RikkiXu commited on
Commit
bf9d77d
1 Parent(s): e70018a

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 an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4969
21
+ - Rewards/chosen: -1.1626
22
+ - Rewards/rejected: -2.1853
23
+ - Rewards/accuracies: 0.7773
24
+ - Rewards/margins: 1.0227
25
+ - Logps/rejected: -481.1959
26
+ - Logps/chosen: -378.8522
27
+ - Logits/rejected: 1.4928
28
+ - Logits/chosen: 0.5873
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
+ | 0.5632 | 0.2092 | 100 | 0.5684 | -0.8769 | -1.4450 | 0.7305 | 0.5681 | -407.1669 | -350.2800 | -0.3489 | -0.6128 |
66
+ | 0.5374 | 0.4184 | 200 | 0.5202 | -0.7727 | -1.5477 | 0.7852 | 0.7750 | -417.4406 | -339.8678 | -0.1011 | -0.6617 |
67
+ | 0.4826 | 0.6276 | 300 | 0.5018 | -1.1013 | -2.0815 | 0.7734 | 0.9802 | -470.8159 | -372.7218 | 1.3131 | 0.4518 |
68
+ | 0.495 | 0.8368 | 400 | 0.4969 | -1.1626 | -2.1853 | 0.7773 | 1.0227 | -481.1959 | -378.8522 | 1.4928 | 0.5873 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.40.1
74
+ - Pytorch 2.1.2+cu118
75
+ - Datasets 2.19.0
76
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5340489398485447,
5
+ "train_runtime": 7520.1807,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 8.129,
8
+ "train_steps_per_second": 0.064
9
+ }
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": "4.40.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566bff0ec661fec8f828663bef68e7162c9f30a4a9d678f00d79402950395038
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071f62f7eccae4daa97a875d63185c5f60f851c33bd0d79e92efcfa4e53fbfd3
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353bff0bfe0de90a832913816d2b1919b4db9ef50435ec0ca76c75f0845cb767
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/Apr26_18-03-59_n136-098-146/events.out.tfevents.1714137440.n136-098-146.2262128.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bddd5577979976fa6f7a862a33fe0bb3b7d4b783ce85648da1b10ca496da573
3
- size 35841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33dcbf842c898231ebd42d44931d75d69bdebc9b8e02cc54ceab484995271ebe
3
+ size 41011
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5340489398485447,
5
+ "train_runtime": 7520.1807,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 8.129,
8
+ "train_steps_per_second": 0.064
9
+ }
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": 0.0020920502092050207,
13
+ "grad_norm": 9.298505033829334,
14
+ "learning_rate": 1.0416666666666666e-08,
15
+ "logits/chosen": -2.7660439014434814,
16
+ "logits/rejected": -2.717564582824707,
17
+ "logps/chosen": -269.8568420410156,
18
+ "logps/rejected": -360.52459716796875,
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": 0.02092050209205021,
28
+ "grad_norm": 9.201570340284004,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.592160224914551,
31
+ "logits/rejected": -2.562696695327759,
32
+ "logps/chosen": -264.77496337890625,
33
+ "logps/rejected": -251.57083129882812,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.4513888955116272,
36
+ "rewards/chosen": 0.0002292051794938743,
37
+ "rewards/margins": 0.00040812836959958076,
38
+ "rewards/rejected": -0.00017892329196911305,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04184100418410042,
43
+ "grad_norm": 8.403210934524289,
44
+ "learning_rate": 2.0833333333333333e-07,
45
+ "logits/chosen": -2.653189182281494,
46
+ "logits/rejected": -2.605264663696289,
47
+ "logps/chosen": -281.4413146972656,
48
+ "logps/rejected": -296.7750244140625,
49
+ "loss": 0.6923,
50
+ "rewards/accuracies": 0.53125,
51
+ "rewards/chosen": 0.0011203143512830138,
52
+ "rewards/margins": 0.0008017805521376431,
53
+ "rewards/rejected": 0.000318533944664523,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.06276150627615062,
58
+ "grad_norm": 8.307511730281874,
59
+ "learning_rate": 3.1249999999999997e-07,
60
+ "logits/chosen": -2.6639485359191895,
61
+ "logits/rejected": -2.5914711952209473,
62
+ "logps/chosen": -299.44439697265625,
63
+ "logps/rejected": -263.6602478027344,
64
+ "loss": 0.6886,
65
+ "rewards/accuracies": 0.668749988079071,
66
+ "rewards/chosen": 0.012274232693016529,
67
+ "rewards/margins": 0.009375235997140408,
68
+ "rewards/rejected": 0.002898997161537409,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.08368200836820083,
73
+ "grad_norm": 8.23101419584969,
74
+ "learning_rate": 4.1666666666666667e-07,
75
+ "logits/chosen": -2.5564517974853516,
76
+ "logits/rejected": -2.5212883949279785,
77
+ "logps/chosen": -263.17132568359375,
78
+ "logps/rejected": -245.1162109375,
79
+ "loss": 0.6774,
80
+ "rewards/accuracies": 0.6937500238418579,
81
+ "rewards/chosen": 0.03954031318426132,
82
+ "rewards/margins": 0.04678243398666382,
83
+ "rewards/rejected": -0.007242122199386358,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.10460251046025104,
88
+ "grad_norm": 8.47834585122089,
89
+ "learning_rate": 4.999733114418725e-07,
90
+ "logits/chosen": -2.495573043823242,
91
+ "logits/rejected": -2.4556243419647217,
92
+ "logps/chosen": -279.73748779296875,
93
+ "logps/rejected": -297.7320251464844,
94
+ "loss": 0.6609,
95
+ "rewards/accuracies": 0.5874999761581421,
96
+ "rewards/chosen": -5.648513251799159e-05,
97
+ "rewards/margins": 0.049422554671764374,
98
+ "rewards/rejected": -0.04947904497385025,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.12552301255230125,
103
+ "grad_norm": 11.447029638220144,
104
+ "learning_rate": 4.990398100856366e-07,
105
+ "logits/chosen": -2.5056962966918945,
106
+ "logits/rejected": -2.4333505630493164,
107
+ "logps/chosen": -274.71142578125,
108
+ "logps/rejected": -314.40966796875,
109
+ "loss": 0.6378,
110
+ "rewards/accuracies": 0.6875,
111
+ "rewards/chosen": -0.03104892373085022,
112
+ "rewards/margins": 0.13223406672477722,
113
+ "rewards/rejected": -0.16328299045562744,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.14644351464435146,
118
+ "grad_norm": 13.212333314905758,
119
+ "learning_rate": 4.967775735898179e-07,
120
+ "logits/chosen": -2.325637102127075,
121
+ "logits/rejected": -2.3246896266937256,
122
+ "logps/chosen": -266.88873291015625,
123
+ "logps/rejected": -277.4853515625,
124
+ "loss": 0.6211,
125
+ "rewards/accuracies": 0.8062499761581421,
126
+ "rewards/chosen": -0.012722762301564217,
127
+ "rewards/margins": 0.1949584186077118,
128
+ "rewards/rejected": -0.20768117904663086,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.16736401673640167,
133
+ "grad_norm": 24.02513624388519,
134
+ "learning_rate": 4.931986719649298e-07,
135
+ "logits/chosen": -2.423210859298706,
136
+ "logits/rejected": -2.316833019256592,
137
+ "logps/chosen": -340.6246643066406,
138
+ "logps/rejected": -308.7874755859375,
139
+ "loss": 0.599,
140
+ "rewards/accuracies": 0.675000011920929,
141
+ "rewards/chosen": -0.17806725203990936,
142
+ "rewards/margins": 0.26922112703323364,
143
+ "rewards/rejected": -0.4472884237766266,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.18828451882845187,
148
+ "grad_norm": 21.808882527816824,
149
+ "learning_rate": 4.883222001996351e-07,
150
+ "logits/chosen": -1.0463552474975586,
151
+ "logits/rejected": -0.8626599311828613,
152
+ "logps/chosen": -330.01776123046875,
153
+ "logps/rejected": -381.9994812011719,
154
+ "loss": 0.5615,
155
+ "rewards/accuracies": 0.7562500238418579,
156
+ "rewards/chosen": -0.7090646028518677,
157
+ "rewards/margins": 0.5869495868682861,
158
+ "rewards/rejected": -1.2960141897201538,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.20920502092050208,
163
+ "grad_norm": 19.245462836155387,
164
+ "learning_rate": 4.821741763807186e-07,
165
+ "logits/chosen": -0.5482389330863953,
166
+ "logits/rejected": -0.278412789106369,
167
+ "logps/chosen": -338.76251220703125,
168
+ "logps/rejected": -393.6160888671875,
169
+ "loss": 0.5632,
170
+ "rewards/accuracies": 0.737500011920929,
171
+ "rewards/chosen": -0.7840398550033569,
172
+ "rewards/margins": 0.5818365216255188,
173
+ "rewards/rejected": -1.3658764362335205,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.20920502092050208,
178
+ "eval_logits/chosen": -0.6127901673316956,
179
+ "eval_logits/rejected": -0.3488583564758301,
180
+ "eval_logps/chosen": -350.2799987792969,
181
+ "eval_logps/rejected": -407.1668701171875,
182
+ "eval_loss": 0.5684163570404053,
183
+ "eval_rewards/accuracies": 0.73046875,
184
+ "eval_rewards/chosen": -0.8768651485443115,
185
+ "eval_rewards/margins": 0.5681313276290894,
186
+ "eval_rewards/rejected": -1.4449963569641113,
187
+ "eval_runtime": 96.8146,
188
+ "eval_samples_per_second": 20.658,
189
+ "eval_steps_per_second": 0.331,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.2301255230125523,
194
+ "grad_norm": 22.525663230437072,
195
+ "learning_rate": 4.747874028753375e-07,
196
+ "logits/chosen": -0.790797233581543,
197
+ "logits/rejected": -0.19812031090259552,
198
+ "logps/chosen": -387.7721862792969,
199
+ "logps/rejected": -402.75067138671875,
200
+ "loss": 0.5625,
201
+ "rewards/accuracies": 0.731249988079071,
202
+ "rewards/chosen": -0.8319207429885864,
203
+ "rewards/margins": 0.617226779460907,
204
+ "rewards/rejected": -1.4491477012634277,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 0.2510460251046025,
209
+ "grad_norm": 21.93406688438369,
210
+ "learning_rate": 4.662012913161997e-07,
211
+ "logits/chosen": -0.1478520929813385,
212
+ "logits/rejected": 0.21510139107704163,
213
+ "logps/chosen": -376.58184814453125,
214
+ "logps/rejected": -419.5226135253906,
215
+ "loss": 0.5426,
216
+ "rewards/accuracies": 0.75,
217
+ "rewards/chosen": -0.9541470408439636,
218
+ "rewards/margins": 0.6425132155418396,
219
+ "rewards/rejected": -1.5966601371765137,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 0.2719665271966527,
224
+ "grad_norm": 21.863413590534076,
225
+ "learning_rate": 4.5646165232345103e-07,
226
+ "logits/chosen": 0.039292819797992706,
227
+ "logits/rejected": 0.5163652300834656,
228
+ "logps/chosen": -377.03961181640625,
229
+ "logps/rejected": -429.0581970214844,
230
+ "loss": 0.524,
231
+ "rewards/accuracies": 0.71875,
232
+ "rewards/chosen": -0.9503645896911621,
233
+ "rewards/margins": 0.6558589339256287,
234
+ "rewards/rejected": -1.606223464012146,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 0.2928870292887029,
239
+ "grad_norm": 21.169176355822128,
240
+ "learning_rate": 4.456204510851956e-07,
241
+ "logits/chosen": -0.4013391435146332,
242
+ "logits/rejected": -0.08902309834957123,
243
+ "logps/chosen": -390.9994201660156,
244
+ "logps/rejected": -439.9606018066406,
245
+ "loss": 0.532,
246
+ "rewards/accuracies": 0.731249988079071,
247
+ "rewards/chosen": -0.7503399848937988,
248
+ "rewards/margins": 0.6424974203109741,
249
+ "rewards/rejected": -1.3928372859954834,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 0.3138075313807531,
254
+ "grad_norm": 24.525761488765827,
255
+ "learning_rate": 4.337355301007335e-07,
256
+ "logits/chosen": -0.0023450672160834074,
257
+ "logits/rejected": 0.44477328658103943,
258
+ "logps/chosen": -398.7283630371094,
259
+ "logps/rejected": -448.65374755859375,
260
+ "loss": 0.5354,
261
+ "rewards/accuracies": 0.7124999761581421,
262
+ "rewards/chosen": -1.155042052268982,
263
+ "rewards/margins": 0.5694054365158081,
264
+ "rewards/rejected": -1.7244476079940796,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 0.33472803347280333,
269
+ "grad_norm": 22.353019803776466,
270
+ "learning_rate": 4.2087030056579986e-07,
271
+ "logits/chosen": -0.20696048438549042,
272
+ "logits/rejected": 0.4880790710449219,
273
+ "logps/chosen": -360.6669921875,
274
+ "logps/rejected": -434.037353515625,
275
+ "loss": 0.5315,
276
+ "rewards/accuracies": 0.737500011920929,
277
+ "rewards/chosen": -0.8759892582893372,
278
+ "rewards/margins": 0.8901454210281372,
279
+ "rewards/rejected": -1.7661348581314087,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 0.35564853556485354,
284
+ "grad_norm": 25.914625948890546,
285
+ "learning_rate": 4.070934040463998e-07,
286
+ "logits/chosen": 0.6924982666969299,
287
+ "logits/rejected": 1.1295397281646729,
288
+ "logps/chosen": -374.10723876953125,
289
+ "logps/rejected": -420.09588623046875,
290
+ "loss": 0.5363,
291
+ "rewards/accuracies": 0.7124999761581421,
292
+ "rewards/chosen": -1.247719645500183,
293
+ "rewards/margins": 0.6419915556907654,
294
+ "rewards/rejected": -1.8897111415863037,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 0.37656903765690375,
299
+ "grad_norm": 21.366817652532127,
300
+ "learning_rate": 3.9247834624635404e-07,
301
+ "logits/chosen": 0.7046024203300476,
302
+ "logits/rejected": 1.3452444076538086,
303
+ "logps/chosen": -360.4297180175781,
304
+ "logps/rejected": -401.1781005859375,
305
+ "loss": 0.5038,
306
+ "rewards/accuracies": 0.737500011920929,
307
+ "rewards/chosen": -1.040706753730774,
308
+ "rewards/margins": 0.6953631639480591,
309
+ "rewards/rejected": -1.7360700368881226,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 0.39748953974895396,
314
+ "grad_norm": 24.086446407003773,
315
+ "learning_rate": 3.7710310482256523e-07,
316
+ "logits/chosen": -0.14418189227581024,
317
+ "logits/rejected": 0.45502132177352905,
318
+ "logps/chosen": -359.0705261230469,
319
+ "logps/rejected": -413.5692443847656,
320
+ "loss": 0.512,
321
+ "rewards/accuracies": 0.71875,
322
+ "rewards/chosen": -0.8782768249511719,
323
+ "rewards/margins": 0.6598676443099976,
324
+ "rewards/rejected": -1.5381444692611694,
325
+ "step": 190
326
+ },
327
+ {
328
+ "epoch": 0.41841004184100417,
329
+ "grad_norm": 64.3318645589766,
330
+ "learning_rate": 3.610497133404795e-07,
331
+ "logits/chosen": -0.16302886605262756,
332
+ "logits/rejected": 0.2976584732532501,
333
+ "logps/chosen": -352.27783203125,
334
+ "logps/rejected": -425.39825439453125,
335
+ "loss": 0.5374,
336
+ "rewards/accuracies": 0.731249988079071,
337
+ "rewards/chosen": -0.9238117933273315,
338
+ "rewards/margins": 0.8096807599067688,
339
+ "rewards/rejected": -1.7334924936294556,
340
+ "step": 200
341
+ },
342
+ {
343
+ "epoch": 0.41841004184100417,
344
+ "eval_logits/chosen": -0.661653995513916,
345
+ "eval_logits/rejected": -0.10106822848320007,
346
+ "eval_logps/chosen": -339.8678283691406,
347
+ "eval_logps/rejected": -417.4406433105469,
348
+ "eval_loss": 0.5201992988586426,
349
+ "eval_rewards/accuracies": 0.78515625,
350
+ "eval_rewards/chosen": -0.7727437615394592,
351
+ "eval_rewards/margins": 0.7749909162521362,
352
+ "eval_rewards/rejected": -1.5477344989776611,
353
+ "eval_runtime": 96.6072,
354
+ "eval_samples_per_second": 20.702,
355
+ "eval_steps_per_second": 0.331,
356
+ "step": 200
357
+ },
358
+ {
359
+ "epoch": 0.4393305439330544,
360
+ "grad_norm": 27.061409181894096,
361
+ "learning_rate": 3.4440382358952115e-07,
362
+ "logits/chosen": 0.0046714721247553825,
363
+ "logits/rejected": 0.9609675407409668,
364
+ "logps/chosen": -385.9021301269531,
365
+ "logps/rejected": -421.04376220703125,
366
+ "loss": 0.5291,
367
+ "rewards/accuracies": 0.7875000238418579,
368
+ "rewards/chosen": -0.9620998501777649,
369
+ "rewards/margins": 0.7358611822128296,
370
+ "rewards/rejected": -1.6979610919952393,
371
+ "step": 210
372
+ },
373
+ {
374
+ "epoch": 0.4602510460251046,
375
+ "grad_norm": 30.2004484482118,
376
+ "learning_rate": 3.272542485937368e-07,
377
+ "logits/chosen": 1.2403850555419922,
378
+ "logits/rejected": 2.167426586151123,
379
+ "logps/chosen": -388.68963623046875,
380
+ "logps/rejected": -451.56854248046875,
381
+ "loss": 0.5153,
382
+ "rewards/accuracies": 0.7562500238418579,
383
+ "rewards/chosen": -1.2331252098083496,
384
+ "rewards/margins": 0.8259220123291016,
385
+ "rewards/rejected": -2.059047222137451,
386
+ "step": 220
387
+ },
388
+ {
389
+ "epoch": 0.4811715481171548,
390
+ "grad_norm": 20.504102481838405,
391
+ "learning_rate": 3.096924887558854e-07,
392
+ "logits/chosen": -0.1779499053955078,
393
+ "logits/rejected": 0.3767474591732025,
394
+ "logps/chosen": -345.39398193359375,
395
+ "logps/rejected": -434.6441345214844,
396
+ "loss": 0.5204,
397
+ "rewards/accuracies": 0.762499988079071,
398
+ "rewards/chosen": -0.9652854204177856,
399
+ "rewards/margins": 0.9037777185440063,
400
+ "rewards/rejected": -1.869063138961792,
401
+ "step": 230
402
+ },
403
+ {
404
+ "epoch": 0.502092050209205,
405
+ "grad_norm": 25.85435210721558,
406
+ "learning_rate": 2.9181224366319943e-07,
407
+ "logits/chosen": 0.048077814280986786,
408
+ "logits/rejected": 0.7805795669555664,
409
+ "logps/chosen": -367.3824768066406,
410
+ "logps/rejected": -432.07232666015625,
411
+ "loss": 0.4979,
412
+ "rewards/accuracies": 0.768750011920929,
413
+ "rewards/chosen": -1.0368225574493408,
414
+ "rewards/margins": 0.7932166457176208,
415
+ "rewards/rejected": -1.8300392627716064,
416
+ "step": 240
417
+ },
418
+ {
419
+ "epoch": 0.5230125523012552,
420
+ "grad_norm": 24.42587136099329,
421
+ "learning_rate": 2.7370891215954565e-07,
422
+ "logits/chosen": 0.673697829246521,
423
+ "logits/rejected": 1.6910991668701172,
424
+ "logps/chosen": -414.1255798339844,
425
+ "logps/rejected": -471.29949951171875,
426
+ "loss": 0.5001,
427
+ "rewards/accuracies": 0.75,
428
+ "rewards/chosen": -1.1593507528305054,
429
+ "rewards/margins": 0.9584181904792786,
430
+ "rewards/rejected": -2.117769241333008,
431
+ "step": 250
432
+ },
433
+ {
434
+ "epoch": 0.5439330543933054,
435
+ "grad_norm": 27.657368894192487,
436
+ "learning_rate": 2.55479083351317e-07,
437
+ "logits/chosen": 0.624454140663147,
438
+ "logits/rejected": 1.5941022634506226,
439
+ "logps/chosen": -408.07598876953125,
440
+ "logps/rejected": -454.6495666503906,
441
+ "loss": 0.5019,
442
+ "rewards/accuracies": 0.75,
443
+ "rewards/chosen": -1.1376445293426514,
444
+ "rewards/margins": 0.8690470457077026,
445
+ "rewards/rejected": -2.0066916942596436,
446
+ "step": 260
447
+ },
448
+ {
449
+ "epoch": 0.5648535564853556,
450
+ "grad_norm": 21.64156582174747,
451
+ "learning_rate": 2.3722002126275822e-07,
452
+ "logits/chosen": 0.22647273540496826,
453
+ "logits/rejected": 0.885449230670929,
454
+ "logps/chosen": -374.7611999511719,
455
+ "logps/rejected": -424.3587951660156,
456
+ "loss": 0.5157,
457
+ "rewards/accuracies": 0.6937500238418579,
458
+ "rewards/chosen": -0.9776525497436523,
459
+ "rewards/margins": 0.6894922256469727,
460
+ "rewards/rejected": -1.667145013809204,
461
+ "step": 270
462
+ },
463
+ {
464
+ "epoch": 0.5857740585774058,
465
+ "grad_norm": 28.159079517918425,
466
+ "learning_rate": 2.19029145890313e-07,
467
+ "logits/chosen": 0.3553857207298279,
468
+ "logits/rejected": 1.404651403427124,
469
+ "logps/chosen": -366.23333740234375,
470
+ "logps/rejected": -431.8450622558594,
471
+ "loss": 0.5305,
472
+ "rewards/accuracies": 0.737500011920929,
473
+ "rewards/chosen": -1.045562505722046,
474
+ "rewards/margins": 0.8510251045227051,
475
+ "rewards/rejected": -1.896587610244751,
476
+ "step": 280
477
+ },
478
+ {
479
+ "epoch": 0.606694560669456,
480
+ "grad_norm": 23.668357833413996,
481
+ "learning_rate": 2.0100351342479216e-07,
482
+ "logits/chosen": 0.38658827543258667,
483
+ "logits/rejected": 1.411795973777771,
484
+ "logps/chosen": -377.20208740234375,
485
+ "logps/rejected": -449.6202697753906,
486
+ "loss": 0.5079,
487
+ "rewards/accuracies": 0.762499988079071,
488
+ "rewards/chosen": -1.2611474990844727,
489
+ "rewards/margins": 0.8154961466789246,
490
+ "rewards/rejected": -2.076643466949463,
491
+ "step": 290
492
+ },
493
+ {
494
+ "epoch": 0.6276150627615062,
495
+ "grad_norm": 25.399079532767146,
496
+ "learning_rate": 1.8323929841460178e-07,
497
+ "logits/chosen": 0.3453945219516754,
498
+ "logits/rejected": 1.5490226745605469,
499
+ "logps/chosen": -423.813720703125,
500
+ "logps/rejected": -465.08514404296875,
501
+ "loss": 0.4826,
502
+ "rewards/accuracies": 0.7124999761581421,
503
+ "rewards/chosen": -1.2281761169433594,
504
+ "rewards/margins": 0.821620762348175,
505
+ "rewards/rejected": -2.0497965812683105,
506
+ "step": 300
507
+ },
508
+ {
509
+ "epoch": 0.6276150627615062,
510
+ "eval_logits/chosen": 0.4518190026283264,
511
+ "eval_logits/rejected": 1.3131211996078491,
512
+ "eval_logps/chosen": -372.7217712402344,
513
+ "eval_logps/rejected": -470.81585693359375,
514
+ "eval_loss": 0.5018269419670105,
515
+ "eval_rewards/accuracies": 0.7734375,
516
+ "eval_rewards/chosen": -1.101283073425293,
517
+ "eval_rewards/margins": 0.98020339012146,
518
+ "eval_rewards/rejected": -2.081486701965332,
519
+ "eval_runtime": 96.5631,
520
+ "eval_samples_per_second": 20.712,
521
+ "eval_steps_per_second": 0.331,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 0.6485355648535565,
526
+ "grad_norm": 33.32118469948312,
527
+ "learning_rate": 1.6583128063291573e-07,
528
+ "logits/chosen": 0.7086529731750488,
529
+ "logits/rejected": 1.432820439338684,
530
+ "logps/chosen": -417.11456298828125,
531
+ "logps/rejected": -465.49871826171875,
532
+ "loss": 0.4857,
533
+ "rewards/accuracies": 0.75,
534
+ "rewards/chosen": -1.2177866697311401,
535
+ "rewards/margins": 0.8520353436470032,
536
+ "rewards/rejected": -2.069821834564209,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 0.6694560669456067,
541
+ "grad_norm": 32.370966943547394,
542
+ "learning_rate": 1.488723393865766e-07,
543
+ "logits/chosen": 0.8957827687263489,
544
+ "logits/rejected": 1.8967578411102295,
545
+ "logps/chosen": -423.543212890625,
546
+ "logps/rejected": -458.0819396972656,
547
+ "loss": 0.4785,
548
+ "rewards/accuracies": 0.7562500238418579,
549
+ "rewards/chosen": -1.2987310886383057,
550
+ "rewards/margins": 0.8338556289672852,
551
+ "rewards/rejected": -2.1325864791870117,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 0.6903765690376569,
556
+ "grad_norm": 31.730308695137953,
557
+ "learning_rate": 1.3245295796480788e-07,
558
+ "logits/chosen": 0.5041384100914001,
559
+ "logits/rejected": 1.5472161769866943,
560
+ "logps/chosen": -390.4256286621094,
561
+ "logps/rejected": -465.3321228027344,
562
+ "loss": 0.4858,
563
+ "rewards/accuracies": 0.706250011920929,
564
+ "rewards/chosen": -1.2821542024612427,
565
+ "rewards/margins": 0.7761803269386292,
566
+ "rewards/rejected": -2.0583345890045166,
567
+ "step": 330
568
+ },
569
+ {
570
+ "epoch": 0.7112970711297071,
571
+ "grad_norm": 32.601240272025024,
572
+ "learning_rate": 1.1666074087171627e-07,
573
+ "logits/chosen": 0.5397793054580688,
574
+ "logits/rejected": 1.506024956703186,
575
+ "logps/chosen": -407.0556335449219,
576
+ "logps/rejected": -500.10662841796875,
577
+ "loss": 0.4937,
578
+ "rewards/accuracies": 0.800000011920929,
579
+ "rewards/chosen": -1.1706117391586304,
580
+ "rewards/margins": 1.0300366878509521,
581
+ "rewards/rejected": -2.200648784637451,
582
+ "step": 340
583
+ },
584
+ {
585
+ "epoch": 0.7322175732217573,
586
+ "grad_norm": 27.635567277748542,
587
+ "learning_rate": 1.0157994641835734e-07,
588
+ "logits/chosen": 0.6218138933181763,
589
+ "logits/rejected": 1.4956554174423218,
590
+ "logps/chosen": -377.9348449707031,
591
+ "logps/rejected": -454.3216857910156,
592
+ "loss": 0.4706,
593
+ "rewards/accuracies": 0.7562500238418579,
594
+ "rewards/chosen": -1.1972359418869019,
595
+ "rewards/margins": 0.9388922452926636,
596
+ "rewards/rejected": -2.1361279487609863,
597
+ "step": 350
598
+ },
599
+ {
600
+ "epoch": 0.7531380753138075,
601
+ "grad_norm": 24.687045320186403,
602
+ "learning_rate": 8.729103716819111e-08,
603
+ "logits/chosen": 0.6358219385147095,
604
+ "logits/rejected": 1.956719994544983,
605
+ "logps/chosen": -429.2447814941406,
606
+ "logps/rejected": -485.86962890625,
607
+ "loss": 0.5022,
608
+ "rewards/accuracies": 0.78125,
609
+ "rewards/chosen": -1.265527367591858,
610
+ "rewards/margins": 0.9801186323165894,
611
+ "rewards/rejected": -2.2456459999084473,
612
+ "step": 360
613
+ },
614
+ {
615
+ "epoch": 0.7740585774058577,
616
+ "grad_norm": 28.11584433716017,
617
+ "learning_rate": 7.387025063449081e-08,
618
+ "logits/chosen": 1.1712688207626343,
619
+ "logits/rejected": 2.0544753074645996,
620
+ "logps/chosen": -422.5091247558594,
621
+ "logps/rejected": -463.7154846191406,
622
+ "loss": 0.5029,
623
+ "rewards/accuracies": 0.7250000238418579,
624
+ "rewards/chosen": -1.4717609882354736,
625
+ "rewards/margins": 0.7830532193183899,
626
+ "rewards/rejected": -2.254814386367798,
627
+ "step": 370
628
+ },
629
+ {
630
+ "epoch": 0.7949790794979079,
631
+ "grad_norm": 24.476287038588072,
632
+ "learning_rate": 6.138919252022435e-08,
633
+ "logits/chosen": 1.362653374671936,
634
+ "logits/rejected": 2.166234016418457,
635
+ "logps/chosen": -396.3254699707031,
636
+ "logps/rejected": -516.1082153320312,
637
+ "loss": 0.4967,
638
+ "rewards/accuracies": 0.768750011920929,
639
+ "rewards/chosen": -1.5684077739715576,
640
+ "rewards/margins": 1.005509614944458,
641
+ "rewards/rejected": -2.5739173889160156,
642
+ "step": 380
643
+ },
644
+ {
645
+ "epoch": 0.8158995815899581,
646
+ "grad_norm": 26.234400494581838,
647
+ "learning_rate": 4.991445467064689e-08,
648
+ "logits/chosen": 0.9196502566337585,
649
+ "logits/rejected": 1.507375955581665,
650
+ "logps/chosen": -442.8583984375,
651
+ "logps/rejected": -509.21148681640625,
652
+ "loss": 0.4846,
653
+ "rewards/accuracies": 0.7437499761581421,
654
+ "rewards/chosen": -1.372214913368225,
655
+ "rewards/margins": 0.8801954388618469,
656
+ "rewards/rejected": -2.252410411834717,
657
+ "step": 390
658
+ },
659
+ {
660
+ "epoch": 0.8368200836820083,
661
+ "grad_norm": 27.121453974144618,
662
+ "learning_rate": 3.9507259776993954e-08,
663
+ "logits/chosen": 1.0388725996017456,
664
+ "logits/rejected": 2.068740129470825,
665
+ "logps/chosen": -408.56390380859375,
666
+ "logps/rejected": -501.59442138671875,
667
+ "loss": 0.495,
668
+ "rewards/accuracies": 0.7437499761581421,
669
+ "rewards/chosen": -1.3802869319915771,
670
+ "rewards/margins": 0.9655326008796692,
671
+ "rewards/rejected": -2.3458199501037598,
672
+ "step": 400
673
+ },
674
+ {
675
+ "epoch": 0.8368200836820083,
676
+ "eval_logits/chosen": 0.5873361825942993,
677
+ "eval_logits/rejected": 1.4928171634674072,
678
+ "eval_logps/chosen": -378.8522033691406,
679
+ "eval_logps/rejected": -481.19586181640625,
680
+ "eval_loss": 0.496925413608551,
681
+ "eval_rewards/accuracies": 0.77734375,
682
+ "eval_rewards/chosen": -1.1625876426696777,
683
+ "eval_rewards/margins": 1.0226988792419434,
684
+ "eval_rewards/rejected": -2.1852867603302,
685
+ "eval_runtime": 96.4494,
686
+ "eval_samples_per_second": 20.736,
687
+ "eval_steps_per_second": 0.332,
688
+ "step": 400
689
+ },
690
+ {
691
+ "epoch": 0.8577405857740585,
692
+ "grad_norm": 25.996039172593594,
693
+ "learning_rate": 3.022313472693447e-08,
694
+ "logits/chosen": 0.6017621159553528,
695
+ "logits/rejected": 1.8573381900787354,
696
+ "logps/chosen": -425.21923828125,
697
+ "logps/rejected": -486.6591796875,
698
+ "loss": 0.503,
699
+ "rewards/accuracies": 0.75,
700
+ "rewards/chosen": -1.2630172967910767,
701
+ "rewards/margins": 0.9154027700424194,
702
+ "rewards/rejected": -2.178420305252075,
703
+ "step": 410
704
+ },
705
+ {
706
+ "epoch": 0.8786610878661087,
707
+ "grad_norm": 23.551777016650735,
708
+ "learning_rate": 2.2111614344599684e-08,
709
+ "logits/chosen": 0.4802716374397278,
710
+ "logits/rejected": 1.373286247253418,
711
+ "logps/chosen": -415.99517822265625,
712
+ "logps/rejected": -479.66845703125,
713
+ "loss": 0.4934,
714
+ "rewards/accuracies": 0.699999988079071,
715
+ "rewards/chosen": -1.1892141103744507,
716
+ "rewards/margins": 0.862848162651062,
717
+ "rewards/rejected": -2.0520622730255127,
718
+ "step": 420
719
+ },
720
+ {
721
+ "epoch": 0.899581589958159,
722
+ "grad_norm": 26.58253060605497,
723
+ "learning_rate": 1.521597710086439e-08,
724
+ "logits/chosen": 0.9357998967170715,
725
+ "logits/rejected": 1.944998025894165,
726
+ "logps/chosen": -411.1884765625,
727
+ "logps/rejected": -484.83062744140625,
728
+ "loss": 0.4727,
729
+ "rewards/accuracies": 0.800000011920929,
730
+ "rewards/chosen": -1.3215035200119019,
731
+ "rewards/margins": 0.9490026235580444,
732
+ "rewards/rejected": -2.2705063819885254,
733
+ "step": 430
734
+ },
735
+ {
736
+ "epoch": 0.9205020920502092,
737
+ "grad_norm": 29.91389949643719,
738
+ "learning_rate": 9.57301420397924e-09,
739
+ "logits/chosen": 0.5421011447906494,
740
+ "logits/rejected": 1.6035425662994385,
741
+ "logps/chosen": -402.51129150390625,
742
+ "logps/rejected": -472.44708251953125,
743
+ "loss": 0.4901,
744
+ "rewards/accuracies": 0.762499988079071,
745
+ "rewards/chosen": -1.181741714477539,
746
+ "rewards/margins": 0.8516114950180054,
747
+ "rewards/rejected": -2.033353328704834,
748
+ "step": 440
749
+ },
750
+ {
751
+ "epoch": 0.9414225941422594,
752
+ "grad_norm": 25.77219458607021,
753
+ "learning_rate": 5.212833302556258e-09,
754
+ "logits/chosen": 0.6684173941612244,
755
+ "logits/rejected": 1.5389642715454102,
756
+ "logps/chosen": -420.6578063964844,
757
+ "logps/rejected": -521.8568725585938,
758
+ "loss": 0.4916,
759
+ "rewards/accuracies": 0.699999988079071,
760
+ "rewards/chosen": -1.269736409187317,
761
+ "rewards/margins": 0.8780879974365234,
762
+ "rewards/rejected": -2.147824287414551,
763
+ "step": 450
764
+ },
765
+ {
766
+ "epoch": 0.9623430962343096,
767
+ "grad_norm": 25.79146794601895,
768
+ "learning_rate": 2.158697848236607e-09,
769
+ "logits/chosen": 0.8310929536819458,
770
+ "logits/rejected": 1.7648357152938843,
771
+ "logps/chosen": -395.16680908203125,
772
+ "logps/rejected": -452.0589294433594,
773
+ "loss": 0.4942,
774
+ "rewards/accuracies": 0.6875,
775
+ "rewards/chosen": -1.2320220470428467,
776
+ "rewards/margins": 0.8616892695426941,
777
+ "rewards/rejected": -2.0937113761901855,
778
+ "step": 460
779
+ },
780
+ {
781
+ "epoch": 0.9832635983263598,
782
+ "grad_norm": 25.562634206457844,
783
+ "learning_rate": 4.269029751107489e-10,
784
+ "logits/chosen": 0.6654651761054993,
785
+ "logits/rejected": 1.765618920326233,
786
+ "logps/chosen": -397.56622314453125,
787
+ "logps/rejected": -492.461181640625,
788
+ "loss": 0.4831,
789
+ "rewards/accuracies": 0.762499988079071,
790
+ "rewards/chosen": -1.1886755228042603,
791
+ "rewards/margins": 0.9124252200126648,
792
+ "rewards/rejected": -2.1011009216308594,
793
+ "step": 470
794
+ },
795
+ {
796
+ "epoch": 1.0,
797
+ "step": 478,
798
+ "total_flos": 0.0,
799
+ "train_loss": 0.5340489398485447,
800
+ "train_runtime": 7520.1807,
801
+ "train_samples_per_second": 8.129,
802
+ "train_steps_per_second": 0.064
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
+ }