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: d1_science_mc_llm_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. -->
+
+# d1_science_mc_llm_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/d1_science_mc_llm_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: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 13.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.0,
+    "total_flos": 3.637752234193715e+16,
+    "train_loss": 0.3008259800907511,
+    "train_runtime": 1399.9113,
+    "train_samples_per_second": 2.934,
+    "train_steps_per_second": 0.093
+}

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:b7fbe3580480938235a4e8245771a107b5979ea1117bde5d514ce088bcf50581
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae98b4f32655aac7cf6f7a9d43e0c0347a651568bc43bb80145012496f29884
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3a3ff1d8df2abd1985451131f967b53a0ed3a9e95890d2a9cd3a237f024667
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba351df4b66e5597ebb839a2a5130d27630bd3016aecd5a9bdd40dfdd726415
+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_06-14-08_jpbot-001-31.jupiter.internal/events.out.tfevents.1745813684.jpbot-001-31.jupiter.internal.2832632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce080e33ce40acb3b99038c21f45f15a0e2e82e4636f1ec2b0acfb125716512f
+size 32815

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 06:14:08", "end_time": "2025-04-28 06:38:11"}

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": 13.0,
+    "total_flos": 3.637752234193715e+16,
+    "train_loss": 0.3008259800907511,
+    "train_runtime": 1399.9113,
+    "train_samples_per_second": 2.934,
+    "train_steps_per_second": 0.093
+}

trainer_log.jsonl

@@ -0,0 +1,131 @@
+{"current_steps": 1, "total_steps": 130, "loss": 1.0569, "lr": 7.692307692307694e-07, "epoch": 0.1, "percentage": 0.77, "elapsed_time": "0:00:14", "remaining_time": "0:31:38"}
+{"current_steps": 2, "total_steps": 130, "loss": 0.9812, "lr": 1.5384615384615387e-06, "epoch": 0.2, "percentage": 1.54, "elapsed_time": "0:00:22", "remaining_time": "0:24:00"}
+{"current_steps": 3, "total_steps": 130, "loss": 1.0801, "lr": 2.307692307692308e-06, "epoch": 0.3, "percentage": 2.31, "elapsed_time": "0:00:28", "remaining_time": "0:20:24"}
+{"current_steps": 4, "total_steps": 130, "loss": 1.1116, "lr": 3.0769230769230774e-06, "epoch": 0.4, "percentage": 3.08, "elapsed_time": "0:00:35", "remaining_time": "0:18:53"}
+{"current_steps": 5, "total_steps": 130, "loss": 0.8986, "lr": 3.846153846153847e-06, "epoch": 0.5, "percentage": 3.85, "elapsed_time": "0:00:42", "remaining_time": "0:17:53"}
+{"current_steps": 6, "total_steps": 130, "loss": 0.9908, "lr": 4.615384615384616e-06, "epoch": 0.6, "percentage": 4.62, "elapsed_time": "0:00:51", "remaining_time": "0:17:54"}
+{"current_steps": 7, "total_steps": 130, "loss": 0.8701, "lr": 5.384615384615385e-06, "epoch": 0.7, "percentage": 5.38, "elapsed_time": "0:01:02", "remaining_time": "0:18:20"}
+{"current_steps": 8, "total_steps": 130, "loss": 0.9159, "lr": 6.153846153846155e-06, "epoch": 0.8, "percentage": 6.15, "elapsed_time": "0:01:12", "remaining_time": "0:18:22"}
+{"current_steps": 9, "total_steps": 130, "loss": 1.0084, "lr": 6.923076923076923e-06, "epoch": 0.9, "percentage": 6.92, "elapsed_time": "0:01:20", "remaining_time": "0:18:05"}
+{"current_steps": 10, "total_steps": 130, "loss": 0.8668, "lr": 7.692307692307694e-06, "epoch": 1.0, "percentage": 7.69, "elapsed_time": "0:01:31", "remaining_time": "0:18:12"}
+{"current_steps": 11, "total_steps": 130, "loss": 0.8952, "lr": 8.461538461538462e-06, "epoch": 1.1, "percentage": 8.46, "elapsed_time": "0:01:52", "remaining_time": "0:20:17"}
+{"current_steps": 12, "total_steps": 130, "loss": 0.8292, "lr": 9.230769230769232e-06, "epoch": 1.2, "percentage": 9.23, "elapsed_time": "0:02:01", "remaining_time": "0:19:57"}
+{"current_steps": 13, "total_steps": 130, "loss": 0.8146, "lr": 1e-05, "epoch": 1.3, "percentage": 10.0, "elapsed_time": "0:02:11", "remaining_time": "0:19:42"}
+{"current_steps": 14, "total_steps": 130, "loss": 0.8015, "lr": 9.998197638354428e-06, "epoch": 1.4, "percentage": 10.77, "elapsed_time": "0:02:17", "remaining_time": "0:18:59"}
+{"current_steps": 15, "total_steps": 130, "loss": 0.7967, "lr": 9.992791852820709e-06, "epoch": 1.5, "percentage": 11.54, "elapsed_time": "0:02:27", "remaining_time": "0:18:47"}
+{"current_steps": 16, "total_steps": 130, "loss": 0.7552, "lr": 9.983786540671052e-06, "epoch": 1.6, "percentage": 12.31, "elapsed_time": "0:02:31", "remaining_time": "0:18:02"}
+{"current_steps": 17, "total_steps": 130, "loss": 0.7797, "lr": 9.971188194237141e-06, "epoch": 1.7, "percentage": 13.08, "elapsed_time": "0:02:38", "remaining_time": "0:17:35"}
+{"current_steps": 18, "total_steps": 130, "loss": 0.7646, "lr": 9.955005896229543e-06, "epoch": 1.8, "percentage": 13.85, "elapsed_time": "0:02:46", "remaining_time": "0:17:15"}
+{"current_steps": 19, "total_steps": 130, "loss": 0.6918, "lr": 9.935251313189564e-06, "epoch": 1.9, "percentage": 14.62, "elapsed_time": "0:02:55", "remaining_time": "0:17:02"}
+{"current_steps": 20, "total_steps": 130, "loss": 0.7386, "lr": 9.911938687078324e-06, "epoch": 2.0, "percentage": 15.38, "elapsed_time": "0:03:07", "remaining_time": "0:17:09"}
+{"current_steps": 21, "total_steps": 130, "loss": 0.6268, "lr": 9.885084825009085e-06, "epoch": 2.1, "percentage": 16.15, "elapsed_time": "0:03:36", "remaining_time": "0:18:45"}
+{"current_steps": 22, "total_steps": 130, "loss": 0.6714, "lr": 9.854709087130261e-06, "epoch": 2.2, "percentage": 16.92, "elapsed_time": "0:03:44", "remaining_time": "0:18:20"}
+{"current_steps": 23, "total_steps": 130, "loss": 0.6182, "lr": 9.820833372667813e-06, "epoch": 2.3, "percentage": 17.69, "elapsed_time": "0:03:54", "remaining_time": "0:18:11"}
+{"current_steps": 24, "total_steps": 130, "loss": 0.6419, "lr": 9.783482104137127e-06, "epoch": 2.4, "percentage": 18.46, "elapsed_time": "0:04:04", "remaining_time": "0:18:00"}
+{"current_steps": 25, "total_steps": 130, "loss": 0.6411, "lr": 9.742682209735727e-06, "epoch": 2.5, "percentage": 19.23, "elapsed_time": "0:04:11", "remaining_time": "0:17:37"}
+{"current_steps": 26, "total_steps": 130, "loss": 0.6354, "lr": 9.698463103929542e-06, "epoch": 2.6, "percentage": 20.0, "elapsed_time": "0:04:22", "remaining_time": "0:17:30"}
+{"current_steps": 27, "total_steps": 130, "loss": 0.6336, "lr": 9.650856666246693e-06, "epoch": 2.7, "percentage": 20.77, "elapsed_time": "0:04:29", "remaining_time": "0:17:09"}
+{"current_steps": 28, "total_steps": 130, "loss": 0.5969, "lr": 9.599897218294122e-06, "epoch": 2.8, "percentage": 21.54, "elapsed_time": "0:04:37", "remaining_time": "0:16:49"}
+{"current_steps": 29, "total_steps": 130, "loss": 0.6215, "lr": 9.54562149901362e-06, "epoch": 2.9, "percentage": 22.31, "elapsed_time": "0:04:44", "remaining_time": "0:16:31"}
+{"current_steps": 30, "total_steps": 130, "loss": 0.5623, "lr": 9.488068638195072e-06, "epoch": 3.0, "percentage": 23.08, "elapsed_time": "0:04:49", "remaining_time": "0:16:03"}
+{"current_steps": 31, "total_steps": 130, "loss": 0.5195, "lr": 9.427280128266049e-06, "epoch": 3.1, "percentage": 23.85, "elapsed_time": "0:05:12", "remaining_time": "0:16:37"}
+{"current_steps": 32, "total_steps": 130, "loss": 0.4811, "lr": 9.363299794378072e-06, "epoch": 3.2, "percentage": 24.62, "elapsed_time": "0:05:21", "remaining_time": "0:16:23"}
+{"current_steps": 33, "total_steps": 130, "loss": 0.4356, "lr": 9.296173762811084e-06, "epoch": 3.3, "percentage": 25.38, "elapsed_time": "0:05:29", "remaining_time": "0:16:07"}
+{"current_steps": 34, "total_steps": 130, "loss": 0.4904, "lr": 9.225950427718974e-06, "epoch": 3.4, "percentage": 26.15, "elapsed_time": "0:05:39", "remaining_time": "0:15:57"}
+{"current_steps": 35, "total_steps": 130, "loss": 0.4892, "lr": 9.152680416240059e-06, "epoch": 3.5, "percentage": 26.92, "elapsed_time": "0:05:51", "remaining_time": "0:15:53"}
+{"current_steps": 36, "total_steps": 130, "loss": 0.4691, "lr": 9.076416551997721e-06, "epoch": 3.6, "percentage": 27.69, "elapsed_time": "0:05:58", "remaining_time": "0:15:35"}
+{"current_steps": 37, "total_steps": 130, "loss": 0.472, "lr": 8.997213817017508e-06, "epoch": 3.7, "percentage": 28.46, "elapsed_time": "0:06:04", "remaining_time": "0:15:16"}
+{"current_steps": 38, "total_steps": 130, "loss": 0.457, "lr": 8.915129312088112e-06, "epoch": 3.8, "percentage": 29.23, "elapsed_time": "0:06:11", "remaining_time": "0:14:59"}
+{"current_steps": 39, "total_steps": 130, "loss": 0.5034, "lr": 8.83022221559489e-06, "epoch": 3.9, "percentage": 30.0, "elapsed_time": "0:06:19", "remaining_time": "0:14:46"}
+{"current_steps": 40, "total_steps": 130, "loss": 0.4232, "lr": 8.742553740855507e-06, "epoch": 4.0, "percentage": 30.77, "elapsed_time": "0:06:26", "remaining_time": "0:14:30"}
+{"current_steps": 41, "total_steps": 130, "loss": 0.3753, "lr": 8.652187091988516e-06, "epoch": 4.1, "percentage": 31.54, "elapsed_time": "0:06:48", "remaining_time": "0:14:46"}
+{"current_steps": 42, "total_steps": 130, "loss": 0.3749, "lr": 8.559187418346703e-06, "epoch": 4.2, "percentage": 32.31, "elapsed_time": "0:06:58", "remaining_time": "0:14:37"}
+{"current_steps": 43, "total_steps": 130, "loss": 0.3262, "lr": 8.463621767547998e-06, "epoch": 4.3, "percentage": 33.08, "elapsed_time": "0:07:08", "remaining_time": "0:14:26"}
+{"current_steps": 44, "total_steps": 130, "loss": 0.3447, "lr": 8.36555903713785e-06, "epoch": 4.4, "percentage": 33.85, "elapsed_time": "0:07:19", "remaining_time": "0:14:19"}
+{"current_steps": 45, "total_steps": 130, "loss": 0.3676, "lr": 8.265069924917925e-06, "epoch": 4.5, "percentage": 34.62, "elapsed_time": "0:07:26", "remaining_time": "0:14:02"}
+{"current_steps": 46, "total_steps": 130, "loss": 0.3675, "lr": 8.162226877976886e-06, "epoch": 4.6, "percentage": 35.38, "elapsed_time": "0:07:35", "remaining_time": "0:13:51"}
+{"current_steps": 47, "total_steps": 130, "loss": 0.3422, "lr": 8.057104040460062e-06, "epoch": 4.7, "percentage": 36.15, "elapsed_time": "0:07:42", "remaining_time": "0:13:37"}
+{"current_steps": 48, "total_steps": 130, "loss": 0.3171, "lr": 7.949777200115617e-06, "epoch": 4.8, "percentage": 36.92, "elapsed_time": "0:07:49", "remaining_time": "0:13:22"}
+{"current_steps": 49, "total_steps": 130, "loss": 0.2866, "lr": 7.84032373365578e-06, "epoch": 4.9, "percentage": 37.69, "elapsed_time": "0:07:57", "remaining_time": "0:13:10"}
+{"current_steps": 50, "total_steps": 130, "loss": 0.2796, "lr": 7.728822550972523e-06, "epoch": 5.0, "percentage": 38.46, "elapsed_time": "0:08:04", "remaining_time": "0:12:54"}
+{"current_steps": 51, "total_steps": 130, "loss": 0.2412, "lr": 7.615354038247889e-06, "epoch": 5.1, "percentage": 39.23, "elapsed_time": "0:08:24", "remaining_time": "0:13:01"}
+{"current_steps": 52, "total_steps": 130, "loss": 0.2615, "lr": 7.500000000000001e-06, "epoch": 5.2, "percentage": 40.0, "elapsed_time": "0:08:34", "remaining_time": "0:12:51"}
+{"current_steps": 53, "total_steps": 130, "loss": 0.216, "lr": 7.382843600106539e-06, "epoch": 5.3, "percentage": 40.77, "elapsed_time": "0:08:43", "remaining_time": "0:12:40"}
+{"current_steps": 54, "total_steps": 130, "loss": 0.2468, "lr": 7.263969301848188e-06, "epoch": 5.4, "percentage": 41.54, "elapsed_time": "0:08:54", "remaining_time": "0:12:32"}
+{"current_steps": 55, "total_steps": 130, "loss": 0.2086, "lr": 7.143462807015271e-06, "epoch": 5.5, "percentage": 42.31, "elapsed_time": "0:09:00", "remaining_time": "0:12:16"}
+{"current_steps": 56, "total_steps": 130, "loss": 0.2268, "lr": 7.021410994121525e-06, "epoch": 5.6, "percentage": 43.08, "elapsed_time": "0:09:07", "remaining_time": "0:12:03"}
+{"current_steps": 57, "total_steps": 130, "loss": 0.2727, "lr": 6.897901855769483e-06, "epoch": 5.7, "percentage": 43.85, "elapsed_time": "0:09:16", "remaining_time": "0:11:53"}
+{"current_steps": 58, "total_steps": 130, "loss": 0.2113, "lr": 6.773024435212678e-06, "epoch": 5.8, "percentage": 44.62, "elapsed_time": "0:09:26", "remaining_time": "0:11:43"}
+{"current_steps": 59, "total_steps": 130, "loss": 0.1989, "lr": 6.646868762160399e-06, "epoch": 5.9, "percentage": 45.38, "elapsed_time": "0:09:33", "remaining_time": "0:11:30"}
+{"current_steps": 60, "total_steps": 130, "loss": 0.2347, "lr": 6.519525787871235e-06, "epoch": 6.0, "percentage": 46.15, "elapsed_time": "0:09:40", "remaining_time": "0:11:17"}
+{"current_steps": 61, "total_steps": 130, "loss": 0.1658, "lr": 6.391087319582264e-06, "epoch": 6.1, "percentage": 46.92, "elapsed_time": "0:10:01", "remaining_time": "0:11:20"}
+{"current_steps": 62, "total_steps": 130, "loss": 0.1645, "lr": 6.261645954321109e-06, "epoch": 6.2, "percentage": 47.69, "elapsed_time": "0:10:11", "remaining_time": "0:11:10"}
+{"current_steps": 63, "total_steps": 130, "loss": 0.1835, "lr": 6.131295012148613e-06, "epoch": 6.3, "percentage": 48.46, "elapsed_time": "0:10:21", "remaining_time": "0:11:00"}
+{"current_steps": 64, "total_steps": 130, "loss": 0.1632, "lr": 6.000128468880223e-06, "epoch": 6.4, "percentage": 49.23, "elapsed_time": "0:10:28", "remaining_time": "0:10:47"}
+{"current_steps": 65, "total_steps": 130, "loss": 0.1573, "lr": 5.8682408883346535e-06, "epoch": 6.5, "percentage": 50.0, "elapsed_time": "0:10:36", "remaining_time": "0:10:36"}
+{"current_steps": 66, "total_steps": 130, "loss": 0.152, "lr": 5.735727354158581e-06, "epoch": 6.6, "percentage": 50.77, "elapsed_time": "0:10:43", "remaining_time": "0:10:24"}
+{"current_steps": 67, "total_steps": 130, "loss": 0.1453, "lr": 5.6026834012766155e-06, "epoch": 6.7, "percentage": 51.54, "elapsed_time": "0:10:51", "remaining_time": "0:10:13"}
+{"current_steps": 68, "total_steps": 130, "loss": 0.1155, "lr": 5.469204947015897e-06, "epoch": 6.8, "percentage": 52.31, "elapsed_time": "0:10:58", "remaining_time": "0:10:00"}
+{"current_steps": 69, "total_steps": 130, "loss": 0.1644, "lr": 5.335388221955012e-06, "epoch": 6.9, "percentage": 53.08, "elapsed_time": "0:11:09", "remaining_time": "0:09:52"}
+{"current_steps": 70, "total_steps": 130, "loss": 0.1431, "lr": 5.201329700547077e-06, "epoch": 7.0, "percentage": 53.85, "elapsed_time": "0:11:16", "remaining_time": "0:09:40"}
+{"current_steps": 71, "total_steps": 130, "loss": 0.097, "lr": 5.067126031566988e-06, "epoch": 7.1, "percentage": 54.62, "elapsed_time": "0:11:40", "remaining_time": "0:09:41"}
+{"current_steps": 72, "total_steps": 130, "loss": 0.1277, "lr": 4.932873968433014e-06, "epoch": 7.2, "percentage": 55.38, "elapsed_time": "0:11:49", "remaining_time": "0:09:31"}
+{"current_steps": 73, "total_steps": 130, "loss": 0.1017, "lr": 4.798670299452926e-06, "epoch": 7.3, "percentage": 56.15, "elapsed_time": "0:12:01", "remaining_time": "0:09:23"}
+{"current_steps": 74, "total_steps": 130, "loss": 0.086, "lr": 4.664611778044988e-06, "epoch": 7.4, "percentage": 56.92, "elapsed_time": "0:12:08", "remaining_time": "0:09:11"}
+{"current_steps": 75, "total_steps": 130, "loss": 0.1084, "lr": 4.530795052984104e-06, "epoch": 7.5, "percentage": 57.69, "elapsed_time": "0:12:15", "remaining_time": "0:08:59"}
+{"current_steps": 76, "total_steps": 130, "loss": 0.0994, "lr": 4.397316598723385e-06, "epoch": 7.6, "percentage": 58.46, "elapsed_time": "0:12:24", "remaining_time": "0:08:49"}
+{"current_steps": 77, "total_steps": 130, "loss": 0.0925, "lr": 4.264272645841419e-06, "epoch": 7.7, "percentage": 59.23, "elapsed_time": "0:12:31", "remaining_time": "0:08:37"}
+{"current_steps": 78, "total_steps": 130, "loss": 0.0815, "lr": 4.131759111665349e-06, "epoch": 7.8, "percentage": 60.0, "elapsed_time": "0:12:38", "remaining_time": "0:08:25"}
+{"current_steps": 79, "total_steps": 130, "loss": 0.1225, "lr": 3.999871531119779e-06, "epoch": 7.9, "percentage": 60.77, "elapsed_time": "0:12:47", "remaining_time": "0:08:15"}
+{"current_steps": 80, "total_steps": 130, "loss": 0.1165, "lr": 3.86870498785139e-06, "epoch": 8.0, "percentage": 61.54, "elapsed_time": "0:12:55", "remaining_time": "0:08:04"}
+{"current_steps": 81, "total_steps": 130, "loss": 0.0704, "lr": 3.7383540456788915e-06, "epoch": 8.1, "percentage": 62.31, "elapsed_time": "0:13:19", "remaining_time": "0:08:03"}
+{"current_steps": 82, "total_steps": 130, "loss": 0.0769, "lr": 3.6089126804177373e-06, "epoch": 8.2, "percentage": 63.08, "elapsed_time": "0:13:26", "remaining_time": "0:07:51"}
+{"current_steps": 83, "total_steps": 130, "loss": 0.082, "lr": 3.480474212128766e-06, "epoch": 8.3, "percentage": 63.85, "elapsed_time": "0:13:35", "remaining_time": "0:07:41"}
+{"current_steps": 84, "total_steps": 130, "loss": 0.0914, "lr": 3.3531312378396026e-06, "epoch": 8.4, "percentage": 64.62, "elapsed_time": "0:13:47", "remaining_time": "0:07:32"}
+{"current_steps": 85, "total_steps": 130, "loss": 0.0755, "lr": 3.226975564787322e-06, "epoch": 8.5, "percentage": 65.38, "elapsed_time": "0:13:56", "remaining_time": "0:07:22"}
+{"current_steps": 86, "total_steps": 130, "loss": 0.0641, "lr": 3.1020981442305187e-06, "epoch": 8.6, "percentage": 66.15, "elapsed_time": "0:14:02", "remaining_time": "0:07:11"}
+{"current_steps": 87, "total_steps": 130, "loss": 0.0431, "lr": 2.978589005878476e-06, "epoch": 8.7, "percentage": 66.92, "elapsed_time": "0:14:08", "remaining_time": "0:06:59"}
+{"current_steps": 88, "total_steps": 130, "loss": 0.0836, "lr": 2.8565371929847286e-06, "epoch": 8.8, "percentage": 67.69, "elapsed_time": "0:14:16", "remaining_time": "0:06:48"}
+{"current_steps": 89, "total_steps": 130, "loss": 0.0608, "lr": 2.736030698151815e-06, "epoch": 8.9, "percentage": 68.46, "elapsed_time": "0:14:24", "remaining_time": "0:06:38"}
+{"current_steps": 90, "total_steps": 130, "loss": 0.0613, "lr": 2.6171563998934605e-06, "epoch": 9.0, "percentage": 69.23, "elapsed_time": "0:14:32", "remaining_time": "0:06:27"}
+{"current_steps": 91, "total_steps": 130, "loss": 0.0641, "lr": 2.5000000000000015e-06, "epoch": 9.1, "percentage": 70.0, "elapsed_time": "0:15:38", "remaining_time": "0:06:42"}
+{"current_steps": 92, "total_steps": 130, "loss": 0.0438, "lr": 2.384645961752113e-06, "epoch": 9.2, "percentage": 70.77, "elapsed_time": "0:15:47", "remaining_time": "0:06:31"}
+{"current_steps": 93, "total_steps": 130, "loss": 0.048, "lr": 2.2711774490274767e-06, "epoch": 9.3, "percentage": 71.54, "elapsed_time": "0:15:54", "remaining_time": "0:06:19"}
+{"current_steps": 94, "total_steps": 130, "loss": 0.0727, "lr": 2.159676266344222e-06, "epoch": 9.4, "percentage": 72.31, "elapsed_time": "0:16:04", "remaining_time": "0:06:09"}
+{"current_steps": 95, "total_steps": 130, "loss": 0.0562, "lr": 2.050222799884387e-06, "epoch": 9.5, "percentage": 73.08, "elapsed_time": "0:16:14", "remaining_time": "0:05:59"}
+{"current_steps": 96, "total_steps": 130, "loss": 0.0474, "lr": 1.942895959539939e-06, "epoch": 9.6, "percentage": 73.85, "elapsed_time": "0:16:21", "remaining_time": "0:05:47"}
+{"current_steps": 97, "total_steps": 130, "loss": 0.0452, "lr": 1.8377731220231144e-06, "epoch": 9.7, "percentage": 74.62, "elapsed_time": "0:16:28", "remaining_time": "0:05:36"}
+{"current_steps": 98, "total_steps": 130, "loss": 0.0464, "lr": 1.7349300750820758e-06, "epoch": 9.8, "percentage": 75.38, "elapsed_time": "0:16:37", "remaining_time": "0:05:25"}
+{"current_steps": 99, "total_steps": 130, "loss": 0.0474, "lr": 1.6344409628621482e-06, "epoch": 9.9, "percentage": 76.15, "elapsed_time": "0:16:44", "remaining_time": "0:05:14"}
+{"current_steps": 100, "total_steps": 130, "loss": 0.0228, "lr": 1.5363782324520033e-06, "epoch": 10.0, "percentage": 76.92, "elapsed_time": "0:16:53", "remaining_time": "0:05:04"}
+{"current_steps": 101, "total_steps": 130, "loss": 0.0433, "lr": 1.4408125816532981e-06, "epoch": 10.1, "percentage": 77.69, "elapsed_time": "0:17:34", "remaining_time": "0:05:02"}
+{"current_steps": 102, "total_steps": 130, "loss": 0.0322, "lr": 1.347812908011485e-06, "epoch": 10.2, "percentage": 78.46, "elapsed_time": "0:17:43", "remaining_time": "0:04:51"}
+{"current_steps": 103, "total_steps": 130, "loss": 0.0309, "lr": 1.257446259144494e-06, "epoch": 10.3, "percentage": 79.23, "elapsed_time": "0:17:48", "remaining_time": "0:04:40"}
+{"current_steps": 104, "total_steps": 130, "loss": 0.0476, "lr": 1.1697777844051105e-06, "epoch": 10.4, "percentage": 80.0, "elapsed_time": "0:17:57", "remaining_time": "0:04:29"}
+{"current_steps": 105, "total_steps": 130, "loss": 0.0312, "lr": 1.0848706879118893e-06, "epoch": 10.5, "percentage": 80.77, "elapsed_time": "0:18:05", "remaining_time": "0:04:18"}
+{"current_steps": 106, "total_steps": 130, "loss": 0.031, "lr": 1.0027861829824953e-06, "epoch": 10.6, "percentage": 81.54, "elapsed_time": "0:18:13", "remaining_time": "0:04:07"}
+{"current_steps": 107, "total_steps": 130, "loss": 0.0306, "lr": 9.235834480022788e-07, "epoch": 10.7, "percentage": 82.31, "elapsed_time": "0:18:20", "remaining_time": "0:03:56"}
+{"current_steps": 108, "total_steps": 130, "loss": 0.0385, "lr": 8.473195837599419e-07, "epoch": 10.8, "percentage": 83.08, "elapsed_time": "0:18:32", "remaining_time": "0:03:46"}
+{"current_steps": 109, "total_steps": 130, "loss": 0.0445, "lr": 7.740495722810271e-07, "epoch": 10.9, "percentage": 83.85, "elapsed_time": "0:18:41", "remaining_time": "0:03:36"}
+{"current_steps": 110, "total_steps": 130, "loss": 0.0395, "lr": 7.03826237188916e-07, "epoch": 11.0, "percentage": 84.62, "elapsed_time": "0:18:48", "remaining_time": "0:03:25"}
+{"current_steps": 111, "total_steps": 130, "loss": 0.0202, "lr": 6.367002056219285e-07, "epoch": 11.1, "percentage": 85.38, "elapsed_time": "0:19:26", "remaining_time": "0:03:19"}
+{"current_steps": 112, "total_steps": 130, "loss": 0.0421, "lr": 5.727198717339511e-07, "epoch": 11.2, "percentage": 86.15, "elapsed_time": "0:19:36", "remaining_time": "0:03:09"}
+{"current_steps": 113, "total_steps": 130, "loss": 0.0363, "lr": 5.119313618049309e-07, "epoch": 11.3, "percentage": 86.92, "elapsed_time": "0:19:42", "remaining_time": "0:02:57"}
+{"current_steps": 114, "total_steps": 130, "loss": 0.0348, "lr": 4.54378500986381e-07, "epoch": 11.4, "percentage": 87.69, "elapsed_time": "0:19:51", "remaining_time": "0:02:47"}
+{"current_steps": 115, "total_steps": 130, "loss": 0.0504, "lr": 4.001027817058789e-07, "epoch": 11.5, "percentage": 88.46, "elapsed_time": "0:20:02", "remaining_time": "0:02:36"}
+{"current_steps": 116, "total_steps": 130, "loss": 0.0195, "lr": 3.49143333753309e-07, "epoch": 11.6, "percentage": 89.23, "elapsed_time": "0:20:10", "remaining_time": "0:02:26"}
+{"current_steps": 117, "total_steps": 130, "loss": 0.0317, "lr": 3.015368960704584e-07, "epoch": 11.7, "percentage": 90.0, "elapsed_time": "0:20:17", "remaining_time": "0:02:15"}
+{"current_steps": 118, "total_steps": 130, "loss": 0.0279, "lr": 2.573177902642726e-07, "epoch": 11.8, "percentage": 90.77, "elapsed_time": "0:20:25", "remaining_time": "0:02:04"}
+{"current_steps": 119, "total_steps": 130, "loss": 0.0349, "lr": 2.1651789586287442e-07, "epoch": 11.9, "percentage": 91.54, "elapsed_time": "0:20:33", "remaining_time": "0:01:53"}
+{"current_steps": 120, "total_steps": 130, "loss": 0.0188, "lr": 1.7916662733218848e-07, "epoch": 12.0, "percentage": 92.31, "elapsed_time": "0:20:39", "remaining_time": "0:01:43"}
+{"current_steps": 121, "total_steps": 130, "loss": 0.0274, "lr": 1.4529091286973994e-07, "epoch": 12.1, "percentage": 93.08, "elapsed_time": "0:21:14", "remaining_time": "0:01:34"}
+{"current_steps": 122, "total_steps": 130, "loss": 0.0217, "lr": 1.1491517499091498e-07, "epoch": 12.2, "percentage": 93.85, "elapsed_time": "0:21:20", "remaining_time": "0:01:23"}
+{"current_steps": 123, "total_steps": 130, "loss": 0.0376, "lr": 8.80613129216762e-08, "epoch": 12.3, "percentage": 94.62, "elapsed_time": "0:21:29", "remaining_time": "0:01:13"}
+{"current_steps": 124, "total_steps": 130, "loss": 0.034, "lr": 6.474868681043578e-08, "epoch": 12.4, "percentage": 95.38, "elapsed_time": "0:21:36", "remaining_time": "0:01:02"}
+{"current_steps": 125, "total_steps": 130, "loss": 0.0173, "lr": 4.499410377045765e-08, "epoch": 12.5, "percentage": 96.15, "elapsed_time": "0:21:45", "remaining_time": "0:00:52"}
+{"current_steps": 126, "total_steps": 130, "loss": 0.0505, "lr": 2.8811805762860578e-08, "epoch": 12.6, "percentage": 96.92, "elapsed_time": "0:21:57", "remaining_time": "0:00:41"}
+{"current_steps": 127, "total_steps": 130, "loss": 0.0256, "lr": 1.6213459328950355e-08, "epoch": 12.7, "percentage": 97.69, "elapsed_time": "0:22:02", "remaining_time": "0:00:31"}
+{"current_steps": 128, "total_steps": 130, "loss": 0.0329, "lr": 7.2081471792911914e-09, "epoch": 12.8, "percentage": 98.46, "elapsed_time": "0:22:12", "remaining_time": "0:00:20"}
+{"current_steps": 129, "total_steps": 130, "loss": 0.0225, "lr": 1.8023616455731253e-09, "epoch": 12.9, "percentage": 99.23, "elapsed_time": "0:22:18", "remaining_time": "0:00:10"}
+{"current_steps": 130, "total_steps": 130, "loss": 0.0241, "lr": 0.0, "epoch": 13.0, "percentage": 100.0, "elapsed_time": "0:22:24", "remaining_time": "0:00:00"}
+{"current_steps": 130, "total_steps": 130, "epoch": 13.0, "percentage": 100.0, "elapsed_time": "0:23:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,952 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.628989065346123,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.0569,
+      "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.926975566935615,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 0.9812,
+      "step": 2
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.691019233564874,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.0801,
+      "step": 3
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.636774561564016,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.1116,
+      "step": 4
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.7550427950333605,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.8986,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.929584683404517,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.9908,
+      "step": 6
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.343895298913412,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.8701,
+      "step": 7
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.5534224567567425,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.9159,
+      "step": 8
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.127317665798452,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.0084,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.521696011848076,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.8668,
+      "step": 10
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.307370004120975,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.8952,
+      "step": 11
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.77465828274505,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.8292,
+      "step": 12
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 3.589393752579294,
+      "learning_rate": 1e-05,
+      "loss": 0.8146,
+      "step": 13
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.691240545262518,
+      "learning_rate": 9.998197638354428e-06,
+      "loss": 0.8015,
+      "step": 14
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.870208603579364,
+      "learning_rate": 9.992791852820709e-06,
+      "loss": 0.7967,
+      "step": 15
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.363425458772089,
+      "learning_rate": 9.983786540671052e-06,
+      "loss": 0.7552,
+      "step": 16
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 2.0964925440049673,
+      "learning_rate": 9.971188194237141e-06,
+      "loss": 0.7797,
+      "step": 17
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.307011826886325,
+      "learning_rate": 9.955005896229543e-06,
+      "loss": 0.7646,
+      "step": 18
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.03791893073859,
+      "learning_rate": 9.935251313189564e-06,
+      "loss": 0.6918,
+      "step": 19
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5843342708856971,
+      "learning_rate": 9.911938687078324e-06,
+      "loss": 0.7386,
+      "step": 20
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.3945841245924093,
+      "learning_rate": 9.885084825009085e-06,
+      "loss": 0.6268,
+      "step": 21
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.4591448541905794,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.6714,
+      "step": 22
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.081995803911005,
+      "learning_rate": 9.820833372667813e-06,
+      "loss": 0.6182,
+      "step": 23
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1572897175642276,
+      "learning_rate": 9.783482104137127e-06,
+      "loss": 0.6419,
+      "step": 24
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1203779417326247,
+      "learning_rate": 9.742682209735727e-06,
+      "loss": 0.6411,
+      "step": 25
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.4360115874347443,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.6354,
+      "step": 26
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.3740476572624811,
+      "learning_rate": 9.650856666246693e-06,
+      "loss": 0.6336,
+      "step": 27
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.0048907844479906,
+      "learning_rate": 9.599897218294122e-06,
+      "loss": 0.5969,
+      "step": 28
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.8969620941265196,
+      "learning_rate": 9.54562149901362e-06,
+      "loss": 0.6215,
+      "step": 29
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9729488544815679,
+      "learning_rate": 9.488068638195072e-06,
+      "loss": 0.5623,
+      "step": 30
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 1.0594076122500609,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.5195,
+      "step": 31
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.9226486282468062,
+      "learning_rate": 9.363299794378072e-06,
+      "loss": 0.4811,
+      "step": 32
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 1.2623355952454869,
+      "learning_rate": 9.296173762811084e-06,
+      "loss": 0.4356,
+      "step": 33
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.1558393380462555,
+      "learning_rate": 9.225950427718974e-06,
+      "loss": 0.4904,
+      "step": 34
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.9331075971913391,
+      "learning_rate": 9.152680416240059e-06,
+      "loss": 0.4892,
+      "step": 35
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.0230266275334514,
+      "learning_rate": 9.076416551997721e-06,
+      "loss": 0.4691,
+      "step": 36
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.8939167993966137,
+      "learning_rate": 8.997213817017508e-06,
+      "loss": 0.472,
+      "step": 37
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.9719563262774972,
+      "learning_rate": 8.915129312088112e-06,
+      "loss": 0.457,
+      "step": 38
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.9662361203933975,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.5034,
+      "step": 39
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9565291752492383,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.4232,
+      "step": 40
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 0.8690211252018278,
+      "learning_rate": 8.652187091988516e-06,
+      "loss": 0.3753,
+      "step": 41
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.9604557812067797,
+      "learning_rate": 8.559187418346703e-06,
+      "loss": 0.3749,
+      "step": 42
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.8332603853054323,
+      "learning_rate": 8.463621767547998e-06,
+      "loss": 0.3262,
+      "step": 43
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.3382023750702274,
+      "learning_rate": 8.36555903713785e-06,
+      "loss": 0.3447,
+      "step": 44
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.940906170956747,
+      "learning_rate": 8.265069924917925e-06,
+      "loss": 0.3676,
+      "step": 45
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 1.6455420279260802,
+      "learning_rate": 8.162226877976886e-06,
+      "loss": 0.3675,
+      "step": 46
+    },
+    {
+      "epoch": 4.7,
+      "grad_norm": 1.1167050305564408,
+      "learning_rate": 8.057104040460062e-06,
+      "loss": 0.3422,
+      "step": 47
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.9820335827175063,
+      "learning_rate": 7.949777200115617e-06,
+      "loss": 0.3171,
+      "step": 48
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.8261908790850763,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.2866,
+      "step": 49
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.909683189276732,
+      "learning_rate": 7.728822550972523e-06,
+      "loss": 0.2796,
+      "step": 50
+    },
+    {
+      "epoch": 5.1,
+      "grad_norm": 0.8721929726497659,
+      "learning_rate": 7.615354038247889e-06,
+      "loss": 0.2412,
+      "step": 51
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.872514752290956,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2615,
+      "step": 52
+    },
+    {
+      "epoch": 5.3,
+      "grad_norm": 0.9235622203656612,
+      "learning_rate": 7.382843600106539e-06,
+      "loss": 0.216,
+      "step": 53
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.8180110106258557,
+      "learning_rate": 7.263969301848188e-06,
+      "loss": 0.2468,
+      "step": 54
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.9561573162742637,
+      "learning_rate": 7.143462807015271e-06,
+      "loss": 0.2086,
+      "step": 55
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.8573973468377284,
+      "learning_rate": 7.021410994121525e-06,
+      "loss": 0.2268,
+      "step": 56
+    },
+    {
+      "epoch": 5.7,
+      "grad_norm": 0.777598662487049,
+      "learning_rate": 6.897901855769483e-06,
+      "loss": 0.2727,
+      "step": 57
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.8666751731245206,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.2113,
+      "step": 58
+    },
+    {
+      "epoch": 5.9,
+      "grad_norm": 0.7301692900669594,
+      "learning_rate": 6.646868762160399e-06,
+      "loss": 0.1989,
+      "step": 59
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8364720798616666,
+      "learning_rate": 6.519525787871235e-06,
+      "loss": 0.2347,
+      "step": 60
+    },
+    {
+      "epoch": 6.1,
+      "grad_norm": 0.7358648595390387,
+      "learning_rate": 6.391087319582264e-06,
+      "loss": 0.1658,
+      "step": 61
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 0.7355978125074483,
+      "learning_rate": 6.261645954321109e-06,
+      "loss": 0.1645,
+      "step": 62
+    },
+    {
+      "epoch": 6.3,
+      "grad_norm": 0.8091134720979932,
+      "learning_rate": 6.131295012148613e-06,
+      "loss": 0.1835,
+      "step": 63
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.9898312158359583,
+      "learning_rate": 6.000128468880223e-06,
+      "loss": 0.1632,
+      "step": 64
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.860630150742023,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.1573,
+      "step": 65
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.7527986825207875,
+      "learning_rate": 5.735727354158581e-06,
+      "loss": 0.152,
+      "step": 66
+    },
+    {
+      "epoch": 6.7,
+      "grad_norm": 0.7491269290521739,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.1453,
+      "step": 67
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.7295395652061829,
+      "learning_rate": 5.469204947015897e-06,
+      "loss": 0.1155,
+      "step": 68
+    },
+    {
+      "epoch": 6.9,
+      "grad_norm": 0.6582182702096219,
+      "learning_rate": 5.335388221955012e-06,
+      "loss": 0.1644,
+      "step": 69
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.9205094759858898,
+      "learning_rate": 5.201329700547077e-06,
+      "loss": 0.1431,
+      "step": 70
+    },
+    {
+      "epoch": 7.1,
+      "grad_norm": 0.6838678681097919,
+      "learning_rate": 5.067126031566988e-06,
+      "loss": 0.097,
+      "step": 71
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 0.6817143894179786,
+      "learning_rate": 4.932873968433014e-06,
+      "loss": 0.1277,
+      "step": 72
+    },
+    {
+      "epoch": 7.3,
+      "grad_norm": 0.721750115517162,
+      "learning_rate": 4.798670299452926e-06,
+      "loss": 0.1017,
+      "step": 73
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 0.8058306633452632,
+      "learning_rate": 4.664611778044988e-06,
+      "loss": 0.086,
+      "step": 74
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.8022486671577423,
+      "learning_rate": 4.530795052984104e-06,
+      "loss": 0.1084,
+      "step": 75
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 0.686602277840311,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.0994,
+      "step": 76
+    },
+    {
+      "epoch": 7.7,
+      "grad_norm": 0.7113968395778815,
+      "learning_rate": 4.264272645841419e-06,
+      "loss": 0.0925,
+      "step": 77
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.7528301549481683,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.0815,
+      "step": 78
+    },
+    {
+      "epoch": 7.9,
+      "grad_norm": 0.6950568948318089,
+      "learning_rate": 3.999871531119779e-06,
+      "loss": 0.1225,
+      "step": 79
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.7112041161955799,
+      "learning_rate": 3.86870498785139e-06,
+      "loss": 0.1165,
+      "step": 80
+    },
+    {
+      "epoch": 8.1,
+      "grad_norm": 0.5899298132574069,
+      "learning_rate": 3.7383540456788915e-06,
+      "loss": 0.0704,
+      "step": 81
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 0.6301596474133376,
+      "learning_rate": 3.6089126804177373e-06,
+      "loss": 0.0769,
+      "step": 82
+    },
+    {
+      "epoch": 8.3,
+      "grad_norm": 0.5874783368561711,
+      "learning_rate": 3.480474212128766e-06,
+      "loss": 0.082,
+      "step": 83
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 0.6695522296834057,
+      "learning_rate": 3.3531312378396026e-06,
+      "loss": 0.0914,
+      "step": 84
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.7424036348029371,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.0755,
+      "step": 85
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 0.6508006194863323,
+      "learning_rate": 3.1020981442305187e-06,
+      "loss": 0.0641,
+      "step": 86
+    },
+    {
+      "epoch": 8.7,
+      "grad_norm": 0.5398233088546475,
+      "learning_rate": 2.978589005878476e-06,
+      "loss": 0.0431,
+      "step": 87
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.6817404890284527,
+      "learning_rate": 2.8565371929847286e-06,
+      "loss": 0.0836,
+      "step": 88
+    },
+    {
+      "epoch": 8.9,
+      "grad_norm": 0.5802674587793962,
+      "learning_rate": 2.736030698151815e-06,
+      "loss": 0.0608,
+      "step": 89
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6211206768118709,
+      "learning_rate": 2.6171563998934605e-06,
+      "loss": 0.0613,
+      "step": 90
+    },
+    {
+      "epoch": 9.1,
+      "grad_norm": 0.6927166993298396,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.0641,
+      "step": 91
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 0.53045753075823,
+      "learning_rate": 2.384645961752113e-06,
+      "loss": 0.0438,
+      "step": 92
+    },
+    {
+      "epoch": 9.3,
+      "grad_norm": 0.4597224018791461,
+      "learning_rate": 2.2711774490274767e-06,
+      "loss": 0.048,
+      "step": 93
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 0.6199107036518361,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.0727,
+      "step": 94
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.5172798247899627,
+      "learning_rate": 2.050222799884387e-06,
+      "loss": 0.0562,
+      "step": 95
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.45099440837381305,
+      "learning_rate": 1.942895959539939e-06,
+      "loss": 0.0474,
+      "step": 96
+    },
+    {
+      "epoch": 9.7,
+      "grad_norm": 0.5536218098190584,
+      "learning_rate": 1.8377731220231144e-06,
+      "loss": 0.0452,
+      "step": 97
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.5500691213721192,
+      "learning_rate": 1.7349300750820758e-06,
+      "loss": 0.0464,
+      "step": 98
+    },
+    {
+      "epoch": 9.9,
+      "grad_norm": 0.5546941275309164,
+      "learning_rate": 1.6344409628621482e-06,
+      "loss": 0.0474,
+      "step": 99
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5142874798048365,
+      "learning_rate": 1.5363782324520033e-06,
+      "loss": 0.0228,
+      "step": 100
+    },
+    {
+      "epoch": 10.1,
+      "grad_norm": 0.4282072968999265,
+      "learning_rate": 1.4408125816532981e-06,
+      "loss": 0.0433,
+      "step": 101
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 0.3610194560408463,
+      "learning_rate": 1.347812908011485e-06,
+      "loss": 0.0322,
+      "step": 102
+    },
+    {
+      "epoch": 10.3,
+      "grad_norm": 0.3459418349785742,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 0.0309,
+      "step": 103
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 0.38795481698215206,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.0476,
+      "step": 104
+    },
+    {
+      "epoch": 10.5,
+      "grad_norm": 0.3369857181089263,
+      "learning_rate": 1.0848706879118893e-06,
+      "loss": 0.0312,
+      "step": 105
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 0.35594832280975763,
+      "learning_rate": 1.0027861829824953e-06,
+      "loss": 0.031,
+      "step": 106
+    },
+    {
+      "epoch": 10.7,
+      "grad_norm": 0.3051465658343893,
+      "learning_rate": 9.235834480022788e-07,
+      "loss": 0.0306,
+      "step": 107
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.35418615617535526,
+      "learning_rate": 8.473195837599419e-07,
+      "loss": 0.0385,
+      "step": 108
+    },
+    {
+      "epoch": 10.9,
+      "grad_norm": 0.41487442710050876,
+      "learning_rate": 7.740495722810271e-07,
+      "loss": 0.0445,
+      "step": 109
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.3506535489263331,
+      "learning_rate": 7.03826237188916e-07,
+      "loss": 0.0395,
+      "step": 110
+    },
+    {
+      "epoch": 11.1,
+      "grad_norm": 0.25076848290318704,
+      "learning_rate": 6.367002056219285e-07,
+      "loss": 0.0202,
+      "step": 111
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.3445085142207932,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.0421,
+      "step": 112
+    },
+    {
+      "epoch": 11.3,
+      "grad_norm": 0.36519397695444744,
+      "learning_rate": 5.119313618049309e-07,
+      "loss": 0.0363,
+      "step": 113
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.2823084921040321,
+      "learning_rate": 4.54378500986381e-07,
+      "loss": 0.0348,
+      "step": 114
+    },
+    {
+      "epoch": 11.5,
+      "grad_norm": 0.35747979473533786,
+      "learning_rate": 4.001027817058789e-07,
+      "loss": 0.0504,
+      "step": 115
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.26656720599553213,
+      "learning_rate": 3.49143333753309e-07,
+      "loss": 0.0195,
+      "step": 116
+    },
+    {
+      "epoch": 11.7,
+      "grad_norm": 0.29835434328944005,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.0317,
+      "step": 117
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 0.26146046985752625,
+      "learning_rate": 2.573177902642726e-07,
+      "loss": 0.0279,
+      "step": 118
+    },
+    {
+      "epoch": 11.9,
+      "grad_norm": 0.30541939639610116,
+      "learning_rate": 2.1651789586287442e-07,
+      "loss": 0.0349,
+      "step": 119
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.2513413241256307,
+      "learning_rate": 1.7916662733218848e-07,
+      "loss": 0.0188,
+      "step": 120
+    },
+    {
+      "epoch": 12.1,
+      "grad_norm": 0.25866926729566964,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 0.0274,
+      "step": 121
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 0.25317653730579137,
+      "learning_rate": 1.1491517499091498e-07,
+      "loss": 0.0217,
+      "step": 122
+    },
+    {
+      "epoch": 12.3,
+      "grad_norm": 0.2920338488261998,
+      "learning_rate": 8.80613129216762e-08,
+      "loss": 0.0376,
+      "step": 123
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 0.27066598782774043,
+      "learning_rate": 6.474868681043578e-08,
+      "loss": 0.034,
+      "step": 124
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.2353324707949608,
+      "learning_rate": 4.499410377045765e-08,
+      "loss": 0.0173,
+      "step": 125
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 0.31590761075770163,
+      "learning_rate": 2.8811805762860578e-08,
+      "loss": 0.0505,
+      "step": 126
+    },
+    {
+      "epoch": 12.7,
+      "grad_norm": 0.27589308952135705,
+      "learning_rate": 1.6213459328950355e-08,
+      "loss": 0.0256,
+      "step": 127
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.2932967578154668,
+      "learning_rate": 7.2081471792911914e-09,
+      "loss": 0.0329,
+      "step": 128
+    },
+    {
+      "epoch": 12.9,
+      "grad_norm": 0.24279834163633543,
+      "learning_rate": 1.8023616455731253e-09,
+      "loss": 0.0225,
+      "step": 129
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.23021426719861385,
+      "learning_rate": 0.0,
+      "loss": 0.0241,
+      "step": 130
+    },
+    {
+      "epoch": 13.0,
+      "step": 130,
+      "total_flos": 3.637752234193715e+16,
+      "train_loss": 0.3008259800907511,
+      "train_runtime": 1399.9113,
+      "train_samples_per_second": 2.934,
+      "train_steps_per_second": 0.093
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 130,
+  "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": 3.637752234193715e+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:f683265f60f321a1dee49d7fb455f8152ced327d0a4fc1195ca5f546e5bf032a
+size 7352