Hugging Face's logo

tanliboy
/
lambda-qwen2.5-14b-dpo-test

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
tanliboy commited on
Commit
5d863b5
•
1 Parent(s): 3ea4ec1

Model save

Browse files
Files changed (21) hide show
  1. README.md +77 -0
  2. added_tokens.json +24 -0
  3. all_results.json +9 -0
  4. config.json +28 -0
  5. generation_config.json +14 -0
  6. merges.txt +0 -0
  7. model-00001-of-00006.safetensors +3 -0
  8. model-00002-of-00006.safetensors +3 -0
  9. model-00003-of-00006.safetensors +3 -0
  10. model-00004-of-00006.safetensors +3 -0
  11. model-00005-of-00006.safetensors +3 -0
  12. model-00006-of-00006.safetensors +3 -0
  13. model.safetensors.index.json +586 -0
  14. runs/Sep20_06-57-19_action-graph-trainer/events.out.tfevents.1726816203.action-graph-trainer.2950951.0 +3 -0
  15. special_tokens_map.json +31 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +207 -0
  18. train_results.json +9 -0
  19. trainer_state.json +826 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-14B-Instruct
5
+ tags:
6
+ - trl
7
+ - dpo
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: lambda-qwen2.5-14b-dpo-test
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # lambda-qwen2.5-14b-dpo-test
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4924
22
+ - Rewards/chosen: -2.4470
23
+ - Rewards/rejected: -3.3410
24
+ - Rewards/accuracies: 0.7400
25
+ - Rewards/margins: 0.8939
26
+ - Logps/rejected: -828.8748
27
+ - Logps/chosen: -734.7765
28
+ - Logits/rejected: -1.2644
29
+ - Logits/chosen: -1.2477
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-07
49
+ - train_batch_size: 2
50
+ - eval_batch_size: 2
51
+ - seed: 42
52
+ - distributed_type: multi-GPU
53
+ - num_devices: 8
54
+ - gradient_accumulation_steps: 8
55
+ - total_train_batch_size: 128
56
+ - total_eval_batch_size: 16
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: cosine
59
+ - lr_scheduler_warmup_ratio: 0.1
60
+ - num_epochs: 1
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.5269 | 0.2094 | 100 | 0.5333 | -1.6756 | -2.3320 | 0.7000 | 0.6564 | -727.9815 | -657.6356 | -1.3952 | -1.3850 |
67
+ | 0.5086 | 0.4187 | 200 | 0.5044 | -2.0906 | -2.9287 | 0.7040 | 0.8381 | -787.6511 | -699.1298 | -1.2939 | -1.2773 |
68
+ | 0.4787 | 0.6281 | 300 | 0.4948 | -2.2927 | -3.1689 | 0.7320 | 0.8762 | -811.6696 | -719.3386 | -1.2846 | -1.2646 |
69
+ | 0.4825 | 0.8375 | 400 | 0.4924 | -2.4470 | -3.3410 | 0.7400 | 0.8939 | -828.8748 | -734.7765 | -1.2644 | -1.2477 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.44.2
75
+ - Pytorch 2.4.0+cu121
76
+ - Datasets 2.19.1
77
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5192520058629898,
5
+ "train_runtime": 13862.6582,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 4.41,
8
+ "train_steps_per_second": 0.034
9
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.44.2",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.44.2"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516da4aaa4518af2039ac34b5653107ffda5aba90ef9dec3e957335c0b7e75bc
3
+ size 4986211280
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa0837e704042e5770ce3cca698dfafc8d6fa003a4aa097ee8db12ebaa00879
3
+ size 4954847344
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84220f70f94e23397e59ef603b18c43769ec1f2ee6a257147b03f9a6e2aca494
3
+ size 4954847392
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba462440c51912e635fb74132784d6aeb6226047db401c0fa7b1eae517cfd88
3
+ size 4954847392
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898a58dcfe34a5c6fa1b9203fcb36f937f7cde0cbff1c38ee18c4b6c25a6d992
3
+ size 4954847392
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472e4bfc245413b2cd381b8e9affbd7455daa36b1d52fd6d68ed1153475378a1
3
+ size 4734533160
model.safetensors.index.json ADDED
@@ -0,0 +1,586 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29540067328
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
524
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
525
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
526
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
527
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
528
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
529
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
530
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
531
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
532
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
533
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
534
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
535
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
536
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
537
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
538
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
539
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
540
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
541
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
542
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
543
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
544
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
545
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
546
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
547
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
548
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
549
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
550
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
551
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
552
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
553
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
554
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
555
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
556
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
557
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
558
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
559
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
560
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
561
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
562
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
563
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
564
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
565
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
566
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
567
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
568
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
569
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
570
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
571
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
572
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
573
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
574
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
575
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
576
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
577
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
578
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
579
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
580
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
581
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
582
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
583
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
584
+ "model.norm.weight": "model-00006-of-00006.safetensors"
585
+ }
586
+ }
runs/Sep20_06-57-19_action-graph-trainer/events.out.tfevents.1726816203.action-graph-trainer.2950951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5089daf60354357e57d5b98865cb27cdbf35902a0300b6d3c96dcd5ca9e309f5
3
+ size 42423
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "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",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 2048,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5192520058629898,
5
+ "train_runtime": 13862.6582,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 4.41,
8
+ "train_steps_per_second": 0.034
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,826 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.998691442030882,
5
+ "eval_steps": 100,
6
+ "global_step": 477,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002093692750588851,
13
+ "grad_norm": 5.344821351720907,
14
+ "learning_rate": 1.0416666666666666e-08,
15
+ "logits/chosen": -0.9863196015357971,
16
+ "logits/rejected": -1.0256754159927368,
17
+ "logps/chosen": -474.4989013671875,
18
+ "logps/rejected": -524.1282958984375,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 6.122277210971997,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -1.199143886566162,
31
+ "logits/rejected": -1.211472749710083,
32
+ "logps/chosen": -504.70758056640625,
33
+ "logps/rejected": -517.0758666992188,
34
+ "loss": 0.6927,
35
+ "rewards/accuracies": 0.4930555522441864,
36
+ "rewards/chosen": -2.0182769731036387e-05,
37
+ "rewards/margins": 0.0008512942586094141,
38
+ "rewards/rejected": -0.0008714771247468889,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04187385501177702,
43
+ "grad_norm": 6.385948578335296,
44
+ "learning_rate": 2.0833333333333333e-07,
45
+ "logits/chosen": -1.1590700149536133,
46
+ "logits/rejected": -1.1333811283111572,
47
+ "logps/chosen": -488.711669921875,
48
+ "logps/rejected": -505.6346130371094,
49
+ "loss": 0.6921,
50
+ "rewards/accuracies": 0.5375000238418579,
51
+ "rewards/chosen": -0.007256551180034876,
52
+ "rewards/margins": 0.002894227858632803,
53
+ "rewards/rejected": -0.010150779038667679,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.06281078251766553,
58
+ "grad_norm": 5.830212722805484,
59
+ "learning_rate": 3.1249999999999997e-07,
60
+ "logits/chosen": -1.1879990100860596,
61
+ "logits/rejected": -1.2821766138076782,
62
+ "logps/chosen": -507.1835021972656,
63
+ "logps/rejected": -481.771728515625,
64
+ "loss": 0.6858,
65
+ "rewards/accuracies": 0.581250011920929,
66
+ "rewards/chosen": -0.05630107969045639,
67
+ "rewards/margins": 0.009836100041866302,
68
+ "rewards/rejected": -0.06613717973232269,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.08374771002355404,
73
+ "grad_norm": 6.142811166492132,
74
+ "learning_rate": 4.1666666666666667e-07,
75
+ "logits/chosen": -1.2522597312927246,
76
+ "logits/rejected": -1.2801125049591064,
77
+ "logps/chosen": -476.06439208984375,
78
+ "logps/rejected": -518.1241455078125,
79
+ "loss": 0.6659,
80
+ "rewards/accuracies": 0.668749988079071,
81
+ "rewards/chosen": -0.24496185779571533,
82
+ "rewards/margins": 0.0600227527320385,
83
+ "rewards/rejected": -0.30498459935188293,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.10468463752944256,
88
+ "grad_norm": 6.8453175062635125,
89
+ "learning_rate": 4.999731868769026e-07,
90
+ "logits/chosen": -1.34788978099823,
91
+ "logits/rejected": -1.364375114440918,
92
+ "logps/chosen": -533.0452880859375,
93
+ "logps/rejected": -599.4424438476562,
94
+ "loss": 0.6196,
95
+ "rewards/accuracies": 0.737500011920929,
96
+ "rewards/chosen": -0.7288391590118408,
97
+ "rewards/margins": 0.277568519115448,
98
+ "rewards/rejected": -1.006407618522644,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.12562156503533106,
103
+ "grad_norm": 7.830680395352566,
104
+ "learning_rate": 4.990353313429303e-07,
105
+ "logits/chosen": -1.4588544368743896,
106
+ "logits/rejected": -1.4161434173583984,
107
+ "logps/chosen": -587.5367431640625,
108
+ "logps/rejected": -669.0986328125,
109
+ "loss": 0.5822,
110
+ "rewards/accuracies": 0.699999988079071,
111
+ "rewards/chosen": -1.328367829322815,
112
+ "rewards/margins": 0.5138038396835327,
113
+ "rewards/rejected": -1.8421716690063477,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.14655849254121958,
118
+ "grad_norm": 8.114776579993702,
119
+ "learning_rate": 4.967625656594781e-07,
120
+ "logits/chosen": -1.4318482875823975,
121
+ "logits/rejected": -1.4409352540969849,
122
+ "logps/chosen": -666.4456176757812,
123
+ "logps/rejected": -729.1796264648438,
124
+ "loss": 0.5595,
125
+ "rewards/accuracies": 0.6812499761581421,
126
+ "rewards/chosen": -1.651793122291565,
127
+ "rewards/margins": 0.5167388916015625,
128
+ "rewards/rejected": -2.168531894683838,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.16749542004710807,
133
+ "grad_norm": 8.8385356864838,
134
+ "learning_rate": 4.93167072587771e-07,
135
+ "logits/chosen": -1.4754712581634521,
136
+ "logits/rejected": -1.5046911239624023,
137
+ "logps/chosen": -637.0550537109375,
138
+ "logps/rejected": -683.7327270507812,
139
+ "loss": 0.5521,
140
+ "rewards/accuracies": 0.762499988079071,
141
+ "rewards/chosen": -1.4783751964569092,
142
+ "rewards/margins": 0.6370193362236023,
143
+ "rewards/rejected": -2.1153945922851562,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.1884323475529966,
148
+ "grad_norm": 7.273331254641903,
149
+ "learning_rate": 4.882681251368548e-07,
150
+ "logits/chosen": -1.4381468296051025,
151
+ "logits/rejected": -1.4646328687667847,
152
+ "logps/chosen": -618.9959716796875,
153
+ "logps/rejected": -673.4351806640625,
154
+ "loss": 0.534,
155
+ "rewards/accuracies": 0.699999988079071,
156
+ "rewards/chosen": -1.519857406616211,
157
+ "rewards/margins": 0.5099424719810486,
158
+ "rewards/rejected": -2.0297999382019043,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.2093692750588851,
163
+ "grad_norm": 7.2496794921936,
164
+ "learning_rate": 4.820919832540181e-07,
165
+ "logits/chosen": -1.3987996578216553,
166
+ "logits/rejected": -1.4214246273040771,
167
+ "logps/chosen": -632.5852661132812,
168
+ "logps/rejected": -757.4251098632812,
169
+ "loss": 0.5269,
170
+ "rewards/accuracies": 0.824999988079071,
171
+ "rewards/chosen": -1.539336919784546,
172
+ "rewards/margins": 0.8474786877632141,
173
+ "rewards/rejected": -2.3868155479431152,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.2093692750588851,
178
+ "eval_logits/chosen": -1.3850065469741821,
179
+ "eval_logits/rejected": -1.3951938152313232,
180
+ "eval_logps/chosen": -657.6356201171875,
181
+ "eval_logps/rejected": -727.9815063476562,
182
+ "eval_loss": 0.5332552194595337,
183
+ "eval_rewards/accuracies": 0.699999988079071,
184
+ "eval_rewards/chosen": -1.6756343841552734,
185
+ "eval_rewards/margins": 0.6563942432403564,
186
+ "eval_rewards/rejected": -2.332028865814209,
187
+ "eval_runtime": 174.614,
188
+ "eval_samples_per_second": 11.454,
189
+ "eval_steps_per_second": 0.716,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.23030620256477363,
194
+ "grad_norm": 8.10753128188729,
195
+ "learning_rate": 4.7467175306295647e-07,
196
+ "logits/chosen": -1.2935419082641602,
197
+ "logits/rejected": -1.381008505821228,
198
+ "logps/chosen": -657.0072021484375,
199
+ "logps/rejected": -706.2003784179688,
200
+ "loss": 0.529,
201
+ "rewards/accuracies": 0.7562500238418579,
202
+ "rewards/chosen": -1.6493545770645142,
203
+ "rewards/margins": 0.5988022685050964,
204
+ "rewards/rejected": -2.248157024383545,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 0.2512431300706621,
209
+ "grad_norm": 8.142470959373666,
210
+ "learning_rate": 4.6604720940421207e-07,
211
+ "logits/chosen": -1.3212612867355347,
212
+ "logits/rejected": -1.3621456623077393,
213
+ "logps/chosen": -609.11181640625,
214
+ "logps/rejected": -712.6756591796875,
215
+ "loss": 0.5053,
216
+ "rewards/accuracies": 0.762499988079071,
217
+ "rewards/chosen": -1.5495909452438354,
218
+ "rewards/margins": 0.7342188954353333,
219
+ "rewards/rejected": -2.2838101387023926,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 0.2721800575765506,
224
+ "grad_norm": 6.624266912381754,
225
+ "learning_rate": 4.5626458262912735e-07,
226
+ "logits/chosen": -1.3223083019256592,
227
+ "logits/rejected": -1.3553454875946045,
228
+ "logps/chosen": -632.750244140625,
229
+ "logps/rejected": -708.5543823242188,
230
+ "loss": 0.5004,
231
+ "rewards/accuracies": 0.762499988079071,
232
+ "rewards/chosen": -1.4656463861465454,
233
+ "rewards/margins": 0.7802583575248718,
234
+ "rewards/rejected": -2.2459044456481934,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 0.29311698508243916,
239
+ "grad_norm": 9.216064563940549,
240
+ "learning_rate": 4.453763107901675e-07,
241
+ "logits/chosen": -1.4132908582687378,
242
+ "logits/rejected": -1.4507051706314087,
243
+ "logps/chosen": -685.0856323242188,
244
+ "logps/rejected": -762.1068115234375,
245
+ "loss": 0.5347,
246
+ "rewards/accuracies": 0.7437499761581421,
247
+ "rewards/chosen": -1.7906442880630493,
248
+ "rewards/margins": 0.8574408292770386,
249
+ "rewards/rejected": -2.648085117340088,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 0.31405391258832765,
254
+ "grad_norm": 8.861919067605399,
255
+ "learning_rate": 4.3344075855595097e-07,
256
+ "logits/chosen": -1.3353523015975952,
257
+ "logits/rejected": -1.3859806060791016,
258
+ "logps/chosen": -644.6119384765625,
259
+ "logps/rejected": -741.2134399414062,
260
+ "loss": 0.5072,
261
+ "rewards/accuracies": 0.831250011920929,
262
+ "rewards/chosen": -1.672431230545044,
263
+ "rewards/margins": 0.8643969297409058,
264
+ "rewards/rejected": -2.5368282794952393,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 0.33499084009421615,
269
+ "grad_norm": 9.292299719932993,
270
+ "learning_rate": 4.2052190435769554e-07,
271
+ "logits/chosen": -1.2773377895355225,
272
+ "logits/rejected": -1.3252099752426147,
273
+ "logps/chosen": -646.8428344726562,
274
+ "logps/rejected": -767.851806640625,
275
+ "loss": 0.5175,
276
+ "rewards/accuracies": 0.7749999761581421,
277
+ "rewards/chosen": -1.8619630336761475,
278
+ "rewards/margins": 0.8954536318778992,
279
+ "rewards/rejected": -2.7574167251586914,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 0.3559277676001047,
284
+ "grad_norm": 8.535232197560195,
285
+ "learning_rate": 4.0668899744407567e-07,
286
+ "logits/chosen": -1.2284882068634033,
287
+ "logits/rejected": -1.259841799736023,
288
+ "logps/chosen": -643.7806396484375,
289
+ "logps/rejected": -719.5083618164062,
290
+ "loss": 0.5192,
291
+ "rewards/accuracies": 0.668749988079071,
292
+ "rewards/chosen": -1.9132611751556396,
293
+ "rewards/margins": 0.6574370265007019,
294
+ "rewards/rejected": -2.5706982612609863,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 0.3768646951059932,
299
+ "grad_norm": 8.471513794877017,
300
+ "learning_rate": 3.920161866827889e-07,
301
+ "logits/chosen": -1.3475391864776611,
302
+ "logits/rejected": -1.3049246072769165,
303
+ "logps/chosen": -670.0532836914062,
304
+ "logps/rejected": -781.0071411132812,
305
+ "loss": 0.4907,
306
+ "rewards/accuracies": 0.731249988079071,
307
+ "rewards/chosen": -2.043039083480835,
308
+ "rewards/margins": 0.6995586156845093,
309
+ "rewards/rejected": -2.742597818374634,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 0.39780162261188173,
314
+ "grad_norm": 7.575885046762926,
315
+ "learning_rate": 3.765821230985757e-07,
316
+ "logits/chosen": -1.3079270124435425,
317
+ "logits/rejected": -1.2785875797271729,
318
+ "logps/chosen": -679.8087768554688,
319
+ "logps/rejected": -808.7610473632812,
320
+ "loss": 0.501,
321
+ "rewards/accuracies": 0.71875,
322
+ "rewards/chosen": -2.0995121002197266,
323
+ "rewards/margins": 0.7744059562683105,
324
+ "rewards/rejected": -2.873918056488037,
325
+ "step": 190
326
+ },
327
+ {
328
+ "epoch": 0.4187385501177702,
329
+ "grad_norm": 11.938650112523503,
330
+ "learning_rate": 3.604695382782159e-07,
331
+ "logits/chosen": -1.2764681577682495,
332
+ "logits/rejected": -1.2830474376678467,
333
+ "logps/chosen": -700.9818115234375,
334
+ "logps/rejected": -790.2588500976562,
335
+ "loss": 0.5086,
336
+ "rewards/accuracies": 0.6812499761581421,
337
+ "rewards/chosen": -2.1675782203674316,
338
+ "rewards/margins": 0.6838473081588745,
339
+ "rewards/rejected": -2.851425886154175,
340
+ "step": 200
341
+ },
342
+ {
343
+ "epoch": 0.4187385501177702,
344
+ "eval_logits/chosen": -1.2772727012634277,
345
+ "eval_logits/rejected": -1.2939157485961914,
346
+ "eval_logps/chosen": -699.1298217773438,
347
+ "eval_logps/rejected": -787.651123046875,
348
+ "eval_loss": 0.504360556602478,
349
+ "eval_rewards/accuracies": 0.7039999961853027,
350
+ "eval_rewards/chosen": -2.090576171875,
351
+ "eval_rewards/margins": 0.8381478786468506,
352
+ "eval_rewards/rejected": -2.9287240505218506,
353
+ "eval_runtime": 173.7524,
354
+ "eval_samples_per_second": 11.511,
355
+ "eval_steps_per_second": 0.719,
356
+ "step": 200
357
+ },
358
+ {
359
+ "epoch": 0.4396754776236587,
360
+ "grad_norm": 8.791948417829072,
361
+ "learning_rate": 3.4376480090239047e-07,
362
+ "logits/chosen": -1.2757617235183716,
363
+ "logits/rejected": -1.3068811893463135,
364
+ "logps/chosen": -736.14794921875,
365
+ "logps/rejected": -807.1375732421875,
366
+ "loss": 0.5129,
367
+ "rewards/accuracies": 0.71875,
368
+ "rewards/chosen": -2.278721332550049,
369
+ "rewards/margins": 0.7708470225334167,
370
+ "rewards/rejected": -3.0495681762695312,
371
+ "step": 210
372
+ },
373
+ {
374
+ "epoch": 0.46061240512954726,
375
+ "grad_norm": 7.175329586845978,
376
+ "learning_rate": 3.265574537815398e-07,
377
+ "logits/chosen": -1.234605312347412,
378
+ "logits/rejected": -1.238705039024353,
379
+ "logps/chosen": -686.875244140625,
380
+ "logps/rejected": -792.4070434570312,
381
+ "loss": 0.5007,
382
+ "rewards/accuracies": 0.71875,
383
+ "rewards/chosen": -2.308474063873291,
384
+ "rewards/margins": 0.764443039894104,
385
+ "rewards/rejected": -3.0729172229766846,
386
+ "step": 220
387
+ },
388
+ {
389
+ "epoch": 0.48154933263543576,
390
+ "grad_norm": 8.60332250684624,
391
+ "learning_rate": 3.0893973387735683e-07,
392
+ "logits/chosen": -1.2985376119613647,
393
+ "logits/rejected": -1.306581974029541,
394
+ "logps/chosen": -662.0936279296875,
395
+ "logps/rejected": -823.6008911132812,
396
+ "loss": 0.5153,
397
+ "rewards/accuracies": 0.7749999761581421,
398
+ "rewards/chosen": -2.064509868621826,
399
+ "rewards/margins": 1.0347161293029785,
400
+ "rewards/rejected": -3.0992257595062256,
401
+ "step": 230
402
+ },
403
+ {
404
+ "epoch": 0.5024862601413242,
405
+ "grad_norm": 7.615515586975465,
406
+ "learning_rate": 2.910060778827554e-07,
407
+ "logits/chosen": -1.244362711906433,
408
+ "logits/rejected": -1.250091552734375,
409
+ "logps/chosen": -670.7986450195312,
410
+ "logps/rejected": -774.2589721679688,
411
+ "loss": 0.488,
412
+ "rewards/accuracies": 0.71875,
413
+ "rewards/chosen": -2.0815677642822266,
414
+ "rewards/margins": 0.7600711584091187,
415
+ "rewards/rejected": -2.8416390419006348,
416
+ "step": 240
417
+ },
418
+ {
419
+ "epoch": 0.5234231876472127,
420
+ "grad_norm": 8.227460909814754,
421
+ "learning_rate": 2.7285261601056697e-07,
422
+ "logits/chosen": -1.2554184198379517,
423
+ "logits/rejected": -1.2809184789657593,
424
+ "logps/chosen": -725.0731201171875,
425
+ "logps/rejected": -819.86181640625,
426
+ "loss": 0.4948,
427
+ "rewards/accuracies": 0.7562500238418579,
428
+ "rewards/chosen": -2.1545822620391846,
429
+ "rewards/margins": 0.9376426935195923,
430
+ "rewards/rejected": -3.0922253131866455,
431
+ "step": 250
432
+ },
433
+ {
434
+ "epoch": 0.5443601151531012,
435
+ "grad_norm": 9.508165144084513,
436
+ "learning_rate": 2.5457665670441937e-07,
437
+ "logits/chosen": -1.2575011253356934,
438
+ "logits/rejected": -1.3054656982421875,
439
+ "logps/chosen": -716.1454467773438,
440
+ "logps/rejected": -812.8175659179688,
441
+ "loss": 0.4996,
442
+ "rewards/accuracies": 0.737500011920929,
443
+ "rewards/chosen": -2.350128650665283,
444
+ "rewards/margins": 0.9231952428817749,
445
+ "rewards/rejected": -3.2733237743377686,
446
+ "step": 260
447
+ },
448
+ {
449
+ "epoch": 0.5652970426589898,
450
+ "grad_norm": 9.240543953923092,
451
+ "learning_rate": 2.3627616503391812e-07,
452
+ "logits/chosen": -1.2486110925674438,
453
+ "logits/rejected": -1.25895094871521,
454
+ "logps/chosen": -710.92724609375,
455
+ "logps/rejected": -834.6962890625,
456
+ "loss": 0.5086,
457
+ "rewards/accuracies": 0.7562500238418579,
458
+ "rewards/chosen": -2.2452242374420166,
459
+ "rewards/margins": 1.0662496089935303,
460
+ "rewards/rejected": -3.3114733695983887,
461
+ "step": 270
462
+ },
463
+ {
464
+ "epoch": 0.5862339701648783,
465
+ "grad_norm": 8.132372884664997,
466
+ "learning_rate": 2.1804923757009882e-07,
467
+ "logits/chosen": -1.2164264917373657,
468
+ "logits/rejected": -1.3014079332351685,
469
+ "logps/chosen": -720.0590209960938,
470
+ "logps/rejected": -770.1983642578125,
471
+ "loss": 0.4955,
472
+ "rewards/accuracies": 0.731249988079071,
473
+ "rewards/chosen": -2.291123867034912,
474
+ "rewards/margins": 0.673937201499939,
475
+ "rewards/rejected": -2.9650609493255615,
476
+ "step": 280
477
+ },
478
+ {
479
+ "epoch": 0.6071708976707668,
480
+ "grad_norm": 7.699636946017558,
481
+ "learning_rate": 1.9999357655598891e-07,
482
+ "logits/chosen": -1.249624252319336,
483
+ "logits/rejected": -1.2436301708221436,
484
+ "logps/chosen": -687.5323486328125,
485
+ "logps/rejected": -815.8274536132812,
486
+ "loss": 0.4944,
487
+ "rewards/accuracies": 0.7437499761581421,
488
+ "rewards/chosen": -2.2351253032684326,
489
+ "rewards/margins": 0.8806158900260925,
490
+ "rewards/rejected": -3.115741491317749,
491
+ "step": 290
492
+ },
493
+ {
494
+ "epoch": 0.6281078251766553,
495
+ "grad_norm": 7.183044496877634,
496
+ "learning_rate": 1.8220596619089573e-07,
497
+ "logits/chosen": -1.214294672012329,
498
+ "logits/rejected": -1.278714656829834,
499
+ "logps/chosen": -711.4762573242188,
500
+ "logps/rejected": -826.3113403320312,
501
+ "loss": 0.4787,
502
+ "rewards/accuracies": 0.793749988079071,
503
+ "rewards/chosen": -2.1853926181793213,
504
+ "rewards/margins": 1.0479013919830322,
505
+ "rewards/rejected": -3.2332940101623535,
506
+ "step": 300
507
+ },
508
+ {
509
+ "epoch": 0.6281078251766553,
510
+ "eval_logits/chosen": -1.2646288871765137,
511
+ "eval_logits/rejected": -1.2846323251724243,
512
+ "eval_logps/chosen": -719.3385620117188,
513
+ "eval_logps/rejected": -811.6696166992188,
514
+ "eval_loss": 0.49482667446136475,
515
+ "eval_rewards/accuracies": 0.7319999933242798,
516
+ "eval_rewards/chosen": -2.292664051055908,
517
+ "eval_rewards/margins": 0.8762450218200684,
518
+ "eval_rewards/rejected": -3.1689090728759766,
519
+ "eval_runtime": 173.013,
520
+ "eval_samples_per_second": 11.56,
521
+ "eval_steps_per_second": 0.722,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 0.6490447526825438,
526
+ "grad_norm": 11.871889943001767,
527
+ "learning_rate": 1.647817538357072e-07,
528
+ "logits/chosen": -1.2392758131027222,
529
+ "logits/rejected": -1.3158223628997803,
530
+ "logps/chosen": -731.3906860351562,
531
+ "logps/rejected": -812.5341186523438,
532
+ "loss": 0.4937,
533
+ "rewards/accuracies": 0.8125,
534
+ "rewards/chosen": -2.279770851135254,
535
+ "rewards/margins": 1.1058552265167236,
536
+ "rewards/rejected": -3.3856253623962402,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 0.6699816801884323,
541
+ "grad_norm": 8.733519859905128,
542
+ "learning_rate": 1.478143389201113e-07,
543
+ "logits/chosen": -1.255499005317688,
544
+ "logits/rejected": -1.310626745223999,
545
+ "logps/chosen": -706.554443359375,
546
+ "logps/rejected": -809.0241088867188,
547
+ "loss": 0.4781,
548
+ "rewards/accuracies": 0.75,
549
+ "rewards/chosen": -2.4083428382873535,
550
+ "rewards/margins": 0.9482523202896118,
551
+ "rewards/rejected": -3.3565948009490967,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 0.6909186076943209,
556
+ "grad_norm": 8.449035915191043,
557
+ "learning_rate": 1.3139467229135998e-07,
558
+ "logits/chosen": -1.2453768253326416,
559
+ "logits/rejected": -1.2541320323944092,
560
+ "logps/chosen": -725.0225830078125,
561
+ "logps/rejected": -829.4249877929688,
562
+ "loss": 0.4839,
563
+ "rewards/accuracies": 0.7562500238418579,
564
+ "rewards/chosen": -2.4690725803375244,
565
+ "rewards/margins": 0.8669673800468445,
566
+ "rewards/rejected": -3.336040496826172,
567
+ "step": 330
568
+ },
569
+ {
570
+ "epoch": 0.7118555352002094,
571
+ "grad_norm": 9.726561036240426,
572
+ "learning_rate": 1.1561076868822755e-07,
573
+ "logits/chosen": -1.1633121967315674,
574
+ "logits/rejected": -1.2020900249481201,
575
+ "logps/chosen": -733.0904541015625,
576
+ "logps/rejected": -856.1812744140625,
577
+ "loss": 0.499,
578
+ "rewards/accuracies": 0.7749999761581421,
579
+ "rewards/chosen": -2.551614284515381,
580
+ "rewards/margins": 0.9220356941223145,
581
+ "rewards/rejected": -3.4736499786376953,
582
+ "step": 340
583
+ },
584
+ {
585
+ "epoch": 0.7327924627060979,
586
+ "grad_norm": 8.334278257541456,
587
+ "learning_rate": 1.0054723495346482e-07,
588
+ "logits/chosen": -1.2510846853256226,
589
+ "logits/rejected": -1.2921613454818726,
590
+ "logps/chosen": -709.3406982421875,
591
+ "logps/rejected": -806.6890869140625,
592
+ "loss": 0.461,
593
+ "rewards/accuracies": 0.762499988079071,
594
+ "rewards/chosen": -2.4316649436950684,
595
+ "rewards/margins": 0.9165409207344055,
596
+ "rewards/rejected": -3.348206043243408,
597
+ "step": 350
598
+ },
599
+ {
600
+ "epoch": 0.7537293902119864,
601
+ "grad_norm": 8.447055903339363,
602
+ "learning_rate": 8.628481651367875e-08,
603
+ "logits/chosen": -1.2806235551834106,
604
+ "logits/rejected": -1.3330801725387573,
605
+ "logps/chosen": -759.4558715820312,
606
+ "logps/rejected": -859.9752807617188,
607
+ "loss": 0.5053,
608
+ "rewards/accuracies": 0.800000011920929,
609
+ "rewards/chosen": -2.384193181991577,
610
+ "rewards/margins": 1.1400038003921509,
611
+ "rewards/rejected": -3.5241971015930176,
612
+ "step": 360
613
+ },
614
+ {
615
+ "epoch": 0.7746663177178749,
616
+ "grad_norm": 7.277711887873546,
617
+ "learning_rate": 7.289996455765748e-08,
618
+ "logits/chosen": -1.254237174987793,
619
+ "logits/rejected": -1.30390465259552,
620
+ "logps/chosen": -721.6316528320312,
621
+ "logps/rejected": -797.1998291015625,
622
+ "loss": 0.4865,
623
+ "rewards/accuracies": 0.762499988079071,
624
+ "rewards/chosen": -2.433364152908325,
625
+ "rewards/margins": 0.8884729146957397,
626
+ "rewards/rejected": -3.3218369483947754,
627
+ "step": 370
628
+ },
629
+ {
630
+ "epoch": 0.7956032452237635,
631
+ "grad_norm": 8.0205493017487,
632
+ "learning_rate": 6.046442623320145e-08,
633
+ "logits/chosen": -1.2699052095413208,
634
+ "logits/rejected": -1.3266394138336182,
635
+ "logps/chosen": -743.0064086914062,
636
+ "logps/rejected": -852.3271484375,
637
+ "loss": 0.4851,
638
+ "rewards/accuracies": 0.7562500238418579,
639
+ "rewards/chosen": -2.516409397125244,
640
+ "rewards/margins": 1.0128896236419678,
641
+ "rewards/rejected": -3.529299259185791,
642
+ "step": 380
643
+ },
644
+ {
645
+ "epoch": 0.816540172729652,
646
+ "grad_norm": 8.82315393673875,
647
+ "learning_rate": 4.904486005914027e-08,
648
+ "logits/chosen": -1.2463610172271729,
649
+ "logits/rejected": -1.2608873844146729,
650
+ "logps/chosen": -727.2433471679688,
651
+ "logps/rejected": -831.7511596679688,
652
+ "loss": 0.4765,
653
+ "rewards/accuracies": 0.731249988079071,
654
+ "rewards/chosen": -2.392064332962036,
655
+ "rewards/margins": 0.8088263273239136,
656
+ "rewards/rejected": -3.200890302658081,
657
+ "step": 390
658
+ },
659
+ {
660
+ "epoch": 0.8374771002355405,
661
+ "grad_norm": 8.332606925483372,
662
+ "learning_rate": 3.8702478614051345e-08,
663
+ "logits/chosen": -1.2610491514205933,
664
+ "logits/rejected": -1.3101046085357666,
665
+ "logps/chosen": -675.9216918945312,
666
+ "logps/rejected": -812.0501708984375,
667
+ "loss": 0.4825,
668
+ "rewards/accuracies": 0.8062499761581421,
669
+ "rewards/chosen": -2.404404401779175,
670
+ "rewards/margins": 1.064521074295044,
671
+ "rewards/rejected": -3.4689254760742188,
672
+ "step": 400
673
+ },
674
+ {
675
+ "epoch": 0.8374771002355405,
676
+ "eval_logits/chosen": -1.247671365737915,
677
+ "eval_logits/rejected": -1.2644414901733398,
678
+ "eval_logps/chosen": -734.7764892578125,
679
+ "eval_logps/rejected": -828.874755859375,
680
+ "eval_loss": 0.4924214482307434,
681
+ "eval_rewards/accuracies": 0.7400000095367432,
682
+ "eval_rewards/chosen": -2.4470431804656982,
683
+ "eval_rewards/margins": 0.8939173817634583,
684
+ "eval_rewards/rejected": -3.3409602642059326,
685
+ "eval_runtime": 172.7999,
686
+ "eval_samples_per_second": 11.574,
687
+ "eval_steps_per_second": 0.723,
688
+ "step": 400
689
+ },
690
+ {
691
+ "epoch": 0.8584140277414289,
692
+ "grad_norm": 7.409919398422161,
693
+ "learning_rate": 2.9492720416985e-08,
694
+ "logits/chosen": -1.2109179496765137,
695
+ "logits/rejected": -1.2863398790359497,
696
+ "logps/chosen": -763.9716796875,
697
+ "logps/rejected": -842.8446044921875,
698
+ "loss": 0.4935,
699
+ "rewards/accuracies": 0.762499988079071,
700
+ "rewards/chosen": -2.5099594593048096,
701
+ "rewards/margins": 0.8958646059036255,
702
+ "rewards/rejected": -3.4058241844177246,
703
+ "step": 410
704
+ },
705
+ {
706
+ "epoch": 0.8793509552473174,
707
+ "grad_norm": 7.7696194448634275,
708
+ "learning_rate": 2.1464952759020856e-08,
709
+ "logits/chosen": -1.207766056060791,
710
+ "logits/rejected": -1.2242529392242432,
711
+ "logps/chosen": -737.0940551757812,
712
+ "logps/rejected": -902.7199096679688,
713
+ "loss": 0.4795,
714
+ "rewards/accuracies": 0.7875000238418579,
715
+ "rewards/chosen": -2.6334424018859863,
716
+ "rewards/margins": 1.135379433631897,
717
+ "rewards/rejected": -3.768822193145752,
718
+ "step": 420
719
+ },
720
+ {
721
+ "epoch": 0.9002878827532059,
722
+ "grad_norm": 8.567338429000005,
723
+ "learning_rate": 1.4662207078575684e-08,
724
+ "logits/chosen": -1.2356188297271729,
725
+ "logits/rejected": -1.275846242904663,
726
+ "logps/chosen": -750.3199462890625,
727
+ "logps/rejected": -832.4161987304688,
728
+ "loss": 0.4693,
729
+ "rewards/accuracies": 0.78125,
730
+ "rewards/chosen": -2.4712231159210205,
731
+ "rewards/margins": 1.0153119564056396,
732
+ "rewards/rejected": -3.486534833908081,
733
+ "step": 430
734
+ },
735
+ {
736
+ "epoch": 0.9212248102590945,
737
+ "grad_norm": 8.619770650174253,
738
+ "learning_rate": 9.12094829893642e-09,
739
+ "logits/chosen": -1.26433527469635,
740
+ "logits/rejected": -1.3092998266220093,
741
+ "logps/chosen": -719.7817993164062,
742
+ "logps/rejected": -813.6593627929688,
743
+ "loss": 0.4889,
744
+ "rewards/accuracies": 0.768750011920929,
745
+ "rewards/chosen": -2.478425979614258,
746
+ "rewards/margins": 0.9797126054763794,
747
+ "rewards/rejected": -3.4581382274627686,
748
+ "step": 440
749
+ },
750
+ {
751
+ "epoch": 0.942161737764983,
752
+ "grad_norm": 7.405850569844442,
753
+ "learning_rate": 4.8708793644441086e-09,
754
+ "logits/chosen": -1.1603410243988037,
755
+ "logits/rejected": -1.2475802898406982,
756
+ "logps/chosen": -723.2225341796875,
757
+ "logps/rejected": -873.5631103515625,
758
+ "loss": 0.4742,
759
+ "rewards/accuracies": 0.800000011920929,
760
+ "rewards/chosen": -2.4385993480682373,
761
+ "rewards/margins": 1.1800200939178467,
762
+ "rewards/rejected": -3.618619441986084,
763
+ "step": 450
764
+ },
765
+ {
766
+ "epoch": 0.9630986652708715,
767
+ "grad_norm": 8.784099959292528,
768
+ "learning_rate": 1.9347820230782295e-09,
769
+ "logits/chosen": -1.2129580974578857,
770
+ "logits/rejected": -1.300582766532898,
771
+ "logps/chosen": -732.4578857421875,
772
+ "logps/rejected": -833.5997314453125,
773
+ "loss": 0.4817,
774
+ "rewards/accuracies": 0.78125,
775
+ "rewards/chosen": -2.5728919506073,
776
+ "rewards/margins": 1.036318063735962,
777
+ "rewards/rejected": -3.609210252761841,
778
+ "step": 460
779
+ },
780
+ {
781
+ "epoch": 0.98403559277676,
782
+ "grad_norm": 9.493475272094026,
783
+ "learning_rate": 3.2839470889836627e-10,
784
+ "logits/chosen": -1.2292336225509644,
785
+ "logits/rejected": -1.2678720951080322,
786
+ "logps/chosen": -725.6412963867188,
787
+ "logps/rejected": -856.3084716796875,
788
+ "loss": 0.4615,
789
+ "rewards/accuracies": 0.7437499761581421,
790
+ "rewards/chosen": -2.491250514984131,
791
+ "rewards/margins": 1.0373666286468506,
792
+ "rewards/rejected": -3.5286173820495605,
793
+ "step": 470
794
+ },
795
+ {
796
+ "epoch": 0.998691442030882,
797
+ "step": 477,
798
+ "total_flos": 0.0,
799
+ "train_loss": 0.5192520058629898,
800
+ "train_runtime": 13862.6582,
801
+ "train_samples_per_second": 4.41,
802
+ "train_steps_per_second": 0.034
803
+ }
804
+ ],
805
+ "logging_steps": 10,
806
+ "max_steps": 477,
807
+ "num_input_tokens_seen": 0,
808
+ "num_train_epochs": 1,
809
+ "save_steps": 500,
810
+ "stateful_callbacks": {
811
+ "TrainerControl": {
812
+ "args": {
813
+ "should_epoch_stop": false,
814
+ "should_evaluate": false,
815
+ "should_log": false,
816
+ "should_save": false,
817
+ "should_training_stop": false
818
+ },
819
+ "attributes": {}
820
+ }
821
+ },
822
+ "total_flos": 0.0,
823
+ "train_batch_size": 2,
824
+ "trial_name": null,
825
+ "trial_params": null
826
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ab02bd175d5ee79de434a512bce065cfdf5a991a72c713eb4a7a6485eec735
3
+ size 7544
vocab.json ADDED
The diff for this file is too large to render. See raw diff