JW17 commited on
Commit
98af5c4
1 Parent(s): c91b847

Model save

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch
3
+ tags:
4
+ - trl
5
+ - orpo
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: kaist-mistral-orpo-OHP-15k-Mathcode-2epoch-ohp-15k-strat-1-1epoch
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # kaist-mistral-orpo-OHP-15k-Mathcode-2epoch-ohp-15k-strat-1-1epoch
16
+
17
+ This model is a fine-tuned version of [orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch](https://huggingface.co/orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-06
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 4
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 64
44
+ - total_eval_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.39.3
56
+ - Pytorch 2.1.2.post303
57
+ - Datasets 2.18.0
58
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5704265398017326,
4
+ "train_runtime": 3228.2239,
5
+ "train_samples": 14928,
6
+ "train_samples_per_second": 4.624,
7
+ "train_steps_per_second": 0.072
8
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
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": "4.39.3"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd2d1d05b43c19ad7291d872899afe2fd85b007eb6bf169a51d3ea4e6901535
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8868165d9937fc26677fe6b8984fbd28bd3eecc9717cc95fa8355bbab011f9
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f526bc0872afeaea547f3599bd5ef0a092e957c45bd348d69cd4c234d8cb29
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
runs/Apr27_23-03-51_gpu-1/events.out.tfevents.1714227609.gpu-1.2805816.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965eaeaf8ada699390d79ebc9cbbca4197227b24f24246ae6810488d6bbb8664
3
+ size 25257
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5704265398017326,
4
+ "train_runtime": 3228.2239,
5
+ "train_samples": 14928,
6
+ "train_samples_per_second": 4.624,
7
+ "train_steps_per_second": 0.072
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9978586723768736,
5
+ "eval_steps": 500,
6
+ "global_step": 233,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 5.59375,
14
+ "learning_rate": 4.977309719247571e-06,
15
+ "log_odds_chosen": 0.06703004986047745,
16
+ "log_odds_ratio": -0.7092211842536926,
17
+ "logits/chosen": -3.2759811878204346,
18
+ "logits/rejected": -3.2908482551574707,
19
+ "logps/chosen": -0.7329679727554321,
20
+ "logps/rejected": -0.7760596871376038,
21
+ "loss": 0.6188,
22
+ "nll_loss": 0.47388267517089844,
23
+ "rewards/accuracies": 0.4937500059604645,
24
+ "rewards/chosen": -0.1465936005115509,
25
+ "rewards/margins": 0.008618330582976341,
26
+ "rewards/rejected": -0.15521195530891418,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "grad_norm": 5.21875,
32
+ "learning_rate": 4.909650756062782e-06,
33
+ "log_odds_chosen": 0.054611045867204666,
34
+ "log_odds_ratio": -0.7257325053215027,
35
+ "logits/chosen": -3.2224247455596924,
36
+ "logits/rejected": -3.236621141433716,
37
+ "logps/chosen": -0.7471343874931335,
38
+ "logps/rejected": -0.7686465978622437,
39
+ "loss": 0.5619,
40
+ "nll_loss": 0.4292874336242676,
41
+ "rewards/accuracies": 0.53125,
42
+ "rewards/chosen": -0.1494268774986267,
43
+ "rewards/margins": 0.004302443936467171,
44
+ "rewards/rejected": -0.15372933447360992,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.13,
49
+ "grad_norm": 4.15625,
50
+ "learning_rate": 4.7982512711416995e-06,
51
+ "log_odds_chosen": 0.06513820588588715,
52
+ "log_odds_ratio": -0.7152190208435059,
53
+ "logits/chosen": -3.165383815765381,
54
+ "logits/rejected": -3.1888585090637207,
55
+ "logps/chosen": -0.7319885492324829,
56
+ "logps/rejected": -0.7425517439842224,
57
+ "loss": 0.5721,
58
+ "nll_loss": 0.43641433119773865,
59
+ "rewards/accuracies": 0.518750011920929,
60
+ "rewards/chosen": -0.14639770984649658,
61
+ "rewards/margins": 0.0021126591600477695,
62
+ "rewards/rejected": -0.14851033687591553,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.17,
67
+ "grad_norm": 4.21875,
68
+ "learning_rate": 4.64513341295515e-06,
69
+ "log_odds_chosen": -0.017645269632339478,
70
+ "log_odds_ratio": -0.7585808038711548,
71
+ "logits/chosen": -3.1905665397644043,
72
+ "logits/rejected": -3.186293125152588,
73
+ "logps/chosen": -0.7048856019973755,
74
+ "logps/rejected": -0.7017339468002319,
75
+ "loss": 0.5925,
76
+ "nll_loss": 0.4144836366176605,
77
+ "rewards/accuracies": 0.4625000059604645,
78
+ "rewards/chosen": -0.14097711443901062,
79
+ "rewards/margins": -0.0006303312256932259,
80
+ "rewards/rejected": -0.14034679532051086,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.21,
85
+ "grad_norm": 4.40625,
86
+ "learning_rate": 4.453076611255507e-06,
87
+ "log_odds_chosen": 0.14627456665039062,
88
+ "log_odds_ratio": -0.6653262972831726,
89
+ "logits/chosen": -3.1202988624572754,
90
+ "logits/rejected": -3.1385226249694824,
91
+ "logps/chosen": -0.6960284113883972,
92
+ "logps/rejected": -0.7755590081214905,
93
+ "loss": 0.5531,
94
+ "nll_loss": 0.3655123710632324,
95
+ "rewards/accuracies": 0.6312500238418579,
96
+ "rewards/chosen": -0.139205664396286,
97
+ "rewards/margins": 0.015906114131212234,
98
+ "rewards/rejected": -0.15511178970336914,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.26,
103
+ "grad_norm": 4.6875,
104
+ "learning_rate": 4.22556712424355e-06,
105
+ "log_odds_chosen": 0.12080030143260956,
106
+ "log_odds_ratio": -0.6814600229263306,
107
+ "logits/chosen": -3.0596089363098145,
108
+ "logits/rejected": -3.056286573410034,
109
+ "logps/chosen": -0.6838747262954712,
110
+ "logps/rejected": -0.7580210566520691,
111
+ "loss": 0.5745,
112
+ "nll_loss": 0.4387393891811371,
113
+ "rewards/accuracies": 0.5625,
114
+ "rewards/chosen": -0.1367749273777008,
115
+ "rewards/margins": 0.014829280786216259,
116
+ "rewards/rejected": -0.15160420536994934,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.3,
121
+ "grad_norm": 4.34375,
122
+ "learning_rate": 3.9667347552265945e-06,
123
+ "log_odds_chosen": 0.09098054468631744,
124
+ "log_odds_ratio": -0.7007282376289368,
125
+ "logits/chosen": -3.1298584938049316,
126
+ "logits/rejected": -3.135943651199341,
127
+ "logps/chosen": -0.7081547975540161,
128
+ "logps/rejected": -0.7608820796012878,
129
+ "loss": 0.6087,
130
+ "nll_loss": 0.4499574303627014,
131
+ "rewards/accuracies": 0.5874999761581421,
132
+ "rewards/chosen": -0.14163094758987427,
133
+ "rewards/margins": 0.0105454595759511,
134
+ "rewards/rejected": -0.1521764099597931,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.34,
139
+ "grad_norm": 4.40625,
140
+ "learning_rate": 3.68127788750129e-06,
141
+ "log_odds_chosen": 0.18564960360527039,
142
+ "log_odds_ratio": -0.6482046842575073,
143
+ "logits/chosen": -3.142078399658203,
144
+ "logits/rejected": -3.145967960357666,
145
+ "logps/chosen": -0.6542805433273315,
146
+ "logps/rejected": -0.7562066912651062,
147
+ "loss": 0.5855,
148
+ "nll_loss": 0.40380844473838806,
149
+ "rewards/accuracies": 0.65625,
150
+ "rewards/chosen": -0.13085612654685974,
151
+ "rewards/margins": 0.020385239273309708,
152
+ "rewards/rejected": -0.15124136209487915,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.39,
157
+ "grad_norm": 3.921875,
158
+ "learning_rate": 3.3743781982447533e-06,
159
+ "log_odds_chosen": 0.13925865292549133,
160
+ "log_odds_ratio": -0.6794918775558472,
161
+ "logits/chosen": -3.1532516479492188,
162
+ "logits/rejected": -3.1458470821380615,
163
+ "logps/chosen": -0.6936465501785278,
164
+ "logps/rejected": -0.7801955938339233,
165
+ "loss": 0.567,
166
+ "nll_loss": 0.4436867833137512,
167
+ "rewards/accuracies": 0.5562499761581421,
168
+ "rewards/chosen": -0.1387293040752411,
169
+ "rewards/margins": 0.01730981469154358,
170
+ "rewards/rejected": -0.15603913366794586,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.43,
175
+ "grad_norm": 3.75,
176
+ "learning_rate": 3.0516065995466336e-06,
177
+ "log_odds_chosen": 0.16556194424629211,
178
+ "log_odds_ratio": -0.6641014218330383,
179
+ "logits/chosen": -3.1563491821289062,
180
+ "logits/rejected": -3.1614346504211426,
181
+ "logps/chosen": -0.6500056982040405,
182
+ "logps/rejected": -0.7318493127822876,
183
+ "loss": 0.5861,
184
+ "nll_loss": 0.45738714933395386,
185
+ "rewards/accuracies": 0.5687500238418579,
186
+ "rewards/chosen": -0.13000114262104034,
187
+ "rewards/margins": 0.016368722543120384,
188
+ "rewards/rejected": -0.14636987447738647,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.47,
193
+ "grad_norm": 4.0625,
194
+ "learning_rate": 2.7188221139616303e-06,
195
+ "log_odds_chosen": 0.10007637739181519,
196
+ "log_odds_ratio": -0.6944689750671387,
197
+ "logits/chosen": -3.105386972427368,
198
+ "logits/rejected": -3.1417195796966553,
199
+ "logps/chosen": -0.7295275926589966,
200
+ "logps/rejected": -0.7832143902778625,
201
+ "loss": 0.5604,
202
+ "nll_loss": 0.4221896231174469,
203
+ "rewards/accuracies": 0.5625,
204
+ "rewards/chosen": -0.1459055244922638,
205
+ "rewards/margins": 0.010737359523773193,
206
+ "rewards/rejected": -0.156642884016037,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.51,
211
+ "grad_norm": 3.609375,
212
+ "learning_rate": 2.3820655202161237e-06,
213
+ "log_odds_chosen": 0.18686607480049133,
214
+ "log_odds_ratio": -0.6535667777061462,
215
+ "logits/chosen": -3.1217126846313477,
216
+ "logits/rejected": -3.1293649673461914,
217
+ "logps/chosen": -0.632846474647522,
218
+ "logps/rejected": -0.726894736289978,
219
+ "loss": 0.5714,
220
+ "nll_loss": 0.4484385848045349,
221
+ "rewards/accuracies": 0.612500011920929,
222
+ "rewards/chosen": -0.12656930088996887,
223
+ "rewards/margins": 0.018809664994478226,
224
+ "rewards/rejected": -0.1453789472579956,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.56,
229
+ "grad_norm": 4.0,
230
+ "learning_rate": 2.0474496996359676e-06,
231
+ "log_odds_chosen": 0.12438281625509262,
232
+ "log_odds_ratio": -0.6807030439376831,
233
+ "logits/chosen": -3.114492177963257,
234
+ "logits/rejected": -3.1283891201019287,
235
+ "logps/chosen": -0.6877269148826599,
236
+ "logps/rejected": -0.7388188242912292,
237
+ "loss": 0.5653,
238
+ "nll_loss": 0.407818466424942,
239
+ "rewards/accuracies": 0.5687500238418579,
240
+ "rewards/chosen": -0.1375453919172287,
241
+ "rewards/margins": 0.010218393988907337,
242
+ "rewards/rejected": -0.14776377379894257,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.6,
247
+ "grad_norm": 4.375,
248
+ "learning_rate": 1.7210486737516947e-06,
249
+ "log_odds_chosen": 0.13585877418518066,
250
+ "log_odds_ratio": -0.6894018650054932,
251
+ "logits/chosen": -3.094355583190918,
252
+ "logits/rejected": -3.100367784500122,
253
+ "logps/chosen": -0.6505359411239624,
254
+ "logps/rejected": -0.7270746231079102,
255
+ "loss": 0.5667,
256
+ "nll_loss": 0.38747844099998474,
257
+ "rewards/accuracies": 0.6000000238418579,
258
+ "rewards/chosen": -0.13010717928409576,
259
+ "rewards/margins": 0.015307746827602386,
260
+ "rewards/rejected": -0.14541491866111755,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.64,
265
+ "grad_norm": 4.15625,
266
+ "learning_rate": 1.4087873472954638e-06,
267
+ "log_odds_chosen": 0.14618463814258575,
268
+ "log_odds_ratio": -0.6783791780471802,
269
+ "logits/chosen": -3.124422788619995,
270
+ "logits/rejected": -3.1180996894836426,
271
+ "logps/chosen": -0.7014532089233398,
272
+ "logps/rejected": -0.7804998159408569,
273
+ "loss": 0.5371,
274
+ "nll_loss": 0.3992606997489929,
275
+ "rewards/accuracies": 0.625,
276
+ "rewards/chosen": -0.14029064774513245,
277
+ "rewards/margins": 0.015809325501322746,
278
+ "rewards/rejected": -0.15609999001026154,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.69,
283
+ "grad_norm": 3.796875,
284
+ "learning_rate": 1.116333957999608e-06,
285
+ "log_odds_chosen": 0.06774308532476425,
286
+ "log_odds_ratio": -0.7074956893920898,
287
+ "logits/chosen": -3.1124911308288574,
288
+ "logits/rejected": -3.1118929386138916,
289
+ "logps/chosen": -0.7164414525032043,
290
+ "logps/rejected": -0.7556790113449097,
291
+ "loss": 0.5714,
292
+ "nll_loss": 0.40609636902809143,
293
+ "rewards/accuracies": 0.5249999761581421,
294
+ "rewards/chosen": -0.14328829944133759,
295
+ "rewards/margins": 0.007847519591450691,
296
+ "rewards/rejected": -0.15113583207130432,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.73,
301
+ "grad_norm": 3.890625,
302
+ "learning_rate": 8.48997185472226e-07,
303
+ "log_odds_chosen": 0.14430537819862366,
304
+ "log_odds_ratio": -0.6831859946250916,
305
+ "logits/chosen": -3.1008052825927734,
306
+ "logits/rejected": -3.118614912033081,
307
+ "logps/chosen": -0.6754971742630005,
308
+ "logps/rejected": -0.7525571584701538,
309
+ "loss": 0.5597,
310
+ "nll_loss": 0.41810712218284607,
311
+ "rewards/accuracies": 0.550000011920929,
312
+ "rewards/chosen": -0.13509942591190338,
313
+ "rewards/margins": 0.015411997213959694,
314
+ "rewards/rejected": -0.15051142871379852,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.77,
319
+ "grad_norm": 4.65625,
320
+ "learning_rate": 6.11629786852592e-07,
321
+ "log_odds_chosen": 0.20049241185188293,
322
+ "log_odds_ratio": -0.6564125418663025,
323
+ "logits/chosen": -3.0964746475219727,
324
+ "logits/rejected": -3.097423553466797,
325
+ "logps/chosen": -0.6751464009284973,
326
+ "logps/rejected": -0.7748547196388245,
327
+ "loss": 0.5689,
328
+ "nll_loss": 0.4084566533565521,
329
+ "rewards/accuracies": 0.625,
330
+ "rewards/chosen": -0.13502928614616394,
331
+ "rewards/margins": 0.019941668957471848,
332
+ "rewards/rejected": -0.1549709588289261,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.81,
337
+ "grad_norm": 3.8125,
338
+ "learning_rate": 4.0854050847362966e-07,
339
+ "log_odds_chosen": 0.1618964970111847,
340
+ "log_odds_ratio": -0.6639573574066162,
341
+ "logits/chosen": -3.1198277473449707,
342
+ "logits/rejected": -3.1235454082489014,
343
+ "logps/chosen": -0.6751562356948853,
344
+ "logps/rejected": -0.7577996253967285,
345
+ "loss": 0.5453,
346
+ "nll_loss": 0.4503118097782135,
347
+ "rewards/accuracies": 0.6312500238418579,
348
+ "rewards/chosen": -0.13503125309944153,
349
+ "rewards/margins": 0.016528675332665443,
350
+ "rewards/rejected": -0.15155991911888123,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.86,
355
+ "grad_norm": 3.78125,
356
+ "learning_rate": 2.4341587253072035e-07,
357
+ "log_odds_chosen": 0.21062397956848145,
358
+ "log_odds_ratio": -0.6452255249023438,
359
+ "logits/chosen": -3.0891025066375732,
360
+ "logits/rejected": -3.077317714691162,
361
+ "logps/chosen": -0.6431701183319092,
362
+ "logps/rejected": -0.7490943670272827,
363
+ "loss": 0.5505,
364
+ "nll_loss": 0.3902386724948883,
365
+ "rewards/accuracies": 0.643750011920929,
366
+ "rewards/chosen": -0.1286340355873108,
367
+ "rewards/margins": 0.021184856072068214,
368
+ "rewards/rejected": -0.14981889724731445,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 0.9,
373
+ "grad_norm": 4.28125,
374
+ "learning_rate": 1.1925325850281416e-07,
375
+ "log_odds_chosen": 0.08836773782968521,
376
+ "log_odds_ratio": -0.7011784315109253,
377
+ "logits/chosen": -3.1118626594543457,
378
+ "logits/rejected": -3.1287245750427246,
379
+ "logps/chosen": -0.6649689674377441,
380
+ "logps/rejected": -0.6961485743522644,
381
+ "loss": 0.534,
382
+ "nll_loss": 0.34850066900253296,
383
+ "rewards/accuracies": 0.5625,
384
+ "rewards/chosen": -0.13299378752708435,
385
+ "rewards/margins": 0.00623591523617506,
386
+ "rewards/rejected": -0.13922971487045288,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 0.94,
391
+ "grad_norm": 3.984375,
392
+ "learning_rate": 3.830649404690939e-08,
393
+ "log_odds_chosen": 0.10791333764791489,
394
+ "log_odds_ratio": -0.691511332988739,
395
+ "logits/chosen": -3.0939254760742188,
396
+ "logits/rejected": -3.1030945777893066,
397
+ "logps/chosen": -0.6941600441932678,
398
+ "logps/rejected": -0.7733976244926453,
399
+ "loss": 0.5775,
400
+ "nll_loss": 0.40806055068969727,
401
+ "rewards/accuracies": 0.5249999761581421,
402
+ "rewards/chosen": -0.1388320028781891,
403
+ "rewards/margins": 0.015847522765398026,
404
+ "rewards/rejected": -0.15467952191829681,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 0.99,
409
+ "grad_norm": 4.15625,
410
+ "learning_rate": 2.044943012210754e-09,
411
+ "log_odds_chosen": 0.10530634969472885,
412
+ "log_odds_ratio": -0.69704669713974,
413
+ "logits/chosen": -3.1206929683685303,
414
+ "logits/rejected": -3.117326259613037,
415
+ "logps/chosen": -0.6853540539741516,
416
+ "logps/rejected": -0.7511805295944214,
417
+ "loss": 0.567,
418
+ "nll_loss": 0.40571802854537964,
419
+ "rewards/accuracies": 0.581250011920929,
420
+ "rewards/chosen": -0.13707080483436584,
421
+ "rewards/margins": 0.013165315613150597,
422
+ "rewards/rejected": -0.150236114859581,
423
+ "step": 230
424
+ },
425
+ {
426
+ "epoch": 1.0,
427
+ "step": 233,
428
+ "total_flos": 0.0,
429
+ "train_loss": 0.5704265398017326,
430
+ "train_runtime": 3228.2239,
431
+ "train_samples_per_second": 4.624,
432
+ "train_steps_per_second": 0.072
433
+ }
434
+ ],
435
+ "logging_steps": 10,
436
+ "max_steps": 233,
437
+ "num_input_tokens_seen": 0,
438
+ "num_train_epochs": 1,
439
+ "save_steps": 500,
440
+ "total_flos": 0.0,
441
+ "train_batch_size": 8,
442
+ "trial_name": null,
443
+ "trial_params": null
444
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b5ae5e0c8e5c4b9b4558b5e79128e80e16cb3805972b94714ad40ea14053df
3
+ size 5496