tengxiao1 commited on
Commit
7a271e3
1 Parent(s): f13a361
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - alignment_handbook-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - princeton-nlp/mistral-instruct-ultrafeedback
9
+ model-index:
10
+ - name: Mistral-7B-Base-SimPO2-5e-7
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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tengxiao01/huggingface/runs/jcsdn1jt)
18
+ # Mistral-7B-Base-SimPO2-5e-7
19
+
20
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the princeton-nlp/mistral-instruct-ultrafeedback dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Logits/chosen: -2.9000
23
+ - Logits/rejected: -2.8928
24
+ - Logps/chosen: -1.1346
25
+ - Logps/rejected: -1.2466
26
+ - Loss: -0.0708
27
+ - Rewards/accuracies: 0.5758
28
+ - Rewards/chosen: -1.1346
29
+ - Rewards/margins: 0.1120
30
+ - Rewards/rejected: -1.2466
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 5e-07
50
+ - train_batch_size: 2
51
+ - eval_batch_size: 4
52
+ - seed: 42
53
+ - distributed_type: multi-GPU
54
+ - num_devices: 4
55
+ - gradient_accumulation_steps: 16
56
+ - total_train_batch_size: 128
57
+ - total_eval_batch_size: 16
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 1
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
66
+ |:-------------:|:------:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
67
+ | -0.0905 | 0.8573 | 400 | -2.9000 | -2.8928 | -1.1346 | -1.2466 | -0.0708 | 0.5758 | -1.1346 | 0.1120 | -1.2466 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.42.0
73
+ - Pytorch 2.1.2+cu121
74
+ - Datasets 2.14.6
75
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9987943737441393,
3
+ "eval_logits/chosen": -2.8956403732299805,
4
+ "eval_logits/rejected": -2.887930154800415,
5
+ "eval_logps/chosen": -1.1685596704483032,
6
+ "eval_logps/rejected": -1.2866594791412354,
7
+ "eval_loss": -0.07405862212181091,
8
+ "eval_rewards/accuracies": 0.5797872543334961,
9
+ "eval_rewards/chosen": -1.1685596704483032,
10
+ "eval_rewards/margins": 0.11809979379177094,
11
+ "eval_rewards/rejected": -1.2866594791412354,
12
+ "eval_runtime": 432.6369,
13
+ "eval_samples": 2994,
14
+ "eval_samples_per_second": 6.92,
15
+ "eval_steps_per_second": 0.435,
16
+ "total_flos": 0.0,
17
+ "train_loss": 0.0,
18
+ "train_runtime": 4.3106,
19
+ "train_samples": 59720,
20
+ "train_samples_per_second": 13854.197,
21
+ "train_steps_per_second": 108.105
22
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.42.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9987943737441393,
3
+ "eval_logits/chosen": -2.8956403732299805,
4
+ "eval_logits/rejected": -2.887930154800415,
5
+ "eval_logps/chosen": -1.1685596704483032,
6
+ "eval_logps/rejected": -1.2866594791412354,
7
+ "eval_loss": -0.07405862212181091,
8
+ "eval_rewards/accuracies": 0.5797872543334961,
9
+ "eval_rewards/chosen": -1.1685596704483032,
10
+ "eval_rewards/margins": 0.11809979379177094,
11
+ "eval_rewards/rejected": -1.2866594791412354,
12
+ "eval_runtime": 432.6369,
13
+ "eval_samples": 2994,
14
+ "eval_samples_per_second": 6.92,
15
+ "eval_steps_per_second": 0.435
16
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.42.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86ac70d9836b2d4195eee1d3dbc4402a7a0c20acffa8d338364fbcbeedf14c5
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a21eafd141af9dd8067a4a78c38a4f8d7d3e1523345be7af9c02bf5a88d9115
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a86de4c4ce516205d7e88bc37604be949702a33ff400ebb201352d450f703996
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 2048,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9987943737441393,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 4.3106,
6
+ "train_samples": 59720,
7
+ "train_samples_per_second": 13854.197,
8
+ "train_steps_per_second": 108.105
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9987943737441393,
5
+ "eval_steps": 400,
6
+ "global_step": 466,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010716677829872739,
13
+ "grad_norm": 8.776682238147446,
14
+ "learning_rate": 5.3191489361702123e-08,
15
+ "logits/chosen": -2.8905415534973145,
16
+ "logits/rejected": -2.8877615928649902,
17
+ "logps/chosen": -0.9742914438247681,
18
+ "logps/rejected": -0.9831219911575317,
19
+ "loss": 0.0001,
20
+ "rewards/accuracies": 0.4749999940395355,
21
+ "rewards/chosen": -0.9742914438247681,
22
+ "rewards/margins": 0.008830604143440723,
23
+ "rewards/rejected": -0.9831219911575317,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.021433355659745478,
28
+ "grad_norm": 9.810248541108757,
29
+ "learning_rate": 1.0638297872340425e-07,
30
+ "logits/chosen": -2.9070327281951904,
31
+ "logits/rejected": -2.8929152488708496,
32
+ "logps/chosen": -0.978168785572052,
33
+ "logps/rejected": -1.001371145248413,
34
+ "loss": -0.0,
35
+ "rewards/accuracies": 0.512499988079071,
36
+ "rewards/chosen": -0.978168785572052,
37
+ "rewards/margins": 0.023202406242489815,
38
+ "rewards/rejected": -1.001371145248413,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.032150033489618215,
43
+ "grad_norm": 7.0995253496741135,
44
+ "learning_rate": 1.5957446808510638e-07,
45
+ "logits/chosen": -2.895216703414917,
46
+ "logits/rejected": -2.9180421829223633,
47
+ "logps/chosen": -0.9596306085586548,
48
+ "logps/rejected": -0.9847423434257507,
49
+ "loss": -0.0001,
50
+ "rewards/accuracies": 0.518750011920929,
51
+ "rewards/chosen": -0.9596306085586548,
52
+ "rewards/margins": 0.02511175535619259,
53
+ "rewards/rejected": -0.9847423434257507,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.042866711319490956,
58
+ "grad_norm": 7.785343608601427,
59
+ "learning_rate": 2.127659574468085e-07,
60
+ "logits/chosen": -2.902580976486206,
61
+ "logits/rejected": -2.9009933471679688,
62
+ "logps/chosen": -0.9715825319290161,
63
+ "logps/rejected": -0.9759886860847473,
64
+ "loss": -0.0,
65
+ "rewards/accuracies": 0.5375000238418579,
66
+ "rewards/chosen": -0.9715825319290161,
67
+ "rewards/margins": 0.00440616998821497,
68
+ "rewards/rejected": -0.9759886860847473,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.0535833891493637,
73
+ "grad_norm": 6.677386701450202,
74
+ "learning_rate": 2.659574468085106e-07,
75
+ "logits/chosen": -2.8314852714538574,
76
+ "logits/rejected": -2.8363277912139893,
77
+ "logps/chosen": -0.9519669413566589,
78
+ "logps/rejected": -1.0002533197402954,
79
+ "loss": -0.0003,
80
+ "rewards/accuracies": 0.5562499761581421,
81
+ "rewards/chosen": -0.9519669413566589,
82
+ "rewards/margins": 0.048286281526088715,
83
+ "rewards/rejected": -1.0002533197402954,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06430006697923643,
88
+ "grad_norm": 8.4552870442767,
89
+ "learning_rate": 3.1914893617021275e-07,
90
+ "logits/chosen": -2.895077705383301,
91
+ "logits/rejected": -2.9221832752227783,
92
+ "logps/chosen": -0.983117938041687,
93
+ "logps/rejected": -0.9829673767089844,
94
+ "loss": -0.0002,
95
+ "rewards/accuracies": 0.46875,
96
+ "rewards/chosen": -0.983117938041687,
97
+ "rewards/margins": -0.00015044640167616308,
98
+ "rewards/rejected": -0.9829673767089844,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07501674480910918,
103
+ "grad_norm": 7.60248558460589,
104
+ "learning_rate": 3.7234042553191484e-07,
105
+ "logits/chosen": -2.9559242725372314,
106
+ "logits/rejected": -2.9249794483184814,
107
+ "logps/chosen": -0.95380699634552,
108
+ "logps/rejected": -0.9984177350997925,
109
+ "loss": -0.0004,
110
+ "rewards/accuracies": 0.581250011920929,
111
+ "rewards/chosen": -0.95380699634552,
112
+ "rewards/margins": 0.04461073502898216,
113
+ "rewards/rejected": -0.9984177350997925,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08573342263898191,
118
+ "grad_norm": 8.131750300550957,
119
+ "learning_rate": 4.25531914893617e-07,
120
+ "logits/chosen": -2.8956754207611084,
121
+ "logits/rejected": -2.8939049243927,
122
+ "logps/chosen": -0.9987373352050781,
123
+ "logps/rejected": -0.9930660128593445,
124
+ "loss": -0.0015,
125
+ "rewards/accuracies": 0.48124998807907104,
126
+ "rewards/chosen": -0.9987373352050781,
127
+ "rewards/margins": -0.005671312101185322,
128
+ "rewards/rejected": -0.9930660128593445,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.09645010046885466,
133
+ "grad_norm": 7.488747662199227,
134
+ "learning_rate": 4.787234042553192e-07,
135
+ "logits/chosen": -2.8674330711364746,
136
+ "logits/rejected": -2.856853485107422,
137
+ "logps/chosen": -0.9764472246170044,
138
+ "logps/rejected": -0.9902997016906738,
139
+ "loss": -0.001,
140
+ "rewards/accuracies": 0.512499988079071,
141
+ "rewards/chosen": -0.9764472246170044,
142
+ "rewards/margins": 0.013852563686668873,
143
+ "rewards/rejected": -0.9902997016906738,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.1071667782987274,
148
+ "grad_norm": 7.447612263721868,
149
+ "learning_rate": 4.999367579541646e-07,
150
+ "logits/chosen": -2.875795364379883,
151
+ "logits/rejected": -2.8871512413024902,
152
+ "logps/chosen": -0.9369581937789917,
153
+ "logps/rejected": -0.9167054891586304,
154
+ "loss": -0.0027,
155
+ "rewards/accuracies": 0.4937500059604645,
156
+ "rewards/chosen": -0.9369581937789917,
157
+ "rewards/margins": -0.020252685993909836,
158
+ "rewards/rejected": -0.9167054891586304,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11788345612860013,
163
+ "grad_norm": 8.432358893020524,
164
+ "learning_rate": 4.99550394651012e-07,
165
+ "logits/chosen": -2.915107011795044,
166
+ "logits/rejected": -2.925875186920166,
167
+ "logps/chosen": -0.9737237095832825,
168
+ "logps/rejected": -1.0020536184310913,
169
+ "loss": -0.0022,
170
+ "rewards/accuracies": 0.5375000238418579,
171
+ "rewards/chosen": -0.9737237095832825,
172
+ "rewards/margins": 0.028329964727163315,
173
+ "rewards/rejected": -1.0020536184310913,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12860013395847286,
178
+ "grad_norm": 9.97321343058875,
179
+ "learning_rate": 4.988133448023071e-07,
180
+ "logits/chosen": -2.8224921226501465,
181
+ "logits/rejected": -2.8447964191436768,
182
+ "logps/chosen": -0.9149552583694458,
183
+ "logps/rejected": -0.9350795745849609,
184
+ "loss": -0.0041,
185
+ "rewards/accuracies": 0.5,
186
+ "rewards/chosen": -0.9149552583694458,
187
+ "rewards/margins": 0.02012430503964424,
188
+ "rewards/rejected": -0.9350795745849609,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.13931681178834562,
193
+ "grad_norm": 8.412802955896868,
194
+ "learning_rate": 4.977266441646379e-07,
195
+ "logits/chosen": -2.900336503982544,
196
+ "logits/rejected": -2.9115452766418457,
197
+ "logps/chosen": -0.8882263898849487,
198
+ "logps/rejected": -0.9012020230293274,
199
+ "loss": -0.0057,
200
+ "rewards/accuracies": 0.5375000238418579,
201
+ "rewards/chosen": -0.8882263898849487,
202
+ "rewards/margins": 0.012975621037185192,
203
+ "rewards/rejected": -0.9012020230293274,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.15003348961821836,
208
+ "grad_norm": 8.21023142941744,
209
+ "learning_rate": 4.962918198495654e-07,
210
+ "logits/chosen": -2.816331386566162,
211
+ "logits/rejected": -2.839690685272217,
212
+ "logps/chosen": -0.9164741635322571,
213
+ "logps/rejected": -0.9583846926689148,
214
+ "loss": -0.007,
215
+ "rewards/accuracies": 0.550000011920929,
216
+ "rewards/chosen": -0.9164741635322571,
217
+ "rewards/margins": 0.04191048443317413,
218
+ "rewards/rejected": -0.9583846926689148,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.1607501674480911,
223
+ "grad_norm": 8.354728288045035,
224
+ "learning_rate": 4.945108881776135e-07,
225
+ "logits/chosen": -2.8184382915496826,
226
+ "logits/rejected": -2.81858229637146,
227
+ "logps/chosen": -0.8914631009101868,
228
+ "logps/rejected": -0.9294856190681458,
229
+ "loss": -0.0066,
230
+ "rewards/accuracies": 0.5562499761581421,
231
+ "rewards/chosen": -0.8914631009101868,
232
+ "rewards/margins": 0.038022562861442566,
233
+ "rewards/rejected": -0.9294856190681458,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.17146684527796383,
238
+ "grad_norm": 9.546162491226012,
239
+ "learning_rate": 4.923863518447879e-07,
240
+ "logits/chosen": -2.840766191482544,
241
+ "logits/rejected": -2.8635830879211426,
242
+ "logps/chosen": -0.887871265411377,
243
+ "logps/rejected": -0.958912193775177,
244
+ "loss": -0.006,
245
+ "rewards/accuracies": 0.581250011920929,
246
+ "rewards/chosen": -0.887871265411377,
247
+ "rewards/margins": 0.07104082405567169,
248
+ "rewards/rejected": -0.958912193775177,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.18218352310783656,
253
+ "grad_norm": 9.354318155678731,
254
+ "learning_rate": 4.899211964056035e-07,
255
+ "logits/chosen": -2.854689359664917,
256
+ "logits/rejected": -2.866008758544922,
257
+ "logps/chosen": -0.9082525968551636,
258
+ "logps/rejected": -0.9574602842330933,
259
+ "loss": -0.0132,
260
+ "rewards/accuracies": 0.59375,
261
+ "rewards/chosen": -0.9082525968551636,
262
+ "rewards/margins": 0.04920773208141327,
263
+ "rewards/rejected": -0.9574602842330933,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.19290020093770932,
268
+ "grad_norm": 9.38237658589797,
269
+ "learning_rate": 4.871188860775643e-07,
270
+ "logits/chosen": -2.830294132232666,
271
+ "logits/rejected": -2.8332040309906006,
272
+ "logps/chosen": -0.9233630895614624,
273
+ "logps/rejected": -0.9633795022964478,
274
+ "loss": -0.0142,
275
+ "rewards/accuracies": 0.53125,
276
+ "rewards/chosen": -0.9233630895614624,
277
+ "rewards/margins": 0.040016382932662964,
278
+ "rewards/rejected": -0.9633795022964478,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.20361687876758205,
283
+ "grad_norm": 8.979685614931006,
284
+ "learning_rate": 4.839833588729897e-07,
285
+ "logits/chosen": -2.8387644290924072,
286
+ "logits/rejected": -2.8495821952819824,
287
+ "logps/chosen": -0.9509484171867371,
288
+ "logps/rejected": -0.974162220954895,
289
+ "loss": -0.0085,
290
+ "rewards/accuracies": 0.5249999761581421,
291
+ "rewards/chosen": -0.9509484171867371,
292
+ "rewards/margins": 0.02321377769112587,
293
+ "rewards/rejected": -0.974162220954895,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2143335565974548,
298
+ "grad_norm": 9.427728619757332,
299
+ "learning_rate": 4.80519021065031e-07,
300
+ "logits/chosen": -2.860654354095459,
301
+ "logits/rejected": -2.8680408000946045,
302
+ "logps/chosen": -0.9869228601455688,
303
+ "logps/rejected": -1.0385963916778564,
304
+ "loss": -0.015,
305
+ "rewards/accuracies": 0.581250011920929,
306
+ "rewards/chosen": -0.9869228601455688,
307
+ "rewards/margins": 0.05167357996106148,
308
+ "rewards/rejected": -1.0385963916778564,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.22505023442732752,
313
+ "grad_norm": 8.191485445947501,
314
+ "learning_rate": 4.767307409956528e-07,
315
+ "logits/chosen": -2.859048843383789,
316
+ "logits/rejected": -2.8625106811523438,
317
+ "logps/chosen": -0.8909996151924133,
318
+ "logps/rejected": -0.9282458424568176,
319
+ "loss": -0.0154,
320
+ "rewards/accuracies": 0.5687500238418579,
321
+ "rewards/chosen": -0.8909996151924133,
322
+ "rewards/margins": 0.03724620118737221,
323
+ "rewards/rejected": -0.9282458424568176,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23576691225720026,
328
+ "grad_norm": 9.657244741544229,
329
+ "learning_rate": 4.726238422342805e-07,
330
+ "logits/chosen": -2.8523192405700684,
331
+ "logits/rejected": -2.84688138961792,
332
+ "logps/chosen": -0.9256642460823059,
333
+ "logps/rejected": -0.9944097399711609,
334
+ "loss": -0.0136,
335
+ "rewards/accuracies": 0.606249988079071,
336
+ "rewards/chosen": -0.9256642460823059,
337
+ "rewards/margins": 0.06874561309814453,
338
+ "rewards/rejected": -0.9944097399711609,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24648359008707302,
343
+ "grad_norm": 11.45037121550009,
344
+ "learning_rate": 4.6820409609673027e-07,
345
+ "logits/chosen": -2.895726203918457,
346
+ "logits/rejected": -2.900205612182617,
347
+ "logps/chosen": -0.9234002828598022,
348
+ "logps/rejected": -0.938769519329071,
349
+ "loss": -0.0216,
350
+ "rewards/accuracies": 0.518750011920929,
351
+ "rewards/chosen": -0.9234002828598022,
352
+ "rewards/margins": 0.015369323082268238,
353
+ "rewards/rejected": -0.938769519329071,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2572002679169457,
358
+ "grad_norm": 9.77719736840442,
359
+ "learning_rate": 4.6347771353493173e-07,
360
+ "logits/chosen": -2.9136910438537598,
361
+ "logits/rejected": -2.930593252182007,
362
+ "logps/chosen": -0.9225813150405884,
363
+ "logps/rejected": -0.917222797870636,
364
+ "loss": -0.0168,
365
+ "rewards/accuracies": 0.5,
366
+ "rewards/chosen": -0.9225813150405884,
367
+ "rewards/margins": -0.005358507391065359,
368
+ "rewards/rejected": -0.917222797870636,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.2679169457468185,
373
+ "grad_norm": 10.417139695198527,
374
+ "learning_rate": 4.5845133640884217e-07,
375
+ "logits/chosen": -2.898656129837036,
376
+ "logits/rejected": -2.8996481895446777,
377
+ "logps/chosen": -0.9208585619926453,
378
+ "logps/rejected": -0.9479470252990723,
379
+ "loss": -0.0193,
380
+ "rewards/accuracies": 0.543749988079071,
381
+ "rewards/chosen": -0.9208585619926453,
382
+ "rewards/margins": 0.0270883496850729,
383
+ "rewards/rejected": -0.9479470252990723,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.27863362357669125,
388
+ "grad_norm": 11.697763554027677,
389
+ "learning_rate": 4.531320281528169e-07,
390
+ "logits/chosen": -2.9303739070892334,
391
+ "logits/rejected": -2.9241251945495605,
392
+ "logps/chosen": -0.9110285639762878,
393
+ "logps/rejected": -0.9726667404174805,
394
+ "loss": -0.0227,
395
+ "rewards/accuracies": 0.543749988079071,
396
+ "rewards/chosen": -0.9110285639762878,
397
+ "rewards/margins": 0.06163806468248367,
398
+ "rewards/rejected": -0.9726667404174805,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.289350301406564,
403
+ "grad_norm": 11.144902490144164,
404
+ "learning_rate": 4.4752726384955293e-07,
405
+ "logits/chosen": -2.9404830932617188,
406
+ "logits/rejected": -2.947343111038208,
407
+ "logps/chosen": -0.9363792538642883,
408
+ "logps/rejected": -0.9744508862495422,
409
+ "loss": -0.0195,
410
+ "rewards/accuracies": 0.5625,
411
+ "rewards/chosen": -0.9363792538642883,
412
+ "rewards/margins": 0.03807152435183525,
413
+ "rewards/rejected": -0.9744508862495422,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.3000669792364367,
418
+ "grad_norm": 11.921950508886521,
419
+ "learning_rate": 4.4164491972555294e-07,
420
+ "logits/chosen": -2.8976681232452393,
421
+ "logits/rejected": -2.898315906524658,
422
+ "logps/chosen": -0.9219269752502441,
423
+ "logps/rejected": -0.9640507698059082,
424
+ "loss": -0.0259,
425
+ "rewards/accuracies": 0.5625,
426
+ "rewards/chosen": -0.9219269752502441,
427
+ "rewards/margins": 0.04212382063269615,
428
+ "rewards/rejected": -0.9640507698059082,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.31078365706630945,
433
+ "grad_norm": 13.471098814591679,
434
+ "learning_rate": 4.3549326208287393e-07,
435
+ "logits/chosen": -2.9619617462158203,
436
+ "logits/rejected": -2.9274888038635254,
437
+ "logps/chosen": -0.9526675343513489,
438
+ "logps/rejected": -1.007359266281128,
439
+ "loss": -0.0355,
440
+ "rewards/accuracies": 0.5625,
441
+ "rewards/chosen": -0.9526675343513489,
442
+ "rewards/margins": 0.0546916201710701,
443
+ "rewards/rejected": -1.007359266281128,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.3215003348961822,
448
+ "grad_norm": 12.766870563789471,
449
+ "learning_rate": 4.2908093568271187e-07,
450
+ "logits/chosen": -2.9606540203094482,
451
+ "logits/rejected": -2.9726486206054688,
452
+ "logps/chosen": -0.9194633364677429,
453
+ "logps/rejected": -0.9709534645080566,
454
+ "loss": -0.0371,
455
+ "rewards/accuracies": 0.581250011920929,
456
+ "rewards/chosen": -0.9194633364677429,
457
+ "rewards/margins": 0.05149019509553909,
458
+ "rewards/rejected": -0.9709534645080566,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3322170127260549,
463
+ "grad_norm": 12.28868938106036,
464
+ "learning_rate": 4.2241695159714843e-07,
465
+ "logits/chosen": -3.043233633041382,
466
+ "logits/rejected": -3.0254199504852295,
467
+ "logps/chosen": -0.9320791959762573,
468
+ "logps/rejected": -0.9708281755447388,
469
+ "loss": -0.0274,
470
+ "rewards/accuracies": 0.5625,
471
+ "rewards/chosen": -0.9320791959762573,
472
+ "rewards/margins": 0.038748957216739655,
473
+ "rewards/rejected": -0.9708281755447388,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.34293369055592765,
478
+ "grad_norm": 16.212616603609877,
479
+ "learning_rate": 4.1551067454613074e-07,
480
+ "logits/chosen": -2.943720579147339,
481
+ "logits/rejected": -2.928537607192993,
482
+ "logps/chosen": -0.921017050743103,
483
+ "logps/rejected": -0.9882138967514038,
484
+ "loss": -0.0359,
485
+ "rewards/accuracies": 0.574999988079071,
486
+ "rewards/chosen": -0.921017050743103,
487
+ "rewards/margins": 0.06719694286584854,
488
+ "rewards/rejected": -0.9882138967514038,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.3536503683858004,
493
+ "grad_norm": 15.792664568932544,
494
+ "learning_rate": 4.0837180973747876e-07,
495
+ "logits/chosen": -3.0298409461975098,
496
+ "logits/rejected": -3.0069289207458496,
497
+ "logps/chosen": -0.9174503087997437,
498
+ "logps/rejected": -0.9726656079292297,
499
+ "loss": -0.0342,
500
+ "rewards/accuracies": 0.5687500238418579,
501
+ "rewards/chosen": -0.9174503087997437,
502
+ "rewards/margins": 0.05521535873413086,
503
+ "rewards/rejected": -0.9726656079292297,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3643670462156731,
508
+ "grad_norm": 10.787104513853434,
509
+ "learning_rate": 4.0101038922841455e-07,
510
+ "logits/chosen": -2.968522548675537,
511
+ "logits/rejected": -2.9739623069763184,
512
+ "logps/chosen": -0.9771224856376648,
513
+ "logps/rejected": -1.0373847484588623,
514
+ "loss": -0.0466,
515
+ "rewards/accuracies": 0.5375000238418579,
516
+ "rewards/chosen": -0.9771224856376648,
517
+ "rewards/margins": 0.06026231497526169,
518
+ "rewards/rejected": -1.0373847484588623,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.3750837240455459,
523
+ "grad_norm": 13.17830711446757,
524
+ "learning_rate": 3.934367578277783e-07,
525
+ "logits/chosen": -2.9837470054626465,
526
+ "logits/rejected": -2.9880218505859375,
527
+ "logps/chosen": -1.000985026359558,
528
+ "logps/rejected": -1.0419981479644775,
529
+ "loss": -0.0381,
530
+ "rewards/accuracies": 0.612500011920929,
531
+ "rewards/chosen": -1.000985026359558,
532
+ "rewards/margins": 0.041013117879629135,
533
+ "rewards/rejected": -1.0419981479644775,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.38580040187541864,
538
+ "grad_norm": 14.72612824066128,
539
+ "learning_rate": 3.856615585587434e-07,
540
+ "logits/chosen": -2.9933667182922363,
541
+ "logits/rejected": -3.0047719478607178,
542
+ "logps/chosen": -1.0653940439224243,
543
+ "logps/rejected": -1.1087322235107422,
544
+ "loss": -0.0319,
545
+ "rewards/accuracies": 0.518750011920929,
546
+ "rewards/chosen": -1.0653940439224243,
547
+ "rewards/margins": 0.043338216841220856,
548
+ "rewards/rejected": -1.1087322235107422,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.3965170797052914,
553
+ "grad_norm": 13.397319728202142,
554
+ "learning_rate": 3.776957177024581e-07,
555
+ "logits/chosen": -2.9812378883361816,
556
+ "logits/rejected": -2.9986259937286377,
557
+ "logps/chosen": -1.0316323041915894,
558
+ "logps/rejected": -1.0616919994354248,
559
+ "loss": -0.033,
560
+ "rewards/accuracies": 0.574999988079071,
561
+ "rewards/chosen": -1.0316323041915894,
562
+ "rewards/margins": 0.030059661716222763,
563
+ "rewards/rejected": -1.0616919994354248,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.4072337575351641,
568
+ "grad_norm": 14.059564629221503,
569
+ "learning_rate": 3.69550429443633e-07,
570
+ "logits/chosen": -2.8960227966308594,
571
+ "logits/rejected": -2.913637161254883,
572
+ "logps/chosen": -1.012019157409668,
573
+ "logps/rejected": -1.215237021446228,
574
+ "loss": -0.0447,
575
+ "rewards/accuracies": 0.65625,
576
+ "rewards/chosen": -1.012019157409668,
577
+ "rewards/margins": 0.20321793854236603,
578
+ "rewards/rejected": -1.215237021446228,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.41795043536503684,
583
+ "grad_norm": 14.952805148520074,
584
+ "learning_rate": 3.612371401396502e-07,
585
+ "logits/chosen": -3.007540225982666,
586
+ "logits/rejected": -2.9880564212799072,
587
+ "logps/chosen": -1.0366661548614502,
588
+ "logps/rejected": -1.0943790674209595,
589
+ "loss": -0.0368,
590
+ "rewards/accuracies": 0.5625,
591
+ "rewards/chosen": -1.0366661548614502,
592
+ "rewards/margins": 0.05771297961473465,
593
+ "rewards/rejected": -1.0943790674209595,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4286671131949096,
598
+ "grad_norm": 14.170450035952996,
599
+ "learning_rate": 3.527675322353011e-07,
600
+ "logits/chosen": -2.922602415084839,
601
+ "logits/rejected": -2.9457390308380127,
602
+ "logps/chosen": -0.970561146736145,
603
+ "logps/rejected": -1.0033313035964966,
604
+ "loss": -0.0473,
605
+ "rewards/accuracies": 0.518750011920929,
606
+ "rewards/chosen": -0.970561146736145,
607
+ "rewards/margins": 0.032770149409770966,
608
+ "rewards/rejected": -1.0033313035964966,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.4393837910247823,
613
+ "grad_norm": 15.488305590600266,
614
+ "learning_rate": 3.4415350784575693e-07,
615
+ "logits/chosen": -3.004404067993164,
616
+ "logits/rejected": -2.9882898330688477,
617
+ "logps/chosen": -0.9613070487976074,
618
+ "logps/rejected": -1.0151447057724,
619
+ "loss": -0.044,
620
+ "rewards/accuracies": 0.612500011920929,
621
+ "rewards/chosen": -0.9613070487976074,
622
+ "rewards/margins": 0.053837649524211884,
623
+ "rewards/rejected": -1.0151447057724,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.45010046885465504,
628
+ "grad_norm": 13.543647630514888,
629
+ "learning_rate": 3.3540717203084224e-07,
630
+ "logits/chosen": -2.956808090209961,
631
+ "logits/rejected": -2.9622817039489746,
632
+ "logps/chosen": -0.9170505404472351,
633
+ "logps/rejected": -0.9884069561958313,
634
+ "loss": -0.0514,
635
+ "rewards/accuracies": 0.606249988079071,
636
+ "rewards/chosen": -0.9170505404472351,
637
+ "rewards/margins": 0.07135634124279022,
638
+ "rewards/rejected": -0.9884069561958313,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.4608171466845278,
643
+ "grad_norm": 14.183913951293327,
644
+ "learning_rate": 3.265408157841153e-07,
645
+ "logits/chosen": -2.9880080223083496,
646
+ "logits/rejected": -2.986445903778076,
647
+ "logps/chosen": -0.9918737411499023,
648
+ "logps/rejected": -1.0286133289337158,
649
+ "loss": -0.0446,
650
+ "rewards/accuracies": 0.550000011920929,
651
+ "rewards/chosen": -0.9918737411499023,
652
+ "rewards/margins": 0.036739740520715714,
653
+ "rewards/rejected": -1.0286133289337158,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.4715338245144005,
658
+ "grad_norm": 16.687524624276737,
659
+ "learning_rate": 3.1756689876066187e-07,
660
+ "logits/chosen": -2.940664291381836,
661
+ "logits/rejected": -2.940556049346924,
662
+ "logps/chosen": -0.9756967425346375,
663
+ "logps/rejected": -1.0494619607925415,
664
+ "loss": -0.0496,
665
+ "rewards/accuracies": 0.5375000238418579,
666
+ "rewards/chosen": -0.9756967425346375,
667
+ "rewards/margins": 0.07376515865325928,
668
+ "rewards/rejected": -1.0494619607925415,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4822505023442733,
673
+ "grad_norm": 15.106449736541158,
674
+ "learning_rate": 3.0849803176787184e-07,
675
+ "logits/chosen": -2.978764057159424,
676
+ "logits/rejected": -3.02057147026062,
677
+ "logps/chosen": -0.9675830602645874,
678
+ "logps/rejected": -1.0782067775726318,
679
+ "loss": -0.0528,
680
+ "rewards/accuracies": 0.606249988079071,
681
+ "rewards/chosen": -0.9675830602645874,
682
+ "rewards/margins": 0.11062371730804443,
683
+ "rewards/rejected": -1.0782067775726318,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.49296718017414604,
688
+ "grad_norm": 19.732642999044504,
689
+ "learning_rate": 2.993469590438065e-07,
690
+ "logits/chosen": -2.91894793510437,
691
+ "logits/rejected": -2.92021107673645,
692
+ "logps/chosen": -0.9777423143386841,
693
+ "logps/rejected": -1.0478038787841797,
694
+ "loss": -0.0487,
695
+ "rewards/accuracies": 0.606249988079071,
696
+ "rewards/chosen": -0.9777423143386841,
697
+ "rewards/margins": 0.07006163895130157,
698
+ "rewards/rejected": -1.0478038787841797,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.5036838580040187,
703
+ "grad_norm": 15.470655040763342,
704
+ "learning_rate": 2.901265403480597e-07,
705
+ "logits/chosen": -2.868373394012451,
706
+ "logits/rejected": -2.8822197914123535,
707
+ "logps/chosen": -0.9746626615524292,
708
+ "logps/rejected": -1.109392523765564,
709
+ "loss": -0.0532,
710
+ "rewards/accuracies": 0.574999988079071,
711
+ "rewards/chosen": -0.9746626615524292,
712
+ "rewards/margins": 0.13472989201545715,
713
+ "rewards/rejected": -1.109392523765564,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5144005358338914,
718
+ "grad_norm": 18.117444556863273,
719
+ "learning_rate": 2.808497328902782e-07,
720
+ "logits/chosen": -2.829807758331299,
721
+ "logits/rejected": -2.837395191192627,
722
+ "logps/chosen": -1.0404951572418213,
723
+ "logps/rejected": -1.1007030010223389,
724
+ "loss": -0.0453,
725
+ "rewards/accuracies": 0.6000000238418579,
726
+ "rewards/chosen": -1.0404951572418213,
727
+ "rewards/margins": 0.06020789220929146,
728
+ "rewards/rejected": -1.1007030010223389,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5251172136637642,
733
+ "grad_norm": 18.628678925066545,
734
+ "learning_rate": 2.715295731217396e-07,
735
+ "logits/chosen": -2.81119966506958,
736
+ "logits/rejected": -2.815497636795044,
737
+ "logps/chosen": -1.0369569063186646,
738
+ "logps/rejected": -1.112683892250061,
739
+ "loss": -0.0596,
740
+ "rewards/accuracies": 0.5562499761581421,
741
+ "rewards/chosen": -1.0369569063186646,
742
+ "rewards/margins": 0.07572712004184723,
743
+ "rewards/rejected": -1.112683892250061,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.535833891493637,
748
+ "grad_norm": 17.866763466807367,
749
+ "learning_rate": 2.621791584155725e-07,
750
+ "logits/chosen": -2.83900785446167,
751
+ "logits/rejected": -2.859978199005127,
752
+ "logps/chosen": -1.1023390293121338,
753
+ "logps/rejected": -1.1515963077545166,
754
+ "loss": -0.0617,
755
+ "rewards/accuracies": 0.6187499761581421,
756
+ "rewards/chosen": -1.1023390293121338,
757
+ "rewards/margins": 0.04925721138715744,
758
+ "rewards/rejected": -1.1515963077545166,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.5465505693235098,
763
+ "grad_norm": 17.478329638335467,
764
+ "learning_rate": 2.52811628661367e-07,
765
+ "logits/chosen": -2.8983101844787598,
766
+ "logits/rejected": -2.908754348754883,
767
+ "logps/chosen": -1.0288032293319702,
768
+ "logps/rejected": -1.134108066558838,
769
+ "loss": -0.0631,
770
+ "rewards/accuracies": 0.543749988079071,
771
+ "rewards/chosen": -1.0288032293319702,
772
+ "rewards/margins": 0.10530481487512589,
773
+ "rewards/rejected": -1.134108066558838,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5572672471533825,
778
+ "grad_norm": 15.049601923886751,
779
+ "learning_rate": 2.434401478000353e-07,
780
+ "logits/chosen": -2.8707144260406494,
781
+ "logits/rejected": -2.876131057739258,
782
+ "logps/chosen": -1.0516908168792725,
783
+ "logps/rejected": -1.1409704685211182,
784
+ "loss": -0.0405,
785
+ "rewards/accuracies": 0.5,
786
+ "rewards/chosen": -1.0516908168792725,
787
+ "rewards/margins": 0.08927960693836212,
788
+ "rewards/rejected": -1.1409704685211182,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5679839249832552,
793
+ "grad_norm": 14.714810625194913,
794
+ "learning_rate": 2.340778853248759e-07,
795
+ "logits/chosen": -2.86578369140625,
796
+ "logits/rejected": -2.8567006587982178,
797
+ "logps/chosen": -1.0564695596694946,
798
+ "logps/rejected": -1.199512004852295,
799
+ "loss": -0.0695,
800
+ "rewards/accuracies": 0.6312500238418579,
801
+ "rewards/chosen": -1.0564695596694946,
802
+ "rewards/margins": 0.143042653799057,
803
+ "rewards/rejected": -1.199512004852295,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.578700602813128,
808
+ "grad_norm": 18.053080062016626,
809
+ "learning_rate": 2.247379977748339e-07,
810
+ "logits/chosen": -2.9022586345672607,
811
+ "logits/rejected": -2.9201228618621826,
812
+ "logps/chosen": -1.0403499603271484,
813
+ "logps/rejected": -1.1265124082565308,
814
+ "loss": -0.0673,
815
+ "rewards/accuracies": 0.606249988079071,
816
+ "rewards/chosen": -1.0403499603271484,
817
+ "rewards/margins": 0.08616244792938232,
818
+ "rewards/rejected": -1.1265124082565308,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.5894172806430007,
823
+ "grad_norm": 14.15566071309189,
824
+ "learning_rate": 2.1543361024596573e-07,
825
+ "logits/chosen": -2.9802463054656982,
826
+ "logits/rejected": -2.988959550857544,
827
+ "logps/chosen": -0.9800962209701538,
828
+ "logps/rejected": -1.0803120136260986,
829
+ "loss": -0.0525,
830
+ "rewards/accuracies": 0.59375,
831
+ "rewards/chosen": -0.9800962209701538,
832
+ "rewards/margins": 0.1002158373594284,
833
+ "rewards/rejected": -1.0803120136260986,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.6001339584728734,
838
+ "grad_norm": 17.56629547418189,
839
+ "learning_rate": 2.0617779794709082e-07,
840
+ "logits/chosen": -2.8620638847351074,
841
+ "logits/rejected": -2.8629186153411865,
842
+ "logps/chosen": -1.103073000907898,
843
+ "logps/rejected": -1.196608304977417,
844
+ "loss": -0.0632,
845
+ "rewards/accuracies": 0.581250011920929,
846
+ "rewards/chosen": -1.103073000907898,
847
+ "rewards/margins": 0.09353531897068024,
848
+ "rewards/rejected": -1.196608304977417,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.6108506363027462,
853
+ "grad_norm": 15.46761530330997,
854
+ "learning_rate": 1.9698356782554687e-07,
855
+ "logits/chosen": -2.9556548595428467,
856
+ "logits/rejected": -2.9529995918273926,
857
+ "logps/chosen": -1.109263300895691,
858
+ "logps/rejected": -1.1731650829315186,
859
+ "loss": -0.0564,
860
+ "rewards/accuracies": 0.5249999761581421,
861
+ "rewards/chosen": -1.109263300895691,
862
+ "rewards/margins": 0.06390184909105301,
863
+ "rewards/rejected": -1.1731650829315186,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6215673141326189,
868
+ "grad_norm": 16.8037567850014,
869
+ "learning_rate": 1.878638402888727e-07,
870
+ "logits/chosen": -2.9940178394317627,
871
+ "logits/rejected": -2.9970099925994873,
872
+ "logps/chosen": -0.9795197248458862,
873
+ "logps/rejected": -1.0418453216552734,
874
+ "loss": -0.0668,
875
+ "rewards/accuracies": 0.5687500238418579,
876
+ "rewards/chosen": -0.9795197248458862,
877
+ "rewards/margins": 0.06232555955648422,
878
+ "rewards/rejected": -1.0418453216552734,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6322839919624916,
883
+ "grad_norm": 16.60747046570722,
884
+ "learning_rate": 1.7883143104810223e-07,
885
+ "logits/chosen": -2.9415085315704346,
886
+ "logits/rejected": -2.9544739723205566,
887
+ "logps/chosen": -1.069349765777588,
888
+ "logps/rejected": -1.2494323253631592,
889
+ "loss": -0.0739,
890
+ "rewards/accuracies": 0.625,
891
+ "rewards/chosen": -1.069349765777588,
892
+ "rewards/margins": 0.1800827533006668,
893
+ "rewards/rejected": -1.2494323253631592,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6430006697923644,
898
+ "grad_norm": 15.422934564351497,
899
+ "learning_rate": 1.6989903310818548e-07,
900
+ "logits/chosen": -3.0317275524139404,
901
+ "logits/rejected": -3.049278736114502,
902
+ "logps/chosen": -1.0510863065719604,
903
+ "logps/rejected": -1.1395753622055054,
904
+ "loss": -0.0517,
905
+ "rewards/accuracies": 0.5874999761581421,
906
+ "rewards/chosen": -1.0510863065719604,
907
+ "rewards/margins": 0.08848897367715836,
908
+ "rewards/rejected": -1.1395753622055054,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6537173476222371,
913
+ "grad_norm": 17.56071364411128,
914
+ "learning_rate": 1.610791989308466e-07,
915
+ "logits/chosen": -2.9625232219696045,
916
+ "logits/rejected": -2.9480719566345215,
917
+ "logps/chosen": -1.0810691118240356,
918
+ "logps/rejected": -1.1474703550338745,
919
+ "loss": -0.0711,
920
+ "rewards/accuracies": 0.581250011920929,
921
+ "rewards/chosen": -1.0810691118240356,
922
+ "rewards/margins": 0.06640125066041946,
923
+ "rewards/rejected": -1.1474703550338745,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6644340254521098,
928
+ "grad_norm": 19.400175535223255,
929
+ "learning_rate": 1.523843227949418e-07,
930
+ "logits/chosen": -3.0158638954162598,
931
+ "logits/rejected": -3.014029026031494,
932
+ "logps/chosen": -1.054434061050415,
933
+ "logps/rejected": -1.1792142391204834,
934
+ "loss": -0.0711,
935
+ "rewards/accuracies": 0.625,
936
+ "rewards/chosen": -1.054434061050415,
937
+ "rewards/margins": 0.12478007376194,
938
+ "rewards/rejected": -1.1792142391204834,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6751507032819826,
943
+ "grad_norm": 18.063066961906372,
944
+ "learning_rate": 1.4382662337910867e-07,
945
+ "logits/chosen": -2.9173102378845215,
946
+ "logits/rejected": -2.9165103435516357,
947
+ "logps/chosen": -1.1207153797149658,
948
+ "logps/rejected": -1.2241191864013672,
949
+ "loss": -0.0582,
950
+ "rewards/accuracies": 0.6312500238418579,
951
+ "rewards/chosen": -1.1207153797149658,
952
+ "rewards/margins": 0.10340368747711182,
953
+ "rewards/rejected": -1.2241191864013672,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6858673811118553,
958
+ "grad_norm": 17.656998709658712,
959
+ "learning_rate": 1.3541812659118104e-07,
960
+ "logits/chosen": -2.924173593521118,
961
+ "logits/rejected": -2.901674747467041,
962
+ "logps/chosen": -1.1284511089324951,
963
+ "logps/rejected": -1.2347378730773926,
964
+ "loss": -0.0605,
965
+ "rewards/accuracies": 0.6000000238418579,
966
+ "rewards/chosen": -1.1284511089324951,
967
+ "rewards/margins": 0.10628668963909149,
968
+ "rewards/rejected": -1.2347378730773926,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.696584058941728,
973
+ "grad_norm": 17.674353062779463,
974
+ "learning_rate": 1.2717064866850047e-07,
975
+ "logits/chosen": -2.9069221019744873,
976
+ "logits/rejected": -2.9266703128814697,
977
+ "logps/chosen": -1.0635308027267456,
978
+ "logps/rejected": -1.2443645000457764,
979
+ "loss": -0.076,
980
+ "rewards/accuracies": 0.637499988079071,
981
+ "rewards/chosen": -1.0635308027267456,
982
+ "rewards/margins": 0.1808338761329651,
983
+ "rewards/rejected": -1.2443645000457764,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.7073007367716008,
988
+ "grad_norm": 16.692003983984833,
989
+ "learning_rate": 1.1909577957287117e-07,
990
+ "logits/chosen": -2.9482550621032715,
991
+ "logits/rejected": -2.9383444786071777,
992
+ "logps/chosen": -1.1115998029708862,
993
+ "logps/rejected": -1.269691824913025,
994
+ "loss": -0.0875,
995
+ "rewards/accuracies": 0.606249988079071,
996
+ "rewards/chosen": -1.1115998029708862,
997
+ "rewards/margins": 0.15809203684329987,
998
+ "rewards/rejected": -1.269691824913025,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7180174146014735,
1003
+ "grad_norm": 16.832132437998734,
1004
+ "learning_rate": 1.1120486670349441e-07,
1005
+ "logits/chosen": -3.0022974014282227,
1006
+ "logits/rejected": -3.0084285736083984,
1007
+ "logps/chosen": -1.1076433658599854,
1008
+ "logps/rejected": -1.2158708572387695,
1009
+ "loss": -0.0631,
1010
+ "rewards/accuracies": 0.6187499761581421,
1011
+ "rewards/chosen": -1.1076433658599854,
1012
+ "rewards/margins": 0.10822737216949463,
1013
+ "rewards/rejected": -1.2158708572387695,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7287340924313462,
1018
+ "grad_norm": 16.746834458412387,
1019
+ "learning_rate": 1.0350899895076948e-07,
1020
+ "logits/chosen": -2.960242509841919,
1021
+ "logits/rejected": -2.9590137004852295,
1022
+ "logps/chosen": -1.1618969440460205,
1023
+ "logps/rejected": -1.3054715394973755,
1024
+ "loss": -0.063,
1025
+ "rewards/accuracies": 0.6000000238418579,
1026
+ "rewards/chosen": -1.1618969440460205,
1027
+ "rewards/margins": 0.14357443153858185,
1028
+ "rewards/rejected": -1.3054715394973755,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.739450770261219,
1033
+ "grad_norm": 16.472011449839883,
1034
+ "learning_rate": 9.601899111337069e-08,
1035
+ "logits/chosen": -2.9834091663360596,
1036
+ "logits/rejected": -2.9975457191467285,
1037
+ "logps/chosen": -1.126527190208435,
1038
+ "logps/rejected": -1.3144327402114868,
1039
+ "loss": -0.0777,
1040
+ "rewards/accuracies": 0.543749988079071,
1041
+ "rewards/chosen": -1.126527190208435,
1042
+ "rewards/margins": 0.18790560960769653,
1043
+ "rewards/rejected": -1.3144327402114868,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7501674480910918,
1048
+ "grad_norm": 17.215572295903478,
1049
+ "learning_rate": 8.874536870049765e-08,
1050
+ "logits/chosen": -2.969423294067383,
1051
+ "logits/rejected": -2.969230890274048,
1052
+ "logps/chosen": -1.127826452255249,
1053
+ "logps/rejected": -1.271470069885254,
1054
+ "loss": -0.0752,
1055
+ "rewards/accuracies": 0.6000000238418579,
1056
+ "rewards/chosen": -1.127826452255249,
1057
+ "rewards/margins": 0.1436435580253601,
1058
+ "rewards/rejected": -1.271470069885254,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7608841259209645,
1063
+ "grad_norm": 19.033752258043222,
1064
+ "learning_rate": 8.169835314065663e-08,
1065
+ "logits/chosen": -2.9632205963134766,
1066
+ "logits/rejected": -2.9548847675323486,
1067
+ "logps/chosen": -1.1820392608642578,
1068
+ "logps/rejected": -1.2698676586151123,
1069
+ "loss": -0.0668,
1070
+ "rewards/accuracies": 0.518750011920929,
1071
+ "rewards/chosen": -1.1820392608642578,
1072
+ "rewards/margins": 0.08782847970724106,
1073
+ "rewards/rejected": -1.2698676586151123,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7716008037508373,
1078
+ "grad_norm": 17.064795493163807,
1079
+ "learning_rate": 7.488784741775816e-08,
1080
+ "logits/chosen": -2.976466178894043,
1081
+ "logits/rejected": -2.9713473320007324,
1082
+ "logps/chosen": -1.054131269454956,
1083
+ "logps/rejected": -1.1566834449768066,
1084
+ "loss": -0.0663,
1085
+ "rewards/accuracies": 0.5625,
1086
+ "rewards/chosen": -1.054131269454956,
1087
+ "rewards/margins": 0.10255217552185059,
1088
+ "rewards/rejected": -1.1566834449768066,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.78231748158071,
1093
+ "grad_norm": 17.868156711335107,
1094
+ "learning_rate": 6.832342215471715e-08,
1095
+ "logits/chosen": -2.98659086227417,
1096
+ "logits/rejected": -2.986912488937378,
1097
+ "logps/chosen": -1.1025737524032593,
1098
+ "logps/rejected": -1.242219090461731,
1099
+ "loss": -0.0823,
1100
+ "rewards/accuracies": 0.612500011920929,
1101
+ "rewards/chosen": -1.1025737524032593,
1102
+ "rewards/margins": 0.13964524865150452,
1103
+ "rewards/rejected": -1.242219090461731,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7930341594105828,
1108
+ "grad_norm": 24.714287844140323,
1109
+ "learning_rate": 6.201430216410985e-08,
1110
+ "logits/chosen": -3.0034446716308594,
1111
+ "logits/rejected": -3.001354217529297,
1112
+ "logps/chosen": -1.1147871017456055,
1113
+ "logps/rejected": -1.200984239578247,
1114
+ "loss": -0.081,
1115
+ "rewards/accuracies": 0.5625,
1116
+ "rewards/chosen": -1.1147871017456055,
1117
+ "rewards/margins": 0.08619704097509384,
1118
+ "rewards/rejected": -1.200984239578247,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.8037508372404555,
1123
+ "grad_norm": 20.89166421346418,
1124
+ "learning_rate": 5.596935348479029e-08,
1125
+ "logits/chosen": -2.9388105869293213,
1126
+ "logits/rejected": -2.948521137237549,
1127
+ "logps/chosen": -1.2442572116851807,
1128
+ "logps/rejected": -1.393157958984375,
1129
+ "loss": -0.0861,
1130
+ "rewards/accuracies": 0.5625,
1131
+ "rewards/chosen": -1.2442572116851807,
1132
+ "rewards/margins": 0.1489005833864212,
1133
+ "rewards/rejected": -1.393157958984375,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.8144675150703282,
1138
+ "grad_norm": 22.406198534031674,
1139
+ "learning_rate": 5.01970709226808e-08,
1140
+ "logits/chosen": -3.028179883956909,
1141
+ "logits/rejected": -3.009589672088623,
1142
+ "logps/chosen": -1.0915172100067139,
1143
+ "logps/rejected": -1.243607997894287,
1144
+ "loss": -0.0837,
1145
+ "rewards/accuracies": 0.637499988079071,
1146
+ "rewards/chosen": -1.0915172100067139,
1147
+ "rewards/margins": 0.1520906686782837,
1148
+ "rewards/rejected": -1.243607997894287,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.825184192900201,
1153
+ "grad_norm": 24.898962036749563,
1154
+ "learning_rate": 4.4705566113246635e-08,
1155
+ "logits/chosen": -2.9715943336486816,
1156
+ "logits/rejected": -2.949638605117798,
1157
+ "logps/chosen": -1.228461503982544,
1158
+ "logps/rejected": -1.3865272998809814,
1159
+ "loss": -0.0897,
1160
+ "rewards/accuracies": 0.612500011920929,
1161
+ "rewards/chosen": -1.228461503982544,
1162
+ "rewards/margins": 0.15806564688682556,
1163
+ "rewards/rejected": -1.3865272998809814,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.8359008707300737,
1168
+ "grad_norm": 19.449984589836117,
1169
+ "learning_rate": 3.950255612243042e-08,
1170
+ "logits/chosen": -2.951904058456421,
1171
+ "logits/rejected": -2.928208827972412,
1172
+ "logps/chosen": -1.2001017332077026,
1173
+ "logps/rejected": -1.3440535068511963,
1174
+ "loss": -0.0724,
1175
+ "rewards/accuracies": 0.612500011920929,
1176
+ "rewards/chosen": -1.2001017332077026,
1177
+ "rewards/margins": 0.1439516693353653,
1178
+ "rewards/rejected": -1.3440535068511963,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8466175485599464,
1183
+ "grad_norm": 19.857222600639766,
1184
+ "learning_rate": 3.459535260206384e-08,
1185
+ "logits/chosen": -2.9977169036865234,
1186
+ "logits/rejected": -3.020946979522705,
1187
+ "logps/chosen": -1.096103549003601,
1188
+ "logps/rejected": -1.21526300907135,
1189
+ "loss": -0.0898,
1190
+ "rewards/accuracies": 0.6312500238418579,
1191
+ "rewards/chosen": -1.096103549003601,
1192
+ "rewards/margins": 0.11915931850671768,
1193
+ "rewards/rejected": -1.21526300907135,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8573342263898192,
1198
+ "grad_norm": 21.73532568075866,
1199
+ "learning_rate": 2.999085151499764e-08,
1200
+ "logits/chosen": -2.9534425735473633,
1201
+ "logits/rejected": -2.9359939098358154,
1202
+ "logps/chosen": -1.0908204317092896,
1203
+ "logps/rejected": -1.356081485748291,
1204
+ "loss": -0.0905,
1205
+ "rewards/accuracies": 0.737500011920929,
1206
+ "rewards/chosen": -1.0908204317092896,
1207
+ "rewards/margins": 0.2652612626552582,
1208
+ "rewards/rejected": -1.356081485748291,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8573342263898192,
1213
+ "eval_logits/chosen": -2.8999884128570557,
1214
+ "eval_logits/rejected": -2.892754316329956,
1215
+ "eval_logps/chosen": -1.1346372365951538,
1216
+ "eval_logps/rejected": -1.2466005086898804,
1217
+ "eval_loss": -0.07080772519111633,
1218
+ "eval_rewards/accuracies": 0.5757978558540344,
1219
+ "eval_rewards/chosen": -1.1346372365951538,
1220
+ "eval_rewards/margins": 0.11196334660053253,
1221
+ "eval_rewards/rejected": -1.2466005086898804,
1222
+ "eval_runtime": 432.4273,
1223
+ "eval_samples_per_second": 6.924,
1224
+ "eval_steps_per_second": 0.435,
1225
+ "step": 400
1226
+ },
1227
+ {
1228
+ "epoch": 0.8680509042196919,
1229
+ "grad_norm": 19.440021908588918,
1230
+ "learning_rate": 2.5695523444387747e-08,
1231
+ "logits/chosen": -2.9388387203216553,
1232
+ "logits/rejected": -2.9628615379333496,
1233
+ "logps/chosen": -1.111882209777832,
1234
+ "logps/rejected": -1.2351758480072021,
1235
+ "loss": -0.09,
1236
+ "rewards/accuracies": 0.625,
1237
+ "rewards/chosen": -1.111882209777832,
1238
+ "rewards/margins": 0.12329357862472534,
1239
+ "rewards/rejected": -1.2351758480072021,
1240
+ "step": 405
1241
+ },
1242
+ {
1243
+ "epoch": 0.8787675820495646,
1244
+ "grad_norm": 19.454852119565878,
1245
+ "learning_rate": 2.1715404500756875e-08,
1246
+ "logits/chosen": -2.98136305809021,
1247
+ "logits/rejected": -3.0059518814086914,
1248
+ "logps/chosen": -1.090047836303711,
1249
+ "logps/rejected": -1.203460693359375,
1250
+ "loss": -0.0823,
1251
+ "rewards/accuracies": 0.5874999761581421,
1252
+ "rewards/chosen": -1.090047836303711,
1253
+ "rewards/margins": 0.11341279745101929,
1254
+ "rewards/rejected": -1.203460693359375,
1255
+ "step": 410
1256
+ },
1257
+ {
1258
+ "epoch": 0.8894842598794374,
1259
+ "grad_norm": 27.119138813457198,
1260
+ "learning_rate": 1.8056087839608546e-08,
1261
+ "logits/chosen": -2.9424166679382324,
1262
+ "logits/rejected": -2.9254748821258545,
1263
+ "logps/chosen": -1.1260377168655396,
1264
+ "logps/rejected": -1.3184921741485596,
1265
+ "loss": -0.1086,
1266
+ "rewards/accuracies": 0.6875,
1267
+ "rewards/chosen": -1.1260377168655396,
1268
+ "rewards/margins": 0.19245454668998718,
1269
+ "rewards/rejected": -1.3184921741485596,
1270
+ "step": 415
1271
+ },
1272
+ {
1273
+ "epoch": 0.9002009377093101,
1274
+ "grad_norm": 19.3060602023721,
1275
+ "learning_rate": 1.4722715801513935e-08,
1276
+ "logits/chosen": -2.9605276584625244,
1277
+ "logits/rejected": -2.967475414276123,
1278
+ "logps/chosen": -1.0344493389129639,
1279
+ "logps/rejected": -1.0916310548782349,
1280
+ "loss": -0.0802,
1281
+ "rewards/accuracies": 0.5249999761581421,
1282
+ "rewards/chosen": -1.0344493389129639,
1283
+ "rewards/margins": 0.057181768119335175,
1284
+ "rewards/rejected": -1.0916310548782349,
1285
+ "step": 420
1286
+ },
1287
+ {
1288
+ "epoch": 0.9109176155391828,
1289
+ "grad_norm": 20.048601077954377,
1290
+ "learning_rate": 1.1719972685717395e-08,
1291
+ "logits/chosen": -2.970942258834839,
1292
+ "logits/rejected": -2.9757351875305176,
1293
+ "logps/chosen": -1.0653189420700073,
1294
+ "logps/rejected": -1.3184258937835693,
1295
+ "loss": -0.1043,
1296
+ "rewards/accuracies": 0.65625,
1297
+ "rewards/chosen": -1.0653189420700073,
1298
+ "rewards/margins": 0.2531070411205292,
1299
+ "rewards/rejected": -1.3184258937835693,
1300
+ "step": 425
1301
+ },
1302
+ {
1303
+ "epoch": 0.9216342933690556,
1304
+ "grad_norm": 21.66418470338373,
1305
+ "learning_rate": 9.05207816741485e-09,
1306
+ "logits/chosen": -2.939943313598633,
1307
+ "logits/rejected": -2.9273343086242676,
1308
+ "logps/chosen": -1.2503459453582764,
1309
+ "logps/rejected": -1.4009029865264893,
1310
+ "loss": -0.1013,
1311
+ "rewards/accuracies": 0.59375,
1312
+ "rewards/chosen": -1.2503459453582764,
1313
+ "rewards/margins": 0.15055687725543976,
1314
+ "rewards/rejected": -1.4009029865264893,
1315
+ "step": 430
1316
+ },
1317
+ {
1318
+ "epoch": 0.9323509711989283,
1319
+ "grad_norm": 21.774320932145653,
1320
+ "learning_rate": 6.722781367956481e-09,
1321
+ "logits/chosen": -3.0610954761505127,
1322
+ "logits/rejected": -3.0484843254089355,
1323
+ "logps/chosen": -1.0789310932159424,
1324
+ "logps/rejected": -1.2742266654968262,
1325
+ "loss": -0.1009,
1326
+ "rewards/accuracies": 0.59375,
1327
+ "rewards/chosen": -1.0789310932159424,
1328
+ "rewards/margins": 0.19529545307159424,
1329
+ "rewards/rejected": -1.2742266654968262,
1330
+ "step": 435
1331
+ },
1332
+ {
1333
+ "epoch": 0.943067649028801,
1334
+ "grad_norm": 19.319233646112725,
1335
+ "learning_rate": 4.735355586305861e-09,
1336
+ "logits/chosen": -2.94116473197937,
1337
+ "logits/rejected": -2.949489116668701,
1338
+ "logps/chosen": -1.1311179399490356,
1339
+ "logps/rejected": -1.3173315525054932,
1340
+ "loss": -0.0993,
1341
+ "rewards/accuracies": 0.6499999761581421,
1342
+ "rewards/chosen": -1.1311179399490356,
1343
+ "rewards/margins": 0.1862136423587799,
1344
+ "rewards/rejected": -1.3173315525054932,
1345
+ "step": 440
1346
+ },
1347
+ {
1348
+ "epoch": 0.9537843268586738,
1349
+ "grad_norm": 19.556600822562356,
1350
+ "learning_rate": 3.0925936991598454e-09,
1351
+ "logits/chosen": -2.9415977001190186,
1352
+ "logits/rejected": -2.944352388381958,
1353
+ "logps/chosen": -1.1981102228164673,
1354
+ "logps/rejected": -1.329925775527954,
1355
+ "loss": -0.0746,
1356
+ "rewards/accuracies": 0.6187499761581421,
1357
+ "rewards/chosen": -1.1981102228164673,
1358
+ "rewards/margins": 0.1318153738975525,
1359
+ "rewards/rejected": -1.329925775527954,
1360
+ "step": 445
1361
+ },
1362
+ {
1363
+ "epoch": 0.9645010046885466,
1364
+ "grad_norm": 24.43813858171124,
1365
+ "learning_rate": 1.7968042361930225e-09,
1366
+ "logits/chosen": -2.958519697189331,
1367
+ "logits/rejected": -2.9468445777893066,
1368
+ "logps/chosen": -1.1451342105865479,
1369
+ "logps/rejected": -1.265005111694336,
1370
+ "loss": -0.0894,
1371
+ "rewards/accuracies": 0.5687500238418579,
1372
+ "rewards/chosen": -1.1451342105865479,
1373
+ "rewards/margins": 0.11987074464559555,
1374
+ "rewards/rejected": -1.265005111694336,
1375
+ "step": 450
1376
+ },
1377
+ {
1378
+ "epoch": 0.9752176825184193,
1379
+ "grad_norm": 23.495311684580507,
1380
+ "learning_rate": 8.498081359423759e-10,
1381
+ "logits/chosen": -2.9030869007110596,
1382
+ "logits/rejected": -2.932225465774536,
1383
+ "logps/chosen": -1.1186686754226685,
1384
+ "logps/rejected": -1.335756540298462,
1385
+ "loss": -0.1008,
1386
+ "rewards/accuracies": 0.606249988079071,
1387
+ "rewards/chosen": -1.1186686754226685,
1388
+ "rewards/margins": 0.21708789467811584,
1389
+ "rewards/rejected": -1.335756540298462,
1390
+ "step": 455
1391
+ },
1392
+ {
1393
+ "epoch": 0.9859343603482921,
1394
+ "grad_norm": 20.358552883416746,
1395
+ "learning_rate": 2.5293618689056774e-10,
1396
+ "logits/chosen": -2.9370243549346924,
1397
+ "logits/rejected": -2.953622341156006,
1398
+ "logps/chosen": -1.1718332767486572,
1399
+ "logps/rejected": -1.4025189876556396,
1400
+ "loss": -0.0805,
1401
+ "rewards/accuracies": 0.606249988079071,
1402
+ "rewards/chosen": -1.1718332767486572,
1403
+ "rewards/margins": 0.230685755610466,
1404
+ "rewards/rejected": -1.4025189876556396,
1405
+ "step": 460
1406
+ },
1407
+ {
1408
+ "epoch": 0.9966510381781648,
1409
+ "grad_norm": 27.657325299971138,
1410
+ "learning_rate": 7.02715734424153e-12,
1411
+ "logits/chosen": -2.9429261684417725,
1412
+ "logits/rejected": -2.951002359390259,
1413
+ "logps/chosen": -1.2534146308898926,
1414
+ "logps/rejected": -1.3702634572982788,
1415
+ "loss": -0.0688,
1416
+ "rewards/accuracies": 0.6187499761581421,
1417
+ "rewards/chosen": -1.2534146308898926,
1418
+ "rewards/margins": 0.11684894561767578,
1419
+ "rewards/rejected": -1.3702634572982788,
1420
+ "step": 465
1421
+ },
1422
+ {
1423
+ "epoch": 0.9987943737441393,
1424
+ "step": 466,
1425
+ "total_flos": 0.0,
1426
+ "train_loss": 0.0,
1427
+ "train_runtime": 4.3106,
1428
+ "train_samples_per_second": 13854.197,
1429
+ "train_steps_per_second": 108.105
1430
+ }
1431
+ ],
1432
+ "logging_steps": 5,
1433
+ "max_steps": 466,
1434
+ "num_input_tokens_seen": 0,
1435
+ "num_train_epochs": 1,
1436
+ "save_steps": 1000000,
1437
+ "stateful_callbacks": {
1438
+ "TrainerControl": {
1439
+ "args": {
1440
+ "should_epoch_stop": false,
1441
+ "should_evaluate": false,
1442
+ "should_log": false,
1443
+ "should_save": true,
1444
+ "should_training_stop": true
1445
+ },
1446
+ "attributes": {}
1447
+ }
1448
+ },
1449
+ "total_flos": 0.0,
1450
+ "train_batch_size": 2,
1451
+ "trial_name": null,
1452
+ "trial_params": null
1453
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be465117a6d2106022526ee1bd1d741b052c43e8c7af05d0aa7ae9ba7ef3f4b7
3
+ size 7416