abgoswam commited on
Commit
1b22adc
1 Parent(s): ba6b7de

Model save

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: zephyr-7b-dpo-full
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # zephyr-7b-dpo-full
17
+
18
+ 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 None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5000
21
+ - Rewards/chosen: -2.3681
22
+ - Rewards/rejected: -3.4811
23
+ - Rewards/accuracies: 0.7695
24
+ - Rewards/margins: 1.1129
25
+ - Logps/rejected: -610.7911
26
+ - Logps/chosen: -499.4172
27
+ - Logits/rejected: -0.0390
28
+ - Logits/chosen: -0.5081
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-07
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - num_devices: 8
53
+ - gradient_accumulation_steps: 2
54
+ - total_train_batch_size: 128
55
+ - total_eval_batch_size: 64
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: cosine
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - num_epochs: 1
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
64
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
65
+ | 0.5875 | 0.21 | 100 | 0.5814 | -0.6485 | -1.1103 | 0.6953 | 0.4618 | -373.7126 | -327.4548 | -1.8929 | -1.8392 |
66
+ | 0.5306 | 0.42 | 200 | 0.5258 | -1.1476 | -1.9595 | 0.7578 | 0.8118 | -458.6297 | -377.3649 | -0.1647 | -0.4835 |
67
+ | 0.5097 | 0.63 | 300 | 0.5079 | -2.3601 | -3.3817 | 0.7656 | 1.0216 | -600.8517 | -498.6086 | -0.0574 | -0.4658 |
68
+ | 0.4906 | 0.84 | 400 | 0.5000 | -2.3681 | -3.4811 | 0.7695 | 1.1129 | -610.7911 | -499.4172 | -0.0390 | -0.5081 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.38.2
74
+ - Pytorch 2.1.2
75
+ - Datasets 2.14.6
76
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.535196884905444,
4
+ "train_runtime": 3527.4214,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 17.331,
7
+ "train_steps_per_second": 0.136
8
+ }
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": "4.38.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23fa8169c3c25ed7df40b8ed99b8e24e67385bcbb0312e5ed0f5ff2b7ac9321
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91acbf3d987a1c6de2dfbabfe72245eaf0557444a725eb8366b94e26dc2ef45e
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e11803ee3075f50990ecd10b6daba209733ec926ee98208fdbe447c8850772
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
+ }
runs/Mar11_14-59-16_node-0/events.out.tfevents.1710194390.node-0.16413.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ed7ccdb04fd8b4308ab8be4fd47242e782f14027c670a20da81b20630ab9c96
3
- size 35714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a58b6d7a03de6e774bf4ec060d4adcbb7c4f152706308844414284bae1de74
3
+ size 40884
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.535196884905444,
4
+ "train_runtime": 3527.4214,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 17.331,
7
+ "train_steps_per_second": 0.136
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,814 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 100,
6
+ "global_step": 478,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 8.482095207381906,
14
+ "learning_rate": 1.0416666666666666e-08,
15
+ "logits/chosen": -2.715719223022461,
16
+ "logits/rejected": -2.648977279663086,
17
+ "logps/chosen": -280.43304443359375,
18
+ "logps/rejected": -269.5838623046875,
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": 0.02,
28
+ "grad_norm": 8.16883844563723,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.732839345932007,
31
+ "logits/rejected": -2.667829990386963,
32
+ "logps/chosen": -252.18836975097656,
33
+ "logps/rejected": -247.36721801757812,
34
+ "loss": 0.6932,
35
+ "rewards/accuracies": 0.4027777910232544,
36
+ "rewards/chosen": -0.00020123104332014918,
37
+ "rewards/margins": -0.000496760243549943,
38
+ "rewards/rejected": 0.00029552922933362424,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "grad_norm": 14.177063698718772,
44
+ "learning_rate": 2.0833333333333333e-07,
45
+ "logits/chosen": -2.69161057472229,
46
+ "logits/rejected": -2.6473488807678223,
47
+ "logps/chosen": -281.9129333496094,
48
+ "logps/rejected": -240.79598999023438,
49
+ "loss": 0.6923,
50
+ "rewards/accuracies": 0.574999988079071,
51
+ "rewards/chosen": -0.0002729900588747114,
52
+ "rewards/margins": 0.0022440399043262005,
53
+ "rewards/rejected": -0.002517030341550708,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.06,
58
+ "grad_norm": 9.049842796547402,
59
+ "learning_rate": 3.1249999999999997e-07,
60
+ "logits/chosen": -2.7057762145996094,
61
+ "logits/rejected": -2.6666598320007324,
62
+ "logps/chosen": -263.8976135253906,
63
+ "logps/rejected": -272.29376220703125,
64
+ "loss": 0.688,
65
+ "rewards/accuracies": 0.637499988079071,
66
+ "rewards/chosen": 0.005987819284200668,
67
+ "rewards/margins": 0.008191236294806004,
68
+ "rewards/rejected": -0.0022034167777746916,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.08,
73
+ "grad_norm": 8.064536836305289,
74
+ "learning_rate": 4.1666666666666667e-07,
75
+ "logits/chosen": -2.644676446914673,
76
+ "logits/rejected": -2.6523287296295166,
77
+ "logps/chosen": -250.64651489257812,
78
+ "logps/rejected": -240.74032592773438,
79
+ "loss": 0.6775,
80
+ "rewards/accuracies": 0.6499999761581421,
81
+ "rewards/chosen": 0.03351370617747307,
82
+ "rewards/margins": 0.024272698909044266,
83
+ "rewards/rejected": 0.009241009131073952,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.1,
88
+ "grad_norm": 10.48307069571783,
89
+ "learning_rate": 4.999733114418725e-07,
90
+ "logits/chosen": -2.61690616607666,
91
+ "logits/rejected": -2.606698989868164,
92
+ "logps/chosen": -280.32537841796875,
93
+ "logps/rejected": -285.14044189453125,
94
+ "loss": 0.6572,
95
+ "rewards/accuracies": 0.706250011920929,
96
+ "rewards/chosen": 0.027328694239258766,
97
+ "rewards/margins": 0.08270208537578583,
98
+ "rewards/rejected": -0.05537338927388191,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.13,
103
+ "grad_norm": 11.217495552902317,
104
+ "learning_rate": 4.990398100856366e-07,
105
+ "logits/chosen": -2.6028363704681396,
106
+ "logits/rejected": -2.567634344100952,
107
+ "logps/chosen": -257.1751403808594,
108
+ "logps/rejected": -286.7103271484375,
109
+ "loss": 0.6382,
110
+ "rewards/accuracies": 0.6937500238418579,
111
+ "rewards/chosen": -0.04173869267106056,
112
+ "rewards/margins": 0.14793893694877625,
113
+ "rewards/rejected": -0.1896776258945465,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.15,
118
+ "grad_norm": 17.002512653941917,
119
+ "learning_rate": 4.967775735898179e-07,
120
+ "logits/chosen": -2.5477585792541504,
121
+ "logits/rejected": -2.5538854598999023,
122
+ "logps/chosen": -292.3646240234375,
123
+ "logps/rejected": -295.1927795410156,
124
+ "loss": 0.6089,
125
+ "rewards/accuracies": 0.6312500238418579,
126
+ "rewards/chosen": -0.17977146804332733,
127
+ "rewards/margins": 0.22043642401695251,
128
+ "rewards/rejected": -0.40020790696144104,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.17,
133
+ "grad_norm": 20.83722381714638,
134
+ "learning_rate": 4.931986719649298e-07,
135
+ "logits/chosen": -2.428433895111084,
136
+ "logits/rejected": -2.4765429496765137,
137
+ "logps/chosen": -269.8500671386719,
138
+ "logps/rejected": -280.10003662109375,
139
+ "loss": 0.6115,
140
+ "rewards/accuracies": 0.6875,
141
+ "rewards/chosen": -0.11873555183410645,
142
+ "rewards/margins": 0.21846923232078552,
143
+ "rewards/rejected": -0.3372047543525696,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.19,
148
+ "grad_norm": 20.582635256945927,
149
+ "learning_rate": 4.883222001996351e-07,
150
+ "logits/chosen": -2.3149566650390625,
151
+ "logits/rejected": -2.3007912635803223,
152
+ "logps/chosen": -331.8517761230469,
153
+ "logps/rejected": -353.4700012207031,
154
+ "loss": 0.6084,
155
+ "rewards/accuracies": 0.6625000238418579,
156
+ "rewards/chosen": -0.4723566174507141,
157
+ "rewards/margins": 0.2896661162376404,
158
+ "rewards/rejected": -0.7620226740837097,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.21,
163
+ "grad_norm": 15.474211826471516,
164
+ "learning_rate": 4.821741763807186e-07,
165
+ "logits/chosen": -2.2471911907196045,
166
+ "logits/rejected": -2.2106168270111084,
167
+ "logps/chosen": -346.5975646972656,
168
+ "logps/rejected": -342.70501708984375,
169
+ "loss": 0.5875,
170
+ "rewards/accuracies": 0.737500011920929,
171
+ "rewards/chosen": -0.5387172698974609,
172
+ "rewards/margins": 0.4208316206932068,
173
+ "rewards/rejected": -0.9595489501953125,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.21,
178
+ "eval_logits/chosen": -1.839242935180664,
179
+ "eval_logits/rejected": -1.8929309844970703,
180
+ "eval_logps/chosen": -327.45477294921875,
181
+ "eval_logps/rejected": -373.7126159667969,
182
+ "eval_loss": 0.5814013481140137,
183
+ "eval_rewards/accuracies": 0.6953125,
184
+ "eval_rewards/chosen": -0.6485257148742676,
185
+ "eval_rewards/margins": 0.46177732944488525,
186
+ "eval_rewards/rejected": -1.1103030443191528,
187
+ "eval_runtime": 42.9635,
188
+ "eval_samples_per_second": 46.551,
189
+ "eval_steps_per_second": 0.745,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.23,
194
+ "grad_norm": 20.231938142939548,
195
+ "learning_rate": 4.747874028753375e-07,
196
+ "logits/chosen": -1.7017923593521118,
197
+ "logits/rejected": -1.6744320392608643,
198
+ "logps/chosen": -330.83038330078125,
199
+ "logps/rejected": -384.0965576171875,
200
+ "loss": 0.559,
201
+ "rewards/accuracies": 0.7437499761581421,
202
+ "rewards/chosen": -0.6345968246459961,
203
+ "rewards/margins": 0.5422910451889038,
204
+ "rewards/rejected": -1.1768878698349,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 0.25,
209
+ "grad_norm": 33.96451578064435,
210
+ "learning_rate": 4.662012913161997e-07,
211
+ "logits/chosen": -1.5577061176300049,
212
+ "logits/rejected": -1.454756498336792,
213
+ "logps/chosen": -354.79632568359375,
214
+ "logps/rejected": -374.60076904296875,
215
+ "loss": 0.5508,
216
+ "rewards/accuracies": 0.699999988079071,
217
+ "rewards/chosen": -0.6455836892127991,
218
+ "rewards/margins": 0.6170965433120728,
219
+ "rewards/rejected": -1.2626802921295166,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 0.27,
224
+ "grad_norm": 22.138057395490627,
225
+ "learning_rate": 4.5646165232345103e-07,
226
+ "logits/chosen": -1.985395073890686,
227
+ "logits/rejected": -1.7330490350723267,
228
+ "logps/chosen": -381.68524169921875,
229
+ "logps/rejected": -393.6003723144531,
230
+ "loss": 0.5691,
231
+ "rewards/accuracies": 0.7749999761581421,
232
+ "rewards/chosen": -0.6896110773086548,
233
+ "rewards/margins": 0.46295279264450073,
234
+ "rewards/rejected": -1.1525638103485107,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 0.29,
239
+ "grad_norm": 22.948235111766778,
240
+ "learning_rate": 4.456204510851956e-07,
241
+ "logits/chosen": -1.7121162414550781,
242
+ "logits/rejected": -1.4992659091949463,
243
+ "logps/chosen": -352.444580078125,
244
+ "logps/rejected": -359.44293212890625,
245
+ "loss": 0.5444,
246
+ "rewards/accuracies": 0.6875,
247
+ "rewards/chosen": -0.7159131765365601,
248
+ "rewards/margins": 0.5610858798027039,
249
+ "rewards/rejected": -1.2769991159439087,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 0.31,
254
+ "grad_norm": 21.94614729668817,
255
+ "learning_rate": 4.337355301007335e-07,
256
+ "logits/chosen": -1.6999915838241577,
257
+ "logits/rejected": -1.5280932188034058,
258
+ "logps/chosen": -363.3777770996094,
259
+ "logps/rejected": -409.53472900390625,
260
+ "loss": 0.5354,
261
+ "rewards/accuracies": 0.737500011920929,
262
+ "rewards/chosen": -0.6176407933235168,
263
+ "rewards/margins": 0.7246734499931335,
264
+ "rewards/rejected": -1.3423142433166504,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 0.33,
269
+ "grad_norm": 25.951614311748312,
270
+ "learning_rate": 4.2087030056579986e-07,
271
+ "logits/chosen": -0.8817731142044067,
272
+ "logits/rejected": -0.6137579679489136,
273
+ "logps/chosen": -382.1938171386719,
274
+ "logps/rejected": -432.11004638671875,
275
+ "loss": 0.5293,
276
+ "rewards/accuracies": 0.6875,
277
+ "rewards/chosen": -1.0363513231277466,
278
+ "rewards/margins": 0.7439759373664856,
279
+ "rewards/rejected": -1.7803272008895874,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 0.36,
284
+ "grad_norm": 22.62183660087882,
285
+ "learning_rate": 4.070934040463998e-07,
286
+ "logits/chosen": -0.8362399339675903,
287
+ "logits/rejected": -0.5129006505012512,
288
+ "logps/chosen": -383.85943603515625,
289
+ "logps/rejected": -450.67376708984375,
290
+ "loss": 0.5396,
291
+ "rewards/accuracies": 0.6875,
292
+ "rewards/chosen": -1.1981004476547241,
293
+ "rewards/margins": 0.5252794623374939,
294
+ "rewards/rejected": -1.7233800888061523,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 0.38,
299
+ "grad_norm": 20.471718314655647,
300
+ "learning_rate": 3.9247834624635404e-07,
301
+ "logits/chosen": -1.1186776161193848,
302
+ "logits/rejected": -0.807415783405304,
303
+ "logps/chosen": -367.24517822265625,
304
+ "logps/rejected": -383.65325927734375,
305
+ "loss": 0.5423,
306
+ "rewards/accuracies": 0.7749999761581421,
307
+ "rewards/chosen": -0.7441693544387817,
308
+ "rewards/margins": 0.7058154344558716,
309
+ "rewards/rejected": -1.4499847888946533,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 0.4,
314
+ "grad_norm": 27.806972171143425,
315
+ "learning_rate": 3.7710310482256523e-07,
316
+ "logits/chosen": -0.8124464750289917,
317
+ "logits/rejected": -0.3878273069858551,
318
+ "logps/chosen": -388.7113342285156,
319
+ "logps/rejected": -429.1011657714844,
320
+ "loss": 0.5411,
321
+ "rewards/accuracies": 0.731249988079071,
322
+ "rewards/chosen": -1.1005661487579346,
323
+ "rewards/margins": 0.6401538252830505,
324
+ "rewards/rejected": -1.7407200336456299,
325
+ "step": 190
326
+ },
327
+ {
328
+ "epoch": 0.42,
329
+ "grad_norm": 26.53253409564454,
330
+ "learning_rate": 3.610497133404795e-07,
331
+ "logits/chosen": -0.11316045373678207,
332
+ "logits/rejected": 0.337258517742157,
333
+ "logps/chosen": -417.2351989746094,
334
+ "logps/rejected": -437.7659606933594,
335
+ "loss": 0.5306,
336
+ "rewards/accuracies": 0.7437499761581421,
337
+ "rewards/chosen": -1.1853481531143188,
338
+ "rewards/margins": 0.7383456826210022,
339
+ "rewards/rejected": -1.9236938953399658,
340
+ "step": 200
341
+ },
342
+ {
343
+ "epoch": 0.42,
344
+ "eval_logits/chosen": -0.4834875464439392,
345
+ "eval_logits/rejected": -0.16467474400997162,
346
+ "eval_logps/chosen": -377.3648681640625,
347
+ "eval_logps/rejected": -458.6296691894531,
348
+ "eval_loss": 0.5258087515830994,
349
+ "eval_rewards/accuracies": 0.7578125,
350
+ "eval_rewards/chosen": -1.1476268768310547,
351
+ "eval_rewards/margins": 0.8118469715118408,
352
+ "eval_rewards/rejected": -1.959473729133606,
353
+ "eval_runtime": 42.8446,
354
+ "eval_samples_per_second": 46.68,
355
+ "eval_steps_per_second": 0.747,
356
+ "step": 200
357
+ },
358
+ {
359
+ "epoch": 0.44,
360
+ "grad_norm": 32.607007304168285,
361
+ "learning_rate": 3.4440382358952115e-07,
362
+ "logits/chosen": -0.4726165235042572,
363
+ "logits/rejected": 0.2889423966407776,
364
+ "logps/chosen": -445.2005310058594,
365
+ "logps/rejected": -516.150390625,
366
+ "loss": 0.5157,
367
+ "rewards/accuracies": 0.8125,
368
+ "rewards/chosen": -1.5719295740127563,
369
+ "rewards/margins": 0.899932861328125,
370
+ "rewards/rejected": -2.471862316131592,
371
+ "step": 210
372
+ },
373
+ {
374
+ "epoch": 0.46,
375
+ "grad_norm": 26.982376912169133,
376
+ "learning_rate": 3.272542485937368e-07,
377
+ "logits/chosen": 0.02971530519425869,
378
+ "logits/rejected": 0.6972896456718445,
379
+ "logps/chosen": -488.6690979003906,
380
+ "logps/rejected": -517.7215576171875,
381
+ "loss": 0.5045,
382
+ "rewards/accuracies": 0.706250011920929,
383
+ "rewards/chosen": -1.9397350549697876,
384
+ "rewards/margins": 0.67905592918396,
385
+ "rewards/rejected": -2.618790626525879,
386
+ "step": 220
387
+ },
388
+ {
389
+ "epoch": 0.48,
390
+ "grad_norm": 28.31686307704009,
391
+ "learning_rate": 3.096924887558854e-07,
392
+ "logits/chosen": 0.3274112641811371,
393
+ "logits/rejected": 1.6159236431121826,
394
+ "logps/chosen": -472.36590576171875,
395
+ "logps/rejected": -560.3911743164062,
396
+ "loss": 0.5157,
397
+ "rewards/accuracies": 0.6875,
398
+ "rewards/chosen": -2.139970302581787,
399
+ "rewards/margins": 0.9002918004989624,
400
+ "rewards/rejected": -3.040262460708618,
401
+ "step": 230
402
+ },
403
+ {
404
+ "epoch": 0.5,
405
+ "grad_norm": 26.93455267413187,
406
+ "learning_rate": 2.9181224366319943e-07,
407
+ "logits/chosen": 0.34222739934921265,
408
+ "logits/rejected": 1.275580644607544,
409
+ "logps/chosen": -493.95916748046875,
410
+ "logps/rejected": -570.4260864257812,
411
+ "loss": 0.4844,
412
+ "rewards/accuracies": 0.737500011920929,
413
+ "rewards/chosen": -2.126845598220825,
414
+ "rewards/margins": 0.9677503705024719,
415
+ "rewards/rejected": -3.0945961475372314,
416
+ "step": 240
417
+ },
418
+ {
419
+ "epoch": 0.52,
420
+ "grad_norm": 34.97761081158377,
421
+ "learning_rate": 2.7370891215954565e-07,
422
+ "logits/chosen": 0.15051239728927612,
423
+ "logits/rejected": 1.3550792932510376,
424
+ "logps/chosen": -447.21490478515625,
425
+ "logps/rejected": -547.626708984375,
426
+ "loss": 0.5157,
427
+ "rewards/accuracies": 0.768750011920929,
428
+ "rewards/chosen": -2.229414463043213,
429
+ "rewards/margins": 1.004492998123169,
430
+ "rewards/rejected": -3.2339072227478027,
431
+ "step": 250
432
+ },
433
+ {
434
+ "epoch": 0.54,
435
+ "grad_norm": 22.98186057582904,
436
+ "learning_rate": 2.55479083351317e-07,
437
+ "logits/chosen": -0.6737252473831177,
438
+ "logits/rejected": -0.22596630454063416,
439
+ "logps/chosen": -423.21124267578125,
440
+ "logps/rejected": -537.1641845703125,
441
+ "loss": 0.4931,
442
+ "rewards/accuracies": 0.7749999761581421,
443
+ "rewards/chosen": -1.5507694482803345,
444
+ "rewards/margins": 1.1678037643432617,
445
+ "rewards/rejected": -2.7185730934143066,
446
+ "step": 260
447
+ },
448
+ {
449
+ "epoch": 0.56,
450
+ "grad_norm": 24.568187901601522,
451
+ "learning_rate": 2.3722002126275822e-07,
452
+ "logits/chosen": -0.7251144647598267,
453
+ "logits/rejected": 0.055858515202999115,
454
+ "logps/chosen": -460.47369384765625,
455
+ "logps/rejected": -515.4779663085938,
456
+ "loss": 0.5056,
457
+ "rewards/accuracies": 0.824999988079071,
458
+ "rewards/chosen": -1.7928097248077393,
459
+ "rewards/margins": 0.9766537547111511,
460
+ "rewards/rejected": -2.769463300704956,
461
+ "step": 270
462
+ },
463
+ {
464
+ "epoch": 0.59,
465
+ "grad_norm": 26.18745823449182,
466
+ "learning_rate": 2.19029145890313e-07,
467
+ "logits/chosen": -0.2248018980026245,
468
+ "logits/rejected": 0.7499777674674988,
469
+ "logps/chosen": -570.017822265625,
470
+ "logps/rejected": -637.1007690429688,
471
+ "loss": 0.4807,
472
+ "rewards/accuracies": 0.800000011920929,
473
+ "rewards/chosen": -2.686659097671509,
474
+ "rewards/margins": 1.049829125404358,
475
+ "rewards/rejected": -3.736487865447998,
476
+ "step": 280
477
+ },
478
+ {
479
+ "epoch": 0.61,
480
+ "grad_norm": 27.843254345626296,
481
+ "learning_rate": 2.0100351342479216e-07,
482
+ "logits/chosen": 0.017834633588790894,
483
+ "logits/rejected": 0.5087012052536011,
484
+ "logps/chosen": -523.2457275390625,
485
+ "logps/rejected": -614.5767211914062,
486
+ "loss": 0.4986,
487
+ "rewards/accuracies": 0.699999988079071,
488
+ "rewards/chosen": -2.559013605117798,
489
+ "rewards/margins": 0.9906851053237915,
490
+ "rewards/rejected": -3.5496985912323,
491
+ "step": 290
492
+ },
493
+ {
494
+ "epoch": 0.63,
495
+ "grad_norm": 28.812343531542734,
496
+ "learning_rate": 1.8323929841460178e-07,
497
+ "logits/chosen": -0.09833024442195892,
498
+ "logits/rejected": 0.13667245209217072,
499
+ "logps/chosen": -530.9118041992188,
500
+ "logps/rejected": -594.4251098632812,
501
+ "loss": 0.5097,
502
+ "rewards/accuracies": 0.6499999761581421,
503
+ "rewards/chosen": -2.618612766265869,
504
+ "rewards/margins": 0.6055675745010376,
505
+ "rewards/rejected": -3.224180221557617,
506
+ "step": 300
507
+ },
508
+ {
509
+ "epoch": 0.63,
510
+ "eval_logits/chosen": -0.46580713987350464,
511
+ "eval_logits/rejected": -0.05736924335360527,
512
+ "eval_logps/chosen": -498.608642578125,
513
+ "eval_logps/rejected": -600.8517456054688,
514
+ "eval_loss": 0.5078553557395935,
515
+ "eval_rewards/accuracies": 0.765625,
516
+ "eval_rewards/chosen": -2.3600645065307617,
517
+ "eval_rewards/margins": 1.021630048751831,
518
+ "eval_rewards/rejected": -3.3816945552825928,
519
+ "eval_runtime": 42.9133,
520
+ "eval_samples_per_second": 46.606,
521
+ "eval_steps_per_second": 0.746,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 0.65,
526
+ "grad_norm": 24.395908084810543,
527
+ "learning_rate": 1.6583128063291573e-07,
528
+ "logits/chosen": -0.20998772978782654,
529
+ "logits/rejected": 0.597333550453186,
530
+ "logps/chosen": -553.8638305664062,
531
+ "logps/rejected": -622.6854248046875,
532
+ "loss": 0.4601,
533
+ "rewards/accuracies": 0.8062499761581421,
534
+ "rewards/chosen": -2.6587719917297363,
535
+ "rewards/margins": 1.019250512123108,
536
+ "rewards/rejected": -3.678022861480713,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 0.67,
541
+ "grad_norm": 34.66768420911215,
542
+ "learning_rate": 1.488723393865766e-07,
543
+ "logits/chosen": 0.16718712449073792,
544
+ "logits/rejected": 0.9329349398612976,
545
+ "logps/chosen": -593.7220458984375,
546
+ "logps/rejected": -669.1134033203125,
547
+ "loss": 0.4733,
548
+ "rewards/accuracies": 0.7250000238418579,
549
+ "rewards/chosen": -3.0446815490722656,
550
+ "rewards/margins": 1.103857159614563,
551
+ "rewards/rejected": -4.1485395431518555,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 0.69,
556
+ "grad_norm": 28.471803594507218,
557
+ "learning_rate": 1.3245295796480788e-07,
558
+ "logits/chosen": -0.11941705644130707,
559
+ "logits/rejected": 0.6031097173690796,
560
+ "logps/chosen": -576.390869140625,
561
+ "logps/rejected": -662.9435424804688,
562
+ "loss": 0.4956,
563
+ "rewards/accuracies": 0.75,
564
+ "rewards/chosen": -2.895800828933716,
565
+ "rewards/margins": 1.0525661706924438,
566
+ "rewards/rejected": -3.9483673572540283,
567
+ "step": 330
568
+ },
569
+ {
570
+ "epoch": 0.71,
571
+ "grad_norm": 29.920730024726208,
572
+ "learning_rate": 1.1666074087171627e-07,
573
+ "logits/chosen": -0.6586230397224426,
574
+ "logits/rejected": -0.01618196628987789,
575
+ "logps/chosen": -558.61328125,
576
+ "logps/rejected": -645.0929565429688,
577
+ "loss": 0.4901,
578
+ "rewards/accuracies": 0.78125,
579
+ "rewards/chosen": -2.6631388664245605,
580
+ "rewards/margins": 0.9750139117240906,
581
+ "rewards/rejected": -3.638153076171875,
582
+ "step": 340
583
+ },
584
+ {
585
+ "epoch": 0.73,
586
+ "grad_norm": 28.451943555198234,
587
+ "learning_rate": 1.0157994641835734e-07,
588
+ "logits/chosen": -0.27327781915664673,
589
+ "logits/rejected": 0.1500699818134308,
590
+ "logps/chosen": -551.64501953125,
591
+ "logps/rejected": -615.7404174804688,
592
+ "loss": 0.5079,
593
+ "rewards/accuracies": 0.7250000238418579,
594
+ "rewards/chosen": -2.8532228469848633,
595
+ "rewards/margins": 0.7952502369880676,
596
+ "rewards/rejected": -3.6484732627868652,
597
+ "step": 350
598
+ },
599
+ {
600
+ "epoch": 0.75,
601
+ "grad_norm": 25.677922944710783,
602
+ "learning_rate": 8.729103716819111e-08,
603
+ "logits/chosen": -0.08269649744033813,
604
+ "logits/rejected": 0.27684250473976135,
605
+ "logps/chosen": -541.1990966796875,
606
+ "logps/rejected": -651.2036743164062,
607
+ "loss": 0.4674,
608
+ "rewards/accuracies": 0.7562500238418579,
609
+ "rewards/chosen": -2.9707937240600586,
610
+ "rewards/margins": 0.9196038246154785,
611
+ "rewards/rejected": -3.8903980255126953,
612
+ "step": 360
613
+ },
614
+ {
615
+ "epoch": 0.77,
616
+ "grad_norm": 36.170517312989006,
617
+ "learning_rate": 7.387025063449081e-08,
618
+ "logits/chosen": -0.2130926102399826,
619
+ "logits/rejected": 0.6245878338813782,
620
+ "logps/chosen": -593.176513671875,
621
+ "logps/rejected": -702.429443359375,
622
+ "loss": 0.4914,
623
+ "rewards/accuracies": 0.768750011920929,
624
+ "rewards/chosen": -3.0834755897521973,
625
+ "rewards/margins": 1.1826813220977783,
626
+ "rewards/rejected": -4.266157150268555,
627
+ "step": 370
628
+ },
629
+ {
630
+ "epoch": 0.79,
631
+ "grad_norm": 29.948938424368286,
632
+ "learning_rate": 6.138919252022435e-08,
633
+ "logits/chosen": -0.31227773427963257,
634
+ "logits/rejected": 0.1758570820093155,
635
+ "logps/chosen": -569.8441162109375,
636
+ "logps/rejected": -653.1160278320312,
637
+ "loss": 0.4834,
638
+ "rewards/accuracies": 0.78125,
639
+ "rewards/chosen": -2.861605644226074,
640
+ "rewards/margins": 1.1251481771469116,
641
+ "rewards/rejected": -3.9867539405822754,
642
+ "step": 380
643
+ },
644
+ {
645
+ "epoch": 0.82,
646
+ "grad_norm": 28.643050867948876,
647
+ "learning_rate": 4.991445467064689e-08,
648
+ "logits/chosen": -0.4378163814544678,
649
+ "logits/rejected": 0.1975017786026001,
650
+ "logps/chosen": -487.02447509765625,
651
+ "logps/rejected": -627.4256591796875,
652
+ "loss": 0.4863,
653
+ "rewards/accuracies": 0.856249988079071,
654
+ "rewards/chosen": -2.4755725860595703,
655
+ "rewards/margins": 1.2951563596725464,
656
+ "rewards/rejected": -3.770728588104248,
657
+ "step": 390
658
+ },
659
+ {
660
+ "epoch": 0.84,
661
+ "grad_norm": 28.740512536833982,
662
+ "learning_rate": 3.9507259776993954e-08,
663
+ "logits/chosen": -0.464282363653183,
664
+ "logits/rejected": 0.3086758852005005,
665
+ "logps/chosen": -510.72564697265625,
666
+ "logps/rejected": -584.2462158203125,
667
+ "loss": 0.4906,
668
+ "rewards/accuracies": 0.706250011920929,
669
+ "rewards/chosen": -2.4956374168395996,
670
+ "rewards/margins": 0.9018915891647339,
671
+ "rewards/rejected": -3.397528886795044,
672
+ "step": 400
673
+ },
674
+ {
675
+ "epoch": 0.84,
676
+ "eval_logits/chosen": -0.5081287026405334,
677
+ "eval_logits/rejected": -0.03897371515631676,
678
+ "eval_logps/chosen": -499.4172058105469,
679
+ "eval_logps/rejected": -610.7911376953125,
680
+ "eval_loss": 0.49998462200164795,
681
+ "eval_rewards/accuracies": 0.76953125,
682
+ "eval_rewards/chosen": -2.368149995803833,
683
+ "eval_rewards/margins": 1.1129380464553833,
684
+ "eval_rewards/rejected": -3.4810879230499268,
685
+ "eval_runtime": 43.5613,
686
+ "eval_samples_per_second": 45.912,
687
+ "eval_steps_per_second": 0.735,
688
+ "step": 400
689
+ },
690
+ {
691
+ "epoch": 0.86,
692
+ "grad_norm": 29.137185743173024,
693
+ "learning_rate": 3.022313472693447e-08,
694
+ "logits/chosen": -0.427814781665802,
695
+ "logits/rejected": 0.47378939390182495,
696
+ "logps/chosen": -502.87939453125,
697
+ "logps/rejected": -579.4691162109375,
698
+ "loss": 0.5048,
699
+ "rewards/accuracies": 0.737500011920929,
700
+ "rewards/chosen": -2.4262542724609375,
701
+ "rewards/margins": 0.9697957038879395,
702
+ "rewards/rejected": -3.396049976348877,
703
+ "step": 410
704
+ },
705
+ {
706
+ "epoch": 0.88,
707
+ "grad_norm": 28.72794205317694,
708
+ "learning_rate": 2.2111614344599684e-08,
709
+ "logits/chosen": -0.4604805111885071,
710
+ "logits/rejected": 0.19487139582633972,
711
+ "logps/chosen": -517.6533813476562,
712
+ "logps/rejected": -557.2385864257812,
713
+ "loss": 0.4911,
714
+ "rewards/accuracies": 0.699999988079071,
715
+ "rewards/chosen": -2.416501760482788,
716
+ "rewards/margins": 0.9597095251083374,
717
+ "rewards/rejected": -3.376211643218994,
718
+ "step": 420
719
+ },
720
+ {
721
+ "epoch": 0.9,
722
+ "grad_norm": 21.80245746988776,
723
+ "learning_rate": 1.521597710086439e-08,
724
+ "logits/chosen": -0.3804924488067627,
725
+ "logits/rejected": 0.39526861906051636,
726
+ "logps/chosen": -535.6771240234375,
727
+ "logps/rejected": -618.59326171875,
728
+ "loss": 0.4719,
729
+ "rewards/accuracies": 0.7749999761581421,
730
+ "rewards/chosen": -2.5517053604125977,
731
+ "rewards/margins": 1.1444313526153564,
732
+ "rewards/rejected": -3.696136474609375,
733
+ "step": 430
734
+ },
735
+ {
736
+ "epoch": 0.92,
737
+ "grad_norm": 25.533460874638475,
738
+ "learning_rate": 9.57301420397924e-09,
739
+ "logits/chosen": -0.2722262442111969,
740
+ "logits/rejected": 0.6270692944526672,
741
+ "logps/chosen": -534.4539184570312,
742
+ "logps/rejected": -636.7295532226562,
743
+ "loss": 0.4921,
744
+ "rewards/accuracies": 0.7562500238418579,
745
+ "rewards/chosen": -2.657174587249756,
746
+ "rewards/margins": 1.1696617603302002,
747
+ "rewards/rejected": -3.826836347579956,
748
+ "step": 440
749
+ },
750
+ {
751
+ "epoch": 0.94,
752
+ "grad_norm": 29.41617255057514,
753
+ "learning_rate": 5.212833302556258e-09,
754
+ "logits/chosen": -0.4902656078338623,
755
+ "logits/rejected": 0.2050538957118988,
756
+ "logps/chosen": -552.1812744140625,
757
+ "logps/rejected": -615.8868408203125,
758
+ "loss": 0.4784,
759
+ "rewards/accuracies": 0.7749999761581421,
760
+ "rewards/chosen": -2.5670862197875977,
761
+ "rewards/margins": 1.0947918891906738,
762
+ "rewards/rejected": -3.6618781089782715,
763
+ "step": 450
764
+ },
765
+ {
766
+ "epoch": 0.96,
767
+ "grad_norm": 26.40697406008373,
768
+ "learning_rate": 2.158697848236607e-09,
769
+ "logits/chosen": -0.5525180697441101,
770
+ "logits/rejected": 0.4095240533351898,
771
+ "logps/chosen": -521.8342895507812,
772
+ "logps/rejected": -599.0489501953125,
773
+ "loss": 0.4933,
774
+ "rewards/accuracies": 0.75,
775
+ "rewards/chosen": -2.4641835689544678,
776
+ "rewards/margins": 1.049481987953186,
777
+ "rewards/rejected": -3.5136656761169434,
778
+ "step": 460
779
+ },
780
+ {
781
+ "epoch": 0.98,
782
+ "grad_norm": 40.87484210645662,
783
+ "learning_rate": 4.269029751107489e-10,
784
+ "logits/chosen": -0.38540196418762207,
785
+ "logits/rejected": 0.25467342138290405,
786
+ "logps/chosen": -550.1776123046875,
787
+ "logps/rejected": -633.5750732421875,
788
+ "loss": 0.4908,
789
+ "rewards/accuracies": 0.71875,
790
+ "rewards/chosen": -2.6054952144622803,
791
+ "rewards/margins": 0.973294734954834,
792
+ "rewards/rejected": -3.5787901878356934,
793
+ "step": 470
794
+ },
795
+ {
796
+ "epoch": 1.0,
797
+ "step": 478,
798
+ "total_flos": 0.0,
799
+ "train_loss": 0.535196884905444,
800
+ "train_runtime": 3527.4214,
801
+ "train_samples_per_second": 17.331,
802
+ "train_steps_per_second": 0.136
803
+ }
804
+ ],
805
+ "logging_steps": 10,
806
+ "max_steps": 478,
807
+ "num_input_tokens_seen": 0,
808
+ "num_train_epochs": 1,
809
+ "save_steps": 100,
810
+ "total_flos": 0.0,
811
+ "train_batch_size": 8,
812
+ "trial_name": null,
813
+ "trial_params": null
814
+ }