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: c1_math_nod_1s_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. -->
+
+# c1_math_nod_1s_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/c1_math_nod_1s_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": 1.3891141298133402e+17,
+    "train_loss": 0.36694383532063574,
+    "train_runtime": 4769.333,
+    "train_samples_per_second": 0.861,
+    "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 sha256:6b554776d33932e308bd64b699c96b1a0450cceb2626eda79fd3c334dbbd475e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33763192439bbd7f3f88c893e8fb8625a074820a2e411900dd6cbfc78efbc22f
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91e82e66f5cc03c21eb9411fe975372e5e100a4ada3ff7a3f8fd21f7fda2cc9
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc0a3bebb06ac622c3bc825af5cd65506a50c6031405bcc62ca42d23cd3a580
+size 1089994880

model.safetensors.index.json

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

runs/Apr26_21-57-36_jrc0921/events.out.tfevents.1745697492.jrc0921.4044461.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d91a6f689fba1d67153bf2af2b5fbd308db48b22cf322519039b69ce05b2be3
+size 30072

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-26 21:57:36", "end_time": "2025-04-26 23:17:52"}

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": 1.3891141298133402e+17,
+    "train_loss": 0.36694383532063574,
+    "train_runtime": 4769.333,
+    "train_samples_per_second": 0.861,
+    "train_steps_per_second": 0.025
+}

trainer_log.jsonl

@@ -0,0 +1,118 @@
+{"current_steps": 1, "total_steps": 117, "loss": 0.8244, "lr": 8.333333333333333e-07, "epoch": 0.10126582278481013, "percentage": 0.85, "elapsed_time": "0:00:50", "remaining_time": "1:37:02"}
+{"current_steps": 2, "total_steps": 117, "loss": 0.8005, "lr": 1.6666666666666667e-06, "epoch": 0.20253164556962025, "percentage": 1.71, "elapsed_time": "0:01:30", "remaining_time": "1:26:37"}
+{"current_steps": 3, "total_steps": 117, "loss": 0.795, "lr": 2.5e-06, "epoch": 0.3037974683544304, "percentage": 2.56, "elapsed_time": "0:02:06", "remaining_time": "1:19:52"}
+{"current_steps": 4, "total_steps": 117, "loss": 0.7591, "lr": 3.3333333333333333e-06, "epoch": 0.4050632911392405, "percentage": 3.42, "elapsed_time": "0:02:44", "remaining_time": "1:17:22"}
+{"current_steps": 5, "total_steps": 117, "loss": 0.757, "lr": 4.166666666666667e-06, "epoch": 0.5063291139240507, "percentage": 4.27, "elapsed_time": "0:03:26", "remaining_time": "1:17:08"}
+{"current_steps": 6, "total_steps": 117, "loss": 0.7443, "lr": 5e-06, "epoch": 0.6075949367088608, "percentage": 5.13, "elapsed_time": "0:04:07", "remaining_time": "1:16:13"}
+{"current_steps": 7, "total_steps": 117, "loss": 0.7004, "lr": 5.833333333333334e-06, "epoch": 0.7088607594936709, "percentage": 5.98, "elapsed_time": "0:04:46", "remaining_time": "1:14:58"}
+{"current_steps": 8, "total_steps": 117, "loss": 0.7013, "lr": 6.666666666666667e-06, "epoch": 0.810126582278481, "percentage": 6.84, "elapsed_time": "0:05:24", "remaining_time": "1:13:37"}
+{"current_steps": 9, "total_steps": 117, "loss": 0.7496, "lr": 7.500000000000001e-06, "epoch": 0.9113924050632911, "percentage": 7.69, "elapsed_time": "0:06:04", "remaining_time": "1:12:57"}
+{"current_steps": 10, "total_steps": 117, "loss": 1.0467, "lr": 8.333333333333334e-06, "epoch": 1.0506329113924051, "percentage": 8.55, "elapsed_time": "0:07:03", "remaining_time": "1:15:32"}
+{"current_steps": 11, "total_steps": 117, "loss": 0.7055, "lr": 9.166666666666666e-06, "epoch": 1.1518987341772151, "percentage": 9.4, "elapsed_time": "0:07:46", "remaining_time": "1:14:56"}
+{"current_steps": 12, "total_steps": 117, "loss": 0.6902, "lr": 1e-05, "epoch": 1.2531645569620253, "percentage": 10.26, "elapsed_time": "0:08:23", "remaining_time": "1:13:22"}
+{"current_steps": 13, "total_steps": 117, "loss": 0.6389, "lr": 9.997762161417517e-06, "epoch": 1.3544303797468356, "percentage": 11.11, "elapsed_time": "0:09:01", "remaining_time": "1:12:13"}
+{"current_steps": 14, "total_steps": 117, "loss": 0.6053, "lr": 9.991050648838676e-06, "epoch": 1.4556962025316456, "percentage": 11.97, "elapsed_time": "0:09:44", "remaining_time": "1:11:37"}
+{"current_steps": 15, "total_steps": 117, "loss": 0.6248, "lr": 9.979871469976197e-06, "epoch": 1.5569620253164556, "percentage": 12.82, "elapsed_time": "0:10:21", "remaining_time": "1:10:23"}
+{"current_steps": 16, "total_steps": 117, "loss": 0.5832, "lr": 9.964234631709188e-06, "epoch": 1.6582278481012658, "percentage": 13.68, "elapsed_time": "0:10:58", "remaining_time": "1:09:15"}
+{"current_steps": 17, "total_steps": 117, "loss": 0.6072, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:11:34", "remaining_time": "1:08:05"}
+{"current_steps": 18, "total_steps": 117, "loss": 0.5818, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:12:07", "remaining_time": "1:06:43"}
+{"current_steps": 19, "total_steps": 117, "loss": 0.8314, "lr": 9.890738003669029e-06, "epoch": 1.9620253164556962, "percentage": 16.24, "elapsed_time": "0:12:47", "remaining_time": "1:05:58"}
+{"current_steps": 20, "total_steps": 117, "loss": 0.5352, "lr": 9.857450191464337e-06, "epoch": 2.1012658227848102, "percentage": 17.09, "elapsed_time": "0:13:50", "remaining_time": "1:07:06"}
+{"current_steps": 21, "total_steps": 117, "loss": 0.5103, "lr": 9.819814303479268e-06, "epoch": 2.2025316455696204, "percentage": 17.95, "elapsed_time": "0:14:28", "remaining_time": "1:06:09"}
+{"current_steps": 22, "total_steps": 117, "loss": 0.5434, "lr": 9.777864028930705e-06, "epoch": 2.3037974683544302, "percentage": 18.8, "elapsed_time": "0:15:09", "remaining_time": "1:05:26"}
+{"current_steps": 23, "total_steps": 117, "loss": 0.5204, "lr": 9.731636918995821e-06, "epoch": 2.4050632911392404, "percentage": 19.66, "elapsed_time": "0:15:44", "remaining_time": "1:04:19"}
+{"current_steps": 24, "total_steps": 117, "loss": 0.5108, "lr": 9.681174353198687e-06, "epoch": 2.5063291139240507, "percentage": 20.51, "elapsed_time": "0:16:17", "remaining_time": "1:03:07"}
+{"current_steps": 25, "total_steps": 117, "loss": 0.5301, "lr": 9.626521502369984e-06, "epoch": 2.607594936708861, "percentage": 21.37, "elapsed_time": "0:16:55", "remaining_time": "1:02:17"}
+{"current_steps": 26, "total_steps": 117, "loss": 0.5237, "lr": 9.567727288213005e-06, "epoch": 2.708860759493671, "percentage": 22.22, "elapsed_time": "0:17:35", "remaining_time": "1:01:33"}
+{"current_steps": 27, "total_steps": 117, "loss": 0.5347, "lr": 9.504844339512096e-06, "epoch": 2.810126582278481, "percentage": 23.08, "elapsed_time": "0:18:20", "remaining_time": "1:01:07"}
+{"current_steps": 28, "total_steps": 117, "loss": 0.4941, "lr": 9.437928945022772e-06, "epoch": 2.911392405063291, "percentage": 23.93, "elapsed_time": "0:18:56", "remaining_time": "1:00:10"}
+{"current_steps": 29, "total_steps": 117, "loss": 0.7523, "lr": 9.36704100308565e-06, "epoch": 3.050632911392405, "percentage": 24.79, "elapsed_time": "0:20:02", "remaining_time": "1:00:47"}
+{"current_steps": 30, "total_steps": 117, "loss": 0.4766, "lr": 9.292243968009332e-06, "epoch": 3.151898734177215, "percentage": 25.64, "elapsed_time": "0:20:35", "remaining_time": "0:59:41"}
+{"current_steps": 31, "total_steps": 117, "loss": 0.4715, "lr": 9.213604793270196e-06, "epoch": 3.2531645569620253, "percentage": 26.5, "elapsed_time": "0:21:11", "remaining_time": "0:58:48"}
+{"current_steps": 32, "total_steps": 117, "loss": 0.4053, "lr": 9.131193871579975e-06, "epoch": 3.3544303797468356, "percentage": 27.35, "elapsed_time": "0:21:47", "remaining_time": "0:57:53"}
+{"current_steps": 33, "total_steps": 117, "loss": 0.4867, "lr": 9.045084971874738e-06, "epoch": 3.4556962025316453, "percentage": 28.21, "elapsed_time": "0:22:28", "remaining_time": "0:57:12"}
+{"current_steps": 34, "total_steps": 117, "loss": 0.4526, "lr": 8.955355173281709e-06, "epoch": 3.5569620253164556, "percentage": 29.06, "elapsed_time": "0:23:11", "remaining_time": "0:56:37"}
+{"current_steps": 35, "total_steps": 117, "loss": 0.455, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:23:53", "remaining_time": "0:55:57"}
+{"current_steps": 36, "total_steps": 117, "loss": 0.4267, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:24:25", "remaining_time": "0:54:58"}
+{"current_steps": 37, "total_steps": 117, "loss": 0.4134, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:25:00", "remaining_time": "0:54:03"}
+{"current_steps": 38, "total_steps": 117, "loss": 0.6812, "lr": 8.561880484756726e-06, "epoch": 3.962025316455696, "percentage": 32.48, "elapsed_time": "0:25:37", "remaining_time": "0:53:16"}
+{"current_steps": 39, "total_steps": 117, "loss": 0.3917, "lr": 8.455313244934324e-06, "epoch": 4.10126582278481, "percentage": 33.33, "elapsed_time": "0:26:37", "remaining_time": "0:53:14"}
+{"current_steps": 40, "total_steps": 117, "loss": 0.4073, "lr": 8.345653031794292e-06, "epoch": 4.2025316455696204, "percentage": 34.19, "elapsed_time": "0:27:12", "remaining_time": "0:52:23"}
+{"current_steps": 41, "total_steps": 117, "loss": 0.3952, "lr": 8.232998006078998e-06, "epoch": 4.30379746835443, "percentage": 35.04, "elapsed_time": "0:27:56", "remaining_time": "0:51:47"}
+{"current_steps": 42, "total_steps": 117, "loss": 0.39, "lr": 8.117449009293668e-06, "epoch": 4.405063291139241, "percentage": 35.9, "elapsed_time": "0:28:31", "remaining_time": "0:50:56"}
+{"current_steps": 43, "total_steps": 117, "loss": 0.4016, "lr": 7.99910947343957e-06, "epoch": 4.506329113924051, "percentage": 36.75, "elapsed_time": "0:29:16", "remaining_time": "0:50:22"}
+{"current_steps": 44, "total_steps": 117, "loss": 0.3841, "lr": 7.87808532842837e-06, "epoch": 4.6075949367088604, "percentage": 37.61, "elapsed_time": "0:29:53", "remaining_time": "0:49:35"}
+{"current_steps": 45, "total_steps": 117, "loss": 0.3739, "lr": 7.754484907260513e-06, "epoch": 4.708860759493671, "percentage": 38.46, "elapsed_time": "0:30:36", "remaining_time": "0:48:58"}
+{"current_steps": 46, "total_steps": 117, "loss": 0.3855, "lr": 7.628418849052523e-06, "epoch": 4.810126582278481, "percentage": 39.32, "elapsed_time": "0:31:11", "remaining_time": "0:48:08"}
+{"current_steps": 47, "total_steps": 117, "loss": 0.3636, "lr": 7.500000000000001e-06, "epoch": 4.911392405063291, "percentage": 40.17, "elapsed_time": "0:31:47", "remaining_time": "0:47:20"}
+{"current_steps": 48, "total_steps": 117, "loss": 0.561, "lr": 7.369343312364994e-06, "epoch": 5.050632911392405, "percentage": 41.03, "elapsed_time": "0:32:51", "remaining_time": "0:47:14"}
+{"current_steps": 49, "total_steps": 117, "loss": 0.3512, "lr": 7.236565741578163e-06, "epoch": 5.151898734177215, "percentage": 41.88, "elapsed_time": "0:33:31", "remaining_time": "0:46:31"}
+{"current_steps": 50, "total_steps": 117, "loss": 0.3451, "lr": 7.101786141547829e-06, "epoch": 5.253164556962025, "percentage": 42.74, "elapsed_time": "0:34:08", "remaining_time": "0:45:44"}
+{"current_steps": 51, "total_steps": 117, "loss": 0.3095, "lr": 6.965125158269619e-06, "epoch": 5.3544303797468356, "percentage": 43.59, "elapsed_time": "0:34:50", "remaining_time": "0:45:04"}
+{"current_steps": 52, "total_steps": 117, "loss": 0.3322, "lr": 6.8267051218319766e-06, "epoch": 5.455696202531645, "percentage": 44.44, "elapsed_time": "0:35:25", "remaining_time": "0:44:16"}
+{"current_steps": 53, "total_steps": 117, "loss": 0.3158, "lr": 6.686649936914151e-06, "epoch": 5.556962025316456, "percentage": 45.3, "elapsed_time": "0:36:00", "remaining_time": "0:43:29"}
+{"current_steps": 54, "total_steps": 117, "loss": 0.3381, "lr": 6.545084971874738e-06, "epoch": 5.658227848101266, "percentage": 46.15, "elapsed_time": "0:36:34", "remaining_time": "0:42:40"}
+{"current_steps": 55, "total_steps": 117, "loss": 0.2936, "lr": 6.402136946530014e-06, "epoch": 5.759493670886076, "percentage": 47.01, "elapsed_time": "0:37:10", "remaining_time": "0:41:54"}
+{"current_steps": 56, "total_steps": 117, "loss": 0.3255, "lr": 6.257933818722544e-06, "epoch": 5.860759493670886, "percentage": 47.86, "elapsed_time": "0:37:51", "remaining_time": "0:41:14"}
+{"current_steps": 57, "total_steps": 117, "loss": 0.5212, "lr": 6.112604669781572e-06, "epoch": 5.962025316455696, "percentage": 48.72, "elapsed_time": "0:38:25", "remaining_time": "0:40:27"}
+{"current_steps": 58, "total_steps": 117, "loss": 0.2912, "lr": 5.9662795889777666e-06, "epoch": 6.10126582278481, "percentage": 49.57, "elapsed_time": "0:39:30", "remaining_time": "0:40:11"}
+{"current_steps": 59, "total_steps": 117, "loss": 0.2875, "lr": 5.819089557075689e-06, "epoch": 6.2025316455696204, "percentage": 50.43, "elapsed_time": "0:40:06", "remaining_time": "0:39:25"}
+{"current_steps": 60, "total_steps": 117, "loss": 0.2851, "lr": 5.671166329088278e-06, "epoch": 6.30379746835443, "percentage": 51.28, "elapsed_time": "0:40:36", "remaining_time": "0:38:34"}
+{"current_steps": 61, "total_steps": 117, "loss": 0.2838, "lr": 5.522642316338268e-06, "epoch": 6.405063291139241, "percentage": 52.14, "elapsed_time": "0:41:15", "remaining_time": "0:37:52"}
+{"current_steps": 62, "total_steps": 117, "loss": 0.2862, "lr": 5.373650467932122e-06, "epoch": 6.506329113924051, "percentage": 52.99, "elapsed_time": "0:41:54", "remaining_time": "0:37:11"}
+{"current_steps": 63, "total_steps": 117, "loss": 0.2762, "lr": 5.224324151752575e-06, "epoch": 6.6075949367088604, "percentage": 53.85, "elapsed_time": "0:42:24", "remaining_time": "0:36:20"}
+{"current_steps": 64, "total_steps": 117, "loss": 0.2708, "lr": 5.074797035076319e-06, "epoch": 6.708860759493671, "percentage": 54.7, "elapsed_time": "0:43:02", "remaining_time": "0:35:38"}
+{"current_steps": 65, "total_steps": 117, "loss": 0.2538, "lr": 4.9252029649236835e-06, "epoch": 6.810126582278481, "percentage": 55.56, "elapsed_time": "0:43:42", "remaining_time": "0:34:57"}
+{"current_steps": 66, "total_steps": 117, "loss": 0.2762, "lr": 4.775675848247427e-06, "epoch": 6.911392405063291, "percentage": 56.41, "elapsed_time": "0:44:19", "remaining_time": "0:34:15"}
+{"current_steps": 67, "total_steps": 117, "loss": 0.3676, "lr": 4.626349532067879e-06, "epoch": 7.050632911392405, "percentage": 57.26, "elapsed_time": "0:45:19", "remaining_time": "0:33:49"}
+{"current_steps": 68, "total_steps": 117, "loss": 0.2414, "lr": 4.477357683661734e-06, "epoch": 7.151898734177215, "percentage": 58.12, "elapsed_time": "0:45:55", "remaining_time": "0:33:05"}
+{"current_steps": 69, "total_steps": 117, "loss": 0.2369, "lr": 4.3288336709117246e-06, "epoch": 7.253164556962025, "percentage": 58.97, "elapsed_time": "0:46:30", "remaining_time": "0:32:20"}
+{"current_steps": 70, "total_steps": 117, "loss": 0.2503, "lr": 4.180910442924312e-06, "epoch": 7.3544303797468356, "percentage": 59.83, "elapsed_time": "0:47:08", "remaining_time": "0:31:39"}
+{"current_steps": 71, "total_steps": 117, "loss": 0.2436, "lr": 4.033720411022235e-06, "epoch": 7.455696202531645, "percentage": 60.68, "elapsed_time": "0:47:54", "remaining_time": "0:31:02"}
+{"current_steps": 72, "total_steps": 117, "loss": 0.2147, "lr": 3.887395330218429e-06, "epoch": 7.556962025316456, "percentage": 61.54, "elapsed_time": "0:48:29", "remaining_time": "0:30:18"}
+{"current_steps": 73, "total_steps": 117, "loss": 0.2216, "lr": 3.7420661812774577e-06, "epoch": 7.658227848101266, "percentage": 62.39, "elapsed_time": "0:49:04", "remaining_time": "0:29:34"}
+{"current_steps": 74, "total_steps": 117, "loss": 0.2408, "lr": 3.5978630534699873e-06, "epoch": 7.759493670886076, "percentage": 63.25, "elapsed_time": "0:49:41", "remaining_time": "0:28:52"}
+{"current_steps": 75, "total_steps": 117, "loss": 0.2163, "lr": 3.4549150281252635e-06, "epoch": 7.860759493670886, "percentage": 64.1, "elapsed_time": "0:50:15", "remaining_time": "0:28:08"}
+{"current_steps": 76, "total_steps": 117, "loss": 0.3386, "lr": 3.3133500630858507e-06, "epoch": 7.962025316455696, "percentage": 64.96, "elapsed_time": "0:51:01", "remaining_time": "0:27:31"}
+{"current_steps": 77, "total_steps": 117, "loss": 0.1991, "lr": 3.173294878168025e-06, "epoch": 8.10126582278481, "percentage": 65.81, "elapsed_time": "0:52:08", "remaining_time": "0:27:05"}
+{"current_steps": 78, "total_steps": 117, "loss": 0.1907, "lr": 3.0348748417303826e-06, "epoch": 8.20253164556962, "percentage": 66.67, "elapsed_time": "0:52:48", "remaining_time": "0:26:24"}
+{"current_steps": 79, "total_steps": 117, "loss": 0.1961, "lr": 2.8982138584521734e-06, "epoch": 8.30379746835443, "percentage": 67.52, "elapsed_time": "0:53:22", "remaining_time": "0:25:40"}
+{"current_steps": 80, "total_steps": 117, "loss": 0.2018, "lr": 2.7634342584218364e-06, "epoch": 8.405063291139241, "percentage": 68.38, "elapsed_time": "0:54:05", "remaining_time": "0:25:00"}
+{"current_steps": 81, "total_steps": 117, "loss": 0.1869, "lr": 2.6306566876350072e-06, "epoch": 8.50632911392405, "percentage": 69.23, "elapsed_time": "0:54:39", "remaining_time": "0:24:17"}
+{"current_steps": 82, "total_steps": 117, "loss": 0.1977, "lr": 2.5000000000000015e-06, "epoch": 8.60759493670886, "percentage": 70.09, "elapsed_time": "0:55:15", "remaining_time": "0:23:35"}
+{"current_steps": 83, "total_steps": 117, "loss": 0.198, "lr": 2.371581150947476e-06, "epoch": 8.708860759493671, "percentage": 70.94, "elapsed_time": "0:55:55", "remaining_time": "0:22:54"}
+{"current_steps": 84, "total_steps": 117, "loss": 0.1953, "lr": 2.245515092739488e-06, "epoch": 8.810126582278482, "percentage": 71.79, "elapsed_time": "0:56:32", "remaining_time": "0:22:12"}
+{"current_steps": 85, "total_steps": 117, "loss": 0.1913, "lr": 2.1219146715716332e-06, "epoch": 8.91139240506329, "percentage": 72.65, "elapsed_time": "0:57:02", "remaining_time": "0:21:28"}
+{"current_steps": 86, "total_steps": 117, "loss": 0.2902, "lr": 2.0008905265604316e-06, "epoch": 9.050632911392405, "percentage": 73.5, "elapsed_time": "0:58:06", "remaining_time": "0:20:56"}
+{"current_steps": 87, "total_steps": 117, "loss": 0.1704, "lr": 1.8825509907063328e-06, "epoch": 9.151898734177216, "percentage": 74.36, "elapsed_time": "0:58:47", "remaining_time": "0:20:16"}
+{"current_steps": 88, "total_steps": 117, "loss": 0.1645, "lr": 1.7670019939210025e-06, "epoch": 9.253164556962025, "percentage": 75.21, "elapsed_time": "0:59:18", "remaining_time": "0:19:32"}
+{"current_steps": 89, "total_steps": 117, "loss": 0.1648, "lr": 1.6543469682057105e-06, "epoch": 9.354430379746836, "percentage": 76.07, "elapsed_time": "0:59:56", "remaining_time": "0:18:51"}
+{"current_steps": 90, "total_steps": 117, "loss": 0.1678, "lr": 1.544686755065677e-06, "epoch": 9.455696202531646, "percentage": 76.92, "elapsed_time": "1:00:33", "remaining_time": "0:18:09"}
+{"current_steps": 91, "total_steps": 117, "loss": 0.1797, "lr": 1.438119515243277e-06, "epoch": 9.556962025316455, "percentage": 77.78, "elapsed_time": "1:01:10", "remaining_time": "0:17:28"}
+{"current_steps": 92, "total_steps": 117, "loss": 0.1733, "lr": 1.3347406408508695e-06, "epoch": 9.658227848101266, "percentage": 78.63, "elapsed_time": "1:01:46", "remaining_time": "0:16:47"}
+{"current_steps": 93, "total_steps": 117, "loss": 0.1764, "lr": 1.234642669981946e-06, "epoch": 9.759493670886076, "percentage": 79.49, "elapsed_time": "1:02:27", "remaining_time": "0:16:07"}
+{"current_steps": 94, "total_steps": 117, "loss": 0.1715, "lr": 1.137915203877003e-06, "epoch": 9.860759493670885, "percentage": 80.34, "elapsed_time": "1:03:10", "remaining_time": "0:15:27"}
+{"current_steps": 95, "total_steps": 117, "loss": 0.2587, "lr": 1.044644826718295e-06, "epoch": 9.962025316455696, "percentage": 81.2, "elapsed_time": "1:03:45", "remaining_time": "0:14:45"}
+{"current_steps": 96, "total_steps": 117, "loss": 0.1595, "lr": 9.549150281252633e-07, "epoch": 10.10126582278481, "percentage": 82.05, "elapsed_time": "1:04:51", "remaining_time": "0:14:11"}
+{"current_steps": 97, "total_steps": 117, "loss": 0.1514, "lr": 8.688061284200266e-07, "epoch": 10.20253164556962, "percentage": 82.91, "elapsed_time": "1:05:26", "remaining_time": "0:13:29"}
+{"current_steps": 98, "total_steps": 117, "loss": 0.1599, "lr": 7.863952067298042e-07, "epoch": 10.30379746835443, "percentage": 83.76, "elapsed_time": "1:05:55", "remaining_time": "0:12:46"}
+{"current_steps": 99, "total_steps": 117, "loss": 0.1588, "lr": 7.077560319906696e-07, "epoch": 10.405063291139241, "percentage": 84.62, "elapsed_time": "1:06:32", "remaining_time": "0:12:05"}
+{"current_steps": 100, "total_steps": 117, "loss": 0.1556, "lr": 6.329589969143518e-07, "epoch": 10.50632911392405, "percentage": 85.47, "elapsed_time": "1:07:11", "remaining_time": "0:11:25"}
+{"current_steps": 101, "total_steps": 117, "loss": 0.1564, "lr": 5.620710549772295e-07, "epoch": 10.60759493670886, "percentage": 86.32, "elapsed_time": "1:07:52", "remaining_time": "0:10:45"}
+{"current_steps": 102, "total_steps": 117, "loss": 0.1549, "lr": 4.951556604879049e-07, "epoch": 10.708860759493671, "percentage": 87.18, "elapsed_time": "1:08:30", "remaining_time": "0:10:04"}
+{"current_steps": 103, "total_steps": 117, "loss": 0.1593, "lr": 4.322727117869951e-07, "epoch": 10.810126582278482, "percentage": 88.03, "elapsed_time": "1:09:09", "remaining_time": "0:09:23"}
+{"current_steps": 104, "total_steps": 117, "loss": 0.1557, "lr": 3.734784976300165e-07, "epoch": 10.91139240506329, "percentage": 88.89, "elapsed_time": "1:09:45", "remaining_time": "0:08:43"}
+{"current_steps": 105, "total_steps": 117, "loss": 0.2388, "lr": 3.18825646801314e-07, "epoch": 11.050632911392405, "percentage": 89.74, "elapsed_time": "1:10:47", "remaining_time": "0:08:05"}
+{"current_steps": 106, "total_steps": 117, "loss": 0.1564, "lr": 2.6836308100417874e-07, "epoch": 11.151898734177216, "percentage": 90.6, "elapsed_time": "1:11:25", "remaining_time": "0:07:24"}
+{"current_steps": 107, "total_steps": 117, "loss": 0.1531, "lr": 2.2213597106929608e-07, "epoch": 11.253164556962025, "percentage": 91.45, "elapsed_time": "1:12:00", "remaining_time": "0:06:43"}
+{"current_steps": 108, "total_steps": 117, "loss": 0.1421, "lr": 1.801856965207338e-07, "epoch": 11.354430379746836, "percentage": 92.31, "elapsed_time": "1:12:40", "remaining_time": "0:06:03"}
+{"current_steps": 109, "total_steps": 117, "loss": 0.1396, "lr": 1.4254980853566248e-07, "epoch": 11.455696202531646, "percentage": 93.16, "elapsed_time": "1:13:09", "remaining_time": "0:05:22"}
+{"current_steps": 110, "total_steps": 117, "loss": 0.1417, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "1:13:49", "remaining_time": "0:04:41"}
+{"current_steps": 111, "total_steps": 117, "loss": 0.152, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "1:14:29", "remaining_time": "0:04:01"}
+{"current_steps": 112, "total_steps": 117, "loss": 0.1694, "lr": 5.584586887435739e-08, "epoch": 11.759493670886076, "percentage": 95.73, "elapsed_time": "1:15:11", "remaining_time": "0:03:21"}
+{"current_steps": 113, "total_steps": 117, "loss": 0.142, "lr": 3.576536829081323e-08, "epoch": 11.860759493670885, "percentage": 96.58, "elapsed_time": "1:15:49", "remaining_time": "0:02:41"}
+{"current_steps": 114, "total_steps": 117, "loss": 0.2282, "lr": 2.012853002380466e-08, "epoch": 11.962025316455696, "percentage": 97.44, "elapsed_time": "1:16:24", "remaining_time": "0:02:00"}
+{"current_steps": 115, "total_steps": 117, "loss": 0.1459, "lr": 8.949351161324227e-09, "epoch": 12.10126582278481, "percentage": 98.29, "elapsed_time": "1:17:15", "remaining_time": "0:01:20"}
+{"current_steps": 116, "total_steps": 117, "loss": 0.1477, "lr": 2.237838582483387e-09, "epoch": 12.20253164556962, "percentage": 99.15, "elapsed_time": "1:17:53", "remaining_time": "0:00:40"}
+{"current_steps": 117, "total_steps": 117, "loss": 0.1503, "lr": 0.0, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:18:30", "remaining_time": "0:00:00"}
+{"current_steps": 117, "total_steps": 117, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:19:27", "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": 6.487739085997507,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.8244,
+      "step": 1
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 6.257010782872823,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8005,
+      "step": 2
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 6.0499568796484535,
+      "learning_rate": 2.5e-06,
+      "loss": 0.795,
+      "step": 3
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 5.336074973883894,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7591,
+      "step": 4
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 4.225684729831529,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.757,
+      "step": 5
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 2.4648598269206192,
+      "learning_rate": 5e-06,
+      "loss": 0.7443,
+      "step": 6
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 1.9837709702470825,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.7004,
+      "step": 7
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 3.5039128786145803,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7013,
+      "step": 8
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 4.267004233786538,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7496,
+      "step": 9
+    },
+    {
+      "epoch": 1.0506329113924051,
+      "grad_norm": 6.390009655169567,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.0467,
+      "step": 10
+    },
+    {
+      "epoch": 1.1518987341772151,
+      "grad_norm": 3.8481575964942105,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.7055,
+      "step": 11
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 3.483386642960325,
+      "learning_rate": 1e-05,
+      "loss": 0.6902,
+      "step": 12
+    },
+    {
+      "epoch": 1.3544303797468356,
+      "grad_norm": 2.0491269459986303,
+      "learning_rate": 9.997762161417517e-06,
+      "loss": 0.6389,
+      "step": 13
+    },
+    {
+      "epoch": 1.4556962025316456,
+      "grad_norm": 1.562818895988004,
+      "learning_rate": 9.991050648838676e-06,
+      "loss": 0.6053,
+      "step": 14
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 1.710709037259949,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.6248,
+      "step": 15
+    },
+    {
+      "epoch": 1.6582278481012658,
+      "grad_norm": 1.5132825781260761,
+      "learning_rate": 9.964234631709188e-06,
+      "loss": 0.5832,
+      "step": 16
+    },
+    {
+      "epoch": 1.759493670886076,
+      "grad_norm": 1.0478138179186807,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 0.6072,
+      "step": 17
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.9131672793873219,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.5818,
+      "step": 18
+    },
+    {
+      "epoch": 1.9620253164556962,
+      "grad_norm": 1.6688149050953398,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.8314,
+      "step": 19
+    },
+    {
+      "epoch": 2.1012658227848102,
+      "grad_norm": 0.8178363803961444,
+      "learning_rate": 9.857450191464337e-06,
+      "loss": 0.5352,
+      "step": 20
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.8121062449916002,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.5103,
+      "step": 21
+    },
+    {
+      "epoch": 2.3037974683544302,
+      "grad_norm": 0.9370478193496051,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 0.5434,
+      "step": 22
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 0.6998663270374709,
+      "learning_rate": 9.731636918995821e-06,
+      "loss": 0.5204,
+      "step": 23
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.7313686130024222,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.5108,
+      "step": 24
+    },
+    {
+      "epoch": 2.607594936708861,
+      "grad_norm": 0.8626878184370473,
+      "learning_rate": 9.626521502369984e-06,
+      "loss": 0.5301,
+      "step": 25
+    },
+    {
+      "epoch": 2.708860759493671,
+      "grad_norm": 0.8678070384977639,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 0.5237,
+      "step": 26
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.7048955390634051,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.5347,
+      "step": 27
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 0.6211734825674653,
+      "learning_rate": 9.437928945022772e-06,
+      "loss": 0.4941,
+      "step": 28
+    },
+    {
+      "epoch": 3.050632911392405,
+      "grad_norm": 1.2186257127731135,
+      "learning_rate": 9.36704100308565e-06,
+      "loss": 0.7523,
+      "step": 29
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.7163249719895798,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.4766,
+      "step": 30
+    },
+    {
+      "epoch": 3.2531645569620253,
+      "grad_norm": 0.6167728084773804,
+      "learning_rate": 9.213604793270196e-06,
+      "loss": 0.4715,
+      "step": 31
+    },
+    {
+      "epoch": 3.3544303797468356,
+      "grad_norm": 0.5877254693272708,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.4053,
+      "step": 32
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.673114317487297,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.4867,
+      "step": 33
+    },
+    {
+      "epoch": 3.5569620253164556,
+      "grad_norm": 0.6047629625040978,
+      "learning_rate": 8.955355173281709e-06,
+      "loss": 0.4526,
+      "step": 34
+    },
+    {
+      "epoch": 3.6582278481012658,
+      "grad_norm": 0.5768060173602658,
+      "learning_rate": 8.862084796122998e-06,
+      "loss": 0.455,
+      "step": 35
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.6456448785604184,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.4267,
+      "step": 36
+    },
+    {
+      "epoch": 3.8607594936708862,
+      "grad_norm": 0.5395336917689473,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 0.4134,
+      "step": 37
+    },
+    {
+      "epoch": 3.962025316455696,
+      "grad_norm": 1.016476729451887,
+      "learning_rate": 8.561880484756726e-06,
+      "loss": 0.6812,
+      "step": 38
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.5440357050854963,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.3917,
+      "step": 39
+    },
+    {
+      "epoch": 4.2025316455696204,
+      "grad_norm": 0.7178204930607096,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 0.4073,
+      "step": 40
+    },
+    {
+      "epoch": 4.30379746835443,
+      "grad_norm": 0.5923000027862751,
+      "learning_rate": 8.232998006078998e-06,
+      "loss": 0.3952,
+      "step": 41
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.5312758433075424,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.39,
+      "step": 42
+    },
+    {
+      "epoch": 4.506329113924051,
+      "grad_norm": 0.5481292680986813,
+      "learning_rate": 7.99910947343957e-06,
+      "loss": 0.4016,
+      "step": 43
+    },
+    {
+      "epoch": 4.6075949367088604,
+      "grad_norm": 0.5433592998616376,
+      "learning_rate": 7.87808532842837e-06,
+      "loss": 0.3841,
+      "step": 44
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.5169221768248706,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.3739,
+      "step": 45
+    },
+    {
+      "epoch": 4.810126582278481,
+      "grad_norm": 0.5198192113177972,
+      "learning_rate": 7.628418849052523e-06,
+      "loss": 0.3855,
+      "step": 46
+    },
+    {
+      "epoch": 4.911392405063291,
+      "grad_norm": 0.5037430966881292,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3636,
+      "step": 47
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.804212479465148,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.561,
+      "step": 48
+    },
+    {
+      "epoch": 5.151898734177215,
+      "grad_norm": 0.5773209439403371,
+      "learning_rate": 7.236565741578163e-06,
+      "loss": 0.3512,
+      "step": 49
+    },
+    {
+      "epoch": 5.253164556962025,
+      "grad_norm": 0.5801145503247521,
+      "learning_rate": 7.101786141547829e-06,
+      "loss": 0.3451,
+      "step": 50
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.4766380687877858,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.3095,
+      "step": 51
+    },
+    {
+      "epoch": 5.455696202531645,
+      "grad_norm": 0.6043731919022627,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 0.3322,
+      "step": 52
+    },
+    {
+      "epoch": 5.556962025316456,
+      "grad_norm": 0.5826259443445325,
+      "learning_rate": 6.686649936914151e-06,
+      "loss": 0.3158,
+      "step": 53
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.5254698673509745,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.3381,
+      "step": 54
+    },
+    {
+      "epoch": 5.759493670886076,
+      "grad_norm": 0.43198260930804677,
+      "learning_rate": 6.402136946530014e-06,
+      "loss": 0.2936,
+      "step": 55
+    },
+    {
+      "epoch": 5.860759493670886,
+      "grad_norm": 0.5048637411191237,
+      "learning_rate": 6.257933818722544e-06,
+      "loss": 0.3255,
+      "step": 56
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.9683128691761499,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.5212,
+      "step": 57
+    },
+    {
+      "epoch": 6.10126582278481,
+      "grad_norm": 0.543079050452297,
+      "learning_rate": 5.9662795889777666e-06,
+      "loss": 0.2912,
+      "step": 58
+    },
+    {
+      "epoch": 6.2025316455696204,
+      "grad_norm": 0.5964623589945404,
+      "learning_rate": 5.819089557075689e-06,
+      "loss": 0.2875,
+      "step": 59
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.5365959324885466,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.2851,
+      "step": 60
+    },
+    {
+      "epoch": 6.405063291139241,
+      "grad_norm": 0.6841574260627378,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 0.2838,
+      "step": 61
+    },
+    {
+      "epoch": 6.506329113924051,
+      "grad_norm": 0.5767066827202523,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 0.2862,
+      "step": 62
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.5369687345202557,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.2762,
+      "step": 63
+    },
+    {
+      "epoch": 6.708860759493671,
+      "grad_norm": 0.613460922979565,
+      "learning_rate": 5.074797035076319e-06,
+      "loss": 0.2708,
+      "step": 64
+    },
+    {
+      "epoch": 6.810126582278481,
+      "grad_norm": 0.4972076370281023,
+      "learning_rate": 4.9252029649236835e-06,
+      "loss": 0.2538,
+      "step": 65
+    },
+    {
+      "epoch": 6.911392405063291,
+      "grad_norm": 0.5402631015512322,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.2762,
+      "step": 66
+    },
+    {
+      "epoch": 7.050632911392405,
+      "grad_norm": 0.8588042109008247,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 0.3676,
+      "step": 67
+    },
+    {
+      "epoch": 7.151898734177215,
+      "grad_norm": 0.4711679650181232,
+      "learning_rate": 4.477357683661734e-06,
+      "loss": 0.2414,
+      "step": 68
+    },
+    {
+      "epoch": 7.253164556962025,
+      "grad_norm": 0.5186059854924637,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.2369,
+      "step": 69
+    },
+    {
+      "epoch": 7.3544303797468356,
+      "grad_norm": 0.5285126867852405,
+      "learning_rate": 4.180910442924312e-06,
+      "loss": 0.2503,
+      "step": 70
+    },
+    {
+      "epoch": 7.455696202531645,
+      "grad_norm": 0.570558167173894,
+      "learning_rate": 4.033720411022235e-06,
+      "loss": 0.2436,
+      "step": 71
+    },
+    {
+      "epoch": 7.556962025316456,
+      "grad_norm": 0.47801917015352163,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.2147,
+      "step": 72
+    },
+    {
+      "epoch": 7.658227848101266,
+      "grad_norm": 0.42211425280473075,
+      "learning_rate": 3.7420661812774577e-06,
+      "loss": 0.2216,
+      "step": 73
+    },
+    {
+      "epoch": 7.759493670886076,
+      "grad_norm": 0.4670149872455072,
+      "learning_rate": 3.5978630534699873e-06,
+      "loss": 0.2408,
+      "step": 74
+    },
+    {
+      "epoch": 7.860759493670886,
+      "grad_norm": 0.4410218475930808,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.2163,
+      "step": 75
+    },
+    {
+      "epoch": 7.962025316455696,
+      "grad_norm": 0.6700490085033992,
+      "learning_rate": 3.3133500630858507e-06,
+      "loss": 0.3386,
+      "step": 76
+    },
+    {
+      "epoch": 8.10126582278481,
+      "grad_norm": 0.42265333632498664,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 0.1991,
+      "step": 77
+    },
+    {
+      "epoch": 8.20253164556962,
+      "grad_norm": 0.4496495131329505,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.1907,
+      "step": 78
+    },
+    {
+      "epoch": 8.30379746835443,
+      "grad_norm": 0.48240621681785484,
+      "learning_rate": 2.8982138584521734e-06,
+      "loss": 0.1961,
+      "step": 79
+    },
+    {
+      "epoch": 8.405063291139241,
+      "grad_norm": 0.4157845027851205,
+      "learning_rate": 2.7634342584218364e-06,
+      "loss": 0.2018,
+      "step": 80
+    },
+    {
+      "epoch": 8.50632911392405,
+      "grad_norm": 0.4555086067711132,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.1869,
+      "step": 81
+    },
+    {
+      "epoch": 8.60759493670886,
+      "grad_norm": 0.47102008241653187,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1977,
+      "step": 82
+    },
+    {
+      "epoch": 8.708860759493671,
+      "grad_norm": 0.4278201643332222,
+      "learning_rate": 2.371581150947476e-06,
+      "loss": 0.198,
+      "step": 83
+    },
+    {
+      "epoch": 8.810126582278482,
+      "grad_norm": 0.4277331561596734,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.1953,
+      "step": 84
+    },
+    {
+      "epoch": 8.91139240506329,
+      "grad_norm": 0.41215113208433574,
+      "learning_rate": 2.1219146715716332e-06,
+      "loss": 0.1913,
+      "step": 85
+    },
+    {
+      "epoch": 9.050632911392405,
+      "grad_norm": 0.6501081020554252,
+      "learning_rate": 2.0008905265604316e-06,
+      "loss": 0.2902,
+      "step": 86
+    },
+    {
+      "epoch": 9.151898734177216,
+      "grad_norm": 0.49351299237832125,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.1704,
+      "step": 87
+    },
+    {
+      "epoch": 9.253164556962025,
+      "grad_norm": 0.45485629042101366,
+      "learning_rate": 1.7670019939210025e-06,
+      "loss": 0.1645,
+      "step": 88
+    },
+    {
+      "epoch": 9.354430379746836,
+      "grad_norm": 0.43594878006143273,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 0.1648,
+      "step": 89
+    },
+    {
+      "epoch": 9.455696202531646,
+      "grad_norm": 0.524229117333008,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.1678,
+      "step": 90
+    },
+    {
+      "epoch": 9.556962025316455,
+      "grad_norm": 0.5762699897421659,
+      "learning_rate": 1.438119515243277e-06,
+      "loss": 0.1797,
+      "step": 91
+    },
+    {
+      "epoch": 9.658227848101266,
+      "grad_norm": 0.44393882516851846,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 0.1733,
+      "step": 92
+    },
+    {
+      "epoch": 9.759493670886076,
+      "grad_norm": 0.40560141070817374,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.1764,
+      "step": 93
+    },
+    {
+      "epoch": 9.860759493670885,
+      "grad_norm": 0.46367104250146185,
+      "learning_rate": 1.137915203877003e-06,
+      "loss": 0.1715,
+      "step": 94
+    },
+    {
+      "epoch": 9.962025316455696,
+      "grad_norm": 0.7723363958460977,
+      "learning_rate": 1.044644826718295e-06,
+      "loss": 0.2587,
+      "step": 95
+    },
+    {
+      "epoch": 10.10126582278481,
+      "grad_norm": 0.5107525831617175,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.1595,
+      "step": 96
+    },
+    {
+      "epoch": 10.20253164556962,
+      "grad_norm": 0.46771561743202794,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 0.1514,
+      "step": 97
+    },
+    {
+      "epoch": 10.30379746835443,
+      "grad_norm": 0.3871064090616983,
+      "learning_rate": 7.863952067298042e-07,
+      "loss": 0.1599,
+      "step": 98
+    },
+    {
+      "epoch": 10.405063291139241,
+      "grad_norm": 0.40633333182562176,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.1588,
+      "step": 99
+    },
+    {
+      "epoch": 10.50632911392405,
+      "grad_norm": 0.5179830815968256,
+      "learning_rate": 6.329589969143518e-07,
+      "loss": 0.1556,
+      "step": 100
+    },
+    {
+      "epoch": 10.60759493670886,
+      "grad_norm": 0.5068373306196533,
+      "learning_rate": 5.620710549772295e-07,
+      "loss": 0.1564,
+      "step": 101
+    },
+    {
+      "epoch": 10.708860759493671,
+      "grad_norm": 0.4646560863434988,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.1549,
+      "step": 102
+    },
+    {
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.4470174054593301,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 0.1593,
+      "step": 103
+    },
+    {
+      "epoch": 10.91139240506329,
+      "grad_norm": 0.41781726782966944,
+      "learning_rate": 3.734784976300165e-07,
+      "loss": 0.1557,
+      "step": 104
+    },
+    {
+      "epoch": 11.050632911392405,
+      "grad_norm": 0.6163624530493312,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.2388,
+      "step": 105
+    },
+    {
+      "epoch": 11.151898734177216,
+      "grad_norm": 0.3779658087921075,
+      "learning_rate": 2.6836308100417874e-07,
+      "loss": 0.1564,
+      "step": 106
+    },
+    {
+      "epoch": 11.253164556962025,
+      "grad_norm": 0.3962142815005405,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 0.1531,
+      "step": 107
+    },
+    {
+      "epoch": 11.354430379746836,
+      "grad_norm": 0.37796569420656834,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.1421,
+      "step": 108
+    },
+    {
+      "epoch": 11.455696202531646,
+      "grad_norm": 0.4190534604243063,
+      "learning_rate": 1.4254980853566248e-07,
+      "loss": 0.1396,
+      "step": 109
+    },
+    {
+      "epoch": 11.556962025316455,
+      "grad_norm": 0.3927060853622339,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 0.1417,
+      "step": 110
+    },
+    {
+      "epoch": 11.658227848101266,
+      "grad_norm": 0.3910392543626813,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.152,
+      "step": 111
+    },
+    {
+      "epoch": 11.759493670886076,
+      "grad_norm": 0.3832903001655876,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 0.1694,
+      "step": 112
+    },
+    {
+      "epoch": 11.860759493670885,
+      "grad_norm": 0.38553168802846804,
+      "learning_rate": 3.576536829081323e-08,
+      "loss": 0.142,
+      "step": 113
+    },
+    {
+      "epoch": 11.962025316455696,
+      "grad_norm": 0.5786623878371228,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.2282,
+      "step": 114
+    },
+    {
+      "epoch": 12.10126582278481,
+      "grad_norm": 0.3666509583277426,
+      "learning_rate": 8.949351161324227e-09,
+      "loss": 0.1459,
+      "step": 115
+    },
+    {
+      "epoch": 12.20253164556962,
+      "grad_norm": 0.38747422449556695,
+      "learning_rate": 2.237838582483387e-09,
+      "loss": 0.1477,
+      "step": 116
+    },
+    {
+      "epoch": 12.30379746835443,
+      "grad_norm": 0.33864628427433874,
+      "learning_rate": 0.0,
+      "loss": 0.1503,
+      "step": 117
+    },
+    {
+      "epoch": 12.30379746835443,
+      "step": 117,
+      "total_flos": 1.3891141298133402e+17,
+      "train_loss": 0.36694383532063574,
+      "train_runtime": 4769.333,
+      "train_samples_per_second": 0.861,
+      "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": 1.3891141298133402e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1681fa4daa502eb8f03d49ab867d1d5a30bb0ea97dc4b6a27d4b6186bb6255
+size 7288