Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 stage1_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+stage2_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

stage2_7b/README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_7b_stage2
+  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. -->
+
+# sft_7b_stage2
+
+This model is a fine-tuned version of [saves/qwen2.5_3d/full/sft_7b_stage1_abl_lr](https://huggingface.co/saves/qwen2.5_3d/full/sft_7b_stage1_abl_lr) on the shapenet_cap, the abo, the objaverse_cap and the 3d_mm_vet datasets.
+It achieves the following results on the evaluation set:
+- Loss: 2.3431
+
+## 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: 1.5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.7683        | 2.5563 | 1000 | 2.3431          |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.4.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

stage2_7b/added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</pointcloud>": 151669,
+  "</tool_call>": 151658,
+  "<layer_sep>": 151667,
+  "<point_patch>": 151666,
+  "<pointcloud>": 151665,
+  "<row_sep>": 151668,
+  "<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
+}

stage2_7b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9977671451355663,
+    "eval_loss": 2.343059778213501,
+    "eval_runtime": 20.0302,
+    "eval_samples_per_second": 263.602,
+    "eval_steps_per_second": 8.238,
+    "total_flos": 102874311622656.0,
+    "train_loss": 2.6594049156169453,
+    "train_runtime": 4231.9475,
+    "train_samples_per_second": 71.111,
+    "train_steps_per_second": 0.277
+}

stage2_7b/config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "point_patch_size": 512,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151670
+}

stage2_7b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9977671451355663,
+    "eval_loss": 2.343059778213501,
+    "eval_runtime": 20.0302,
+    "eval_samples_per_second": 263.602,
+    "eval_steps_per_second": 8.238
+}

stage2_7b/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.51.3"
+}

stage2_7b/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa871138c9f932642a8b39c206fb40d1b40eabc901008cf1558de7f6480b6a93
+size 4874836584

stage2_7b/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd60960618e5faa4a0b0f13b71d814a82db30f99a90a09182b2280fb5cca1bc3
+size 4932751008

stage2_7b/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde4257020df954bc23663453015f0c09789631186adfdd4a39694b30b9d3268
+size 4330865200

stage2_7b/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff9a55d14a343c9bcaf1b5387eb8221383d83cc6892611d37abbf9698557598
+size 1087170688

stage2_7b/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15225584640
+  },
+  "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"
+  }
+}

stage2_7b/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

stage2_7b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0753d5702df82d1b95a420b85e1d0087f2694c4698707a8c69ae45fc22da41f5
+size 11422839

stage2_7b/tokenizer_config.json

@@ -0,0 +1,249 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<pointcloud>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<point_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<layer_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<row_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</pointcloud>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

stage2_7b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9977671451355663,
+    "total_flos": 102874311622656.0,
+    "train_loss": 2.6594049156169453,
+    "train_runtime": 4231.9475,
+    "train_samples_per_second": 71.111,
+    "train_steps_per_second": 0.277
+}

stage2_7b/trainer_log.jsonl

@@ -0,0 +1,119 @@
+{"current_steps": 10, "total_steps": 1173, "loss": 13.0588, "lr": 1.1440677966101696e-06, "epoch": 0.025518341307814992, "percentage": 0.85, "elapsed_time": "0:00:40", "remaining_time": "1:17:32"}
+{"current_steps": 20, "total_steps": 1173, "loss": 11.6024, "lr": 2.4152542372881355e-06, "epoch": 0.051036682615629984, "percentage": 1.71, "elapsed_time": "0:01:14", "remaining_time": "1:11:44"}
+{"current_steps": 30, "total_steps": 1173, "loss": 9.677, "lr": 3.686440677966102e-06, "epoch": 0.07655502392344497, "percentage": 2.56, "elapsed_time": "0:01:49", "remaining_time": "1:09:21"}
+{"current_steps": 40, "total_steps": 1173, "loss": 7.5451, "lr": 4.957627118644068e-06, "epoch": 0.10207336523125997, "percentage": 3.41, "elapsed_time": "0:02:23", "remaining_time": "1:07:52"}
+{"current_steps": 50, "total_steps": 1173, "loss": 6.2001, "lr": 6.2288135593220344e-06, "epoch": 0.12759170653907495, "percentage": 4.26, "elapsed_time": "0:02:58", "remaining_time": "1:06:45"}
+{"current_steps": 60, "total_steps": 1173, "loss": 5.4325, "lr": 7.5e-06, "epoch": 0.15311004784688995, "percentage": 5.12, "elapsed_time": "0:03:32", "remaining_time": "1:05:50"}
+{"current_steps": 70, "total_steps": 1173, "loss": 4.8224, "lr": 8.771186440677966e-06, "epoch": 0.17862838915470494, "percentage": 5.97, "elapsed_time": "0:04:07", "remaining_time": "1:05:00"}
+{"current_steps": 80, "total_steps": 1173, "loss": 4.3397, "lr": 1.0042372881355933e-05, "epoch": 0.20414673046251994, "percentage": 6.82, "elapsed_time": "0:04:42", "remaining_time": "1:04:13"}
+{"current_steps": 90, "total_steps": 1173, "loss": 4.0637, "lr": 1.1313559322033899e-05, "epoch": 0.22966507177033493, "percentage": 7.67, "elapsed_time": "0:05:16", "remaining_time": "1:03:31"}
+{"current_steps": 100, "total_steps": 1173, "loss": 3.8254, "lr": 1.2584745762711864e-05, "epoch": 0.2551834130781499, "percentage": 8.53, "elapsed_time": "0:05:51", "remaining_time": "1:02:48"}
+{"current_steps": 110, "total_steps": 1173, "loss": 3.6752, "lr": 1.385593220338983e-05, "epoch": 0.2807017543859649, "percentage": 9.38, "elapsed_time": "0:06:25", "remaining_time": "1:02:06"}
+{"current_steps": 120, "total_steps": 1173, "loss": 3.5183, "lr": 1.4999966747387387e-05, "epoch": 0.3062200956937799, "percentage": 10.23, "elapsed_time": "0:07:00", "remaining_time": "1:01:26"}
+{"current_steps": 130, "total_steps": 1173, "loss": 3.4113, "lr": 1.4995976790645575e-05, "epoch": 0.3317384370015949, "percentage": 11.08, "elapsed_time": "0:07:34", "remaining_time": "1:00:46"}
+{"current_steps": 140, "total_steps": 1173, "loss": 3.3294, "lr": 1.4985340365156019e-05, "epoch": 0.3572567783094099, "percentage": 11.94, "elapsed_time": "0:08:08", "remaining_time": "1:00:07"}
+{"current_steps": 150, "total_steps": 1173, "loss": 3.2443, "lr": 1.496806690193372e-05, "epoch": 0.3827751196172249, "percentage": 12.79, "elapsed_time": "0:08:43", "remaining_time": "0:59:28"}
+{"current_steps": 160, "total_steps": 1173, "loss": 3.1948, "lr": 1.494417171686568e-05, "epoch": 0.4082934609250399, "percentage": 13.64, "elapsed_time": "0:09:17", "remaining_time": "0:58:50"}
+{"current_steps": 170, "total_steps": 1173, "loss": 3.1538, "lr": 1.4913675997130732e-05, "epoch": 0.43381180223285487, "percentage": 14.49, "elapsed_time": "0:09:52", "remaining_time": "0:58:13"}
+{"current_steps": 180, "total_steps": 1173, "loss": 3.0716, "lr": 1.4876606782413468e-05, "epoch": 0.45933014354066987, "percentage": 15.35, "elapsed_time": "0:10:26", "remaining_time": "0:57:36"}
+{"current_steps": 190, "total_steps": 1173, "loss": 3.038, "lr": 1.4832996940928936e-05, "epoch": 0.48484848484848486, "percentage": 16.2, "elapsed_time": "0:11:00", "remaining_time": "0:56:59"}
+{"current_steps": 200, "total_steps": 1173, "loss": 2.9772, "lr": 1.4782885140279318e-05, "epoch": 0.5103668261562998, "percentage": 17.05, "elapsed_time": "0:11:35", "remaining_time": "0:56:22"}
+{"current_steps": 210, "total_steps": 1173, "loss": 2.9469, "lr": 1.4726315813168478e-05, "epoch": 0.5358851674641149, "percentage": 17.9, "elapsed_time": "0:12:09", "remaining_time": "0:55:46"}
+{"current_steps": 220, "total_steps": 1173, "loss": 2.9032, "lr": 1.466333911800475e-05, "epoch": 0.5614035087719298, "percentage": 18.76, "elapsed_time": "0:12:44", "remaining_time": "0:55:10"}
+{"current_steps": 230, "total_steps": 1173, "loss": 2.8903, "lr": 1.4594010894426907e-05, "epoch": 0.5869218500797448, "percentage": 19.61, "elapsed_time": "0:13:18", "remaining_time": "0:54:34"}
+{"current_steps": 240, "total_steps": 1173, "loss": 2.8585, "lr": 1.4518392613792747e-05, "epoch": 0.6124401913875598, "percentage": 20.46, "elapsed_time": "0:13:53", "remaining_time": "0:53:59"}
+{"current_steps": 250, "total_steps": 1173, "loss": 2.8197, "lr": 1.4436551324674196e-05, "epoch": 0.6379585326953748, "percentage": 21.31, "elapsed_time": "0:14:27", "remaining_time": "0:53:23"}
+{"current_steps": 260, "total_steps": 1173, "loss": 2.7953, "lr": 1.4348559593407249e-05, "epoch": 0.6634768740031898, "percentage": 22.17, "elapsed_time": "0:15:02", "remaining_time": "0:52:47"}
+{"current_steps": 270, "total_steps": 1173, "loss": 2.7817, "lr": 1.4254495439749472e-05, "epoch": 0.6889952153110048, "percentage": 23.02, "elapsed_time": "0:15:36", "remaining_time": "0:52:12"}
+{"current_steps": 280, "total_steps": 1173, "loss": 2.7489, "lr": 1.4154442267702106e-05, "epoch": 0.7145135566188198, "percentage": 23.87, "elapsed_time": "0:16:12", "remaining_time": "0:51:40"}
+{"current_steps": 290, "total_steps": 1173, "loss": 2.7492, "lr": 1.4048488791558127e-05, "epoch": 0.7400318979266348, "percentage": 24.72, "elapsed_time": "0:16:46", "remaining_time": "0:51:05"}
+{"current_steps": 300, "total_steps": 1173, "loss": 2.7359, "lr": 1.3936728957241805e-05, "epoch": 0.7655502392344498, "percentage": 25.58, "elapsed_time": "0:17:21", "remaining_time": "0:50:30"}
+{"current_steps": 310, "total_steps": 1173, "loss": 2.682, "lr": 1.3819261859009536e-05, "epoch": 0.7910685805422647, "percentage": 26.43, "elapsed_time": "0:17:55", "remaining_time": "0:49:55"}
+{"current_steps": 320, "total_steps": 1173, "loss": 2.6693, "lr": 1.3696191651585793e-05, "epoch": 0.8165869218500797, "percentage": 27.28, "elapsed_time": "0:18:30", "remaining_time": "0:49:20"}
+{"current_steps": 330, "total_steps": 1173, "loss": 2.6371, "lr": 1.3567627457812107e-05, "epoch": 0.8421052631578947, "percentage": 28.13, "elapsed_time": "0:19:05", "remaining_time": "0:48:45"}
+{"current_steps": 340, "total_steps": 1173, "loss": 2.6105, "lr": 1.3433683271890945e-05, "epoch": 0.8676236044657097, "percentage": 28.99, "elapsed_time": "0:19:39", "remaining_time": "0:48:10"}
+{"current_steps": 350, "total_steps": 1173, "loss": 2.5997, "lr": 1.3294477858310318e-05, "epoch": 0.8931419457735247, "percentage": 29.84, "elapsed_time": "0:20:14", "remaining_time": "0:47:35"}
+{"current_steps": 360, "total_steps": 1173, "loss": 2.6038, "lr": 1.315013464653869e-05, "epoch": 0.9186602870813397, "percentage": 30.69, "elapsed_time": "0:20:48", "remaining_time": "0:47:00"}
+{"current_steps": 370, "total_steps": 1173, "loss": 2.5724, "lr": 1.300078162158359e-05, "epoch": 0.9441786283891547, "percentage": 31.54, "elapsed_time": "0:21:23", "remaining_time": "0:46:25"}
+{"current_steps": 380, "total_steps": 1173, "loss": 2.572, "lr": 1.2846551210510956e-05, "epoch": 0.9696969696969697, "percentage": 32.4, "elapsed_time": "0:21:58", "remaining_time": "0:45:51"}
+{"current_steps": 390, "total_steps": 1173, "loss": 2.5526, "lr": 1.2687580165025842e-05, "epoch": 0.9952153110047847, "percentage": 33.25, "elapsed_time": "0:22:33", "remaining_time": "0:45:16"}
+{"current_steps": 400, "total_steps": 1173, "loss": 2.6489, "lr": 1.2524009440218576e-05, "epoch": 1.0229665071770335, "percentage": 34.1, "elapsed_time": "0:23:09", "remaining_time": "0:44:44"}
+{"current_steps": 410, "total_steps": 1173, "loss": 2.3534, "lr": 1.2355984069583902e-05, "epoch": 1.0484848484848486, "percentage": 34.95, "elapsed_time": "0:23:43", "remaining_time": "0:44:09"}
+{"current_steps": 420, "total_steps": 1173, "loss": 2.3209, "lr": 1.218365303642392e-05, "epoch": 1.0740031897926634, "percentage": 35.81, "elapsed_time": "0:24:18", "remaining_time": "0:43:34"}
+{"current_steps": 430, "total_steps": 1173, "loss": 2.3114, "lr": 1.200716914174885e-05, "epoch": 1.0995215311004785, "percentage": 36.66, "elapsed_time": "0:24:53", "remaining_time": "0:43:00"}
+{"current_steps": 440, "total_steps": 1173, "loss": 2.3196, "lr": 1.1826688868792723e-05, "epoch": 1.1250398724082935, "percentage": 37.51, "elapsed_time": "0:25:27", "remaining_time": "0:42:25"}
+{"current_steps": 450, "total_steps": 1173, "loss": 2.2972, "lr": 1.1642372244264167e-05, "epoch": 1.1505582137161086, "percentage": 38.36, "elapsed_time": "0:26:02", "remaining_time": "0:41:50"}
+{"current_steps": 460, "total_steps": 1173, "loss": 2.2779, "lr": 1.1454382696455303e-05, "epoch": 1.1760765550239234, "percentage": 39.22, "elapsed_time": "0:26:37", "remaining_time": "0:41:15"}
+{"current_steps": 470, "total_steps": 1173, "loss": 2.2627, "lr": 1.126288691033452e-05, "epoch": 1.2015948963317384, "percentage": 40.07, "elapsed_time": "0:27:11", "remaining_time": "0:40:40"}
+{"current_steps": 480, "total_steps": 1173, "loss": 2.2969, "lr": 1.106805467975168e-05, "epoch": 1.2271132376395535, "percentage": 40.92, "elapsed_time": "0:27:46", "remaining_time": "0:40:05"}
+{"current_steps": 490, "total_steps": 1173, "loss": 2.2616, "lr": 1.087005875688676e-05, "epoch": 1.2526315789473683, "percentage": 41.77, "elapsed_time": "0:28:21", "remaining_time": "0:39:31"}
+{"current_steps": 500, "total_steps": 1173, "loss": 2.2511, "lr": 1.0669074699075414e-05, "epoch": 1.2781499202551834, "percentage": 42.63, "elapsed_time": "0:28:55", "remaining_time": "0:38:56"}
+{"current_steps": 510, "total_steps": 1173, "loss": 2.2503, "lr": 1.0465280713147303e-05, "epoch": 1.3036682615629984, "percentage": 43.48, "elapsed_time": "0:29:30", "remaining_time": "0:38:21"}
+{"current_steps": 520, "total_steps": 1173, "loss": 2.2372, "lr": 1.0258857497415165e-05, "epoch": 1.3291866028708135, "percentage": 44.33, "elapsed_time": "0:30:04", "remaining_time": "0:37:46"}
+{"current_steps": 530, "total_steps": 1173, "loss": 2.2551, "lr": 1.0049988081454802e-05, "epoch": 1.3547049441786285, "percentage": 45.18, "elapsed_time": "0:30:39", "remaining_time": "0:37:11"}
+{"current_steps": 540, "total_steps": 1173, "loss": 2.2482, "lr": 9.838857663817956e-06, "epoch": 1.3802232854864434, "percentage": 46.04, "elapsed_time": "0:31:14", "remaining_time": "0:36:37"}
+{"current_steps": 550, "total_steps": 1173, "loss": 2.2707, "lr": 9.625653447822052e-06, "epoch": 1.4057416267942584, "percentage": 46.89, "elapsed_time": "0:31:48", "remaining_time": "0:36:02"}
+{"current_steps": 560, "total_steps": 1173, "loss": 2.2295, "lr": 9.410564475562346e-06, "epoch": 1.4312599681020735, "percentage": 47.74, "elapsed_time": "0:32:23", "remaining_time": "0:35:27"}
+{"current_steps": 570, "total_steps": 1173, "loss": 2.1887, "lr": 9.193781460293695e-06, "epoch": 1.4567783094098883, "percentage": 48.59, "elapsed_time": "0:32:58", "remaining_time": "0:34:52"}
+{"current_steps": 580, "total_steps": 1173, "loss": 2.212, "lr": 8.975496617330568e-06, "epoch": 1.4822966507177033, "percentage": 49.45, "elapsed_time": "0:33:35", "remaining_time": "0:34:21"}
+{"current_steps": 590, "total_steps": 1173, "loss": 2.2421, "lr": 8.755903493615193e-06, "epoch": 1.5078149920255184, "percentage": 50.3, "elapsed_time": "0:34:10", "remaining_time": "0:33:46"}
+{"current_steps": 600, "total_steps": 1173, "loss": 2.2001, "lr": 8.535196796105018e-06, "epoch": 1.5333333333333332, "percentage": 51.15, "elapsed_time": "0:34:45", "remaining_time": "0:33:11"}
+{"current_steps": 610, "total_steps": 1173, "loss": 2.1919, "lr": 8.3135722191316e-06, "epoch": 1.5588516746411485, "percentage": 52.0, "elapsed_time": "0:35:19", "remaining_time": "0:32:36"}
+{"current_steps": 620, "total_steps": 1173, "loss": 2.181, "lr": 8.09122627088403e-06, "epoch": 1.5843700159489633, "percentage": 52.86, "elapsed_time": "0:35:54", "remaining_time": "0:32:01"}
+{"current_steps": 630, "total_steps": 1173, "loss": 2.2188, "lr": 7.868356099170721e-06, "epoch": 1.6098883572567781, "percentage": 53.71, "elapsed_time": "0:36:28", "remaining_time": "0:31:26"}
+{"current_steps": 640, "total_steps": 1173, "loss": 2.2191, "lr": 7.645159316614082e-06, "epoch": 1.6354066985645934, "percentage": 54.56, "elapsed_time": "0:37:03", "remaining_time": "0:30:51"}
+{"current_steps": 650, "total_steps": 1173, "loss": 2.1925, "lr": 7.421833825433035e-06, "epoch": 1.6609250398724082, "percentage": 55.41, "elapsed_time": "0:37:38", "remaining_time": "0:30:17"}
+{"current_steps": 660, "total_steps": 1173, "loss": 2.1633, "lr": 7.198577641968766e-06, "epoch": 1.6864433811802233, "percentage": 56.27, "elapsed_time": "0:38:12", "remaining_time": "0:29:42"}
+{"current_steps": 670, "total_steps": 1173, "loss": 2.1864, "lr": 6.97558872110929e-06, "epoch": 1.7119617224880384, "percentage": 57.12, "elapsed_time": "0:38:47", "remaining_time": "0:29:07"}
+{"current_steps": 680, "total_steps": 1173, "loss": 2.1915, "lr": 6.753064780768488e-06, "epoch": 1.7374800637958532, "percentage": 57.97, "elapsed_time": "0:39:22", "remaining_time": "0:28:32"}
+{"current_steps": 690, "total_steps": 1173, "loss": 2.1748, "lr": 6.5312031265752946e-06, "epoch": 1.7629984051036682, "percentage": 58.82, "elapsed_time": "0:39:56", "remaining_time": "0:27:57"}
+{"current_steps": 700, "total_steps": 1173, "loss": 2.1473, "lr": 6.310200476928403e-06, "epoch": 1.7885167464114833, "percentage": 59.68, "elapsed_time": "0:40:31", "remaining_time": "0:27:22"}
+{"current_steps": 710, "total_steps": 1173, "loss": 2.1668, "lr": 6.090252788571685e-06, "epoch": 1.8140350877192981, "percentage": 60.53, "elapsed_time": "0:41:05", "remaining_time": "0:26:48"}
+{"current_steps": 720, "total_steps": 1173, "loss": 2.1442, "lr": 5.87155508284494e-06, "epoch": 1.8395534290271134, "percentage": 61.38, "elapsed_time": "0:41:40", "remaining_time": "0:26:13"}
+{"current_steps": 730, "total_steps": 1173, "loss": 2.1346, "lr": 5.654301272764029e-06, "epoch": 1.8650717703349282, "percentage": 62.23, "elapsed_time": "0:42:15", "remaining_time": "0:25:38"}
+{"current_steps": 740, "total_steps": 1173, "loss": 2.1436, "lr": 5.438683991083748e-06, "epoch": 1.8905901116427433, "percentage": 63.09, "elapsed_time": "0:42:49", "remaining_time": "0:25:03"}
+{"current_steps": 750, "total_steps": 1173, "loss": 2.1523, "lr": 5.224894419495842e-06, "epoch": 1.9161084529505583, "percentage": 63.94, "elapsed_time": "0:43:24", "remaining_time": "0:24:28"}
+{"current_steps": 760, "total_steps": 1173, "loss": 2.1595, "lr": 5.013122119113674e-06, "epoch": 1.9416267942583731, "percentage": 64.79, "elapsed_time": "0:43:59", "remaining_time": "0:23:54"}
+{"current_steps": 770, "total_steps": 1173, "loss": 2.1328, "lr": 4.803554862393779e-06, "epoch": 1.9671451355661882, "percentage": 65.64, "elapsed_time": "0:44:33", "remaining_time": "0:23:19"}
+{"current_steps": 780, "total_steps": 1173, "loss": 2.1694, "lr": 4.596378466643397e-06, "epoch": 1.9926634768740032, "percentage": 66.5, "elapsed_time": "0:45:08", "remaining_time": "0:22:44"}
+{"current_steps": 790, "total_steps": 1173, "loss": 2.126, "lr": 4.391776629261555e-06, "epoch": 2.0204146730462518, "percentage": 67.35, "elapsed_time": "0:45:43", "remaining_time": "0:22:10"}
+{"current_steps": 800, "total_steps": 1173, "loss": 1.8096, "lr": 4.1899307648598355e-06, "epoch": 2.045933014354067, "percentage": 68.2, "elapsed_time": "0:46:18", "remaining_time": "0:21:35"}
+{"current_steps": 810, "total_steps": 1173, "loss": 1.7884, "lr": 3.991019844407206e-06, "epoch": 2.071451355661882, "percentage": 69.05, "elapsed_time": "0:46:52", "remaining_time": "0:21:00"}
+{"current_steps": 820, "total_steps": 1173, "loss": 1.802, "lr": 3.7952202365415787e-06, "epoch": 2.096969696969697, "percentage": 69.91, "elapsed_time": "0:47:26", "remaining_time": "0:20:25"}
+{"current_steps": 830, "total_steps": 1173, "loss": 1.7952, "lr": 3.602705551188764e-06, "epoch": 2.122488038277512, "percentage": 70.76, "elapsed_time": "0:48:01", "remaining_time": "0:19:50"}
+{"current_steps": 840, "total_steps": 1173, "loss": 1.7794, "lr": 3.4136464856275042e-06, "epoch": 2.148006379585327, "percentage": 71.61, "elapsed_time": "0:48:35", "remaining_time": "0:19:15"}
+{"current_steps": 850, "total_steps": 1173, "loss": 1.788, "lr": 3.228210673137064e-06, "epoch": 2.173524720893142, "percentage": 72.46, "elapsed_time": "0:49:09", "remaining_time": "0:18:40"}
+{"current_steps": 860, "total_steps": 1173, "loss": 1.8184, "lr": 3.0465625343615967e-06, "epoch": 2.199043062200957, "percentage": 73.32, "elapsed_time": "0:49:44", "remaining_time": "0:18:06"}
+{"current_steps": 870, "total_steps": 1173, "loss": 1.7802, "lr": 2.8688631315230326e-06, "epoch": 2.2245614035087717, "percentage": 74.17, "elapsed_time": "0:50:18", "remaining_time": "0:17:31"}
+{"current_steps": 880, "total_steps": 1173, "loss": 1.7664, "lr": 2.6952700256118117e-06, "epoch": 2.250079744816587, "percentage": 75.02, "elapsed_time": "0:50:53", "remaining_time": "0:16:56"}
+{"current_steps": 890, "total_steps": 1173, "loss": 1.8002, "lr": 2.5259371366820507e-06, "epoch": 2.275598086124402, "percentage": 75.87, "elapsed_time": "0:51:28", "remaining_time": "0:16:22"}
+{"current_steps": 900, "total_steps": 1173, "loss": 1.7763, "lr": 2.3610146073750176e-06, "epoch": 2.301116427432217, "percentage": 76.73, "elapsed_time": "0:52:02", "remaining_time": "0:15:47"}
+{"current_steps": 910, "total_steps": 1173, "loss": 1.7612, "lr": 2.200648669791939e-06, "epoch": 2.326634768740032, "percentage": 77.58, "elapsed_time": "0:52:37", "remaining_time": "0:15:12"}
+{"current_steps": 920, "total_steps": 1173, "loss": 1.7946, "lr": 2.044981515834167e-06, "epoch": 2.3521531100478468, "percentage": 78.43, "elapsed_time": "0:53:11", "remaining_time": "0:14:37"}
+{"current_steps": 930, "total_steps": 1173, "loss": 1.7869, "lr": 1.8941511711256728e-06, "epoch": 2.377671451355662, "percentage": 79.28, "elapsed_time": "0:53:45", "remaining_time": "0:14:02"}
+{"current_steps": 940, "total_steps": 1173, "loss": 1.7664, "lr": 1.7482913726296778e-06, "epoch": 2.403189792663477, "percentage": 80.14, "elapsed_time": "0:54:20", "remaining_time": "0:13:28"}
+{"current_steps": 950, "total_steps": 1173, "loss": 1.7834, "lr": 1.607531450067886e-06, "epoch": 2.4287081339712917, "percentage": 80.99, "elapsed_time": "0:54:54", "remaining_time": "0:12:53"}
+{"current_steps": 960, "total_steps": 1173, "loss": 1.7711, "lr": 1.4719962112475227e-06, "epoch": 2.454226475279107, "percentage": 81.84, "elapsed_time": "0:55:29", "remaining_time": "0:12:18"}
+{"current_steps": 970, "total_steps": 1173, "loss": 1.7727, "lr": 1.3418058313978064e-06, "epoch": 2.479744816586922, "percentage": 82.69, "elapsed_time": "0:56:03", "remaining_time": "0:11:43"}
+{"current_steps": 980, "total_steps": 1173, "loss": 1.7536, "lr": 1.2170757466140037e-06, "epoch": 2.5052631578947366, "percentage": 83.55, "elapsed_time": "0:56:38", "remaining_time": "0:11:09"}
+{"current_steps": 990, "total_steps": 1173, "loss": 1.7918, "lr": 1.0979165515035402e-06, "epoch": 2.530781499202552, "percentage": 84.4, "elapsed_time": "0:57:12", "remaining_time": "0:10:34"}
+{"current_steps": 1000, "total_steps": 1173, "loss": 1.7683, "lr": 9.844339011249114e-07, "epoch": 2.5562998405103667, "percentage": 85.25, "elapsed_time": "0:57:46", "remaining_time": "0:09:59"}
+{"current_steps": 1000, "total_steps": 1173, "eval_loss": 2.343059778213501, "epoch": 2.5562998405103667, "percentage": 85.25, "elapsed_time": "0:58:07", "remaining_time": "0:10:03"}
+{"current_steps": 1010, "total_steps": 1173, "loss": 1.7602, "lr": 8.767284173063628e-07, "epoch": 2.581818181818182, "percentage": 86.1, "elapsed_time": "0:59:13", "remaining_time": "0:09:33"}
+{"current_steps": 1020, "total_steps": 1173, "loss": 1.7623, "lr": 7.748955994273793e-07, "epoch": 2.607336523125997, "percentage": 86.96, "elapsed_time": "0:59:47", "remaining_time": "0:08:58"}
+{"current_steps": 1030, "total_steps": 1173, "loss": 1.7764, "lr": 6.790257397421221e-07, "epoch": 2.6328548644338117, "percentage": 87.81, "elapsed_time": "1:00:22", "remaining_time": "0:08:22"}
+{"current_steps": 1040, "total_steps": 1173, "loss": 1.7552, "lr": 5.892038433198463e-07, "epoch": 2.658373205741627, "percentage": 88.66, "elapsed_time": "1:00:56", "remaining_time": "0:07:47"}
+{"current_steps": 1050, "total_steps": 1173, "loss": 1.7624, "lr": 5.055095526733442e-07, "epoch": 2.6838915470494418, "percentage": 89.51, "elapsed_time": "1:01:30", "remaining_time": "0:07:12"}
+{"current_steps": 1060, "total_steps": 1173, "loss": 1.7642, "lr": 4.280170771421957e-07, "epoch": 2.709409888357257, "percentage": 90.37, "elapsed_time": "1:02:04", "remaining_time": "0:06:37"}
+{"current_steps": 1070, "total_steps": 1173, "loss": 1.7577, "lr": 3.5679512709346773e-07, "epoch": 2.734928229665072, "percentage": 91.22, "elapsed_time": "1:02:39", "remaining_time": "0:06:01"}
+{"current_steps": 1080, "total_steps": 1173, "loss": 1.7654, "lr": 2.919068529981894e-07, "epoch": 2.7604465709728867, "percentage": 92.07, "elapsed_time": "1:03:13", "remaining_time": "0:05:26"}
+{"current_steps": 1090, "total_steps": 1173, "loss": 1.761, "lr": 2.3340978943763164e-07, "epoch": 2.7859649122807015, "percentage": 92.92, "elapsed_time": "1:03:47", "remaining_time": "0:04:51"}
+{"current_steps": 1100, "total_steps": 1173, "loss": 1.7544, "lr": 1.8135580408903674e-07, "epoch": 2.811483253588517, "percentage": 93.78, "elapsed_time": "1:04:21", "remaining_time": "0:04:16"}
+{"current_steps": 1110, "total_steps": 1173, "loss": 1.7586, "lr": 1.357910517360264e-07, "epoch": 2.8370015948963316, "percentage": 94.63, "elapsed_time": "1:04:56", "remaining_time": "0:03:41"}
+{"current_steps": 1120, "total_steps": 1173, "loss": 1.7541, "lr": 9.675593334447674e-08, "epoch": 2.862519936204147, "percentage": 95.48, "elapsed_time": "1:05:30", "remaining_time": "0:03:05"}
+{"current_steps": 1130, "total_steps": 1173, "loss": 1.77, "lr": 6.428506024012904e-08, "epoch": 2.8880382775119617, "percentage": 96.33, "elapsed_time": "1:06:04", "remaining_time": "0:02:30"}
+{"current_steps": 1140, "total_steps": 1173, "loss": 1.7565, "lr": 3.840722341971664e-08, "epoch": 2.9135566188197766, "percentage": 97.19, "elapsed_time": "1:06:38", "remaining_time": "0:01:55"}
+{"current_steps": 1150, "total_steps": 1173, "loss": 1.7433, "lr": 1.914536802281208e-08, "epoch": 2.939074960127592, "percentage": 98.04, "elapsed_time": "1:07:13", "remaining_time": "0:01:20"}
+{"current_steps": 1160, "total_steps": 1173, "loss": 1.7701, "lr": 6.516572987022851e-09, "epoch": 2.9645933014354067, "percentage": 98.89, "elapsed_time": "1:07:47", "remaining_time": "0:00:45"}
+{"current_steps": 1170, "total_steps": 1173, "loss": 1.7531, "lr": 5.320359045882239e-10, "epoch": 2.990111642743222, "percentage": 99.74, "elapsed_time": "1:08:21", "remaining_time": "0:00:10"}
+{"current_steps": 1173, "total_steps": 1173, "epoch": 2.9977671451355663, "percentage": 100.0, "elapsed_time": "1:09:28", "remaining_time": "0:00:00"}

stage2_7b/trainer_state.json

@@ -0,0 +1,879 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 2.343059778213501,
+  "best_model_checkpoint": "saves/qwen2.5_3d/full/sft_7b_stage2/checkpoint-1000",
+  "epoch": 2.9977671451355663,
+  "eval_steps": 1000,
+  "global_step": 1173,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025518341307814992,
+      "grad_norm": 41.38909683442534,
+      "learning_rate": 1.1440677966101696e-06,
+      "loss": 13.0588,
+      "step": 10
+    },
+    {
+      "epoch": 0.051036682615629984,
+      "grad_norm": 24.45025201744234,
+      "learning_rate": 2.4152542372881355e-06,
+      "loss": 11.6024,
+      "step": 20
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 8.918549090671922,
+      "learning_rate": 3.686440677966102e-06,
+      "loss": 9.677,
+      "step": 30
+    },
+    {
+      "epoch": 0.10207336523125997,
+      "grad_norm": 5.740463305990162,
+      "learning_rate": 4.957627118644068e-06,
+      "loss": 7.5451,
+      "step": 40
+    },
+    {
+      "epoch": 0.12759170653907495,
+      "grad_norm": 4.261996908905627,
+      "learning_rate": 6.2288135593220344e-06,
+      "loss": 6.2001,
+      "step": 50
+    },
+    {
+      "epoch": 0.15311004784688995,
+      "grad_norm": 2.9963531250158075,
+      "learning_rate": 7.5e-06,
+      "loss": 5.4325,
+      "step": 60
+    },
+    {
+      "epoch": 0.17862838915470494,
+      "grad_norm": 2.452719493622236,
+      "learning_rate": 8.771186440677966e-06,
+      "loss": 4.8224,
+      "step": 70
+    },
+    {
+      "epoch": 0.20414673046251994,
+      "grad_norm": 2.296924769718695,
+      "learning_rate": 1.0042372881355933e-05,
+      "loss": 4.3397,
+      "step": 80
+    },
+    {
+      "epoch": 0.22966507177033493,
+      "grad_norm": 2.02789705030659,
+      "learning_rate": 1.1313559322033899e-05,
+      "loss": 4.0637,
+      "step": 90
+    },
+    {
+      "epoch": 0.2551834130781499,
+      "grad_norm": 2.0102538064720865,
+      "learning_rate": 1.2584745762711864e-05,
+      "loss": 3.8254,
+      "step": 100
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.9988271290927235,
+      "learning_rate": 1.385593220338983e-05,
+      "loss": 3.6752,
+      "step": 110
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 1.9671546379874392,
+      "learning_rate": 1.4999966747387387e-05,
+      "loss": 3.5183,
+      "step": 120
+    },
+    {
+      "epoch": 0.3317384370015949,
+      "grad_norm": 2.3495671945712764,
+      "learning_rate": 1.4995976790645575e-05,
+      "loss": 3.4113,
+      "step": 130
+    },
+    {
+      "epoch": 0.3572567783094099,
+      "grad_norm": 2.4845114503377284,
+      "learning_rate": 1.4985340365156019e-05,
+      "loss": 3.3294,
+      "step": 140
+    },
+    {
+      "epoch": 0.3827751196172249,
+      "grad_norm": 2.2685356609887966,
+      "learning_rate": 1.496806690193372e-05,
+      "loss": 3.2443,
+      "step": 150
+    },
+    {
+      "epoch": 0.4082934609250399,
+      "grad_norm": 1.8552414857417485,
+      "learning_rate": 1.494417171686568e-05,
+      "loss": 3.1948,
+      "step": 160
+    },
+    {
+      "epoch": 0.43381180223285487,
+      "grad_norm": 2.5986726068440635,
+      "learning_rate": 1.4913675997130732e-05,
+      "loss": 3.1538,
+      "step": 170
+    },
+    {
+      "epoch": 0.45933014354066987,
+      "grad_norm": 2.3542672335324646,
+      "learning_rate": 1.4876606782413468e-05,
+      "loss": 3.0716,
+      "step": 180
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.1550658582198516,
+      "learning_rate": 1.4832996940928936e-05,
+      "loss": 3.038,
+      "step": 190
+    },
+    {
+      "epoch": 0.5103668261562998,
+      "grad_norm": 2.1753949765417206,
+      "learning_rate": 1.4782885140279318e-05,
+      "loss": 2.9772,
+      "step": 200
+    },
+    {
+      "epoch": 0.5358851674641149,
+      "grad_norm": 1.9692819011886733,
+      "learning_rate": 1.4726315813168478e-05,
+      "loss": 2.9469,
+      "step": 210
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 1.833984536566349,
+      "learning_rate": 1.466333911800475e-05,
+      "loss": 2.9032,
+      "step": 220
+    },
+    {
+      "epoch": 0.5869218500797448,
+      "grad_norm": 2.021073458068275,
+      "learning_rate": 1.4594010894426907e-05,
+      "loss": 2.8903,
+      "step": 230
+    },
+    {
+      "epoch": 0.6124401913875598,
+      "grad_norm": 1.8342599659729268,
+      "learning_rate": 1.4518392613792747e-05,
+      "loss": 2.8585,
+      "step": 240
+    },
+    {
+      "epoch": 0.6379585326953748,
+      "grad_norm": 1.8015476338333145,
+      "learning_rate": 1.4436551324674196e-05,
+      "loss": 2.8197,
+      "step": 250
+    },
+    {
+      "epoch": 0.6634768740031898,
+      "grad_norm": 1.774909204385973,
+      "learning_rate": 1.4348559593407249e-05,
+      "loss": 2.7953,
+      "step": 260
+    },
+    {
+      "epoch": 0.6889952153110048,
+      "grad_norm": 1.913402588745503,
+      "learning_rate": 1.4254495439749472e-05,
+      "loss": 2.7817,
+      "step": 270
+    },
+    {
+      "epoch": 0.7145135566188198,
+      "grad_norm": 1.8231676178000666,
+      "learning_rate": 1.4154442267702106e-05,
+      "loss": 2.7489,
+      "step": 280
+    },
+    {
+      "epoch": 0.7400318979266348,
+      "grad_norm": 1.8647896227394318,
+      "learning_rate": 1.4048488791558127e-05,
+      "loss": 2.7492,
+      "step": 290
+    },
+    {
+      "epoch": 0.7655502392344498,
+      "grad_norm": 1.7710269150416975,
+      "learning_rate": 1.3936728957241805e-05,
+      "loss": 2.7359,
+      "step": 300
+    },
+    {
+      "epoch": 0.7910685805422647,
+      "grad_norm": 1.7971354575124974,
+      "learning_rate": 1.3819261859009536e-05,
+      "loss": 2.682,
+      "step": 310
+    },
+    {
+      "epoch": 0.8165869218500797,
+      "grad_norm": 1.8543518497527265,
+      "learning_rate": 1.3696191651585793e-05,
+      "loss": 2.6693,
+      "step": 320
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 1.671172953201345,
+      "learning_rate": 1.3567627457812107e-05,
+      "loss": 2.6371,
+      "step": 330
+    },
+    {
+      "epoch": 0.8676236044657097,
+      "grad_norm": 1.793308965007255,
+      "learning_rate": 1.3433683271890945e-05,
+      "loss": 2.6105,
+      "step": 340
+    },
+    {
+      "epoch": 0.8931419457735247,
+      "grad_norm": 1.702891636275614,
+      "learning_rate": 1.3294477858310318e-05,
+      "loss": 2.5997,
+      "step": 350
+    },
+    {
+      "epoch": 0.9186602870813397,
+      "grad_norm": 1.8004220505203588,
+      "learning_rate": 1.315013464653869e-05,
+      "loss": 2.6038,
+      "step": 360
+    },
+    {
+      "epoch": 0.9441786283891547,
+      "grad_norm": 1.6762412987987798,
+      "learning_rate": 1.300078162158359e-05,
+      "loss": 2.5724,
+      "step": 370
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.8651248798134779,
+      "learning_rate": 1.2846551210510956e-05,
+      "loss": 2.572,
+      "step": 380
+    },
+    {
+      "epoch": 0.9952153110047847,
+      "grad_norm": 1.8166685018367434,
+      "learning_rate": 1.2687580165025842e-05,
+      "loss": 2.5526,
+      "step": 390
+    },
+    {
+      "epoch": 1.0229665071770335,
+      "grad_norm": 1.9595305580742408,
+      "learning_rate": 1.2524009440218576e-05,
+      "loss": 2.6489,
+      "step": 400
+    },
+    {
+      "epoch": 1.0484848484848486,
+      "grad_norm": 1.9448735030077777,
+      "learning_rate": 1.2355984069583902e-05,
+      "loss": 2.3534,
+      "step": 410
+    },
+    {
+      "epoch": 1.0740031897926634,
+      "grad_norm": 1.9568519341241308,
+      "learning_rate": 1.218365303642392e-05,
+      "loss": 2.3209,
+      "step": 420
+    },
+    {
+      "epoch": 1.0995215311004785,
+      "grad_norm": 1.97257201705927,
+      "learning_rate": 1.200716914174885e-05,
+      "loss": 2.3114,
+      "step": 430
+    },
+    {
+      "epoch": 1.1250398724082935,
+      "grad_norm": 2.0078778706593234,
+      "learning_rate": 1.1826688868792723e-05,
+      "loss": 2.3196,
+      "step": 440
+    },
+    {
+      "epoch": 1.1505582137161086,
+      "grad_norm": 1.9231486716564377,
+      "learning_rate": 1.1642372244264167e-05,
+      "loss": 2.2972,
+      "step": 450
+    },
+    {
+      "epoch": 1.1760765550239234,
+      "grad_norm": 1.9501054668769524,
+      "learning_rate": 1.1454382696455303e-05,
+      "loss": 2.2779,
+      "step": 460
+    },
+    {
+      "epoch": 1.2015948963317384,
+      "grad_norm": 1.8856831931474254,
+      "learning_rate": 1.126288691033452e-05,
+      "loss": 2.2627,
+      "step": 470
+    },
+    {
+      "epoch": 1.2271132376395535,
+      "grad_norm": 2.0213311293812573,
+      "learning_rate": 1.106805467975168e-05,
+      "loss": 2.2969,
+      "step": 480
+    },
+    {
+      "epoch": 1.2526315789473683,
+      "grad_norm": 1.9724633188826075,
+      "learning_rate": 1.087005875688676e-05,
+      "loss": 2.2616,
+      "step": 490
+    },
+    {
+      "epoch": 1.2781499202551834,
+      "grad_norm": 2.02716350744511,
+      "learning_rate": 1.0669074699075414e-05,
+      "loss": 2.2511,
+      "step": 500
+    },
+    {
+      "epoch": 1.3036682615629984,
+      "grad_norm": 2.0652621663353803,
+      "learning_rate": 1.0465280713147303e-05,
+      "loss": 2.2503,
+      "step": 510
+    },
+    {
+      "epoch": 1.3291866028708135,
+      "grad_norm": 2.033130261702073,
+      "learning_rate": 1.0258857497415165e-05,
+      "loss": 2.2372,
+      "step": 520
+    },
+    {
+      "epoch": 1.3547049441786285,
+      "grad_norm": 2.056888858914891,
+      "learning_rate": 1.0049988081454802e-05,
+      "loss": 2.2551,
+      "step": 530
+    },
+    {
+      "epoch": 1.3802232854864434,
+      "grad_norm": 2.0022262070955525,
+      "learning_rate": 9.838857663817956e-06,
+      "loss": 2.2482,
+      "step": 540
+    },
+    {
+      "epoch": 1.4057416267942584,
+      "grad_norm": 2.078167028605348,
+      "learning_rate": 9.625653447822052e-06,
+      "loss": 2.2707,
+      "step": 550
+    },
+    {
+      "epoch": 1.4312599681020735,
+      "grad_norm": 2.126752097583203,
+      "learning_rate": 9.410564475562346e-06,
+      "loss": 2.2295,
+      "step": 560
+    },
+    {
+      "epoch": 1.4567783094098883,
+      "grad_norm": 1.9806408754738973,
+      "learning_rate": 9.193781460293695e-06,
+      "loss": 2.1887,
+      "step": 570
+    },
+    {
+      "epoch": 1.4822966507177033,
+      "grad_norm": 2.0059818507445715,
+      "learning_rate": 8.975496617330568e-06,
+      "loss": 2.212,
+      "step": 580
+    },
+    {
+      "epoch": 1.5078149920255184,
+      "grad_norm": 1.958138514087202,
+      "learning_rate": 8.755903493615193e-06,
+      "loss": 2.2421,
+      "step": 590
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 1.9444870040248599,
+      "learning_rate": 8.535196796105018e-06,
+      "loss": 2.2001,
+      "step": 600
+    },
+    {
+      "epoch": 1.5588516746411485,
+      "grad_norm": 2.0790121588452677,
+      "learning_rate": 8.3135722191316e-06,
+      "loss": 2.1919,
+      "step": 610
+    },
+    {
+      "epoch": 1.5843700159489633,
+      "grad_norm": 2.09803077018995,
+      "learning_rate": 8.09122627088403e-06,
+      "loss": 2.181,
+      "step": 620
+    },
+    {
+      "epoch": 1.6098883572567781,
+      "grad_norm": 2.103389635373312,
+      "learning_rate": 7.868356099170721e-06,
+      "loss": 2.2188,
+      "step": 630
+    },
+    {
+      "epoch": 1.6354066985645934,
+      "grad_norm": 2.2123492409708,
+      "learning_rate": 7.645159316614082e-06,
+      "loss": 2.2191,
+      "step": 640
+    },
+    {
+      "epoch": 1.6609250398724082,
+      "grad_norm": 2.023742495950975,
+      "learning_rate": 7.421833825433035e-06,
+      "loss": 2.1925,
+      "step": 650
+    },
+    {
+      "epoch": 1.6864433811802233,
+      "grad_norm": 2.0082728157794567,
+      "learning_rate": 7.198577641968766e-06,
+      "loss": 2.1633,
+      "step": 660
+    },
+    {
+      "epoch": 1.7119617224880384,
+      "grad_norm": 2.1289624844092665,
+      "learning_rate": 6.97558872110929e-06,
+      "loss": 2.1864,
+      "step": 670
+    },
+    {
+      "epoch": 1.7374800637958532,
+      "grad_norm": 2.0363999925653395,
+      "learning_rate": 6.753064780768488e-06,
+      "loss": 2.1915,
+      "step": 680
+    },
+    {
+      "epoch": 1.7629984051036682,
+      "grad_norm": 2.1325211739700323,
+      "learning_rate": 6.5312031265752946e-06,
+      "loss": 2.1748,
+      "step": 690
+    },
+    {
+      "epoch": 1.7885167464114833,
+      "grad_norm": 2.073383778430727,
+      "learning_rate": 6.310200476928403e-06,
+      "loss": 2.1473,
+      "step": 700
+    },
+    {
+      "epoch": 1.8140350877192981,
+      "grad_norm": 2.0597448767291557,
+      "learning_rate": 6.090252788571685e-06,
+      "loss": 2.1668,
+      "step": 710
+    },
+    {
+      "epoch": 1.8395534290271134,
+      "grad_norm": 2.0432434933668033,
+      "learning_rate": 5.87155508284494e-06,
+      "loss": 2.1442,
+      "step": 720
+    },
+    {
+      "epoch": 1.8650717703349282,
+      "grad_norm": 2.0612494703787,
+      "learning_rate": 5.654301272764029e-06,
+      "loss": 2.1346,
+      "step": 730
+    },
+    {
+      "epoch": 1.8905901116427433,
+      "grad_norm": 2.0948535247185496,
+      "learning_rate": 5.438683991083748e-06,
+      "loss": 2.1436,
+      "step": 740
+    },
+    {
+      "epoch": 1.9161084529505583,
+      "grad_norm": 2.085105020269672,
+      "learning_rate": 5.224894419495842e-06,
+      "loss": 2.1523,
+      "step": 750
+    },
+    {
+      "epoch": 1.9416267942583731,
+      "grad_norm": 1.990712509803804,
+      "learning_rate": 5.013122119113674e-06,
+      "loss": 2.1595,
+      "step": 760
+    },
+    {
+      "epoch": 1.9671451355661882,
+      "grad_norm": 2.0676031547838565,
+      "learning_rate": 4.803554862393779e-06,
+      "loss": 2.1328,
+      "step": 770
+    },
+    {
+      "epoch": 1.9926634768740032,
+      "grad_norm": 2.0958105821364095,
+      "learning_rate": 4.596378466643397e-06,
+      "loss": 2.1694,
+      "step": 780
+    },
+    {
+      "epoch": 2.0204146730462518,
+      "grad_norm": 2.3390863338233348,
+      "learning_rate": 4.391776629261555e-06,
+      "loss": 2.126,
+      "step": 790
+    },
+    {
+      "epoch": 2.045933014354067,
+      "grad_norm": 2.168148536310652,
+      "learning_rate": 4.1899307648598355e-06,
+      "loss": 1.8096,
+      "step": 800
+    },
+    {
+      "epoch": 2.071451355661882,
+      "grad_norm": 2.107040319291286,
+      "learning_rate": 3.991019844407206e-06,
+      "loss": 1.7884,
+      "step": 810
+    },
+    {
+      "epoch": 2.096969696969697,
+      "grad_norm": 2.3752722791144096,
+      "learning_rate": 3.7952202365415787e-06,
+      "loss": 1.802,
+      "step": 820
+    },
+    {
+      "epoch": 2.122488038277512,
+      "grad_norm": 2.2622817947741636,
+      "learning_rate": 3.602705551188764e-06,
+      "loss": 1.7952,
+      "step": 830
+    },
+    {
+      "epoch": 2.148006379585327,
+      "grad_norm": 2.2685137603537058,
+      "learning_rate": 3.4136464856275042e-06,
+      "loss": 1.7794,
+      "step": 840
+    },
+    {
+      "epoch": 2.173524720893142,
+      "grad_norm": 2.3902445863895094,
+      "learning_rate": 3.228210673137064e-06,
+      "loss": 1.788,
+      "step": 850
+    },
+    {
+      "epoch": 2.199043062200957,
+      "grad_norm": 2.3611950118719314,
+      "learning_rate": 3.0465625343615967e-06,
+      "loss": 1.8184,
+      "step": 860
+    },
+    {
+      "epoch": 2.2245614035087717,
+      "grad_norm": 2.3628012509214322,
+      "learning_rate": 2.8688631315230326e-06,
+      "loss": 1.7802,
+      "step": 870
+    },
+    {
+      "epoch": 2.250079744816587,
+      "grad_norm": 2.274090723203016,
+      "learning_rate": 2.6952700256118117e-06,
+      "loss": 1.7664,
+      "step": 880
+    },
+    {
+      "epoch": 2.275598086124402,
+      "grad_norm": 2.4526876937461646,
+      "learning_rate": 2.5259371366820507e-06,
+      "loss": 1.8002,
+      "step": 890
+    },
+    {
+      "epoch": 2.301116427432217,
+      "grad_norm": 2.3336921883837616,
+      "learning_rate": 2.3610146073750176e-06,
+      "loss": 1.7763,
+      "step": 900
+    },
+    {
+      "epoch": 2.326634768740032,
+      "grad_norm": 2.271646264284567,
+      "learning_rate": 2.200648669791939e-06,
+      "loss": 1.7612,
+      "step": 910
+    },
+    {
+      "epoch": 2.3521531100478468,
+      "grad_norm": 2.4913302090031952,
+      "learning_rate": 2.044981515834167e-06,
+      "loss": 1.7946,
+      "step": 920
+    },
+    {
+      "epoch": 2.377671451355662,
+      "grad_norm": 2.439411059369649,
+      "learning_rate": 1.8941511711256728e-06,
+      "loss": 1.7869,
+      "step": 930
+    },
+    {
+      "epoch": 2.403189792663477,
+      "grad_norm": 2.3140599984104138,
+      "learning_rate": 1.7482913726296778e-06,
+      "loss": 1.7664,
+      "step": 940
+    },
+    {
+      "epoch": 2.4287081339712917,
+      "grad_norm": 2.500843401322422,
+      "learning_rate": 1.607531450067886e-06,
+      "loss": 1.7834,
+      "step": 950
+    },
+    {
+      "epoch": 2.454226475279107,
+      "grad_norm": 2.4192381369051033,
+      "learning_rate": 1.4719962112475227e-06,
+      "loss": 1.7711,
+      "step": 960
+    },
+    {
+      "epoch": 2.479744816586922,
+      "grad_norm": 2.381315270199767,
+      "learning_rate": 1.3418058313978064e-06,
+      "loss": 1.7727,
+      "step": 970
+    },
+    {
+      "epoch": 2.5052631578947366,
+      "grad_norm": 2.4411828126850454,
+      "learning_rate": 1.2170757466140037e-06,
+      "loss": 1.7536,
+      "step": 980
+    },
+    {
+      "epoch": 2.530781499202552,
+      "grad_norm": 2.4714371413125504,
+      "learning_rate": 1.0979165515035402e-06,
+      "loss": 1.7918,
+      "step": 990
+    },
+    {
+      "epoch": 2.5562998405103667,
+      "grad_norm": 2.3600482331288557,
+      "learning_rate": 9.844339011249114e-07,
+      "loss": 1.7683,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5562998405103667,
+      "eval_loss": 2.343059778213501,
+      "eval_runtime": 20.7074,
+      "eval_samples_per_second": 254.982,
+      "eval_steps_per_second": 7.968,
+      "step": 1000
+    },
+    {
+      "epoch": 2.581818181818182,
+      "grad_norm": 2.42847050890942,
+      "learning_rate": 8.767284173063628e-07,
+      "loss": 1.7602,
+      "step": 1010
+    },
+    {
+      "epoch": 2.607336523125997,
+      "grad_norm": 2.495286470584022,
+      "learning_rate": 7.748955994273793e-07,
+      "loss": 1.7623,
+      "step": 1020
+    },
+    {
+      "epoch": 2.6328548644338117,
+      "grad_norm": 2.380920410548109,
+      "learning_rate": 6.790257397421221e-07,
+      "loss": 1.7764,
+      "step": 1030
+    },
+    {
+      "epoch": 2.658373205741627,
+      "grad_norm": 2.4026078375726305,
+      "learning_rate": 5.892038433198463e-07,
+      "loss": 1.7552,
+      "step": 1040
+    },
+    {
+      "epoch": 2.6838915470494418,
+      "grad_norm": 2.4208779504436673,
+      "learning_rate": 5.055095526733442e-07,
+      "loss": 1.7624,
+      "step": 1050
+    },
+    {
+      "epoch": 2.709409888357257,
+      "grad_norm": 2.349970978991061,
+      "learning_rate": 4.280170771421957e-07,
+      "loss": 1.7642,
+      "step": 1060
+    },
+    {
+      "epoch": 2.734928229665072,
+      "grad_norm": 2.3526689883363248,
+      "learning_rate": 3.5679512709346773e-07,
+      "loss": 1.7577,
+      "step": 1070
+    },
+    {
+      "epoch": 2.7604465709728867,
+      "grad_norm": 2.450274730203489,
+      "learning_rate": 2.919068529981894e-07,
+      "loss": 1.7654,
+      "step": 1080
+    },
+    {
+      "epoch": 2.7859649122807015,
+      "grad_norm": 2.3651571766241246,
+      "learning_rate": 2.3340978943763164e-07,
+      "loss": 1.761,
+      "step": 1090
+    },
+    {
+      "epoch": 2.811483253588517,
+      "grad_norm": 2.404642620983574,
+      "learning_rate": 1.8135580408903674e-07,
+      "loss": 1.7544,
+      "step": 1100
+    },
+    {
+      "epoch": 2.8370015948963316,
+      "grad_norm": 2.473317448160841,
+      "learning_rate": 1.357910517360264e-07,
+      "loss": 1.7586,
+      "step": 1110
+    },
+    {
+      "epoch": 2.862519936204147,
+      "grad_norm": 2.325829716379361,
+      "learning_rate": 9.675593334447674e-08,
+      "loss": 1.7541,
+      "step": 1120
+    },
+    {
+      "epoch": 2.8880382775119617,
+      "grad_norm": 2.430438279086189,
+      "learning_rate": 6.428506024012904e-08,
+      "loss": 1.77,
+      "step": 1130
+    },
+    {
+      "epoch": 2.9135566188197766,
+      "grad_norm": 2.3903497741918414,
+      "learning_rate": 3.840722341971664e-08,
+      "loss": 1.7565,
+      "step": 1140
+    },
+    {
+      "epoch": 2.939074960127592,
+      "grad_norm": 2.3801298605080023,
+      "learning_rate": 1.914536802281208e-08,
+      "loss": 1.7433,
+      "step": 1150
+    },
+    {
+      "epoch": 2.9645933014354067,
+      "grad_norm": 2.364114165792993,
+      "learning_rate": 6.516572987022851e-09,
+      "loss": 1.7701,
+      "step": 1160
+    },
+    {
+      "epoch": 2.990111642743222,
+      "grad_norm": 2.2932824036528032,
+      "learning_rate": 5.320359045882239e-10,
+      "loss": 1.7531,
+      "step": 1170
+    },
+    {
+      "epoch": 2.9977671451355663,
+      "step": 1173,
+      "total_flos": 102874311622656.0,
+      "train_loss": 2.6594049156169453,
+      "train_runtime": 4231.9475,
+      "train_samples_per_second": 71.111,
+      "train_steps_per_second": 0.277
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1173,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3000,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 102874311622656.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

stage2_7b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c337e674550f83bafb07bd7bc9a20b10ee3ba3107a1031a643397933ee4e26
+size 7544