lewtun HF staff commited on
Commit
ee89efc
1 Parent(s): 0388590

Model save

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: lewtun/gemma-7b-sft-full-ultrachat-v0
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: gemma-7b-dpo-full-ultrafeedback-beta-0.01
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
+ # gemma-7b-dpo-full-ultrafeedback-beta-0.01
17
+
18
+ This model is a fine-tuned version of [lewtun/gemma-7b-sft-full-ultrachat-v0](https://huggingface.co/lewtun/gemma-7b-sft-full-ultrachat-v0) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4718
21
+ - Rewards/chosen: -0.8508
22
+ - Rewards/rejected: -2.1538
23
+ - Rewards/accuracies: 0.7817
24
+ - Rewards/margins: 1.3030
25
+ - Logps/rejected: -1100.8470
26
+ - Logps/chosen: -990.8950
27
+ - Logits/rejected: 89.1600
28
+ - Logits/chosen: 104.0108
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: 2
49
+ - eval_batch_size: 4
50
+ - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - num_devices: 8
53
+ - gradient_accumulation_steps: 8
54
+ - total_train_batch_size: 128
55
+ - total_eval_batch_size: 32
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
+ | 0.552 | 0.21 | 100 | 0.5756 | -2.8657 | -3.5901 | 0.7460 | 0.7243 | -1244.4771 | -1192.3933 | 82.3244 | 96.5612 |
66
+ | 0.501 | 0.42 | 200 | 0.4914 | -1.6427 | -2.6660 | 0.7817 | 1.0233 | -1152.0745 | -1070.0895 | 91.1202 | 105.1467 |
67
+ | 0.4893 | 0.63 | 300 | 0.4810 | -1.6604 | -2.8398 | 0.7619 | 1.1794 | -1169.4480 | -1071.8550 | 87.4237 | 101.9799 |
68
+ | 0.4759 | 0.84 | 400 | 0.4718 | -0.8508 | -2.1538 | 0.7817 | 1.3030 | -1100.8470 | -990.8950 | 89.1600 | 104.0108 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.39.0.dev0
74
+ - Pytorch 2.1.2+cu121
75
+ - Datasets 2.14.6
76
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5152078939433867,
4
+ "train_runtime": 5321.4428,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 11.488,
7
+ "train_steps_per_second": 0.09
8
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d37d3e20e6926aee530b2cab69fbb64f6a22df46d727a472fd44b710f424e8
3
+ size 4995496656
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17111c7a14501043c274618bb8ec08e66ddf9447e102b75cb2e3ebf07dffad6f
3
+ size 4982953168
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3bbbffa1f9a6cd81d6b5b7273d1d26d399317f65517cbf5c74bd5f1d7e99c1
3
+ size 4982953200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e5b1fb7457fbf470a4844162ff99e5397754c5576b938a46e11c613151cfbc
3
+ size 2113988336
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17075361792
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.norm.weight": "model-00004-of-00004.safetensors"
260
+ }
261
+ }
runs/Feb29_22-08-46_ip-26-0-161-178/events.out.tfevents.1709244785.ip-26-0-161-178.1167714.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32292ebbde3c8f16459199568711098c4770b7cc9a9d4b9d373006d42f21b24c
3
- size 35892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5278b627d72d88fd1f2e5d65580a25bb7b3aa9b7fb3793b1bfc38c30b7afa80
3
+ size 41062
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5152078939433867,
4
+ "train_runtime": 5321.4428,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 11.488,
7
+ "train_steps_per_second": 0.09
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,814 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.998691442030882,
5
+ "eval_steps": 100,
6
+ "global_step": 477,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 19.889135020542987,
14
+ "learning_rate": 1.0416666666666666e-08,
15
+ "logits/chosen": 173.92840576171875,
16
+ "logits/rejected": 133.92694091796875,
17
+ "logps/chosen": -944.73779296875,
18
+ "logps/rejected": -877.1348876953125,
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": 18.648812633756638,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": 158.15008544921875,
31
+ "logits/rejected": 151.00912475585938,
32
+ "logps/chosen": -866.2621459960938,
33
+ "logps/rejected": -858.798583984375,
34
+ "loss": 0.6925,
35
+ "rewards/accuracies": 0.4444444477558136,
36
+ "rewards/chosen": 0.0011810450814664364,
37
+ "rewards/margins": -9.146943193627521e-05,
38
+ "rewards/rejected": 0.0012725150445476174,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "grad_norm": 132.24935780648104,
44
+ "learning_rate": 2.0833333333333333e-07,
45
+ "logits/chosen": 162.58755493164062,
46
+ "logits/rejected": 141.87896728515625,
47
+ "logps/chosen": -871.9114990234375,
48
+ "logps/rejected": -856.8277587890625,
49
+ "loss": 0.69,
50
+ "rewards/accuracies": 0.5249999761581421,
51
+ "rewards/chosen": 0.02589397504925728,
52
+ "rewards/margins": 0.012839567847549915,
53
+ "rewards/rejected": 0.013054406270384789,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.06,
58
+ "grad_norm": 29.299152561983977,
59
+ "learning_rate": 3.1249999999999997e-07,
60
+ "logits/chosen": 148.5764617919922,
61
+ "logits/rejected": 148.60226440429688,
62
+ "logps/chosen": -834.642578125,
63
+ "logps/rejected": -821.4388427734375,
64
+ "loss": 0.6792,
65
+ "rewards/accuracies": 0.5249999761581421,
66
+ "rewards/chosen": 0.09783056378364563,
67
+ "rewards/margins": 0.019630378112196922,
68
+ "rewards/rejected": 0.07820017635822296,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.08,
73
+ "grad_norm": 20.662529763504946,
74
+ "learning_rate": 4.1666666666666667e-07,
75
+ "logits/chosen": 149.3659210205078,
76
+ "logits/rejected": 131.38018798828125,
77
+ "logps/chosen": -907.97509765625,
78
+ "logps/rejected": -912.3134765625,
79
+ "loss": 0.6489,
80
+ "rewards/accuracies": 0.606249988079071,
81
+ "rewards/chosen": 0.009358148090541363,
82
+ "rewards/margins": 0.11060555279254913,
83
+ "rewards/rejected": -0.1012474074959755,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.1,
88
+ "grad_norm": 37.45560682117618,
89
+ "learning_rate": 4.999731868769026e-07,
90
+ "logits/chosen": 141.44911193847656,
91
+ "logits/rejected": 129.70591735839844,
92
+ "logps/chosen": -925.8624877929688,
93
+ "logps/rejected": -942.8903198242188,
94
+ "loss": 0.6263,
95
+ "rewards/accuracies": 0.7562500238418579,
96
+ "rewards/chosen": -0.42348790168762207,
97
+ "rewards/margins": 0.23968985676765442,
98
+ "rewards/rejected": -0.6631777286529541,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.13,
103
+ "grad_norm": 35.27997957962436,
104
+ "learning_rate": 4.990353313429303e-07,
105
+ "logits/chosen": 104.57405090332031,
106
+ "logits/rejected": 102.98997497558594,
107
+ "logps/chosen": -994.7630615234375,
108
+ "logps/rejected": -1038.8465576171875,
109
+ "loss": 0.6063,
110
+ "rewards/accuracies": 0.6312500238418579,
111
+ "rewards/chosen": -1.1830905675888062,
112
+ "rewards/margins": 0.3269960284233093,
113
+ "rewards/rejected": -1.5100867748260498,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.15,
118
+ "grad_norm": 49.67365299996332,
119
+ "learning_rate": 4.967625656594781e-07,
120
+ "logits/chosen": 119.69749450683594,
121
+ "logits/rejected": 109.80323791503906,
122
+ "logps/chosen": -1019.2648315429688,
123
+ "logps/rejected": -1040.623779296875,
124
+ "loss": 0.5565,
125
+ "rewards/accuracies": 0.6875,
126
+ "rewards/chosen": -1.3080466985702515,
127
+ "rewards/margins": 0.5215330123901367,
128
+ "rewards/rejected": -1.8295797109603882,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.17,
133
+ "grad_norm": 37.66437513199864,
134
+ "learning_rate": 4.93167072587771e-07,
135
+ "logits/chosen": 120.96675109863281,
136
+ "logits/rejected": 99.65242767333984,
137
+ "logps/chosen": -1079.8636474609375,
138
+ "logps/rejected": -1099.0491943359375,
139
+ "loss": 0.5567,
140
+ "rewards/accuracies": 0.7749999761581421,
141
+ "rewards/chosen": -1.4773412942886353,
142
+ "rewards/margins": 0.6472301483154297,
143
+ "rewards/rejected": -2.1245713233947754,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.19,
148
+ "grad_norm": 40.6528309450039,
149
+ "learning_rate": 4.882681251368548e-07,
150
+ "logits/chosen": 102.38163757324219,
151
+ "logits/rejected": 100.23868560791016,
152
+ "logps/chosen": -1027.5,
153
+ "logps/rejected": -1059.419921875,
154
+ "loss": 0.5699,
155
+ "rewards/accuracies": 0.699999988079071,
156
+ "rewards/chosen": -1.292600393295288,
157
+ "rewards/margins": 0.5152118802070618,
158
+ "rewards/rejected": -1.8078124523162842,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.21,
163
+ "grad_norm": 38.60858209436158,
164
+ "learning_rate": 4.820919832540181e-07,
165
+ "logits/chosen": 118.79133605957031,
166
+ "logits/rejected": 104.7783432006836,
167
+ "logps/chosen": -1127.0018310546875,
168
+ "logps/rejected": -1152.863037109375,
169
+ "loss": 0.552,
170
+ "rewards/accuracies": 0.6499999761581421,
171
+ "rewards/chosen": -2.3822240829467773,
172
+ "rewards/margins": 0.6033691167831421,
173
+ "rewards/rejected": -2.985593318939209,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.21,
178
+ "eval_logits/chosen": 96.5611801147461,
179
+ "eval_logits/rejected": 82.32440185546875,
180
+ "eval_logps/chosen": -1192.393310546875,
181
+ "eval_logps/rejected": -1244.47705078125,
182
+ "eval_loss": 0.5756222009658813,
183
+ "eval_rewards/accuracies": 0.7460317611694336,
184
+ "eval_rewards/chosen": -2.8657495975494385,
185
+ "eval_rewards/margins": 0.7243059873580933,
186
+ "eval_rewards/rejected": -3.590055465698242,
187
+ "eval_runtime": 98.8707,
188
+ "eval_samples_per_second": 20.228,
189
+ "eval_steps_per_second": 0.637,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.23,
194
+ "grad_norm": 34.77575362187783,
195
+ "learning_rate": 4.7467175306295647e-07,
196
+ "logits/chosen": 113.10517883300781,
197
+ "logits/rejected": 108.6837158203125,
198
+ "logps/chosen": -1058.0145263671875,
199
+ "logps/rejected": -1144.630859375,
200
+ "loss": 0.5379,
201
+ "rewards/accuracies": 0.7562500238418579,
202
+ "rewards/chosen": -1.9207611083984375,
203
+ "rewards/margins": 0.8025757074356079,
204
+ "rewards/rejected": -2.723336696624756,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 0.25,
209
+ "grad_norm": 37.99281988815398,
210
+ "learning_rate": 4.6604720940421207e-07,
211
+ "logits/chosen": 127.37345123291016,
212
+ "logits/rejected": 113.18028259277344,
213
+ "logps/chosen": -1034.3157958984375,
214
+ "logps/rejected": -1087.8922119140625,
215
+ "loss": 0.561,
216
+ "rewards/accuracies": 0.75,
217
+ "rewards/chosen": -1.195056676864624,
218
+ "rewards/margins": 0.6624664068222046,
219
+ "rewards/rejected": -1.857522964477539,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 0.27,
224
+ "grad_norm": 30.358803498156306,
225
+ "learning_rate": 4.5626458262912735e-07,
226
+ "logits/chosen": 117.21207427978516,
227
+ "logits/rejected": 122.45979309082031,
228
+ "logps/chosen": -1013.4964599609375,
229
+ "logps/rejected": -1076.5015869140625,
230
+ "loss": 0.5326,
231
+ "rewards/accuracies": 0.71875,
232
+ "rewards/chosen": -1.4635175466537476,
233
+ "rewards/margins": 0.6195371150970459,
234
+ "rewards/rejected": -2.083055019378662,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 0.29,
239
+ "grad_norm": 33.33546006946111,
240
+ "learning_rate": 4.453763107901675e-07,
241
+ "logits/chosen": 120.96626281738281,
242
+ "logits/rejected": 99.00543212890625,
243
+ "logps/chosen": -1037.393798828125,
244
+ "logps/rejected": -1113.715576171875,
245
+ "loss": 0.5061,
246
+ "rewards/accuracies": 0.7437499761581421,
247
+ "rewards/chosen": -1.6467615365982056,
248
+ "rewards/margins": 0.959250807762146,
249
+ "rewards/rejected": -2.6060123443603516,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 0.31,
254
+ "grad_norm": 36.216638034956645,
255
+ "learning_rate": 4.3344075855595097e-07,
256
+ "logits/chosen": 107.6335678100586,
257
+ "logits/rejected": 96.20887756347656,
258
+ "logps/chosen": -982.7149658203125,
259
+ "logps/rejected": -1042.314697265625,
260
+ "loss": 0.5158,
261
+ "rewards/accuracies": 0.7749999761581421,
262
+ "rewards/chosen": -0.9869440197944641,
263
+ "rewards/margins": 0.917373538017273,
264
+ "rewards/rejected": -1.9043172597885132,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 0.33,
269
+ "grad_norm": 41.67256305682121,
270
+ "learning_rate": 4.2052190435769554e-07,
271
+ "logits/chosen": 113.42124938964844,
272
+ "logits/rejected": 102.60457611083984,
273
+ "logps/chosen": -1003.9383544921875,
274
+ "logps/rejected": -1058.088134765625,
275
+ "loss": 0.5019,
276
+ "rewards/accuracies": 0.6812499761581421,
277
+ "rewards/chosen": -1.3599907159805298,
278
+ "rewards/margins": 0.8325563669204712,
279
+ "rewards/rejected": -2.192547082901001,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 0.36,
284
+ "grad_norm": 45.33240260875551,
285
+ "learning_rate": 4.0668899744407567e-07,
286
+ "logits/chosen": 111.82502746582031,
287
+ "logits/rejected": 104.21772766113281,
288
+ "logps/chosen": -1027.629638671875,
289
+ "logps/rejected": -1113.077880859375,
290
+ "loss": 0.5128,
291
+ "rewards/accuracies": 0.7250000238418579,
292
+ "rewards/chosen": -1.418601632118225,
293
+ "rewards/margins": 0.8126633763313293,
294
+ "rewards/rejected": -2.231265068054199,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 0.38,
299
+ "grad_norm": 39.41765859124985,
300
+ "learning_rate": 3.920161866827889e-07,
301
+ "logits/chosen": 119.5909423828125,
302
+ "logits/rejected": 101.44880676269531,
303
+ "logps/chosen": -926.8933715820312,
304
+ "logps/rejected": -969.1472778320312,
305
+ "loss": 0.5088,
306
+ "rewards/accuracies": 0.706250011920929,
307
+ "rewards/chosen": -0.4561997354030609,
308
+ "rewards/margins": 0.7785950899124146,
309
+ "rewards/rejected": -1.2347948551177979,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 0.4,
314
+ "grad_norm": 43.60352127706551,
315
+ "learning_rate": 3.765821230985757e-07,
316
+ "logits/chosen": 129.9263916015625,
317
+ "logits/rejected": 123.3591079711914,
318
+ "logps/chosen": -996.8531494140625,
319
+ "logps/rejected": -1059.179443359375,
320
+ "loss": 0.5073,
321
+ "rewards/accuracies": 0.706250011920929,
322
+ "rewards/chosen": -1.3905432224273682,
323
+ "rewards/margins": 0.9462689161300659,
324
+ "rewards/rejected": -2.3368120193481445,
325
+ "step": 190
326
+ },
327
+ {
328
+ "epoch": 0.42,
329
+ "grad_norm": 41.35808766754113,
330
+ "learning_rate": 3.604695382782159e-07,
331
+ "logits/chosen": 124.6067886352539,
332
+ "logits/rejected": 118.35124206542969,
333
+ "logps/chosen": -1090.52783203125,
334
+ "logps/rejected": -1147.1068115234375,
335
+ "loss": 0.501,
336
+ "rewards/accuracies": 0.7749999761581421,
337
+ "rewards/chosen": -2.105625629425049,
338
+ "rewards/margins": 0.8636106252670288,
339
+ "rewards/rejected": -2.969236373901367,
340
+ "step": 200
341
+ },
342
+ {
343
+ "epoch": 0.42,
344
+ "eval_logits/chosen": 105.14665222167969,
345
+ "eval_logits/rejected": 91.12017059326172,
346
+ "eval_logps/chosen": -1070.0894775390625,
347
+ "eval_logps/rejected": -1152.074462890625,
348
+ "eval_loss": 0.49135974049568176,
349
+ "eval_rewards/accuracies": 0.7817460298538208,
350
+ "eval_rewards/chosen": -1.6427117586135864,
351
+ "eval_rewards/margins": 1.0233176946640015,
352
+ "eval_rewards/rejected": -2.666029453277588,
353
+ "eval_runtime": 98.2325,
354
+ "eval_samples_per_second": 20.36,
355
+ "eval_steps_per_second": 0.641,
356
+ "step": 200
357
+ },
358
+ {
359
+ "epoch": 0.44,
360
+ "grad_norm": 40.009657639886804,
361
+ "learning_rate": 3.4376480090239047e-07,
362
+ "logits/chosen": 119.9991683959961,
363
+ "logits/rejected": 104.25712585449219,
364
+ "logps/chosen": -1026.137451171875,
365
+ "logps/rejected": -1069.336669921875,
366
+ "loss": 0.4974,
367
+ "rewards/accuracies": 0.7250000238418579,
368
+ "rewards/chosen": -1.1238807439804077,
369
+ "rewards/margins": 0.9766911268234253,
370
+ "rewards/rejected": -2.100571870803833,
371
+ "step": 210
372
+ },
373
+ {
374
+ "epoch": 0.46,
375
+ "grad_norm": 37.28316867834671,
376
+ "learning_rate": 3.265574537815398e-07,
377
+ "logits/chosen": 124.17179107666016,
378
+ "logits/rejected": 104.73355865478516,
379
+ "logps/chosen": -962.50244140625,
380
+ "logps/rejected": -1003.451171875,
381
+ "loss": 0.4961,
382
+ "rewards/accuracies": 0.7437499761581421,
383
+ "rewards/chosen": -0.7499821782112122,
384
+ "rewards/margins": 0.8301311731338501,
385
+ "rewards/rejected": -1.580113172531128,
386
+ "step": 220
387
+ },
388
+ {
389
+ "epoch": 0.48,
390
+ "grad_norm": 54.558673930247686,
391
+ "learning_rate": 3.0893973387735683e-07,
392
+ "logits/chosen": 130.6039581298828,
393
+ "logits/rejected": 105.5712661743164,
394
+ "logps/chosen": -944.1550903320312,
395
+ "logps/rejected": -1030.9761962890625,
396
+ "loss": 0.4864,
397
+ "rewards/accuracies": 0.7437499761581421,
398
+ "rewards/chosen": -0.652384877204895,
399
+ "rewards/margins": 1.2353802919387817,
400
+ "rewards/rejected": -1.8877651691436768,
401
+ "step": 230
402
+ },
403
+ {
404
+ "epoch": 0.5,
405
+ "grad_norm": 44.93883051182552,
406
+ "learning_rate": 2.910060778827554e-07,
407
+ "logits/chosen": 124.2732162475586,
408
+ "logits/rejected": 106.26287841796875,
409
+ "logps/chosen": -974.0313720703125,
410
+ "logps/rejected": -1065.3079833984375,
411
+ "loss": 0.4814,
412
+ "rewards/accuracies": 0.7562500238418579,
413
+ "rewards/chosen": -0.758819043636322,
414
+ "rewards/margins": 1.1402368545532227,
415
+ "rewards/rejected": -1.8990558385849,
416
+ "step": 240
417
+ },
418
+ {
419
+ "epoch": 0.52,
420
+ "grad_norm": 44.64312531732698,
421
+ "learning_rate": 2.7285261601056697e-07,
422
+ "logits/chosen": 116.86869812011719,
423
+ "logits/rejected": 101.10758972167969,
424
+ "logps/chosen": -952.7760620117188,
425
+ "logps/rejected": -1048.2093505859375,
426
+ "loss": 0.4998,
427
+ "rewards/accuracies": 0.78125,
428
+ "rewards/chosen": -0.9232794046401978,
429
+ "rewards/margins": 1.1742398738861084,
430
+ "rewards/rejected": -2.0975191593170166,
431
+ "step": 250
432
+ },
433
+ {
434
+ "epoch": 0.54,
435
+ "grad_norm": 40.68735732627764,
436
+ "learning_rate": 2.5457665670441937e-07,
437
+ "logits/chosen": 123.28076171875,
438
+ "logits/rejected": 102.635986328125,
439
+ "logps/chosen": -893.8860473632812,
440
+ "logps/rejected": -1004.1375732421875,
441
+ "loss": 0.4785,
442
+ "rewards/accuracies": 0.7875000238418579,
443
+ "rewards/chosen": -0.23751500248908997,
444
+ "rewards/margins": 1.1629530191421509,
445
+ "rewards/rejected": -1.4004679918289185,
446
+ "step": 260
447
+ },
448
+ {
449
+ "epoch": 0.57,
450
+ "grad_norm": 38.53534572807841,
451
+ "learning_rate": 2.3627616503391812e-07,
452
+ "logits/chosen": 118.7505874633789,
453
+ "logits/rejected": 110.69478607177734,
454
+ "logps/chosen": -951.8123779296875,
455
+ "logps/rejected": -1055.506103515625,
456
+ "loss": 0.4888,
457
+ "rewards/accuracies": 0.731249988079071,
458
+ "rewards/chosen": -0.709445595741272,
459
+ "rewards/margins": 1.0170724391937256,
460
+ "rewards/rejected": -1.7265180349349976,
461
+ "step": 270
462
+ },
463
+ {
464
+ "epoch": 0.59,
465
+ "grad_norm": 39.95351928619943,
466
+ "learning_rate": 2.1804923757009882e-07,
467
+ "logits/chosen": 130.1121063232422,
468
+ "logits/rejected": 109.01686096191406,
469
+ "logps/chosen": -1051.2080078125,
470
+ "logps/rejected": -1150.492431640625,
471
+ "loss": 0.4577,
472
+ "rewards/accuracies": 0.7749999761581421,
473
+ "rewards/chosen": -1.1860597133636475,
474
+ "rewards/margins": 1.2530558109283447,
475
+ "rewards/rejected": -2.439115285873413,
476
+ "step": 280
477
+ },
478
+ {
479
+ "epoch": 0.61,
480
+ "grad_norm": 36.79184277903521,
481
+ "learning_rate": 1.9999357655598891e-07,
482
+ "logits/chosen": 125.7824935913086,
483
+ "logits/rejected": 115.7079086303711,
484
+ "logps/chosen": -1027.8924560546875,
485
+ "logps/rejected": -1112.7578125,
486
+ "loss": 0.4803,
487
+ "rewards/accuracies": 0.768750011920929,
488
+ "rewards/chosen": -1.5402090549468994,
489
+ "rewards/margins": 1.2050487995147705,
490
+ "rewards/rejected": -2.74525785446167,
491
+ "step": 290
492
+ },
493
+ {
494
+ "epoch": 0.63,
495
+ "grad_norm": 42.82758424377552,
496
+ "learning_rate": 1.8220596619089573e-07,
497
+ "logits/chosen": 122.8412094116211,
498
+ "logits/rejected": 110.88859558105469,
499
+ "logps/chosen": -1007.1027221679688,
500
+ "logps/rejected": -1088.6361083984375,
501
+ "loss": 0.4893,
502
+ "rewards/accuracies": 0.75,
503
+ "rewards/chosen": -1.636523962020874,
504
+ "rewards/margins": 1.004431962966919,
505
+ "rewards/rejected": -2.640956163406372,
506
+ "step": 300
507
+ },
508
+ {
509
+ "epoch": 0.63,
510
+ "eval_logits/chosen": 101.97990417480469,
511
+ "eval_logits/rejected": 87.42365264892578,
512
+ "eval_logps/chosen": -1071.85498046875,
513
+ "eval_logps/rejected": -1169.447998046875,
514
+ "eval_loss": 0.48103758692741394,
515
+ "eval_rewards/accuracies": 0.761904776096344,
516
+ "eval_rewards/chosen": -1.6603679656982422,
517
+ "eval_rewards/margins": 1.1793973445892334,
518
+ "eval_rewards/rejected": -2.8397650718688965,
519
+ "eval_runtime": 101.0727,
520
+ "eval_samples_per_second": 19.788,
521
+ "eval_steps_per_second": 0.623,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 0.65,
526
+ "grad_norm": 38.54631864265249,
527
+ "learning_rate": 1.647817538357072e-07,
528
+ "logits/chosen": 113.38005065917969,
529
+ "logits/rejected": 110.6764144897461,
530
+ "logps/chosen": -995.9137573242188,
531
+ "logps/rejected": -1127.708251953125,
532
+ "loss": 0.4446,
533
+ "rewards/accuracies": 0.78125,
534
+ "rewards/chosen": -1.5860974788665771,
535
+ "rewards/margins": 1.1870568990707397,
536
+ "rewards/rejected": -2.7731544971466064,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 0.67,
541
+ "grad_norm": 44.46063064657573,
542
+ "learning_rate": 1.478143389201113e-07,
543
+ "logits/chosen": 119.3581771850586,
544
+ "logits/rejected": 113.27059173583984,
545
+ "logps/chosen": -1008.1510620117188,
546
+ "logps/rejected": -1137.126220703125,
547
+ "loss": 0.4747,
548
+ "rewards/accuracies": 0.768750011920929,
549
+ "rewards/chosen": -1.4959969520568848,
550
+ "rewards/margins": 1.4020049571990967,
551
+ "rewards/rejected": -2.898001194000244,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 0.69,
556
+ "grad_norm": 34.37130611293822,
557
+ "learning_rate": 1.3139467229135998e-07,
558
+ "logits/chosen": 129.7974090576172,
559
+ "logits/rejected": 115.29783630371094,
560
+ "logps/chosen": -1069.2001953125,
561
+ "logps/rejected": -1156.9002685546875,
562
+ "loss": 0.4666,
563
+ "rewards/accuracies": 0.75,
564
+ "rewards/chosen": -1.5326635837554932,
565
+ "rewards/margins": 1.1574156284332275,
566
+ "rewards/rejected": -2.6900792121887207,
567
+ "step": 330
568
+ },
569
+ {
570
+ "epoch": 0.71,
571
+ "grad_norm": 37.51413061347318,
572
+ "learning_rate": 1.1561076868822755e-07,
573
+ "logits/chosen": 135.8931884765625,
574
+ "logits/rejected": 121.91889953613281,
575
+ "logps/chosen": -1037.731689453125,
576
+ "logps/rejected": -1122.47412109375,
577
+ "loss": 0.466,
578
+ "rewards/accuracies": 0.7124999761581421,
579
+ "rewards/chosen": -1.680929183959961,
580
+ "rewards/margins": 1.011832356452942,
581
+ "rewards/rejected": -2.6927616596221924,
582
+ "step": 340
583
+ },
584
+ {
585
+ "epoch": 0.73,
586
+ "grad_norm": 44.78811791068193,
587
+ "learning_rate": 1.0054723495346482e-07,
588
+ "logits/chosen": 131.4265899658203,
589
+ "logits/rejected": 113.61830139160156,
590
+ "logps/chosen": -1038.681396484375,
591
+ "logps/rejected": -1120.1895751953125,
592
+ "loss": 0.4816,
593
+ "rewards/accuracies": 0.6937500238418579,
594
+ "rewards/chosen": -1.5251903533935547,
595
+ "rewards/margins": 1.061643362045288,
596
+ "rewards/rejected": -2.5868337154388428,
597
+ "step": 350
598
+ },
599
+ {
600
+ "epoch": 0.75,
601
+ "grad_norm": 48.873185347547825,
602
+ "learning_rate": 8.628481651367875e-08,
603
+ "logits/chosen": 131.0110321044922,
604
+ "logits/rejected": 106.7862548828125,
605
+ "logps/chosen": -1003.0614013671875,
606
+ "logps/rejected": -1117.0228271484375,
607
+ "loss": 0.4628,
608
+ "rewards/accuracies": 0.71875,
609
+ "rewards/chosen": -1.315259337425232,
610
+ "rewards/margins": 1.2398252487182617,
611
+ "rewards/rejected": -2.555084466934204,
612
+ "step": 360
613
+ },
614
+ {
615
+ "epoch": 0.77,
616
+ "grad_norm": 43.10852524272028,
617
+ "learning_rate": 7.289996455765748e-08,
618
+ "logits/chosen": 119.69869232177734,
619
+ "logits/rejected": 114.07867431640625,
620
+ "logps/chosen": -1036.690673828125,
621
+ "logps/rejected": -1146.2222900390625,
622
+ "loss": 0.4818,
623
+ "rewards/accuracies": 0.7749999761581421,
624
+ "rewards/chosen": -1.3266334533691406,
625
+ "rewards/margins": 1.4441391229629517,
626
+ "rewards/rejected": -2.7707724571228027,
627
+ "step": 370
628
+ },
629
+ {
630
+ "epoch": 0.8,
631
+ "grad_norm": 38.151146819157155,
632
+ "learning_rate": 6.046442623320145e-08,
633
+ "logits/chosen": 122.61408996582031,
634
+ "logits/rejected": 126.60284423828125,
635
+ "logps/chosen": -1007.2545166015625,
636
+ "logps/rejected": -1128.876220703125,
637
+ "loss": 0.4616,
638
+ "rewards/accuracies": 0.7437499761581421,
639
+ "rewards/chosen": -1.2509572505950928,
640
+ "rewards/margins": 1.2325677871704102,
641
+ "rewards/rejected": -2.483525037765503,
642
+ "step": 380
643
+ },
644
+ {
645
+ "epoch": 0.82,
646
+ "grad_norm": 42.436222296241255,
647
+ "learning_rate": 4.904486005914027e-08,
648
+ "logits/chosen": 134.9565887451172,
649
+ "logits/rejected": 112.53916931152344,
650
+ "logps/chosen": -989.7498779296875,
651
+ "logps/rejected": -1100.5008544921875,
652
+ "loss": 0.466,
653
+ "rewards/accuracies": 0.7875000238418579,
654
+ "rewards/chosen": -1.100543737411499,
655
+ "rewards/margins": 1.3375900983810425,
656
+ "rewards/rejected": -2.438133955001831,
657
+ "step": 390
658
+ },
659
+ {
660
+ "epoch": 0.84,
661
+ "grad_norm": 45.12243805369195,
662
+ "learning_rate": 3.8702478614051345e-08,
663
+ "logits/chosen": 124.96537780761719,
664
+ "logits/rejected": 101.06147766113281,
665
+ "logps/chosen": -953.6491088867188,
666
+ "logps/rejected": -1035.303466796875,
667
+ "loss": 0.4759,
668
+ "rewards/accuracies": 0.78125,
669
+ "rewards/chosen": -0.9369322061538696,
670
+ "rewards/margins": 1.2312959432601929,
671
+ "rewards/rejected": -2.1682283878326416,
672
+ "step": 400
673
+ },
674
+ {
675
+ "epoch": 0.84,
676
+ "eval_logits/chosen": 104.01083374023438,
677
+ "eval_logits/rejected": 89.1600341796875,
678
+ "eval_logps/chosen": -990.8949584960938,
679
+ "eval_logps/rejected": -1100.8470458984375,
680
+ "eval_loss": 0.47177109122276306,
681
+ "eval_rewards/accuracies": 0.7817460298538208,
682
+ "eval_rewards/chosen": -0.8507668972015381,
683
+ "eval_rewards/margins": 1.3029894828796387,
684
+ "eval_rewards/rejected": -2.153756618499756,
685
+ "eval_runtime": 100.3183,
686
+ "eval_samples_per_second": 19.937,
687
+ "eval_steps_per_second": 0.628,
688
+ "step": 400
689
+ },
690
+ {
691
+ "epoch": 0.86,
692
+ "grad_norm": 41.02552262522525,
693
+ "learning_rate": 2.9492720416985e-08,
694
+ "logits/chosen": 134.49705505371094,
695
+ "logits/rejected": 125.9228744506836,
696
+ "logps/chosen": -977.2227783203125,
697
+ "logps/rejected": -1063.806396484375,
698
+ "loss": 0.4743,
699
+ "rewards/accuracies": 0.706250011920929,
700
+ "rewards/chosen": -0.9780263900756836,
701
+ "rewards/margins": 0.9129725694656372,
702
+ "rewards/rejected": -1.8909988403320312,
703
+ "step": 410
704
+ },
705
+ {
706
+ "epoch": 0.88,
707
+ "grad_norm": 38.58815640645097,
708
+ "learning_rate": 2.1464952759020856e-08,
709
+ "logits/chosen": 125.35734558105469,
710
+ "logits/rejected": 111.65289306640625,
711
+ "logps/chosen": -949.1236572265625,
712
+ "logps/rejected": -1051.959228515625,
713
+ "loss": 0.4823,
714
+ "rewards/accuracies": 0.7437499761581421,
715
+ "rewards/chosen": -0.9723941683769226,
716
+ "rewards/margins": 1.144566297531128,
717
+ "rewards/rejected": -2.116960287094116,
718
+ "step": 420
719
+ },
720
+ {
721
+ "epoch": 0.9,
722
+ "grad_norm": 31.91004161837456,
723
+ "learning_rate": 1.4662207078575684e-08,
724
+ "logits/chosen": 121.03411865234375,
725
+ "logits/rejected": 110.73746490478516,
726
+ "logps/chosen": -962.5640869140625,
727
+ "logps/rejected": -1089.4044189453125,
728
+ "loss": 0.4505,
729
+ "rewards/accuracies": 0.78125,
730
+ "rewards/chosen": -1.0843942165374756,
731
+ "rewards/margins": 1.454674243927002,
732
+ "rewards/rejected": -2.5390686988830566,
733
+ "step": 430
734
+ },
735
+ {
736
+ "epoch": 0.92,
737
+ "grad_norm": 37.24587161270191,
738
+ "learning_rate": 9.12094829893642e-09,
739
+ "logits/chosen": 122.1268081665039,
740
+ "logits/rejected": 124.87750244140625,
741
+ "logps/chosen": -947.4508666992188,
742
+ "logps/rejected": -1111.0018310546875,
743
+ "loss": 0.4731,
744
+ "rewards/accuracies": 0.75,
745
+ "rewards/chosen": -1.1550958156585693,
746
+ "rewards/margins": 1.279443621635437,
747
+ "rewards/rejected": -2.434539318084717,
748
+ "step": 440
749
+ },
750
+ {
751
+ "epoch": 0.94,
752
+ "grad_norm": 33.88329943101718,
753
+ "learning_rate": 4.8708793644441086e-09,
754
+ "logits/chosen": 123.2929916381836,
755
+ "logits/rejected": 118.64930725097656,
756
+ "logps/chosen": -1003.01220703125,
757
+ "logps/rejected": -1144.7047119140625,
758
+ "loss": 0.4683,
759
+ "rewards/accuracies": 0.793749988079071,
760
+ "rewards/chosen": -1.1160547733306885,
761
+ "rewards/margins": 1.316855549812317,
762
+ "rewards/rejected": -2.432910442352295,
763
+ "step": 450
764
+ },
765
+ {
766
+ "epoch": 0.96,
767
+ "grad_norm": 40.762224983725595,
768
+ "learning_rate": 1.9347820230782295e-09,
769
+ "logits/chosen": 126.6349105834961,
770
+ "logits/rejected": 116.65708923339844,
771
+ "logps/chosen": -975.12548828125,
772
+ "logps/rejected": -1110.140625,
773
+ "loss": 0.4745,
774
+ "rewards/accuracies": 0.78125,
775
+ "rewards/chosen": -1.0417004823684692,
776
+ "rewards/margins": 1.3975470066070557,
777
+ "rewards/rejected": -2.4392473697662354,
778
+ "step": 460
779
+ },
780
+ {
781
+ "epoch": 0.98,
782
+ "grad_norm": 47.51695448791754,
783
+ "learning_rate": 3.2839470889836627e-10,
784
+ "logits/chosen": 136.34127807617188,
785
+ "logits/rejected": 115.61125183105469,
786
+ "logps/chosen": -1022.4205322265625,
787
+ "logps/rejected": -1111.9298095703125,
788
+ "loss": 0.4773,
789
+ "rewards/accuracies": 0.768750011920929,
790
+ "rewards/chosen": -1.1639817953109741,
791
+ "rewards/margins": 1.1374759674072266,
792
+ "rewards/rejected": -2.3014578819274902,
793
+ "step": 470
794
+ },
795
+ {
796
+ "epoch": 1.0,
797
+ "step": 477,
798
+ "total_flos": 0.0,
799
+ "train_loss": 0.5152078939433867,
800
+ "train_runtime": 5321.4428,
801
+ "train_samples_per_second": 11.488,
802
+ "train_steps_per_second": 0.09
803
+ }
804
+ ],
805
+ "logging_steps": 10,
806
+ "max_steps": 477,
807
+ "num_input_tokens_seen": 0,
808
+ "num_train_epochs": 1,
809
+ "save_steps": 100,
810
+ "total_flos": 0.0,
811
+ "train_batch_size": 2,
812
+ "trial_name": null,
813
+ "trial_params": null
814
+ }