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: b1_code_top_8_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. -->
+
+# b1_code_top_8_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/b1_code_top_8_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: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- 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": 6.72,
+    "total_flos": 1.2820678594422374e+17,
+    "train_loss": 0.5999843043940408,
+    "train_runtime": 5632.331,
+    "train_samples_per_second": 1.243,
+    "train_steps_per_second": 0.012
+}

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:e50f2d2ebc31ab4ce8dbc63dca1e4b2da70f784a8e345b7180f198c0d2f92aaf
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c59f48475886c8619f5824c36fe57eb61733098767ca55a09200778d787ceae
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab922a0b052c4466466eb07e6581a4423e91421bd5d4c9b9bd0eb2a12a746b34
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7652ab9704f526bd00c9b7283ae39f30f1b5456696c0bfa73b9cecab6e6d1091
+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/Apr19_06-56-46_jpbot-001-36.jupiter.internal/events.out.tfevents.1745038626.jpbot-001-36.jupiter.internal.3706093.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d158a763a3617702197e4a47934d3397264e2d2937725b5a9add9e738f403e98
+size 20353

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": "2025-04-19 06:56:46", "end_time": "2025-04-19 08:31:04"}

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": 6.72,
+    "total_flos": 1.2820678594422374e+17,
+    "train_loss": 0.5999843043940408,
+    "train_runtime": 5632.331,
+    "train_samples_per_second": 1.243,
+    "train_steps_per_second": 0.012
+}

trainer_log.jsonl

@@ -0,0 +1,71 @@
+{"current_steps": 1, "total_steps": 70, "loss": 1.0114, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:01:29", "remaining_time": "1:42:56"}
+{"current_steps": 2, "total_steps": 70, "loss": 1.041, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:02:43", "remaining_time": "1:32:54"}
+{"current_steps": 3, "total_steps": 70, "loss": 1.0925, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:04:00", "remaining_time": "1:29:36"}
+{"current_steps": 4, "total_steps": 70, "loss": 0.9667, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:05:15", "remaining_time": "1:26:46"}
+{"current_steps": 5, "total_steps": 70, "loss": 0.9125, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:06:36", "remaining_time": "1:26:00"}
+{"current_steps": 6, "total_steps": 70, "loss": 0.9275, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:08:06", "remaining_time": "1:26:32"}
+{"current_steps": 7, "total_steps": 70, "loss": 0.9128, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:09:27", "remaining_time": "1:25:04"}
+{"current_steps": 8, "total_steps": 70, "loss": 0.8821, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:10:40", "remaining_time": "1:22:46"}
+{"current_steps": 9, "total_steps": 70, "loss": 0.8571, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:11:58", "remaining_time": "1:21:09"}
+{"current_steps": 10, "total_steps": 70, "loss": 0.8137, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:13:11", "remaining_time": "1:19:11"}
+{"current_steps": 11, "total_steps": 70, "loss": 1.3113, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:15:01", "remaining_time": "1:20:34"}
+{"current_steps": 12, "total_steps": 70, "loss": 0.6879, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:16:09", "remaining_time": "1:18:05"}
+{"current_steps": 13, "total_steps": 70, "loss": 0.7442, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:17:29", "remaining_time": "1:16:39"}
+{"current_steps": 14, "total_steps": 70, "loss": 0.7407, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:18:51", "remaining_time": "1:15:25"}
+{"current_steps": 15, "total_steps": 70, "loss": 0.6901, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:20:01", "remaining_time": "1:13:24"}
+{"current_steps": 16, "total_steps": 70, "loss": 0.7608, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:21:15", "remaining_time": "1:11:45"}
+{"current_steps": 17, "total_steps": 70, "loss": 0.6895, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:22:36", "remaining_time": "1:10:27"}
+{"current_steps": 18, "total_steps": 70, "loss": 0.7521, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:23:54", "remaining_time": "1:09:02"}
+{"current_steps": 19, "total_steps": 70, "loss": 0.6698, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:25:09", "remaining_time": "1:07:30"}
+{"current_steps": 20, "total_steps": 70, "loss": 0.6473, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:26:26", "remaining_time": "1:06:05"}
+{"current_steps": 21, "total_steps": 70, "loss": 1.1523, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:28:26", "remaining_time": "1:06:21"}
+{"current_steps": 22, "total_steps": 70, "loss": 0.6157, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:29:42", "remaining_time": "1:04:49"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.6178, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:30:58", "remaining_time": "1:03:17"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.6317, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:32:12", "remaining_time": "1:01:44"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.6027, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:33:13", "remaining_time": "0:59:47"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.5533, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:34:22", "remaining_time": "0:58:10"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.6066, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:35:38", "remaining_time": "0:56:45"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.5678, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:37:02", "remaining_time": "0:55:34"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.6325, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "0:38:23", "remaining_time": "0:54:17"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.5373, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "0:39:29", "remaining_time": "0:52:38"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.6994, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "0:40:51", "remaining_time": "0:51:23"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.7936, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "0:43:09", "remaining_time": "0:51:15"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.5078, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "0:44:20", "remaining_time": "0:49:42"}
+{"current_steps": 34, "total_steps": 70, "loss": 0.5623, "lr": 1.2225209339563144e-05, "epoch": 3.2640000000000002, "percentage": 48.57, "elapsed_time": "0:45:52", "remaining_time": "0:48:34"}
+{"current_steps": 35, "total_steps": 70, "loss": 0.4179, "lr": 1.1736481776669307e-05, "epoch": 3.36, "percentage": 50.0, "elapsed_time": "0:46:43", "remaining_time": "0:46:43"}
+{"current_steps": 36, "total_steps": 70, "loss": 0.5445, "lr": 1.1243437046474854e-05, "epoch": 3.456, "percentage": 51.43, "elapsed_time": "0:47:59", "remaining_time": "0:45:19"}
+{"current_steps": 37, "total_steps": 70, "loss": 0.4995, "lr": 1.0747300935864245e-05, "epoch": 3.552, "percentage": 52.86, "elapsed_time": "0:49:18", "remaining_time": "0:43:58"}
+{"current_steps": 38, "total_steps": 70, "loss": 0.5807, "lr": 1.0249306917380731e-05, "epoch": 3.648, "percentage": 54.29, "elapsed_time": "0:50:35", "remaining_time": "0:42:36"}
+{"current_steps": 39, "total_steps": 70, "loss": 0.4443, "lr": 9.750693082619274e-06, "epoch": 3.7439999999999998, "percentage": 55.71, "elapsed_time": "0:52:01", "remaining_time": "0:41:20"}
+{"current_steps": 40, "total_steps": 70, "loss": 0.4994, "lr": 9.252699064135759e-06, "epoch": 3.84, "percentage": 57.14, "elapsed_time": "0:53:20", "remaining_time": "0:40:00"}
+{"current_steps": 41, "total_steps": 70, "loss": 0.5195, "lr": 8.756562953525151e-06, "epoch": 3.936, "percentage": 58.57, "elapsed_time": "0:54:44", "remaining_time": "0:38:43"}
+{"current_steps": 42, "total_steps": 70, "loss": 0.7055, "lr": 8.263518223330698e-06, "epoch": 4.032, "percentage": 60.0, "elapsed_time": "0:56:24", "remaining_time": "0:37:36"}
+{"current_steps": 43, "total_steps": 70, "loss": 0.4386, "lr": 7.774790660436857e-06, "epoch": 4.128, "percentage": 61.43, "elapsed_time": "0:57:39", "remaining_time": "0:36:12"}
+{"current_steps": 44, "total_steps": 70, "loss": 0.437, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "0:58:47", "remaining_time": "0:34:44"}
+{"current_steps": 45, "total_steps": 70, "loss": 0.4205, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "0:59:59", "remaining_time": "0:33:19"}
+{"current_steps": 46, "total_steps": 70, "loss": 0.4537, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "1:01:17", "remaining_time": "0:31:58"}
+{"current_steps": 47, "total_steps": 70, "loss": 0.4246, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "1:02:33", "remaining_time": "0:30:36"}
+{"current_steps": 48, "total_steps": 70, "loss": 0.4397, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "1:03:57", "remaining_time": "0:29:18"}
+{"current_steps": 49, "total_steps": 70, "loss": 0.4246, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "1:05:12", "remaining_time": "0:27:56"}
+{"current_steps": 50, "total_steps": 70, "loss": 0.4292, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "1:06:20", "remaining_time": "0:26:32"}
+{"current_steps": 51, "total_steps": 70, "loss": 0.4398, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "1:07:47", "remaining_time": "0:25:15"}
+{"current_steps": 52, "total_steps": 70, "loss": 0.621, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "1:09:14", "remaining_time": "0:23:58"}
+{"current_steps": 53, "total_steps": 70, "loss": 0.4077, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "1:11:12", "remaining_time": "0:22:50"}
+{"current_steps": 54, "total_steps": 70, "loss": 0.3825, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "1:12:26", "remaining_time": "0:21:27"}
+{"current_steps": 55, "total_steps": 70, "loss": 0.4008, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "1:13:30", "remaining_time": "0:20:02"}
+{"current_steps": 56, "total_steps": 70, "loss": 0.3816, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "1:14:48", "remaining_time": "0:18:42"}
+{"current_steps": 57, "total_steps": 70, "loss": 0.405, "lr": 2.0286749277707783e-06, "epoch": 5.4719999999999995, "percentage": 81.43, "elapsed_time": "1:16:17", "remaining_time": "0:17:23"}
+{"current_steps": 58, "total_steps": 70, "loss": 0.3762, "lr": 1.7376122568400533e-06, "epoch": 5.568, "percentage": 82.86, "elapsed_time": "1:17:29", "remaining_time": "0:16:01"}
+{"current_steps": 59, "total_steps": 70, "loss": 0.3877, "lr": 1.467091183678444e-06, "epoch": 5.664, "percentage": 84.29, "elapsed_time": "1:18:52", "remaining_time": "0:14:42"}
+{"current_steps": 60, "total_steps": 70, "loss": 0.3881, "lr": 1.2177842662977136e-06, "epoch": 5.76, "percentage": 85.71, "elapsed_time": "1:20:15", "remaining_time": "0:13:22"}
+{"current_steps": 61, "total_steps": 70, "loss": 0.3721, "lr": 9.903113209758098e-07, "epoch": 5.856, "percentage": 87.14, "elapsed_time": "1:21:19", "remaining_time": "0:11:59"}
+{"current_steps": 62, "total_steps": 70, "loss": 0.3866, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "1:22:30", "remaining_time": "0:10:38"}
+{"current_steps": 63, "total_steps": 70, "loss": 0.6044, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "1:24:19", "remaining_time": "0:09:22"}
+{"current_steps": 64, "total_steps": 70, "loss": 0.336, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "1:25:13", "remaining_time": "0:07:59"}
+{"current_steps": 65, "total_steps": 70, "loss": 0.35, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "1:26:36", "remaining_time": "0:06:39"}
+{"current_steps": 66, "total_steps": 70, "loss": 0.3763, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "1:27:46", "remaining_time": "0:05:19"}
+{"current_steps": 67, "total_steps": 70, "loss": 0.3805, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "1:28:55", "remaining_time": "0:03:58"}
+{"current_steps": 68, "total_steps": 70, "loss": 0.3826, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "1:30:09", "remaining_time": "0:02:39"}
+{"current_steps": 69, "total_steps": 70, "loss": 0.3613, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "1:31:29", "remaining_time": "0:01:19"}
+{"current_steps": 70, "total_steps": 70, "loss": 0.3879, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:32:46", "remaining_time": "0:00:00"}
+{"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:33:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,532 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.72,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.944960466387328,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.0114,
+      "step": 1
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.086483553324464,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.041,
+      "step": 2
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 5.99718694277905,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.0925,
+      "step": 3
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 2.5945150141338624,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.9667,
+      "step": 4
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.691322070793699,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.9125,
+      "step": 5
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 3.636564757900175,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.9275,
+      "step": 6
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 3.777217276184943,
+      "learning_rate": 2e-05,
+      "loss": 0.9128,
+      "step": 7
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.801895386381312,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.8821,
+      "step": 8
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 2.10629151324274,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.8571,
+      "step": 9
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6440589900064753,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.8137,
+      "step": 10
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 2.092646032889902,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 1.3113,
+      "step": 11
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 1.1499358617208464,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.6879,
+      "step": 12
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 1.2388038395776648,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.7442,
+      "step": 13
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 1.0595966899070013,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.7407,
+      "step": 14
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0162689746872489,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.6901,
+      "step": 15
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 1.2220238283984195,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.7608,
+      "step": 16
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8945443299192337,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.6895,
+      "step": 17
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 1.0666561139043083,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.7521,
+      "step": 18
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.9597100466790252,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.6698,
+      "step": 19
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7769867887536602,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.6473,
+      "step": 20
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 1.288167245486445,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.1523,
+      "step": 21
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8422032392080524,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.6157,
+      "step": 22
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.7703640645225037,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.6178,
+      "step": 23
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.963217183539902,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.6317,
+      "step": 24
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.42970396082646,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.6027,
+      "step": 25
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8164650857124783,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.5533,
+      "step": 26
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.7786368384278178,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.6066,
+      "step": 27
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.710769695741534,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5678,
+      "step": 28
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.8865322858182426,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.6325,
+      "step": 29
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5849363222112286,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.5373,
+      "step": 30
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.9767844704922458,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.6994,
+      "step": 31
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.86164608116822,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.7936,
+      "step": 32
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.8237193547271372,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.5078,
+      "step": 33
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.8100977134743738,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.5623,
+      "step": 34
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.5667085900879959,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4179,
+      "step": 35
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 1.1019994059262113,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.5445,
+      "step": 36
+    },
+    {
+      "epoch": 3.552,
+      "grad_norm": 0.7091810014433372,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.4995,
+      "step": 37
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.9405628300626622,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.5807,
+      "step": 38
+    },
+    {
+      "epoch": 3.7439999999999998,
+      "grad_norm": 0.6516410423639595,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.4443,
+      "step": 39
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.8414105089077197,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.4994,
+      "step": 40
+    },
+    {
+      "epoch": 3.936,
+      "grad_norm": 0.666993922442764,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.5195,
+      "step": 41
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.9682206402164324,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.7055,
+      "step": 42
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.5090195286609236,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.4386,
+      "step": 43
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.6237639543839937,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.437,
+      "step": 44
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.546011697031731,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.4205,
+      "step": 45
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.5830602559492782,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.4537,
+      "step": 46
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.5867223908669553,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.4246,
+      "step": 47
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.6031989296649094,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.4397,
+      "step": 48
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.5125385478443895,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4246,
+      "step": 49
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.5367122362937156,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.4292,
+      "step": 50
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 0.4887001636196693,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.4398,
+      "step": 51
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.7739002780453024,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.621,
+      "step": 52
+    },
+    {
+      "epoch": 5.088,
+      "grad_norm": 0.5224586264775329,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.4077,
+      "step": 53
+    },
+    {
+      "epoch": 5.184,
+      "grad_norm": 0.47639037276254115,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.3825,
+      "step": 54
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.4390100164868234,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.4008,
+      "step": 55
+    },
+    {
+      "epoch": 5.376,
+      "grad_norm": 0.42262001081899037,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3816,
+      "step": 56
+    },
+    {
+      "epoch": 5.4719999999999995,
+      "grad_norm": 0.43954542690884474,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.405,
+      "step": 57
+    },
+    {
+      "epoch": 5.568,
+      "grad_norm": 0.38418311432799357,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.3762,
+      "step": 58
+    },
+    {
+      "epoch": 5.664,
+      "grad_norm": 0.4074795238463937,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.3877,
+      "step": 59
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.3790306148786251,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.3881,
+      "step": 60
+    },
+    {
+      "epoch": 5.856,
+      "grad_norm": 0.4030792590172934,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.3721,
+      "step": 61
+    },
+    {
+      "epoch": 5.952,
+      "grad_norm": 0.3809741315217957,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.3866,
+      "step": 62
+    },
+    {
+      "epoch": 6.048,
+      "grad_norm": 0.7607656624613088,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.6044,
+      "step": 63
+    },
+    {
+      "epoch": 6.144,
+      "grad_norm": 0.34745927753316835,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.336,
+      "step": 64
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.3543815281347,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.35,
+      "step": 65
+    },
+    {
+      "epoch": 6.336,
+      "grad_norm": 0.3632710267355952,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.3763,
+      "step": 66
+    },
+    {
+      "epoch": 6.432,
+      "grad_norm": 0.36488026498237486,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.3805,
+      "step": 67
+    },
+    {
+      "epoch": 6.5280000000000005,
+      "grad_norm": 0.358041962170842,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.3826,
+      "step": 68
+    },
+    {
+      "epoch": 6.624,
+      "grad_norm": 0.3414392418565718,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.3613,
+      "step": 69
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 0.34777568542354104,
+      "learning_rate": 0.0,
+      "loss": 0.3879,
+      "step": 70
+    },
+    {
+      "epoch": 6.72,
+      "step": 70,
+      "total_flos": 1.2820678594422374e+17,
+      "train_loss": 0.5999843043940408,
+      "train_runtime": 5632.331,
+      "train_samples_per_second": 1.243,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "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": 1.2820678594422374e+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:c8dc4f39ae795c28797fdafdf330e6c4d19288c9882571e45774836045c3a4c0
+size 7352