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_gpt_1k
+  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_gpt_1k
+
+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_gpt_1k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 96
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.666666666666667,
+    "total_flos": 8.845618236411085e+16,
+    "train_loss": 0.512090947159699,
+    "train_runtime": 1943.4186,
+    "train_samples_per_second": 3.602,
+    "train_steps_per_second": 0.036
+}

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 sha256:24b66650fdebce7b4f67e004dd6436553e87e2a4b71a13e99b37e8bfebc67a1f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ff4b6bed1205c69eb567c775e1e10f42d5025d58fa221d318b9b2954f9aa96
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c751ba778c8f0979fbc4e7980153a9a25e9f1e50f14feb04d2c04a93b8690ec0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e40a3e37ac271cd18c7fad12f9f611cbd058997c43ac772a3781af3d6c9152
+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_06-39-43_jpbot-001-01.jupiter.internal/events.out.tfevents.1745815237.jpbot-001-01.jupiter.internal.386046.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849e11eb26cc48b3be3111565c0b61abc1b43a23465a5298c12b43f8ad47e162
+size 20356

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 06:39:43", "end_time": "2025-04-28 07:13:07"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.666666666666667,
+    "total_flos": 8.845618236411085e+16,
+    "train_loss": 0.512090947159699,
+    "train_runtime": 1943.4186,
+    "train_samples_per_second": 3.602,
+    "train_steps_per_second": 0.036
+}

trainer_log.jsonl

@@ -0,0 +1,71 @@
+{"current_steps": 1, "total_steps": 70, "loss": 0.9707, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:38", "remaining_time": "0:44:36"}
+{"current_steps": 2, "total_steps": 70, "loss": 0.96, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:11", "remaining_time": "0:40:23"}
+{"current_steps": 3, "total_steps": 70, "loss": 0.9999, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:01:40", "remaining_time": "0:37:25"}
+{"current_steps": 4, "total_steps": 70, "loss": 0.9063, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:04", "remaining_time": "0:34:06"}
+{"current_steps": 5, "total_steps": 70, "loss": 0.8984, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:02:30", "remaining_time": "0:32:36"}
+{"current_steps": 6, "total_steps": 70, "loss": 0.8603, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:02:55", "remaining_time": "0:31:09"}
+{"current_steps": 7, "total_steps": 70, "loss": 0.9, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:03:19", "remaining_time": "0:29:51"}
+{"current_steps": 8, "total_steps": 70, "loss": 0.864, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:03:39", "remaining_time": "0:28:22"}
+{"current_steps": 9, "total_steps": 70, "loss": 0.8056, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:04:01", "remaining_time": "0:27:17"}
+{"current_steps": 10, "total_steps": 70, "loss": 0.7777, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:04:26", "remaining_time": "0:26:41"}
+{"current_steps": 11, "total_steps": 70, "loss": 1.1857, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:05:18", "remaining_time": "0:28:30"}
+{"current_steps": 12, "total_steps": 70, "loss": 0.7071, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:05:40", "remaining_time": "0:27:26"}
+{"current_steps": 13, "total_steps": 70, "loss": 0.6966, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:06:05", "remaining_time": "0:26:44"}
+{"current_steps": 14, "total_steps": 70, "loss": 0.6491, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:06:29", "remaining_time": "0:25:57"}
+{"current_steps": 15, "total_steps": 70, "loss": 0.7969, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:06:55", "remaining_time": "0:25:25"}
+{"current_steps": 16, "total_steps": 70, "loss": 0.6197, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:07:20", "remaining_time": "0:24:47"}
+{"current_steps": 17, "total_steps": 70, "loss": 0.63, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:07:45", "remaining_time": "0:24:10"}
+{"current_steps": 18, "total_steps": 70, "loss": 0.6215, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:08:04", "remaining_time": "0:23:19"}
+{"current_steps": 19, "total_steps": 70, "loss": 0.6743, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:08:34", "remaining_time": "0:23:01"}
+{"current_steps": 20, "total_steps": 70, "loss": 0.6626, "lr": 1.7971325072229227e-05, "epoch": 1.9047619047619047, "percentage": 28.57, "elapsed_time": "0:09:03", "remaining_time": "0:22:39"}
+{"current_steps": 21, "total_steps": 70, "loss": 1.0064, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:09:32", "remaining_time": "0:22:14"}
+{"current_steps": 22, "total_steps": 70, "loss": 0.5821, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:10:11", "remaining_time": "0:22:14"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.5465, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:10:37", "remaining_time": "0:21:42"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.5166, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:11:00", "remaining_time": "0:21:06"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.5145, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:11:24", "remaining_time": "0:20:32"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.5293, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:11:54", "remaining_time": "0:20:08"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.552, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:12:16", "remaining_time": "0:19:32"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.5499, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:12:40", "remaining_time": "0:19:00"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.5255, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:13:05", "remaining_time": "0:18:30"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.4913, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:13:34", "remaining_time": "0:18:05"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.5178, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:14:00", "remaining_time": "0:17:37"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.6998, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:15:10", "remaining_time": "0:18:01"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.422, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:15:32", "remaining_time": "0:17:25"}
+{"current_steps": 34, "total_steps": 70, "loss": 0.4443, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:15:59", "remaining_time": "0:16:55"}
+{"current_steps": 35, "total_steps": 70, "loss": 0.3904, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:16:17", "remaining_time": "0:16:17"}
+{"current_steps": 36, "total_steps": 70, "loss": 0.4155, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:16:44", "remaining_time": "0:15:48"}
+{"current_steps": 37, "total_steps": 70, "loss": 0.4029, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:17:14", "remaining_time": "0:15:22"}
+{"current_steps": 38, "total_steps": 70, "loss": 0.4077, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:17:34", "remaining_time": "0:14:47"}
+{"current_steps": 39, "total_steps": 70, "loss": 0.3729, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:17:56", "remaining_time": "0:14:15"}
+{"current_steps": 40, "total_steps": 70, "loss": 0.3925, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:18:28", "remaining_time": "0:13:51"}
+{"current_steps": 41, "total_steps": 70, "loss": 0.4487, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:18:58", "remaining_time": "0:13:25"}
+{"current_steps": 42, "total_steps": 70, "loss": 0.5828, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:19:21", "remaining_time": "0:12:54"}
+{"current_steps": 43, "total_steps": 70, "loss": 0.3392, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:20:11", "remaining_time": "0:12:40"}
+{"current_steps": 44, "total_steps": 70, "loss": 0.3498, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:20:33", "remaining_time": "0:12:09"}
+{"current_steps": 45, "total_steps": 70, "loss": 0.3227, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:21:02", "remaining_time": "0:11:41"}
+{"current_steps": 46, "total_steps": 70, "loss": 0.3265, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:21:28", "remaining_time": "0:11:12"}
+{"current_steps": 47, "total_steps": 70, "loss": 0.3313, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:22:00", "remaining_time": "0:10:46"}
+{"current_steps": 48, "total_steps": 70, "loss": 0.3138, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:22:26", "remaining_time": "0:10:17"}
+{"current_steps": 49, "total_steps": 70, "loss": 0.3182, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:22:50", "remaining_time": "0:09:47"}
+{"current_steps": 50, "total_steps": 70, "loss": 0.3133, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:23:14", "remaining_time": "0:09:17"}
+{"current_steps": 51, "total_steps": 70, "loss": 0.2883, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:23:34", "remaining_time": "0:08:47"}
+{"current_steps": 52, "total_steps": 70, "loss": 0.3216, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:23:56", "remaining_time": "0:08:17"}
+{"current_steps": 53, "total_steps": 70, "loss": 0.4765, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:24:33", "remaining_time": "0:07:52"}
+{"current_steps": 54, "total_steps": 70, "loss": 0.2943, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:25:01", "remaining_time": "0:07:24"}
+{"current_steps": 55, "total_steps": 70, "loss": 0.2719, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:25:25", "remaining_time": "0:06:55"}
+{"current_steps": 56, "total_steps": 70, "loss": 0.2929, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:25:46", "remaining_time": "0:06:26"}
+{"current_steps": 57, "total_steps": 70, "loss": 0.2793, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:26:12", "remaining_time": "0:05:58"}
+{"current_steps": 58, "total_steps": 70, "loss": 0.2474, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:26:40", "remaining_time": "0:05:31"}
+{"current_steps": 59, "total_steps": 70, "loss": 0.2806, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:27:10", "remaining_time": "0:05:03"}
+{"current_steps": 60, "total_steps": 70, "loss": 0.2507, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:27:30", "remaining_time": "0:04:35"}
+{"current_steps": 61, "total_steps": 70, "loss": 0.2571, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:27:53", "remaining_time": "0:04:06"}
+{"current_steps": 62, "total_steps": 70, "loss": 0.306, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:28:23", "remaining_time": "0:03:39"}
+{"current_steps": 63, "total_steps": 70, "loss": 0.3736, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:28:42", "remaining_time": "0:03:11"}
+{"current_steps": 64, "total_steps": 70, "loss": 0.2468, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:29:21", "remaining_time": "0:02:45"}
+{"current_steps": 65, "total_steps": 70, "loss": 0.2541, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:29:45", "remaining_time": "0:02:17"}
+{"current_steps": 66, "total_steps": 70, "loss": 0.2765, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:30:08", "remaining_time": "0:01:49"}
+{"current_steps": 67, "total_steps": 70, "loss": 0.2458, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:30:38", "remaining_time": "0:01:22"}
+{"current_steps": 68, "total_steps": 70, "loss": 0.2598, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:31:05", "remaining_time": "0:00:54"}
+{"current_steps": 69, "total_steps": 70, "loss": 0.2549, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:31:32", "remaining_time": "0:00:27"}
+{"current_steps": 70, "total_steps": 70, "loss": 0.2557, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:31:54", "remaining_time": "0:00:00"}
+{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:32:22", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,532 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.666666666666667,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 6.161017789522275,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.9707,
+      "step": 1
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 5.996260369021778,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.96,
+      "step": 2
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 5.929898499790371,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9999,
+      "step": 3
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 2.3731861863787196,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.9063,
+      "step": 4
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 4.4704202091163,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.8984,
+      "step": 5
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 4.585934932945184,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.8603,
+      "step": 6
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 5.244715927940786,
+      "learning_rate": 2e-05,
+      "loss": 0.9,
+      "step": 7
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 4.0809654928020676,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.864,
+      "step": 8
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 3.2584679496681397,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.8056,
+      "step": 9
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 2.3353254899090388,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.7777,
+      "step": 10
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 3.302286989925438,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 1.1857,
+      "step": 11
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.534876411201704,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.7071,
+      "step": 12
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 1.6143509808336198,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.6966,
+      "step": 13
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.0967170357054743,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6491,
+      "step": 14
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.2633149200229055,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.7969,
+      "step": 15
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 1.1233006352774453,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.6197,
+      "step": 16
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.9771154944828583,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.63,
+      "step": 17
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.803376560782559,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.6215,
+      "step": 18
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.9843821321656877,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.6743,
+      "step": 19
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.7567426775160028,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.6626,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.294239166078661,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.0064,
+      "step": 21
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.8093536138819284,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.5821,
+      "step": 22
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.6912451908217692,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.5465,
+      "step": 23
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.718502236374443,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.5166,
+      "step": 24
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.6693644774077125,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.5145,
+      "step": 25
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.7084938839466517,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.5293,
+      "step": 26
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.6917197929562814,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.552,
+      "step": 27
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.6156868684916943,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5499,
+      "step": 28
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.5941573583394953,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.5255,
+      "step": 29
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.6550934958550261,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.4913,
+      "step": 30
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.7375695546338578,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.5178,
+      "step": 31
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 0.9812861171986549,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.6998,
+      "step": 32
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.6418778321800664,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.422,
+      "step": 33
+    },
+    {
+      "epoch": 3.238095238095238,
+      "grad_norm": 0.681354339259344,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.4443,
+      "step": 34
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.5987719549380569,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.3904,
+      "step": 35
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.6365943733086789,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.4155,
+      "step": 36
+    },
+    {
+      "epoch": 3.5238095238095237,
+      "grad_norm": 0.6020288769546885,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.4029,
+      "step": 37
+    },
+    {
+      "epoch": 3.619047619047619,
+      "grad_norm": 0.5829781638934128,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.4077,
+      "step": 38
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.5281264142620514,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.3729,
+      "step": 39
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.5516361148917616,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.3925,
+      "step": 40
+    },
+    {
+      "epoch": 3.9047619047619047,
+      "grad_norm": 0.572566066974744,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.4487,
+      "step": 41
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7788426656278804,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.5828,
+      "step": 42
+    },
+    {
+      "epoch": 4.095238095238095,
+      "grad_norm": 0.5279619048193416,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3392,
+      "step": 43
+    },
+    {
+      "epoch": 4.190476190476191,
+      "grad_norm": 0.6021057973681291,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.3498,
+      "step": 44
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.5070090371830681,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.3227,
+      "step": 45
+    },
+    {
+      "epoch": 4.380952380952381,
+      "grad_norm": 0.5813127296618199,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.3265,
+      "step": 46
+    },
+    {
+      "epoch": 4.476190476190476,
+      "grad_norm": 0.6163134141663158,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.3313,
+      "step": 47
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.5139660313086627,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.3138,
+      "step": 48
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.5477096668915792,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3182,
+      "step": 49
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.5319032972194806,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.3133,
+      "step": 50
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.46499293280370024,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.2883,
+      "step": 51
+    },
+    {
+      "epoch": 4.9523809523809526,
+      "grad_norm": 0.4677846359922228,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.3216,
+      "step": 52
+    },
+    {
+      "epoch": 5.0476190476190474,
+      "grad_norm": 0.8150740033572704,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.4765,
+      "step": 53
+    },
+    {
+      "epoch": 5.142857142857143,
+      "grad_norm": 0.4845837444708581,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.2943,
+      "step": 54
+    },
+    {
+      "epoch": 5.238095238095238,
+      "grad_norm": 0.45394749867042267,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.2719,
+      "step": 55
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.4345963073955771,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.2929,
+      "step": 56
+    },
+    {
+      "epoch": 5.428571428571429,
+      "grad_norm": 0.4505452463293748,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.2793,
+      "step": 57
+    },
+    {
+      "epoch": 5.523809523809524,
+      "grad_norm": 0.46196303809194533,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.2474,
+      "step": 58
+    },
+    {
+      "epoch": 5.619047619047619,
+      "grad_norm": 0.45217652161509075,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.2806,
+      "step": 59
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.4343220682126627,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.2507,
+      "step": 60
+    },
+    {
+      "epoch": 5.809523809523809,
+      "grad_norm": 0.41985975234139195,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.2571,
+      "step": 61
+    },
+    {
+      "epoch": 5.904761904761905,
+      "grad_norm": 0.42437891072564254,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.306,
+      "step": 62
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5881073197725365,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3736,
+      "step": 63
+    },
+    {
+      "epoch": 6.095238095238095,
+      "grad_norm": 0.41895612223072026,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.2468,
+      "step": 64
+    },
+    {
+      "epoch": 6.190476190476191,
+      "grad_norm": 0.4064693398460585,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.2541,
+      "step": 65
+    },
+    {
+      "epoch": 6.285714285714286,
+      "grad_norm": 0.40069622802006466,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.2765,
+      "step": 66
+    },
+    {
+      "epoch": 6.380952380952381,
+      "grad_norm": 0.3764839577143736,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.2458,
+      "step": 67
+    },
+    {
+      "epoch": 6.476190476190476,
+      "grad_norm": 0.3637603004975795,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.2598,
+      "step": 68
+    },
+    {
+      "epoch": 6.571428571428571,
+      "grad_norm": 0.38093860445170225,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.2549,
+      "step": 69
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.4055886366398278,
+      "learning_rate": 0.0,
+      "loss": 0.2557,
+      "step": 70
+    },
+    {
+      "epoch": 6.666666666666667,
+      "step": 70,
+      "total_flos": 8.845618236411085e+16,
+      "train_loss": 0.512090947159699,
+      "train_runtime": 1943.4186,
+      "train_samples_per_second": 3.602,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.845618236411085e+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 sha256:73153338120067103f19e9348684aca3172d2b5c9a4c418fe0f7fa12b5df6b90
+size 7352