, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:08:09", "remaining_time": "5:57:37"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.7492, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:09:52", "remaining_time": "5:58:47"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.7265, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:11:25", "remaining_time": "5:54:05"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.7563, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:12:57", "remaining_time": "5:49:42"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.7747, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:14:27", "remaining_time": "5:45:20"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.7341, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:15:51", "remaining_time": "5:39:24"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.6844, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:17:24", "remaining_time": "5:37:12"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.692, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:19:18", "remaining_time": "5:41:09"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.6945, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:20:51", "remaining_time": "5:38:39"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.654, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:22:27", "remaining_time": "5:36:46"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.671, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:24:06", "remaining_time": "5:35:50"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.6169, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:25:39", "remaining_time": "5:33:34"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.6203, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:27:17", "remaining_time": "5:32:16"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.6149, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:28:53", "remaining_time": "5:30:33"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.6517, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:30:48", "remaining_time": "5:32:19"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.6033, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:32:20", "remaining_time": "5:29:49"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.64, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:33:58", "remaining_time": "5:28:27"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.5927, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:35:38", "remaining_time": "5:27:15"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.607, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:37:23", "remaining_time": "5:26:45"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.561, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:38:56", "remaining_time": "5:24:34"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.5872, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:40:45", "remaining_time": "5:24:28"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.5711, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:42:16", "remaining_time": "5:21:53"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.5801, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:43:56", "remaining_time": "5:20:33"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.5549, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:45:37", "remaining_time": "5:19:23"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.5468, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:47:02", "remaining_time": "5:16:20"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.5723, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:48:44", "remaining_time": "5:15:11"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.548, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:50:18", "remaining_time": "5:13:09"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.5918, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "0:51:59", "remaining_time": "5:11:56"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.7317, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "0:54:02", "remaining_time": "5:12:47"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.4849, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "0:55:33", "remaining_time": "5:10:28"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.5334, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "0:57:13", "remaining_time": "5:09:01"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.5487, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "0:58:45", "remaining_time": "5:06:51"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.5186, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:00:24", "remaining_time": "5:05:16"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.5121, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:01:46", "remaining_time": "5:02:20"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.4835, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:03:13", "remaining_time": "4:59:57"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.5062, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:04:41", "remaining_time": "4:57:33"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.4821, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:06:23", "remaining_time": "4:56:18"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.4862, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:07:48", "remaining_time": "4:53:48"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.5455, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:09:22", "remaining_time": "4:52:01"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.4558, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:11:06", "remaining_time": "4:50:53"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.4949, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:12:51", "remaining_time": "4:49:49"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.5226, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:14:32", "remaining_time": "4:48:25"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.4988, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:16:12", "remaining_time": "4:46:58"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.4811, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:17:40", "remaining_time": "4:44:47"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.5409, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:19:17", "remaining_time": "4:43:10"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.4574, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:20:42", "remaining_time": "4:40:52"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.4825, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:22:09", "remaining_time": "4:38:40"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.4634, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:23:35", "remaining_time": "4:36:30"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.469, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:25:16", "remaining_time": "4:35:06"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.5486, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:27:02", "remaining_time": "4:34:00"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.4983, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:28:37", "remaining_time": "4:32:17"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.5272, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:30:10", "remaining_time": "4:30:32"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.4924, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:31:45", "remaining_time": "4:28:50"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.4759, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:33:20", "remaining_time": "4:27:07"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.4812, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:34:49", "remaining_time": "4:25:10"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.4888, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:36:28", "remaining_time": "4:23:40"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.5033, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "1:37:51", "remaining_time": "4:21:28"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.4764, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "1:39:21", "remaining_time": "4:19:35"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.4561, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "1:40:58", "remaining_time": "4:18:03"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.5324, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "1:42:38", "remaining_time": "4:16:36"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.578, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:44:12", "remaining_time": "4:14:54"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.544, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:46:21", "remaining_time": "4:14:36"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.4308, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:47:49", "remaining_time": "4:12:39"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.4194, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:49:18", "remaining_time": "4:10:45"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.4197, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:50:57", "remaining_time": "4:09:14"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.434, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:52:29", "remaining_time": "4:07:28"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.4094, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:53:53", "remaining_time": "4:05:26"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.4107, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "1:55:17", "remaining_time": "4:03:23"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.4111, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "1:56:51", "remaining_time": "4:01:42"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.413, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "1:58:32", "remaining_time": "4:00:16"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.4373, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:00:08", "remaining_time": "3:58:41"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.4257, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:01:33", "remaining_time": "3:56:43"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.4014, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:03:17", "remaining_time": "3:55:22"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.3802, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:04:55", "remaining_time": "3:53:50"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.449, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:06:41", "remaining_time": "3:52:32"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.3853, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:08:28", "remaining_time": "3:51:14"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.4197, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:10:14", "remaining_time": "3:49:55"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.4325, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:11:44", "remaining_time": "3:48:08"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.4346, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:13:21", "remaining_time": "3:46:33"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.4168, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:14:47", "remaining_time": "3:44:38"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.4387, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:16:23", "remaining_time": "3:43:02"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.3882, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:17:49", "remaining_time": "3:41:09"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.4384, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:19:24", "remaining_time": "3:39:30"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.4427, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:20:53", "remaining_time": "3:37:44"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.4242, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:22:28", "remaining_time": "3:36:06"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.4079, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:23:48", "remaining_time": "3:34:06"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.4264, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "2:25:23", "remaining_time": "3:32:29"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.4049, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "2:26:59", "remaining_time": "3:30:54"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.4073, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "2:28:30", "remaining_time": "3:29:11"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.4054, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "2:30:00", "remaining_time": "3:27:27"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.3915, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "2:31:34", "remaining_time": "3:25:48"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.4718, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "2:33:12", "remaining_time": "3:24:16"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.3884, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "2:34:49", "remaining_time": "3:22:42"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.5473, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "2:36:16", "remaining_time": "3:20:55"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.3687, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "2:38:27", "remaining_time": "3:20:04"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.3472, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "2:40:02", "remaining_time": "3:18:26"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.3524, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "2:41:40", "remaining_time": "3:16:53"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.3492, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "2:43:24", "remaining_time": "3:15:26"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.3475, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "2:44:55", "remaining_time": "3:13:44"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.3516, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "2:46:11", "remaining_time": "3:11:45"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.3367, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "2:47:42", "remaining_time": "3:10:03"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.3711, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "2:49:14", "remaining_time": "3:08:23"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.3632, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "2:50:38", "remaining_time": "3:06:34"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.3456, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "2:52:07", "remaining_time": "3:04:52"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.3521, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "2:53:42", "remaining_time": "3:03:16"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.3482, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "2:55:00", "remaining_time": "3:01:22"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.347, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "2:56:47", "remaining_time": "2:59:58"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.3523, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "2:58:18", "remaining_time": "2:58:18"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.3406, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "2:59:47", "remaining_time": "2:56:36"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.3488, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:01:18", "remaining_time": "2:54:56"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.3417, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:02:57", "remaining_time": "2:53:24"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.3619, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:04:37", "remaining_time": "2:51:53"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.357, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:06:03", "remaining_time": "2:50:09"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.353, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:07:30", "remaining_time": "2:48:26"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.3616, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:09:01", "remaining_time": "2:46:47"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.3573, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "3:10:31", "remaining_time": "2:45:07"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.3527, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "3:12:10", "remaining_time": "2:43:35"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.3546, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "3:13:35", "remaining_time": "2:41:51"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.3383, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "3:15:00", "remaining_time": "2:40:07"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.3325, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "3:16:29", "remaining_time": "2:38:27"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.3437, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "3:18:07", "remaining_time": "2:36:54"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.3607, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "3:19:33", "remaining_time": "2:35:12"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.3485, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "3:20:59", "remaining_time": "2:33:31"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.3584, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "3:22:29", "remaining_time": "2:31:51"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.3416, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "3:23:52", "remaining_time": "2:30:08"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.3286, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "3:25:23", "remaining_time": "2:28:30"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.4363, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "3:27:31", "remaining_time": "2:27:19"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.2624, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "3:29:09", "remaining_time": "2:25:46"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.2915, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "3:30:50", "remaining_time": "2:24:15"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.2931, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "3:32:21", "remaining_time": "2:22:37"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.2703, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "3:33:39", "remaining_time": "2:20:51"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.2771, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "3:35:08", "remaining_time": "2:19:12"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.2985, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "3:36:47", "remaining_time": "2:17:39"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.2758, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "3:38:11", "remaining_time": "2:15:58"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.2813, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "3:39:50", "remaining_time": "2:14:25"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.3221, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "3:41:26", "remaining_time": "2:12:51"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.3047, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "3:43:10", "remaining_time": "2:11:22"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.2554, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "3:44:38", "remaining_time": "2:09:43"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.2675, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "3:46:13", "remaining_time": "2:08:08"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.2979, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "3:47:41", "remaining_time": "2:06:29"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.3001, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "3:49:31", "remaining_time": "2:05:02"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.2889, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "3:51:02", "remaining_time": "2:03:26"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.2867, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "3:52:34", "remaining_time": "2:01:49"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.28, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "3:54:01", "remaining_time": "2:00:10"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.2734, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "3:55:33", "remaining_time": "1:58:34"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.3092, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "3:57:09", "remaining_time": "1:57:00"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.2669, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "3:58:29", "remaining_time": "1:55:17"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.3186, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "4:00:06", "remaining_time": "1:53:44"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.286, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "4:01:39", "remaining_time": "1:52:08"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.2838, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "4:03:11", "remaining_time": "1:50:32"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.2676, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "4:04:40", "remaining_time": "1:48:55"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.3151, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "4:06:11", "remaining_time": "1:47:19"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.2875, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "4:07:40", "remaining_time": "1:45:41"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.2942, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "4:09:06", "remaining_time": "1:44:03"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.3048, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "4:10:30", "remaining_time": "1:42:24"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.2449, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "4:11:58", "remaining_time": "1:40:47"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.2842, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "4:13:36", "remaining_time": "1:39:14"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.2991, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "4:15:18", "remaining_time": "1:37:42"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.3041, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "4:16:45", "remaining_time": "1:36:05"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.309, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "4:18:37", "remaining_time": "1:34:37"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.2502, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "4:20:12", "remaining_time": "1:33:02"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.2423, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "4:21:55", "remaining_time": "1:31:30"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.2684, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "4:23:35", "remaining_time": "1:29:58"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.2356, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "4:25:05", "remaining_time": "1:28:21"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.2432, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "4:26:41", "remaining_time": "1:26:47"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.2306, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "4:28:08", "remaining_time": "1:25:10"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.2499, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "4:29:46", "remaining_time": "1:23:36"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.268, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "4:31:19", "remaining_time": "1:22:01"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.2262, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "4:32:53", "remaining_time": "1:20:26"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.2461, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "4:34:19", "remaining_time": "1:18:49"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.2493, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "4:35:54", "remaining_time": "1:17:15"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.2504, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "4:37:32", "remaining_time": "1:15:41"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.2463, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "4:39:01", "remaining_time": "1:14:05"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.2606, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "4:40:33", "remaining_time": "1:12:30"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.2228, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "4:41:56", "remaining_time": "1:10:52"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.2477, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "4:43:46", "remaining_time": "1:09:22"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.2358, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "4:45:14", "remaining_time": "1:07:45"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.2372, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "4:46:42", "remaining_time": "1:06:09"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.2578, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "4:48:10", "remaining_time": "1:04:33"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.2225, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "4:49:22", "remaining_time": "1:02:54"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.2503, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "4:50:49", "remaining_time": "1:01:18"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.2596, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "4:52:18", "remaining_time": "0:59:43"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.2301, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "4:53:45", "remaining_time": "0:58:07"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.2429, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "4:55:04", "remaining_time": "0:56:30"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.2291, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "4:56:26", "remaining_time": "0:54:53"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.2571, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "4:58:06", "remaining_time": "0:53:20"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.218, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "4:59:29", "remaining_time": "0:51:44"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.2215, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "5:00:54", "remaining_time": "0:50:09"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.2474, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "5:02:23", "remaining_time": "0:48:34"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.2553, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "5:03:56", "remaining_time": "0:47:00"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.2308, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "5:05:25", "remaining_time": "0:45:25"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.3175, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "5:07:03", "remaining_time": "0:43:51"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.2141, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "5:08:48", "remaining_time": "0:42:19"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.2378, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "5:10:34", "remaining_time": "0:40:46"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.2105, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "5:11:56", "remaining_time": "0:39:11"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.2225, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "5:13:26", "remaining_time": "0:37:36"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.2296, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "5:14:51", "remaining_time": "0:36:01"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.2133, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "5:16:17", "remaining_time": "0:34:26"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.2275, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "5:17:59", "remaining_time": "0:32:53"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.2442, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "5:19:38", "remaining_time": "0:31:20"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.2196, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "5:21:15", "remaining_time": "0:29:46"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.227, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "5:22:43", "remaining_time": "0:28:11"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.2125, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "5:24:11", "remaining_time": "0:26:37"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.244, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "5:25:31", "remaining_time": "0:25:02"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.2124, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "5:26:59", "remaining_time": "0:23:28"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.2194, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "5:28:25", "remaining_time": "0:21:53"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.2325, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "5:29:56", "remaining_time": "0:20:19"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.2102, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "5:31:29", "remaining_time": "0:18:45"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.2152, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "5:33:00", "remaining_time": "0:17:11"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.2158, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "5:34:35", "remaining_time": "0:15:38"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.2276, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "5:36:05", "remaining_time": "0:14:04"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.2327, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "5:37:39", "remaining_time": "0:12:30"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.23, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "5:39:11", "remaining_time": "0:10:56"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.2219, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "5:40:35", "remaining_time": "0:09:22"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.2191, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "5:42:05", "remaining_time": "0:07:48"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.2228, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "5:43:34", "remaining_time": "0:06:14"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.2269, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "5:44:51", "remaining_time": "0:04:40"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.2095, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "5:46:22", "remaining_time": "0:03:07"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.2283, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "5:48:00", "remaining_time": "0:01:33"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.222, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "5:49:46", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "5:50:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1610 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.850632911392405,
+  "eval_steps": 500,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030379746835443037,
+      "grad_norm": 6.048936306987692,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.8419,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.359706790120916,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8759,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.131019897142869,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.8305,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 5.574055055372666,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.8242,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.265951668457725,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.7634,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.464962480859038,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.7492,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.077337266343512,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.7265,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 4.14036522612642,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.7563,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 4.45973658282638,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.7747,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 4.521818388157711,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.7341,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 4.422444866803943,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.6844,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.9402544164657844,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.692,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 2.6928462031464337,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.6945,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 1.8595232870527427,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.654,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.613185640118858,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.671,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.110958057017735,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.6169,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 1.737170053034775,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.6203,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.5084674691399222,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.6149,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.3494948400477569,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.6517,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 1.1751438322676817,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.6033,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 1.0526414875931804,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.64,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 0.9715611441669768,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.5927,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 0.8125624310216422,
+      "learning_rate": 2e-05,
+      "loss": 0.607,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 0.9223345735056782,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.561,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.8243964896311464,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.5872,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 0.7512429692602848,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.5711,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.7459000930728743,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.5801,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 0.6995303209474417,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.5549,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 0.7124104382437041,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.5468,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.7059343154396499,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.5723,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 0.7009167310881045,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.548,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.8724240967159428,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.5918,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 0.8468019563645511,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.7317,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.5559186721993208,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.4849,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.5507474685198273,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.5334,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.543870017484278,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.5487,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.6225002865248337,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.5186,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.5335951367889052,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.5121,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.569943007419904,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.4835,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.5616599542859847,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.5062,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.5176704614796857,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.4821,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.6013616477281641,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.4862,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.5799218399260377,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.5455,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.48791349493694947,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.4558,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.5460867482558168,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.4949,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.5200300630053336,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.5226,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 0.49835905260454255,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.4988,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.555402108007746,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.4811,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.5043821831864128,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.5409,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.5095173005875876,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.4574,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.5297774307671909,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.4825,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.4497569232214527,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.4634,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.5108891340546695,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.469,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.5389740099999035,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.5486,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.5137420177298216,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.4983,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.49925713696145874,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.5272,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.5914481358656738,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.4924,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.4664469979995995,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.4759,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.47080488802947457,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.4812,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.5587905613183901,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.4888,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.5050554675255995,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.5033,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.47145338803039966,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.4764,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.5018576539215808,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.4561,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.45811612746325875,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.5324,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.6144932201086315,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.578,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.5726068435884388,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.544,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.4648598668226982,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.4308,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 0.4721375558424858,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.4194,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.4771552931363247,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.4197,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 0.4797766115828031,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.434,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.4847501246260971,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.4094,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.5715606812513879,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.4107,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.4651167769261771,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.4111,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.45587437771999223,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.413,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 0.5442546749379886,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.4373,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.4824118869055176,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.4257,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.4781817061972643,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.4014,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.4088771271312156,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.3802,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.5516321100838191,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.449,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.4716858671975667,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.3853,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.45334870047529424,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.4197,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.4650898860452062,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.4325,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.6733951603850473,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.4346,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.3741787332470752,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.4168,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.4673023466091711,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.4387,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.5113903636282513,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.3882,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.3987776866070054,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.4384,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.5000328088996094,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.4427,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.42774760061205236,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.4242,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.4770182422848908,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4079,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.5326476152699332,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.4264,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.4142295571778557,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.4049,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.5296388184052468,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.4073,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.4359077641154996,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.4054,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.53763398646354,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.3915,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.5156253519333039,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.4718,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.4317302365758521,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.3884,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.5536609198782718,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.5473,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.5545528571506598,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.3687,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.47540586403474266,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.3472,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 0.515690188434661,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.3524,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.5494008492815136,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.3492,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.5613723693617616,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.3475,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.5459731136472022,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.3516,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.4928481785761879,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.3367,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.5784610134826562,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.3711,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.5334142496880356,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.3632,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.45364002557641886,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.3456,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.5342722692936496,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.3521,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.45373690200799116,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.3482,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.5348735784600784,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.347,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.42289751752473753,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.3523,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.4787683178291163,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.3406,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5114943466720573,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.3488,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.4725452864287685,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.3417,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.42049657665542955,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.3619,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.4686354978703038,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.357,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.4205375090893493,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.353,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.48202907492458946,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.3616,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.43220350995269835,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.3573,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.4056113080170557,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.3527,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.38542910276260156,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.3546,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.41172976094134517,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.3383,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.3422368161340203,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.3325,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.4074688839173423,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.3437,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.34849002000782986,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.3607,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.4029722649627817,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.3485,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.36141335416240483,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.3584,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.37260661041502396,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.3416,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.32216912148540366,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.3286,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.5313463942187743,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.4363,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.4707890932151999,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.2624,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.4041133834341088,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.2915,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.6431830303938959,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.2931,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.453099306620913,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.2703,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.41936391731434275,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.2771,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.4505732726130199,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.2985,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.4103967350890258,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.2758,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.3973605581799497,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.2813,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.4589582439764549,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.3221,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.4274255668686267,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.3047,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.35657773449481966,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.2554,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.3620039303083875,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.2675,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.3989026378463725,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.2979,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.3873971390047792,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.3001,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.3638331605928393,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.2889,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.3838325042159884,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.2867,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.36671976978412335,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.28,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.3529133852651092,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.2734,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.36640770826259494,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.3092,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.3100594224902787,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.2669,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.377115982323163,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.3186,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.33216684017323544,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.286,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.40784371682031095,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.2838,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.3120609511166079,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.2676,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.35298019160098854,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.3151,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.3237915668775047,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.2875,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.3341363814264824,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.2942,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.36919767508786167,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.3048,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.3091966055573231,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.2449,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.30134927381043464,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.2842,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.33724978042903153,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.2991,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.37910349336098464,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.3041,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.4523545633061669,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.309,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.4730924017069626,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.2502,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.32201262114708323,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.2423,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.3821460864301905,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.2684,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.5256405500408324,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.2356,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.4491399278571054,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.2432,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.3335828076072433,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.2306,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.35927027153636726,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.2499,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.37950495707252624,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.268,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.38081595421286196,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.2262,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.3490511429252917,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.2461,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.3185986215642651,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.2493,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.3417114934255241,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.2504,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.3607610625513573,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.2463,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.4170005526871216,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.2606,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.3233946450979762,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.2228,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.3177352084454099,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.2477,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.3141459292831218,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.2358,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.3133255531748914,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.2372,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.33090769348276167,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.2578,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.30752461939556636,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.2225,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.3212700019589481,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.2503,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.30346268594769565,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.2596,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.3006756556681579,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.2301,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.31423052889864206,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.2429,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.30980107031353704,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.2291,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.33434803432375376,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.2571,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.292122548663931,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.218,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.297080299478135,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.2215,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.30222638091145526,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.2474,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.3085881315778646,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.2553,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.28842240439901007,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.2308,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.38844373768880613,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.3175,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.3756548730251041,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.2141,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.36880100887113676,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.2378,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.3740777777425036,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.2105,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.2916833710946818,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.2225,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.2877930871488456,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.2296,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.28872553378838456,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.2133,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.2954608978578038,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.2275,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.30402408500591077,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.2442,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.30076848845189774,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.2196,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.3416948675216863,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.227,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.30696108823223234,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.2125,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.336665786751688,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.244,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.2882724454027941,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.2124,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.29760382515379885,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.2194,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.295342001002325,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.2325,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.2835777661113264,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.2102,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.27479736988784964,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.2152,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.27910917975904814,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.2158,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.2828526623147071,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.2276,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.28225492331747004,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.2327,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.28194784767364817,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.23,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.28029183381258665,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.2219,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.28779964462670415,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.2191,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.2873186242341778,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.2228,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.29578442444567216,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.2269,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.27426473251329325,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.2095,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.27895748053180836,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.2283,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.2729179279839403,
+      "learning_rate": 0.0,
+      "loss": 0.222,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 5.277578878380933e+17,
+      "train_loss": 0.39017832059679286,
+      "train_runtime": 21047.8381,
+      "train_samples_per_second": 1.051,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 224,
+  "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": 5.277578878380933e+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 sha256:37d73dc72f657c33235a9ba13bd93bdc7967fe2f1b103de0a0e549f5f2f3313f
+size 7288