Minbyul commited on
Commit
5bda91f
1 Parent(s): 33df6c0

Model save

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ base_model: epfl-llm/meditron-7b
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: meditron-7b-dpo-full-wo-medication_qa-ep3
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
+ # meditron-7b-dpo-full-wo-medication_qa-ep3
17
+
18
+ This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6293
21
+ - Rewards/chosen: -0.0145
22
+ - Rewards/rejected: -0.1627
23
+ - Rewards/accuracies: 0.7797
24
+ - Rewards/margins: 0.1482
25
+ - Logps/rejected: -1615.9989
26
+ - Logps/chosen: -955.1961
27
+ - Logits/rejected: -0.8722
28
+ - Logits/chosen: -0.7069
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: 4
53
+ - gradient_accumulation_steps: 2
54
+ - total_train_batch_size: 64
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
+ | 0.592 | 0.55 | 100 | 0.6293 | -0.0145 | -0.1627 | 0.7797 | 0.1482 | -1615.9989 | -955.1961 | -0.8722 | -0.7069 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.39.0.dev0
71
+ - Pytorch 2.1.2
72
+ - Datasets 2.14.6
73
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5914445311983646,
4
+ "train_runtime": 2922.1625,
5
+ "train_samples": 11603,
6
+ "train_samples_per_second": 3.971,
7
+ "train_steps_per_second": 0.062
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.0.dev0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7b1dda85ca2de5730cefd566d4331b3b8dae7c4d151488510bf2fece73d467
3
+ size 4939124616
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6801f999037ce86de4dc14dbfd9a881735de7d98b9224e05d289b76fb638a552
3
+ size 4947390880
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6359ec5024dadaa408bc99c5824c8a73ef4dd47f91f1b9535bf322231c0266e5
3
+ size 3590628080
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13477109760
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-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-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-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-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
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5914445311983646,
4
+ "train_runtime": 2922.1625,
5
+ "train_samples": 11603,
6
+ "train_samples_per_second": 3.971,
7
+ "train_steps_per_second": 0.062
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9972451790633609,
5
+ "eval_steps": 100,
6
+ "global_step": 181,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 4.4602671481986516,
14
+ "learning_rate": 2.6315789473684208e-08,
15
+ "logits/chosen": -0.7853389978408813,
16
+ "logits/rejected": -0.651086151599884,
17
+ "logps/chosen": -1158.1322021484375,
18
+ "logps/rejected": -1143.569091796875,
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": 0.06,
28
+ "grad_norm": 4.676508624329794,
29
+ "learning_rate": 2.631578947368421e-07,
30
+ "logits/chosen": -0.709392786026001,
31
+ "logits/rejected": -0.8101767897605896,
32
+ "logps/chosen": -995.121826171875,
33
+ "logps/rejected": -1316.8297119140625,
34
+ "loss": 0.693,
35
+ "rewards/accuracies": 0.4305555522441864,
36
+ "rewards/chosen": -0.0007655912195332348,
37
+ "rewards/margins": -0.00027954205870628357,
38
+ "rewards/rejected": -0.0004860491317231208,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.11,
43
+ "grad_norm": 4.611380190345714,
44
+ "learning_rate": 4.999529926121253e-07,
45
+ "logits/chosen": -0.7076992988586426,
46
+ "logits/rejected": -0.826177716255188,
47
+ "logps/chosen": -942.4779052734375,
48
+ "logps/rejected": -1303.2080078125,
49
+ "loss": 0.6922,
50
+ "rewards/accuracies": 0.581250011920929,
51
+ "rewards/chosen": 0.0009432749939151108,
52
+ "rewards/margins": 0.002406059531494975,
53
+ "rewards/rejected": -0.0014627845957875252,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.17,
58
+ "grad_norm": 4.545137388238839,
59
+ "learning_rate": 4.943334645626589e-07,
60
+ "logits/chosen": -0.7218513488769531,
61
+ "logits/rejected": -0.8190325498580933,
62
+ "logps/chosen": -986.5565185546875,
63
+ "logps/rejected": -1347.8033447265625,
64
+ "loss": 0.6883,
65
+ "rewards/accuracies": 0.699999988079071,
66
+ "rewards/chosen": 0.004364156164228916,
67
+ "rewards/margins": 0.008785699494183064,
68
+ "rewards/rejected": -0.004421542398631573,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.22,
73
+ "grad_norm": 4.401192871872299,
74
+ "learning_rate": 4.795540267200686e-07,
75
+ "logits/chosen": -0.7325557470321655,
76
+ "logits/rejected": -0.7795466184616089,
77
+ "logps/chosen": -1022.5738525390625,
78
+ "logps/rejected": -1272.192626953125,
79
+ "loss": 0.6826,
80
+ "rewards/accuracies": 0.7749999761581421,
81
+ "rewards/chosen": 0.01184375025331974,
82
+ "rewards/margins": 0.019737884402275085,
83
+ "rewards/rejected": -0.007894134148955345,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.28,
88
+ "grad_norm": 4.67072465163404,
89
+ "learning_rate": 4.561687510272767e-07,
90
+ "logits/chosen": -0.7071916460990906,
91
+ "logits/rejected": -0.7952053546905518,
92
+ "logps/chosen": -973.41259765625,
93
+ "logps/rejected": -1254.411376953125,
94
+ "loss": 0.6759,
95
+ "rewards/accuracies": 0.75,
96
+ "rewards/chosen": 0.010998593643307686,
97
+ "rewards/margins": 0.031063910573720932,
98
+ "rewards/rejected": -0.020065316930413246,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.33,
103
+ "grad_norm": 4.340731797997725,
104
+ "learning_rate": 4.2505433694179213e-07,
105
+ "logits/chosen": -0.7227746248245239,
106
+ "logits/rejected": -0.8140878677368164,
107
+ "logps/chosen": -1035.677734375,
108
+ "logps/rejected": -1306.7808837890625,
109
+ "loss": 0.6642,
110
+ "rewards/accuracies": 0.8687499761581421,
111
+ "rewards/chosen": 0.017496155574917793,
112
+ "rewards/margins": 0.06553898006677628,
113
+ "rewards/rejected": -0.04804282635450363,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.39,
118
+ "grad_norm": 4.496628183792233,
119
+ "learning_rate": 3.873772445177015e-07,
120
+ "logits/chosen": -0.7832368612289429,
121
+ "logits/rejected": -0.7676926851272583,
122
+ "logps/chosen": -1028.62890625,
123
+ "logps/rejected": -1254.6610107421875,
124
+ "loss": 0.6538,
125
+ "rewards/accuracies": 0.762499988079071,
126
+ "rewards/chosen": 0.01262822188436985,
127
+ "rewards/margins": 0.07675839215517044,
128
+ "rewards/rejected": -0.06413016468286514,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.44,
133
+ "grad_norm": 4.939508062028092,
134
+ "learning_rate": 3.445499645429106e-07,
135
+ "logits/chosen": -0.7500189542770386,
136
+ "logits/rejected": -0.8156210780143738,
137
+ "logps/chosen": -1028.065185546875,
138
+ "logps/rejected": -1316.736328125,
139
+ "loss": 0.6433,
140
+ "rewards/accuracies": 0.8062499761581421,
141
+ "rewards/chosen": 0.0009801089763641357,
142
+ "rewards/margins": 0.0968375876545906,
143
+ "rewards/rejected": -0.09585747867822647,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.5,
148
+ "grad_norm": 4.7399950008550205,
149
+ "learning_rate": 2.981780651370224e-07,
150
+ "logits/chosen": -0.7468028664588928,
151
+ "logits/rejected": -0.7884877920150757,
152
+ "logps/chosen": -996.8697509765625,
153
+ "logps/rejected": -1192.45654296875,
154
+ "loss": 0.6079,
155
+ "rewards/accuracies": 0.8187500238418579,
156
+ "rewards/chosen": 0.004719099495559931,
157
+ "rewards/margins": 0.21119482815265656,
158
+ "rewards/rejected": -0.20647573471069336,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.55,
163
+ "grad_norm": 5.466151335512206,
164
+ "learning_rate": 2.5e-07,
165
+ "logits/chosen": -0.7582017183303833,
166
+ "logits/rejected": -0.8466933369636536,
167
+ "logps/chosen": -979.6242065429688,
168
+ "logps/rejected": -1357.511962890625,
169
+ "loss": 0.592,
170
+ "rewards/accuracies": 0.8187500238418579,
171
+ "rewards/chosen": -0.00921861082315445,
172
+ "rewards/margins": 0.2683759033679962,
173
+ "rewards/rejected": -0.27759450674057007,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.55,
178
+ "eval_logits/chosen": -0.7069126963615417,
179
+ "eval_logits/rejected": -0.8721536993980408,
180
+ "eval_logps/chosen": -955.1961059570312,
181
+ "eval_logps/rejected": -1615.9989013671875,
182
+ "eval_loss": 0.6292956471443176,
183
+ "eval_rewards/accuracies": 0.7796609997749329,
184
+ "eval_rewards/chosen": -0.0145129868760705,
185
+ "eval_rewards/margins": 0.14818498492240906,
186
+ "eval_rewards/rejected": -0.16269797086715698,
187
+ "eval_runtime": 214.9002,
188
+ "eval_samples_per_second": 8.674,
189
+ "eval_steps_per_second": 0.275,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.61,
194
+ "grad_norm": 4.779970412172738,
195
+ "learning_rate": 2.018219348629775e-07,
196
+ "logits/chosen": -0.779070258140564,
197
+ "logits/rejected": -0.8311734199523926,
198
+ "logps/chosen": -992.7100830078125,
199
+ "logps/rejected": -1354.688720703125,
200
+ "loss": 0.5575,
201
+ "rewards/accuracies": 0.856249988079071,
202
+ "rewards/chosen": -0.0526651069521904,
203
+ "rewards/margins": 0.4234324097633362,
204
+ "rewards/rejected": -0.4760975241661072,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 0.66,
209
+ "grad_norm": 5.9180549707398695,
210
+ "learning_rate": 1.554500354570894e-07,
211
+ "logits/chosen": -0.7683907747268677,
212
+ "logits/rejected": -0.8335941433906555,
213
+ "logps/chosen": -1003.9620971679688,
214
+ "logps/rejected": -1312.5740966796875,
215
+ "loss": 0.5428,
216
+ "rewards/accuracies": 0.8999999761581421,
217
+ "rewards/chosen": -0.06494404375553131,
218
+ "rewards/margins": 0.5937026739120483,
219
+ "rewards/rejected": -0.6586467623710632,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 0.72,
224
+ "grad_norm": 5.7132927229572354,
225
+ "learning_rate": 1.126227554822985e-07,
226
+ "logits/chosen": -0.798209011554718,
227
+ "logits/rejected": -0.8723245859146118,
228
+ "logps/chosen": -1054.9263916015625,
229
+ "logps/rejected": -1349.2750244140625,
230
+ "loss": 0.5312,
231
+ "rewards/accuracies": 0.8125,
232
+ "rewards/chosen": -0.15924784541130066,
233
+ "rewards/margins": 0.5923423767089844,
234
+ "rewards/rejected": -0.7515901923179626,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 0.77,
239
+ "grad_norm": 10.497632384133095,
240
+ "learning_rate": 7.494566305820788e-08,
241
+ "logits/chosen": -0.8022674322128296,
242
+ "logits/rejected": -0.882843017578125,
243
+ "logps/chosen": -1055.48974609375,
244
+ "logps/rejected": -1417.170654296875,
245
+ "loss": 0.4988,
246
+ "rewards/accuracies": 0.862500011920929,
247
+ "rewards/chosen": -0.17785976827144623,
248
+ "rewards/margins": 1.1309340000152588,
249
+ "rewards/rejected": -1.3087936639785767,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 0.83,
254
+ "grad_norm": 6.590111680094942,
255
+ "learning_rate": 4.38312489727233e-08,
256
+ "logits/chosen": -0.7941451668739319,
257
+ "logits/rejected": -0.8360635042190552,
258
+ "logps/chosen": -994.5494384765625,
259
+ "logps/rejected": -1374.3560791015625,
260
+ "loss": 0.4917,
261
+ "rewards/accuracies": 0.8687499761581421,
262
+ "rewards/chosen": -0.2062647044658661,
263
+ "rewards/margins": 0.8967850804328918,
264
+ "rewards/rejected": -1.1030497550964355,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 0.88,
269
+ "grad_norm": 8.361359149599993,
270
+ "learning_rate": 2.044597327993153e-08,
271
+ "logits/chosen": -0.7812503576278687,
272
+ "logits/rejected": -0.8671078681945801,
273
+ "logps/chosen": -1042.375244140625,
274
+ "logps/rejected": -1443.9189453125,
275
+ "loss": 0.4813,
276
+ "rewards/accuracies": 0.8374999761581421,
277
+ "rewards/chosen": -0.2346261441707611,
278
+ "rewards/margins": 0.8702405095100403,
279
+ "rewards/rejected": -1.104866623878479,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 0.94,
284
+ "grad_norm": 7.649602408833162,
285
+ "learning_rate": 5.666535437341108e-09,
286
+ "logits/chosen": -0.792350172996521,
287
+ "logits/rejected": -0.8578357696533203,
288
+ "logps/chosen": -1057.263427734375,
289
+ "logps/rejected": -1363.985107421875,
290
+ "loss": 0.4843,
291
+ "rewards/accuracies": 0.8062499761581421,
292
+ "rewards/chosen": -0.292695015668869,
293
+ "rewards/margins": 1.1091253757476807,
294
+ "rewards/rejected": -1.401820421218872,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 0.99,
299
+ "grad_norm": 8.116244988839705,
300
+ "learning_rate": 4.700738787466463e-11,
301
+ "logits/chosen": -0.7855504751205444,
302
+ "logits/rejected": -0.8505135774612427,
303
+ "logps/chosen": -952.7326049804688,
304
+ "logps/rejected": -1447.79541015625,
305
+ "loss": 0.4771,
306
+ "rewards/accuracies": 0.800000011920929,
307
+ "rewards/chosen": -0.23469653725624084,
308
+ "rewards/margins": 0.9054014086723328,
309
+ "rewards/rejected": -1.140097975730896,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 1.0,
314
+ "step": 181,
315
+ "total_flos": 0.0,
316
+ "train_loss": 0.5914445311983646,
317
+ "train_runtime": 2922.1625,
318
+ "train_samples_per_second": 3.971,
319
+ "train_steps_per_second": 0.062
320
+ }
321
+ ],
322
+ "logging_steps": 10,
323
+ "max_steps": 181,
324
+ "num_input_tokens_seen": 0,
325
+ "num_train_epochs": 1,
326
+ "save_steps": 100,
327
+ "total_flos": 0.0,
328
+ "train_batch_size": 8,
329
+ "trial_name": null,
330
+ "trial_params": null
331
+ }