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: opencodereasoning_0.3k
+  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. -->
+
+# opencodereasoning_0.3k
+
+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/opencodereasoning_0.3k 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- 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: 13.0
+
+### 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": 12.30379746835443,
+    "total_flos": 9.101952189202432e+16,
+    "train_loss": 0.4595338146910708,
+    "train_runtime": 4622.163,
+    "train_samples_per_second": 0.889,
+    "train_steps_per_second": 0.025
+}

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:f787a2bd453b2f8e829b545e18555b1fde46c2e5e3c17d9420b4f3fa4c3f6fc9
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206755356e4b555af9c6ef4335317693473dbeeb55999019d7c0f4bc742f1f4f
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293b39765c6f7144ca0cf7db7d75012e3e38f3666747c5e0a6c08068048e051a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e65bd18e5c2bd0234022e8a182ae46e2893cfb0749a8ed53a63076daf967977
+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_06-58-32_jrc0913/events.out.tfevents.1745816347.jrc0913.4125456.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636ba0967993a704d6ab30418dccd9497d9a1da9e4b225d37d18d944708e38a4
+size 30084

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 06:58:32", "end_time": "2025-04-28 08:16:20"}

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": 12.30379746835443,
+    "total_flos": 9.101952189202432e+16,
+    "train_loss": 0.4595338146910708,
+    "train_runtime": 4622.163,
+    "train_samples_per_second": 0.889,
+    "train_steps_per_second": 0.025
+}

trainer_log.jsonl

@@ -0,0 +1,118 @@
+{"current_steps": 1, "total_steps": 117, "loss": 1.054, "lr": 8.333333333333333e-07, "epoch": 0.10126582278481013, "percentage": 0.85, "elapsed_time": "0:00:48", "remaining_time": "1:33:11"}
+{"current_steps": 2, "total_steps": 117, "loss": 1.0479, "lr": 1.6666666666666667e-06, "epoch": 0.20253164556962025, "percentage": 1.71, "elapsed_time": "0:01:31", "remaining_time": "1:28:01"}
+{"current_steps": 3, "total_steps": 117, "loss": 1.076, "lr": 2.5e-06, "epoch": 0.3037974683544304, "percentage": 2.56, "elapsed_time": "0:02:15", "remaining_time": "1:25:36"}
+{"current_steps": 4, "total_steps": 117, "loss": 1.0488, "lr": 3.3333333333333333e-06, "epoch": 0.4050632911392405, "percentage": 3.42, "elapsed_time": "0:02:56", "remaining_time": "1:22:52"}
+{"current_steps": 5, "total_steps": 117, "loss": 1.0113, "lr": 4.166666666666667e-06, "epoch": 0.5063291139240507, "percentage": 4.27, "elapsed_time": "0:03:36", "remaining_time": "1:20:59"}
+{"current_steps": 6, "total_steps": 117, "loss": 0.9835, "lr": 5e-06, "epoch": 0.6075949367088608, "percentage": 5.13, "elapsed_time": "0:04:13", "remaining_time": "1:18:07"}
+{"current_steps": 7, "total_steps": 117, "loss": 0.9569, "lr": 5.833333333333334e-06, "epoch": 0.7088607594936709, "percentage": 5.98, "elapsed_time": "0:04:52", "remaining_time": "1:16:43"}
+{"current_steps": 8, "total_steps": 117, "loss": 0.9363, "lr": 6.666666666666667e-06, "epoch": 0.810126582278481, "percentage": 6.84, "elapsed_time": "0:05:30", "remaining_time": "1:15:02"}
+{"current_steps": 9, "total_steps": 117, "loss": 0.9485, "lr": 7.500000000000001e-06, "epoch": 0.9113924050632911, "percentage": 7.69, "elapsed_time": "0:06:04", "remaining_time": "1:12:56"}
+{"current_steps": 10, "total_steps": 117, "loss": 1.5612, "lr": 8.333333333333334e-06, "epoch": 1.0506329113924051, "percentage": 8.55, "elapsed_time": "0:07:08", "remaining_time": "1:16:29"}
+{"current_steps": 11, "total_steps": 117, "loss": 0.7947, "lr": 9.166666666666666e-06, "epoch": 1.1518987341772151, "percentage": 9.4, "elapsed_time": "0:07:43", "remaining_time": "1:14:27"}
+{"current_steps": 12, "total_steps": 117, "loss": 0.9017, "lr": 1e-05, "epoch": 1.2531645569620253, "percentage": 10.26, "elapsed_time": "0:08:20", "remaining_time": "1:13:01"}
+{"current_steps": 13, "total_steps": 117, "loss": 0.8621, "lr": 9.997762161417517e-06, "epoch": 1.3544303797468356, "percentage": 11.11, "elapsed_time": "0:09:04", "remaining_time": "1:12:38"}
+{"current_steps": 14, "total_steps": 117, "loss": 0.7153, "lr": 9.991050648838676e-06, "epoch": 1.4556962025316456, "percentage": 11.97, "elapsed_time": "0:09:38", "remaining_time": "1:10:57"}
+{"current_steps": 15, "total_steps": 117, "loss": 0.7946, "lr": 9.979871469976197e-06, "epoch": 1.5569620253164556, "percentage": 12.82, "elapsed_time": "0:10:21", "remaining_time": "1:10:25"}
+{"current_steps": 16, "total_steps": 117, "loss": 0.9096, "lr": 9.964234631709188e-06, "epoch": 1.6582278481012658, "percentage": 13.68, "elapsed_time": "0:10:54", "remaining_time": "1:08:51"}
+{"current_steps": 17, "total_steps": 117, "loss": 0.7832, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:11:28", "remaining_time": "1:07:31"}
+{"current_steps": 18, "total_steps": 117, "loss": 0.7584, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:12:09", "remaining_time": "1:06:49"}
+{"current_steps": 19, "total_steps": 117, "loss": 1.1585, "lr": 9.890738003669029e-06, "epoch": 1.9620253164556962, "percentage": 16.24, "elapsed_time": "0:12:47", "remaining_time": "1:05:56"}
+{"current_steps": 20, "total_steps": 117, "loss": 0.7294, "lr": 9.857450191464337e-06, "epoch": 2.1012658227848102, "percentage": 17.09, "elapsed_time": "0:13:56", "remaining_time": "1:07:39"}
+{"current_steps": 21, "total_steps": 117, "loss": 0.7097, "lr": 9.819814303479268e-06, "epoch": 2.2025316455696204, "percentage": 17.95, "elapsed_time": "0:14:35", "remaining_time": "1:06:43"}
+{"current_steps": 22, "total_steps": 117, "loss": 0.6938, "lr": 9.777864028930705e-06, "epoch": 2.3037974683544302, "percentage": 18.8, "elapsed_time": "0:15:11", "remaining_time": "1:05:36"}
+{"current_steps": 23, "total_steps": 117, "loss": 0.7032, "lr": 9.731636918995821e-06, "epoch": 2.4050632911392404, "percentage": 19.66, "elapsed_time": "0:15:46", "remaining_time": "1:04:26"}
+{"current_steps": 24, "total_steps": 117, "loss": 0.6648, "lr": 9.681174353198687e-06, "epoch": 2.5063291139240507, "percentage": 20.51, "elapsed_time": "0:16:26", "remaining_time": "1:03:41"}
+{"current_steps": 25, "total_steps": 117, "loss": 0.7288, "lr": 9.626521502369984e-06, "epoch": 2.607594936708861, "percentage": 21.37, "elapsed_time": "0:16:59", "remaining_time": "1:02:33"}
+{"current_steps": 26, "total_steps": 117, "loss": 0.6912, "lr": 9.567727288213005e-06, "epoch": 2.708860759493671, "percentage": 22.22, "elapsed_time": "0:17:33", "remaining_time": "1:01:25"}
+{"current_steps": 27, "total_steps": 117, "loss": 0.6945, "lr": 9.504844339512096e-06, "epoch": 2.810126582278481, "percentage": 23.08, "elapsed_time": "0:18:09", "remaining_time": "1:00:32"}
+{"current_steps": 28, "total_steps": 117, "loss": 0.6629, "lr": 9.437928945022772e-06, "epoch": 2.911392405063291, "percentage": 23.93, "elapsed_time": "0:18:47", "remaining_time": "0:59:43"}
+{"current_steps": 29, "total_steps": 117, "loss": 1.005, "lr": 9.36704100308565e-06, "epoch": 3.050632911392405, "percentage": 24.79, "elapsed_time": "0:19:48", "remaining_time": "1:00:06"}
+{"current_steps": 30, "total_steps": 117, "loss": 0.6001, "lr": 9.292243968009332e-06, "epoch": 3.151898734177215, "percentage": 25.64, "elapsed_time": "0:20:26", "remaining_time": "0:59:17"}
+{"current_steps": 31, "total_steps": 117, "loss": 0.5946, "lr": 9.213604793270196e-06, "epoch": 3.2531645569620253, "percentage": 26.5, "elapsed_time": "0:20:54", "remaining_time": "0:58:01"}
+{"current_steps": 32, "total_steps": 117, "loss": 0.566, "lr": 9.131193871579975e-06, "epoch": 3.3544303797468356, "percentage": 27.35, "elapsed_time": "0:21:22", "remaining_time": "0:56:47"}
+{"current_steps": 33, "total_steps": 117, "loss": 0.7532, "lr": 9.045084971874738e-06, "epoch": 3.4556962025316453, "percentage": 28.21, "elapsed_time": "0:22:07", "remaining_time": "0:56:18"}
+{"current_steps": 34, "total_steps": 117, "loss": 0.4619, "lr": 8.955355173281709e-06, "epoch": 3.5569620253164556, "percentage": 29.06, "elapsed_time": "0:22:45", "remaining_time": "0:55:33"}
+{"current_steps": 35, "total_steps": 117, "loss": 0.6378, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:23:23", "remaining_time": "0:54:47"}
+{"current_steps": 36, "total_steps": 117, "loss": 0.5243, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:24:01", "remaining_time": "0:54:03"}
+{"current_steps": 37, "total_steps": 117, "loss": 0.6424, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:24:43", "remaining_time": "0:53:26"}
+{"current_steps": 38, "total_steps": 117, "loss": 0.8755, "lr": 8.561880484756726e-06, "epoch": 3.962025316455696, "percentage": 32.48, "elapsed_time": "0:25:14", "remaining_time": "0:52:29"}
+{"current_steps": 39, "total_steps": 117, "loss": 0.5398, "lr": 8.455313244934324e-06, "epoch": 4.10126582278481, "percentage": 33.33, "elapsed_time": "0:26:18", "remaining_time": "0:52:36"}
+{"current_steps": 40, "total_steps": 117, "loss": 0.5382, "lr": 8.345653031794292e-06, "epoch": 4.2025316455696204, "percentage": 34.19, "elapsed_time": "0:26:56", "remaining_time": "0:51:51"}
+{"current_steps": 41, "total_steps": 117, "loss": 0.5356, "lr": 8.232998006078998e-06, "epoch": 4.30379746835443, "percentage": 35.04, "elapsed_time": "0:27:29", "remaining_time": "0:50:57"}
+{"current_steps": 42, "total_steps": 117, "loss": 0.5194, "lr": 8.117449009293668e-06, "epoch": 4.405063291139241, "percentage": 35.9, "elapsed_time": "0:27:58", "remaining_time": "0:49:56"}
+{"current_steps": 43, "total_steps": 117, "loss": 0.5147, "lr": 7.99910947343957e-06, "epoch": 4.506329113924051, "percentage": 36.75, "elapsed_time": "0:28:34", "remaining_time": "0:49:10"}
+{"current_steps": 44, "total_steps": 117, "loss": 0.4964, "lr": 7.87808532842837e-06, "epoch": 4.6075949367088604, "percentage": 37.61, "elapsed_time": "0:29:05", "remaining_time": "0:48:15"}
+{"current_steps": 45, "total_steps": 117, "loss": 0.483, "lr": 7.754484907260513e-06, "epoch": 4.708860759493671, "percentage": 38.46, "elapsed_time": "0:29:36", "remaining_time": "0:47:21"}
+{"current_steps": 46, "total_steps": 117, "loss": 0.4888, "lr": 7.628418849052523e-06, "epoch": 4.810126582278481, "percentage": 39.32, "elapsed_time": "0:30:17", "remaining_time": "0:46:45"}
+{"current_steps": 47, "total_steps": 117, "loss": 0.473, "lr": 7.500000000000001e-06, "epoch": 4.911392405063291, "percentage": 40.17, "elapsed_time": "0:30:56", "remaining_time": "0:46:04"}
+{"current_steps": 48, "total_steps": 117, "loss": 0.7226, "lr": 7.369343312364994e-06, "epoch": 5.050632911392405, "percentage": 41.03, "elapsed_time": "0:31:53", "remaining_time": "0:45:50"}
+{"current_steps": 49, "total_steps": 117, "loss": 0.4786, "lr": 7.236565741578163e-06, "epoch": 5.151898734177215, "percentage": 41.88, "elapsed_time": "0:32:33", "remaining_time": "0:45:10"}
+{"current_steps": 50, "total_steps": 117, "loss": 0.3273, "lr": 7.101786141547829e-06, "epoch": 5.253164556962025, "percentage": 42.74, "elapsed_time": "0:33:00", "remaining_time": "0:44:13"}
+{"current_steps": 51, "total_steps": 117, "loss": 0.4886, "lr": 6.965125158269619e-06, "epoch": 5.3544303797468356, "percentage": 43.59, "elapsed_time": "0:33:41", "remaining_time": "0:43:36"}
+{"current_steps": 52, "total_steps": 117, "loss": 0.4818, "lr": 6.8267051218319766e-06, "epoch": 5.455696202531645, "percentage": 44.44, "elapsed_time": "0:34:20", "remaining_time": "0:42:55"}
+{"current_steps": 53, "total_steps": 117, "loss": 0.3512, "lr": 6.686649936914151e-06, "epoch": 5.556962025316456, "percentage": 45.3, "elapsed_time": "0:34:53", "remaining_time": "0:42:08"}
+{"current_steps": 54, "total_steps": 117, "loss": 0.3786, "lr": 6.545084971874738e-06, "epoch": 5.658227848101266, "percentage": 46.15, "elapsed_time": "0:35:29", "remaining_time": "0:41:24"}
+{"current_steps": 55, "total_steps": 117, "loss": 0.4644, "lr": 6.402136946530014e-06, "epoch": 5.759493670886076, "percentage": 47.01, "elapsed_time": "0:36:11", "remaining_time": "0:40:47"}
+{"current_steps": 56, "total_steps": 117, "loss": 0.3689, "lr": 6.257933818722544e-06, "epoch": 5.860759493670886, "percentage": 47.86, "elapsed_time": "0:36:49", "remaining_time": "0:40:06"}
+{"current_steps": 57, "total_steps": 117, "loss": 0.6268, "lr": 6.112604669781572e-06, "epoch": 5.962025316455696, "percentage": 48.72, "elapsed_time": "0:37:26", "remaining_time": "0:39:24"}
+{"current_steps": 58, "total_steps": 117, "loss": 0.386, "lr": 5.9662795889777666e-06, "epoch": 6.10126582278481, "percentage": 49.57, "elapsed_time": "0:38:27", "remaining_time": "0:39:07"}
+{"current_steps": 59, "total_steps": 117, "loss": 0.3201, "lr": 5.819089557075689e-06, "epoch": 6.2025316455696204, "percentage": 50.43, "elapsed_time": "0:39:07", "remaining_time": "0:38:27"}
+{"current_steps": 60, "total_steps": 117, "loss": 0.3481, "lr": 5.671166329088278e-06, "epoch": 6.30379746835443, "percentage": 51.28, "elapsed_time": "0:39:40", "remaining_time": "0:37:41"}
+{"current_steps": 61, "total_steps": 117, "loss": 0.3466, "lr": 5.522642316338268e-06, "epoch": 6.405063291139241, "percentage": 52.14, "elapsed_time": "0:40:11", "remaining_time": "0:36:53"}
+{"current_steps": 62, "total_steps": 117, "loss": 0.3546, "lr": 5.373650467932122e-06, "epoch": 6.506329113924051, "percentage": 52.99, "elapsed_time": "0:40:57", "remaining_time": "0:36:19"}
+{"current_steps": 63, "total_steps": 117, "loss": 0.314, "lr": 5.224324151752575e-06, "epoch": 6.6075949367088604, "percentage": 53.85, "elapsed_time": "0:41:25", "remaining_time": "0:35:30"}
+{"current_steps": 64, "total_steps": 117, "loss": 0.3236, "lr": 5.074797035076319e-06, "epoch": 6.708860759493671, "percentage": 54.7, "elapsed_time": "0:41:59", "remaining_time": "0:34:46"}
+{"current_steps": 65, "total_steps": 117, "loss": 0.3308, "lr": 4.9252029649236835e-06, "epoch": 6.810126582278481, "percentage": 55.56, "elapsed_time": "0:42:37", "remaining_time": "0:34:06"}
+{"current_steps": 66, "total_steps": 117, "loss": 0.3232, "lr": 4.775675848247427e-06, "epoch": 6.911392405063291, "percentage": 56.41, "elapsed_time": "0:43:17", "remaining_time": "0:33:27"}
+{"current_steps": 67, "total_steps": 117, "loss": 0.455, "lr": 4.626349532067879e-06, "epoch": 7.050632911392405, "percentage": 57.26, "elapsed_time": "0:44:15", "remaining_time": "0:33:02"}
+{"current_steps": 68, "total_steps": 117, "loss": 0.3172, "lr": 4.477357683661734e-06, "epoch": 7.151898734177215, "percentage": 58.12, "elapsed_time": "0:44:58", "remaining_time": "0:32:24"}
+{"current_steps": 69, "total_steps": 117, "loss": 0.2454, "lr": 4.3288336709117246e-06, "epoch": 7.253164556962025, "percentage": 58.97, "elapsed_time": "0:45:29", "remaining_time": "0:31:38"}
+{"current_steps": 70, "total_steps": 117, "loss": 0.2928, "lr": 4.180910442924312e-06, "epoch": 7.3544303797468356, "percentage": 59.83, "elapsed_time": "0:46:00", "remaining_time": "0:30:53"}
+{"current_steps": 71, "total_steps": 117, "loss": 0.2754, "lr": 4.033720411022235e-06, "epoch": 7.455696202531645, "percentage": 60.68, "elapsed_time": "0:46:36", "remaining_time": "0:30:12"}
+{"current_steps": 72, "total_steps": 117, "loss": 0.2774, "lr": 3.887395330218429e-06, "epoch": 7.556962025316456, "percentage": 61.54, "elapsed_time": "0:47:11", "remaining_time": "0:29:29"}
+{"current_steps": 73, "total_steps": 117, "loss": 0.2268, "lr": 3.7420661812774577e-06, "epoch": 7.658227848101266, "percentage": 62.39, "elapsed_time": "0:47:48", "remaining_time": "0:28:48"}
+{"current_steps": 74, "total_steps": 117, "loss": 0.2376, "lr": 3.5978630534699873e-06, "epoch": 7.759493670886076, "percentage": 63.25, "elapsed_time": "0:48:23", "remaining_time": "0:28:07"}
+{"current_steps": 75, "total_steps": 117, "loss": 0.2417, "lr": 3.4549150281252635e-06, "epoch": 7.860759493670886, "percentage": 64.1, "elapsed_time": "0:48:57", "remaining_time": "0:27:25"}
+{"current_steps": 76, "total_steps": 117, "loss": 0.3908, "lr": 3.3133500630858507e-06, "epoch": 7.962025316455696, "percentage": 64.96, "elapsed_time": "0:49:39", "remaining_time": "0:26:47"}
+{"current_steps": 77, "total_steps": 117, "loss": 0.2232, "lr": 3.173294878168025e-06, "epoch": 8.10126582278481, "percentage": 65.81, "elapsed_time": "0:50:31", "remaining_time": "0:26:14"}
+{"current_steps": 78, "total_steps": 117, "loss": 0.2237, "lr": 3.0348748417303826e-06, "epoch": 8.20253164556962, "percentage": 66.67, "elapsed_time": "0:51:13", "remaining_time": "0:25:36"}
+{"current_steps": 79, "total_steps": 117, "loss": 0.2137, "lr": 2.8982138584521734e-06, "epoch": 8.30379746835443, "percentage": 67.52, "elapsed_time": "0:51:51", "remaining_time": "0:24:56"}
+{"current_steps": 80, "total_steps": 117, "loss": 0.2025, "lr": 2.7634342584218364e-06, "epoch": 8.405063291139241, "percentage": 68.38, "elapsed_time": "0:52:28", "remaining_time": "0:24:15"}
+{"current_steps": 81, "total_steps": 117, "loss": 0.1998, "lr": 2.6306566876350072e-06, "epoch": 8.50632911392405, "percentage": 69.23, "elapsed_time": "0:53:02", "remaining_time": "0:23:34"}
+{"current_steps": 82, "total_steps": 117, "loss": 0.2075, "lr": 2.5000000000000015e-06, "epoch": 8.60759493670886, "percentage": 70.09, "elapsed_time": "0:53:39", "remaining_time": "0:22:54"}
+{"current_steps": 83, "total_steps": 117, "loss": 0.2269, "lr": 2.371581150947476e-06, "epoch": 8.708860759493671, "percentage": 70.94, "elapsed_time": "0:54:17", "remaining_time": "0:22:14"}
+{"current_steps": 84, "total_steps": 117, "loss": 0.2012, "lr": 2.245515092739488e-06, "epoch": 8.810126582278482, "percentage": 71.79, "elapsed_time": "0:54:52", "remaining_time": "0:21:33"}
+{"current_steps": 85, "total_steps": 117, "loss": 0.2054, "lr": 2.1219146715716332e-06, "epoch": 8.91139240506329, "percentage": 72.65, "elapsed_time": "0:55:35", "remaining_time": "0:20:55"}
+{"current_steps": 86, "total_steps": 117, "loss": 0.3057, "lr": 2.0008905265604316e-06, "epoch": 9.050632911392405, "percentage": 73.5, "elapsed_time": "0:56:38", "remaining_time": "0:20:25"}
+{"current_steps": 87, "total_steps": 117, "loss": 0.1753, "lr": 1.8825509907063328e-06, "epoch": 9.151898734177216, "percentage": 74.36, "elapsed_time": "0:57:10", "remaining_time": "0:19:43"}
+{"current_steps": 88, "total_steps": 117, "loss": 0.1839, "lr": 1.7670019939210025e-06, "epoch": 9.253164556962025, "percentage": 75.21, "elapsed_time": "0:57:49", "remaining_time": "0:19:03"}
+{"current_steps": 89, "total_steps": 117, "loss": 0.1495, "lr": 1.6543469682057105e-06, "epoch": 9.354430379746836, "percentage": 76.07, "elapsed_time": "0:58:27", "remaining_time": "0:18:23"}
+{"current_steps": 90, "total_steps": 117, "loss": 0.1764, "lr": 1.544686755065677e-06, "epoch": 9.455696202531646, "percentage": 76.92, "elapsed_time": "0:59:01", "remaining_time": "0:17:42"}
+{"current_steps": 91, "total_steps": 117, "loss": 0.1849, "lr": 1.438119515243277e-06, "epoch": 9.556962025316455, "percentage": 77.78, "elapsed_time": "0:59:34", "remaining_time": "0:17:01"}
+{"current_steps": 92, "total_steps": 117, "loss": 0.1757, "lr": 1.3347406408508695e-06, "epoch": 9.658227848101266, "percentage": 78.63, "elapsed_time": "1:00:08", "remaining_time": "0:16:20"}
+{"current_steps": 93, "total_steps": 117, "loss": 0.1686, "lr": 1.234642669981946e-06, "epoch": 9.759493670886076, "percentage": 79.49, "elapsed_time": "1:00:46", "remaining_time": "0:15:40"}
+{"current_steps": 94, "total_steps": 117, "loss": 0.1922, "lr": 1.137915203877003e-06, "epoch": 9.860759493670885, "percentage": 80.34, "elapsed_time": "1:01:25", "remaining_time": "0:15:01"}
+{"current_steps": 95, "total_steps": 117, "loss": 0.2362, "lr": 1.044644826718295e-06, "epoch": 9.962025316455696, "percentage": 81.2, "elapsed_time": "1:01:55", "remaining_time": "0:14:20"}
+{"current_steps": 96, "total_steps": 117, "loss": 0.178, "lr": 9.549150281252633e-07, "epoch": 10.10126582278481, "percentage": 82.05, "elapsed_time": "1:02:56", "remaining_time": "0:13:46"}
+{"current_steps": 97, "total_steps": 117, "loss": 0.1472, "lr": 8.688061284200266e-07, "epoch": 10.20253164556962, "percentage": 82.91, "elapsed_time": "1:03:30", "remaining_time": "0:13:05"}
+{"current_steps": 98, "total_steps": 117, "loss": 0.1498, "lr": 7.863952067298042e-07, "epoch": 10.30379746835443, "percentage": 83.76, "elapsed_time": "1:04:07", "remaining_time": "0:12:26"}
+{"current_steps": 99, "total_steps": 117, "loss": 0.16, "lr": 7.077560319906696e-07, "epoch": 10.405063291139241, "percentage": 84.62, "elapsed_time": "1:04:45", "remaining_time": "0:11:46"}
+{"current_steps": 100, "total_steps": 117, "loss": 0.1501, "lr": 6.329589969143518e-07, "epoch": 10.50632911392405, "percentage": 85.47, "elapsed_time": "1:05:16", "remaining_time": "0:11:05"}
+{"current_steps": 101, "total_steps": 117, "loss": 0.1474, "lr": 5.620710549772295e-07, "epoch": 10.60759493670886, "percentage": 86.32, "elapsed_time": "1:05:57", "remaining_time": "0:10:26"}
+{"current_steps": 102, "total_steps": 117, "loss": 0.1361, "lr": 4.951556604879049e-07, "epoch": 10.708860759493671, "percentage": 87.18, "elapsed_time": "1:06:30", "remaining_time": "0:09:46"}
+{"current_steps": 103, "total_steps": 117, "loss": 0.1635, "lr": 4.322727117869951e-07, "epoch": 10.810126582278482, "percentage": 88.03, "elapsed_time": "1:07:11", "remaining_time": "0:09:07"}
+{"current_steps": 104, "total_steps": 117, "loss": 0.1611, "lr": 3.734784976300165e-07, "epoch": 10.91139240506329, "percentage": 88.89, "elapsed_time": "1:07:44", "remaining_time": "0:08:28"}
+{"current_steps": 105, "total_steps": 117, "loss": 0.2163, "lr": 3.18825646801314e-07, "epoch": 11.050632911392405, "percentage": 89.74, "elapsed_time": "1:08:43", "remaining_time": "0:07:51"}
+{"current_steps": 106, "total_steps": 117, "loss": 0.1532, "lr": 2.6836308100417874e-07, "epoch": 11.151898734177216, "percentage": 90.6, "elapsed_time": "1:09:23", "remaining_time": "0:07:12"}
+{"current_steps": 107, "total_steps": 117, "loss": 0.1417, "lr": 2.2213597106929608e-07, "epoch": 11.253164556962025, "percentage": 91.45, "elapsed_time": "1:09:55", "remaining_time": "0:06:32"}
+{"current_steps": 108, "total_steps": 117, "loss": 0.1452, "lr": 1.801856965207338e-07, "epoch": 11.354430379746836, "percentage": 92.31, "elapsed_time": "1:10:28", "remaining_time": "0:05:52"}
+{"current_steps": 109, "total_steps": 117, "loss": 0.1502, "lr": 1.4254980853566248e-07, "epoch": 11.455696202531646, "percentage": 93.16, "elapsed_time": "1:10:59", "remaining_time": "0:05:12"}
+{"current_steps": 110, "total_steps": 117, "loss": 0.1259, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "1:11:26", "remaining_time": "0:04:32"}
+{"current_steps": 111, "total_steps": 117, "loss": 0.1307, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "1:12:08", "remaining_time": "0:03:53"}
+{"current_steps": 112, "total_steps": 117, "loss": 0.1354, "lr": 5.584586887435739e-08, "epoch": 11.759493670886076, "percentage": 95.73, "elapsed_time": "1:12:49", "remaining_time": "0:03:15"}
+{"current_steps": 113, "total_steps": 117, "loss": 0.1331, "lr": 3.576536829081323e-08, "epoch": 11.860759493670885, "percentage": 96.58, "elapsed_time": "1:13:25", "remaining_time": "0:02:35"}
+{"current_steps": 114, "total_steps": 117, "loss": 0.2331, "lr": 2.012853002380466e-08, "epoch": 11.962025316455696, "percentage": 97.44, "elapsed_time": "1:14:02", "remaining_time": "0:01:56"}
+{"current_steps": 115, "total_steps": 117, "loss": 0.1322, "lr": 8.949351161324227e-09, "epoch": 12.10126582278481, "percentage": 98.29, "elapsed_time": "1:15:02", "remaining_time": "0:01:18"}
+{"current_steps": 116, "total_steps": 117, "loss": 0.1465, "lr": 2.237838582483387e-09, "epoch": 12.20253164556962, "percentage": 99.15, "elapsed_time": "1:15:29", "remaining_time": "0:00:39"}
+{"current_steps": 117, "total_steps": 117, "loss": 0.1496, "lr": 0.0, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:16:09", "remaining_time": "0:00:00"}
+{"current_steps": 117, "total_steps": 117, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:17:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,861 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.30379746835443,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 6.853755327038079,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.054,
+      "step": 1
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 6.7248331828080925,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0479,
+      "step": 2
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 6.793346657766399,
+      "learning_rate": 2.5e-06,
+      "loss": 1.076,
+      "step": 3
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 6.399417172855183,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0488,
+      "step": 4
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 4.973638656499535,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.0113,
+      "step": 5
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 3.1828149939077117,
+      "learning_rate": 5e-06,
+      "loss": 0.9835,
+      "step": 6
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 2.6352548487400074,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9569,
+      "step": 7
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 3.8080928407525545,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9363,
+      "step": 8
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 4.275332292538442,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9485,
+      "step": 9
+    },
+    {
+      "epoch": 1.0506329113924051,
+      "grad_norm": 6.873397157307676,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.5612,
+      "step": 10
+    },
+    {
+      "epoch": 1.1518987341772151,
+      "grad_norm": 3.3656617520903636,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.7947,
+      "step": 11
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 3.524663093579077,
+      "learning_rate": 1e-05,
+      "loss": 0.9017,
+      "step": 12
+    },
+    {
+      "epoch": 1.3544303797468356,
+      "grad_norm": 2.5091723070752003,
+      "learning_rate": 9.997762161417517e-06,
+      "loss": 0.8621,
+      "step": 13
+    },
+    {
+      "epoch": 1.4556962025316456,
+      "grad_norm": 1.6561631908665362,
+      "learning_rate": 9.991050648838676e-06,
+      "loss": 0.7153,
+      "step": 14
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 1.7934912386240331,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.7946,
+      "step": 15
+    },
+    {
+      "epoch": 1.6582278481012658,
+      "grad_norm": 2.1179200863384553,
+      "learning_rate": 9.964234631709188e-06,
+      "loss": 0.9096,
+      "step": 16
+    },
+    {
+      "epoch": 1.759493670886076,
+      "grad_norm": 1.4608060819959077,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 0.7832,
+      "step": 17
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 1.2126476930576133,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.7584,
+      "step": 18
+    },
+    {
+      "epoch": 1.9620253164556962,
+      "grad_norm": 2.146192940889719,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 1.1585,
+      "step": 19
+    },
+    {
+      "epoch": 2.1012658227848102,
+      "grad_norm": 1.369292660595033,
+      "learning_rate": 9.857450191464337e-06,
+      "loss": 0.7294,
+      "step": 20
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 1.2626340360076094,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.7097,
+      "step": 21
+    },
+    {
+      "epoch": 2.3037974683544302,
+      "grad_norm": 0.9597691127181127,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 0.6938,
+      "step": 22
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 1.2604895009103103,
+      "learning_rate": 9.731636918995821e-06,
+      "loss": 0.7032,
+      "step": 23
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 1.2688720086624306,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.6648,
+      "step": 24
+    },
+    {
+      "epoch": 2.607594936708861,
+      "grad_norm": 1.0868419667652194,
+      "learning_rate": 9.626521502369984e-06,
+      "loss": 0.7288,
+      "step": 25
+    },
+    {
+      "epoch": 2.708860759493671,
+      "grad_norm": 1.3292378755288756,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 0.6912,
+      "step": 26
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 1.2346104887882967,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.6945,
+      "step": 27
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 1.02561670902633,
+      "learning_rate": 9.437928945022772e-06,
+      "loss": 0.6629,
+      "step": 28
+    },
+    {
+      "epoch": 3.050632911392405,
+      "grad_norm": 1.9356146978360425,
+      "learning_rate": 9.36704100308565e-06,
+      "loss": 1.005,
+      "step": 29
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 1.271249473510972,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.6001,
+      "step": 30
+    },
+    {
+      "epoch": 3.2531645569620253,
+      "grad_norm": 1.0253844700862984,
+      "learning_rate": 9.213604793270196e-06,
+      "loss": 0.5946,
+      "step": 31
+    },
+    {
+      "epoch": 3.3544303797468356,
+      "grad_norm": 0.9114775970910892,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.566,
+      "step": 32
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 1.22530795109878,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7532,
+      "step": 33
+    },
+    {
+      "epoch": 3.5569620253164556,
+      "grad_norm": 0.6946604067078974,
+      "learning_rate": 8.955355173281709e-06,
+      "loss": 0.4619,
+      "step": 34
+    },
+    {
+      "epoch": 3.6582278481012658,
+      "grad_norm": 1.047406831639789,
+      "learning_rate": 8.862084796122998e-06,
+      "loss": 0.6378,
+      "step": 35
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.711823766609595,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.5243,
+      "step": 36
+    },
+    {
+      "epoch": 3.8607594936708862,
+      "grad_norm": 0.9122786016111567,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 0.6424,
+      "step": 37
+    },
+    {
+      "epoch": 3.962025316455696,
+      "grad_norm": 1.3017517797000289,
+      "learning_rate": 8.561880484756726e-06,
+      "loss": 0.8755,
+      "step": 38
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.8336965053721384,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.5398,
+      "step": 39
+    },
+    {
+      "epoch": 4.2025316455696204,
+      "grad_norm": 0.7646224552052723,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 0.5382,
+      "step": 40
+    },
+    {
+      "epoch": 4.30379746835443,
+      "grad_norm": 0.7875281400060778,
+      "learning_rate": 8.232998006078998e-06,
+      "loss": 0.5356,
+      "step": 41
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.845564019017656,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5194,
+      "step": 42
+    },
+    {
+      "epoch": 4.506329113924051,
+      "grad_norm": 0.7433701271634005,
+      "learning_rate": 7.99910947343957e-06,
+      "loss": 0.5147,
+      "step": 43
+    },
+    {
+      "epoch": 4.6075949367088604,
+      "grad_norm": 0.9200656896721353,
+      "learning_rate": 7.87808532842837e-06,
+      "loss": 0.4964,
+      "step": 44
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.8863920970016912,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.483,
+      "step": 45
+    },
+    {
+      "epoch": 4.810126582278481,
+      "grad_norm": 0.805646965467507,
+      "learning_rate": 7.628418849052523e-06,
+      "loss": 0.4888,
+      "step": 46
+    },
+    {
+      "epoch": 4.911392405063291,
+      "grad_norm": 0.8469077839570921,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.473,
+      "step": 47
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 1.1316845580084651,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.7226,
+      "step": 48
+    },
+    {
+      "epoch": 5.151898734177215,
+      "grad_norm": 0.7610540567385804,
+      "learning_rate": 7.236565741578163e-06,
+      "loss": 0.4786,
+      "step": 49
+    },
+    {
+      "epoch": 5.253164556962025,
+      "grad_norm": 0.6395383235541354,
+      "learning_rate": 7.101786141547829e-06,
+      "loss": 0.3273,
+      "step": 50
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.8554027282099782,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.4886,
+      "step": 51
+    },
+    {
+      "epoch": 5.455696202531645,
+      "grad_norm": 0.8451926273461702,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 0.4818,
+      "step": 52
+    },
+    {
+      "epoch": 5.556962025316456,
+      "grad_norm": 0.6633671884643004,
+      "learning_rate": 6.686649936914151e-06,
+      "loss": 0.3512,
+      "step": 53
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.7877500797629732,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.3786,
+      "step": 54
+    },
+    {
+      "epoch": 5.759493670886076,
+      "grad_norm": 0.7686923486972509,
+      "learning_rate": 6.402136946530014e-06,
+      "loss": 0.4644,
+      "step": 55
+    },
+    {
+      "epoch": 5.860759493670886,
+      "grad_norm": 0.65164216458978,
+      "learning_rate": 6.257933818722544e-06,
+      "loss": 0.3689,
+      "step": 56
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 1.3973623392345897,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.6268,
+      "step": 57
+    },
+    {
+      "epoch": 6.10126582278481,
+      "grad_norm": 0.8029150370176054,
+      "learning_rate": 5.9662795889777666e-06,
+      "loss": 0.386,
+      "step": 58
+    },
+    {
+      "epoch": 6.2025316455696204,
+      "grad_norm": 0.8520885652834594,
+      "learning_rate": 5.819089557075689e-06,
+      "loss": 0.3201,
+      "step": 59
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 1.024212957711499,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.3481,
+      "step": 60
+    },
+    {
+      "epoch": 6.405063291139241,
+      "grad_norm": 0.9772378939893376,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 0.3466,
+      "step": 61
+    },
+    {
+      "epoch": 6.506329113924051,
+      "grad_norm": 0.8194978346963566,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 0.3546,
+      "step": 62
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.8534533201642622,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.314,
+      "step": 63
+    },
+    {
+      "epoch": 6.708860759493671,
+      "grad_norm": 0.7809321319644733,
+      "learning_rate": 5.074797035076319e-06,
+      "loss": 0.3236,
+      "step": 64
+    },
+    {
+      "epoch": 6.810126582278481,
+      "grad_norm": 0.9096044136211295,
+      "learning_rate": 4.9252029649236835e-06,
+      "loss": 0.3308,
+      "step": 65
+    },
+    {
+      "epoch": 6.911392405063291,
+      "grad_norm": 0.8958045974543299,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.3232,
+      "step": 66
+    },
+    {
+      "epoch": 7.050632911392405,
+      "grad_norm": 1.2284199200433397,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 0.455,
+      "step": 67
+    },
+    {
+      "epoch": 7.151898734177215,
+      "grad_norm": 1.0209394478690026,
+      "learning_rate": 4.477357683661734e-06,
+      "loss": 0.3172,
+      "step": 68
+    },
+    {
+      "epoch": 7.253164556962025,
+      "grad_norm": 0.8411127195413696,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.2454,
+      "step": 69
+    },
+    {
+      "epoch": 7.3544303797468356,
+      "grad_norm": 1.007359276104836,
+      "learning_rate": 4.180910442924312e-06,
+      "loss": 0.2928,
+      "step": 70
+    },
+    {
+      "epoch": 7.455696202531645,
+      "grad_norm": 1.3583271315700094,
+      "learning_rate": 4.033720411022235e-06,
+      "loss": 0.2754,
+      "step": 71
+    },
+    {
+      "epoch": 7.556962025316456,
+      "grad_norm": 0.8444737453345904,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.2774,
+      "step": 72
+    },
+    {
+      "epoch": 7.658227848101266,
+      "grad_norm": 0.7995027858063242,
+      "learning_rate": 3.7420661812774577e-06,
+      "loss": 0.2268,
+      "step": 73
+    },
+    {
+      "epoch": 7.759493670886076,
+      "grad_norm": 0.829822765554238,
+      "learning_rate": 3.5978630534699873e-06,
+      "loss": 0.2376,
+      "step": 74
+    },
+    {
+      "epoch": 7.860759493670886,
+      "grad_norm": 0.7949993356800901,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.2417,
+      "step": 75
+    },
+    {
+      "epoch": 7.962025316455696,
+      "grad_norm": 1.083008382706899,
+      "learning_rate": 3.3133500630858507e-06,
+      "loss": 0.3908,
+      "step": 76
+    },
+    {
+      "epoch": 8.10126582278481,
+      "grad_norm": 0.7384347404687762,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 0.2232,
+      "step": 77
+    },
+    {
+      "epoch": 8.20253164556962,
+      "grad_norm": 0.7489172508921755,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.2237,
+      "step": 78
+    },
+    {
+      "epoch": 8.30379746835443,
+      "grad_norm": 0.7997609752723011,
+      "learning_rate": 2.8982138584521734e-06,
+      "loss": 0.2137,
+      "step": 79
+    },
+    {
+      "epoch": 8.405063291139241,
+      "grad_norm": 0.7934569206656524,
+      "learning_rate": 2.7634342584218364e-06,
+      "loss": 0.2025,
+      "step": 80
+    },
+    {
+      "epoch": 8.50632911392405,
+      "grad_norm": 0.7246422597431458,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.1998,
+      "step": 81
+    },
+    {
+      "epoch": 8.60759493670886,
+      "grad_norm": 0.6754392616504892,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.2075,
+      "step": 82
+    },
+    {
+      "epoch": 8.708860759493671,
+      "grad_norm": 0.6981132485392166,
+      "learning_rate": 2.371581150947476e-06,
+      "loss": 0.2269,
+      "step": 83
+    },
+    {
+      "epoch": 8.810126582278482,
+      "grad_norm": 0.7631604441829668,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.2012,
+      "step": 84
+    },
+    {
+      "epoch": 8.91139240506329,
+      "grad_norm": 0.691094769682961,
+      "learning_rate": 2.1219146715716332e-06,
+      "loss": 0.2054,
+      "step": 85
+    },
+    {
+      "epoch": 9.050632911392405,
+      "grad_norm": 1.044439601871888,
+      "learning_rate": 2.0008905265604316e-06,
+      "loss": 0.3057,
+      "step": 86
+    },
+    {
+      "epoch": 9.151898734177216,
+      "grad_norm": 0.7389192407768973,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.1753,
+      "step": 87
+    },
+    {
+      "epoch": 9.253164556962025,
+      "grad_norm": 0.8928754224532668,
+      "learning_rate": 1.7670019939210025e-06,
+      "loss": 0.1839,
+      "step": 88
+    },
+    {
+      "epoch": 9.354430379746836,
+      "grad_norm": 0.7174544029609661,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 0.1495,
+      "step": 89
+    },
+    {
+      "epoch": 9.455696202531646,
+      "grad_norm": 1.0095542055134636,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.1764,
+      "step": 90
+    },
+    {
+      "epoch": 9.556962025316455,
+      "grad_norm": 0.9898931188613699,
+      "learning_rate": 1.438119515243277e-06,
+      "loss": 0.1849,
+      "step": 91
+    },
+    {
+      "epoch": 9.658227848101266,
+      "grad_norm": 0.6806978513304183,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 0.1757,
+      "step": 92
+    },
+    {
+      "epoch": 9.759493670886076,
+      "grad_norm": 0.7369725238345852,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.1686,
+      "step": 93
+    },
+    {
+      "epoch": 9.860759493670885,
+      "grad_norm": 0.8401916486657559,
+      "learning_rate": 1.137915203877003e-06,
+      "loss": 0.1922,
+      "step": 94
+    },
+    {
+      "epoch": 9.962025316455696,
+      "grad_norm": 1.1445038380201404,
+      "learning_rate": 1.044644826718295e-06,
+      "loss": 0.2362,
+      "step": 95
+    },
+    {
+      "epoch": 10.10126582278481,
+      "grad_norm": 1.713991282049752,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.178,
+      "step": 96
+    },
+    {
+      "epoch": 10.20253164556962,
+      "grad_norm": 0.7263920249731424,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 0.1472,
+      "step": 97
+    },
+    {
+      "epoch": 10.30379746835443,
+      "grad_norm": 0.654115196746866,
+      "learning_rate": 7.863952067298042e-07,
+      "loss": 0.1498,
+      "step": 98
+    },
+    {
+      "epoch": 10.405063291139241,
+      "grad_norm": 0.6984926674484835,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.16,
+      "step": 99
+    },
+    {
+      "epoch": 10.50632911392405,
+      "grad_norm": 0.779812844768717,
+      "learning_rate": 6.329589969143518e-07,
+      "loss": 0.1501,
+      "step": 100
+    },
+    {
+      "epoch": 10.60759493670886,
+      "grad_norm": 0.8903247160522805,
+      "learning_rate": 5.620710549772295e-07,
+      "loss": 0.1474,
+      "step": 101
+    },
+    {
+      "epoch": 10.708860759493671,
+      "grad_norm": 0.8749237869088703,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.1361,
+      "step": 102
+    },
+    {
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.9183489788922128,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 0.1635,
+      "step": 103
+    },
+    {
+      "epoch": 10.91139240506329,
+      "grad_norm": 0.640927724740078,
+      "learning_rate": 3.734784976300165e-07,
+      "loss": 0.1611,
+      "step": 104
+    },
+    {
+      "epoch": 11.050632911392405,
+      "grad_norm": 0.9234957345398533,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.2163,
+      "step": 105
+    },
+    {
+      "epoch": 11.151898734177216,
+      "grad_norm": 0.5850183080908703,
+      "learning_rate": 2.6836308100417874e-07,
+      "loss": 0.1532,
+      "step": 106
+    },
+    {
+      "epoch": 11.253164556962025,
+      "grad_norm": 0.623097599780791,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 0.1417,
+      "step": 107
+    },
+    {
+      "epoch": 11.354430379746836,
+      "grad_norm": 0.8886870572165986,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.1452,
+      "step": 108
+    },
+    {
+      "epoch": 11.455696202531646,
+      "grad_norm": 0.6809910647284587,
+      "learning_rate": 1.4254980853566248e-07,
+      "loss": 0.1502,
+      "step": 109
+    },
+    {
+      "epoch": 11.556962025316455,
+      "grad_norm": 0.6186409670002029,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 0.1259,
+      "step": 110
+    },
+    {
+      "epoch": 11.658227848101266,
+      "grad_norm": 0.6414798273261219,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.1307,
+      "step": 111
+    },
+    {
+      "epoch": 11.759493670886076,
+      "grad_norm": 0.5732446786349397,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 0.1354,
+      "step": 112
+    },
+    {
+      "epoch": 11.860759493670885,
+      "grad_norm": 0.5596747757561155,
+      "learning_rate": 3.576536829081323e-08,
+      "loss": 0.1331,
+      "step": 113
+    },
+    {
+      "epoch": 11.962025316455696,
+      "grad_norm": 0.8922015800275596,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.2331,
+      "step": 114
+    },
+    {
+      "epoch": 12.10126582278481,
+      "grad_norm": 0.5784867209037564,
+      "learning_rate": 8.949351161324227e-09,
+      "loss": 0.1322,
+      "step": 115
+    },
+    {
+      "epoch": 12.20253164556962,
+      "grad_norm": 0.5683118055283999,
+      "learning_rate": 2.237838582483387e-09,
+      "loss": 0.1465,
+      "step": 116
+    },
+    {
+      "epoch": 12.30379746835443,
+      "grad_norm": 0.5300130325739068,
+      "learning_rate": 0.0,
+      "loss": 0.1496,
+      "step": 117
+    },
+    {
+      "epoch": 12.30379746835443,
+      "step": 117,
+      "total_flos": 9.101952189202432e+16,
+      "train_loss": 0.4595338146910708,
+      "train_runtime": 4622.163,
+      "train_samples_per_second": 0.889,
+      "train_steps_per_second": 0.025
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 13,
+  "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": 9.101952189202432e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e98ec080e6d1f19d69a04736b159b0783e9c889f71931b6e92539149cda918
+size 7352