JW17 commited on
Commit
881dc3e
1 Parent(s): 333a875

Model save

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch
3
+ tags:
4
+ - trl
5
+ - orpo
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch-capybara-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-Stratified-1-beta-0.2-2epoch-capybara-1epoch
16
+
17
+ This model is a fine-tuned version of [orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch](https://huggingface.co/orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch) 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": 0.5939142045931579,
4
+ "train_runtime": 4430.1575,
5
+ "train_samples": 14154,
6
+ "train_samples_per_second": 3.195,
7
+ "train_steps_per_second": 0.05
8
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch",
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 sha256:82c644c9e9f126171b3ec72f40210a4fb6f638d2f3dfd83fc4a061f8d778c52c
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:f08062cbb7c9ae69ed5f09cb5dbe6b81164a5a7d75c70d5a52029256ad67ecd3
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55228f74fd0b73e9c01cf1072ee8df36761ce1125293d48f8e2c4438a0327c10
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
runs/Apr26_17-17-26_gpu-1/events.out.tfevents.1714119870.gpu-1.2400704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dcfd8a293889ac48b93b780e0175950a79f283b7417f3978299cd17868ccb58
3
+ size 24434
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": 0.5939142045931579,
4
+ "train_runtime": 4430.1575,
5
+ "train_samples": 14154,
6
+ "train_samples_per_second": 3.195,
7
+ "train_steps_per_second": 0.05
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,426 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9977426636568849,
5
+ "eval_steps": 500,
6
+ "global_step": 221,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 3.3125,
14
+ "learning_rate": 4.9747829807701e-06,
15
+ "log_odds_chosen": 0.29668617248535156,
16
+ "log_odds_ratio": -0.6379951238632202,
17
+ "logits/chosen": -3.2007384300231934,
18
+ "logits/rejected": -3.1898930072784424,
19
+ "logps/chosen": -0.8916305303573608,
20
+ "logps/rejected": -1.0567858219146729,
21
+ "loss": 0.6627,
22
+ "nll_loss": 0.5468634366989136,
23
+ "rewards/accuracies": 0.637499988079071,
24
+ "rewards/chosen": -0.1783261001110077,
25
+ "rewards/margins": 0.033031076192855835,
26
+ "rewards/rejected": -0.2113572061061859,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "grad_norm": 3.234375,
32
+ "learning_rate": 4.89964064152747e-06,
33
+ "log_odds_chosen": 0.3181908428668976,
34
+ "log_odds_ratio": -0.6044929623603821,
35
+ "logits/chosen": -3.215482711791992,
36
+ "logits/rejected": -3.215388059616089,
37
+ "logps/chosen": -0.8658155202865601,
38
+ "logps/rejected": -1.0561679601669312,
39
+ "loss": 0.6162,
40
+ "nll_loss": 0.4879694879055023,
41
+ "rewards/accuracies": 0.625,
42
+ "rewards/chosen": -0.17316310107707977,
43
+ "rewards/margins": 0.03807050734758377,
44
+ "rewards/rejected": -0.21123358607292175,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.14,
49
+ "grad_norm": 3.3125,
50
+ "learning_rate": 4.7760888749230414e-06,
51
+ "log_odds_chosen": 0.3909495174884796,
52
+ "log_odds_ratio": -0.6076517701148987,
53
+ "logits/chosen": -3.2152676582336426,
54
+ "logits/rejected": -3.202721357345581,
55
+ "logps/chosen": -0.8426260948181152,
56
+ "logps/rejected": -1.061783790588379,
57
+ "loss": 0.6037,
58
+ "nll_loss": 0.4774637222290039,
59
+ "rewards/accuracies": 0.675000011920929,
60
+ "rewards/chosen": -0.16852520406246185,
61
+ "rewards/margins": 0.04383154585957527,
62
+ "rewards/rejected": -0.21235676109790802,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.18,
67
+ "grad_norm": 2.96875,
68
+ "learning_rate": 4.6066201667762944e-06,
69
+ "log_odds_chosen": 0.3192257285118103,
70
+ "log_odds_ratio": -0.6141721606254578,
71
+ "logits/chosen": -3.200482130050659,
72
+ "logits/rejected": -3.1900203227996826,
73
+ "logps/chosen": -0.8548553586006165,
74
+ "logps/rejected": -1.034092903137207,
75
+ "loss": 0.6009,
76
+ "nll_loss": 0.4767337441444397,
77
+ "rewards/accuracies": 0.668749988079071,
78
+ "rewards/chosen": -0.17097108066082,
79
+ "rewards/margins": 0.0358474999666214,
80
+ "rewards/rejected": -0.2068185806274414,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.23,
85
+ "grad_norm": 2.84375,
86
+ "learning_rate": 4.3946533136249926e-06,
87
+ "log_odds_chosen": 0.3027415871620178,
88
+ "log_odds_ratio": -0.6166602969169617,
89
+ "logits/chosen": -3.206148147583008,
90
+ "logits/rejected": -3.1972875595092773,
91
+ "logps/chosen": -0.8349093198776245,
92
+ "logps/rejected": -1.0070207118988037,
93
+ "loss": 0.5918,
94
+ "nll_loss": 0.4716118276119232,
95
+ "rewards/accuracies": 0.6625000238418579,
96
+ "rewards/chosen": -0.16698187589645386,
97
+ "rewards/margins": 0.03442227095365524,
98
+ "rewards/rejected": -0.2014041393995285,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.27,
103
+ "grad_norm": 3.09375,
104
+ "learning_rate": 4.1444644532387485e-06,
105
+ "log_odds_chosen": 0.48492059111595154,
106
+ "log_odds_ratio": -0.5473419427871704,
107
+ "logits/chosen": -3.209733247756958,
108
+ "logits/rejected": -3.202362537384033,
109
+ "logps/chosen": -0.8019172549247742,
110
+ "logps/rejected": -1.0743623971939087,
111
+ "loss": 0.5974,
112
+ "nll_loss": 0.476468950510025,
113
+ "rewards/accuracies": 0.706250011920929,
114
+ "rewards/chosen": -0.16038347780704498,
115
+ "rewards/margins": 0.05448903515934944,
116
+ "rewards/rejected": -0.21487247943878174,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.32,
121
+ "grad_norm": 3.28125,
122
+ "learning_rate": 3.861100799460336e-06,
123
+ "log_odds_chosen": 0.331600546836853,
124
+ "log_odds_ratio": -0.6023644208908081,
125
+ "logits/chosen": -3.1663670539855957,
126
+ "logits/rejected": -3.150857925415039,
127
+ "logps/chosen": -0.8181543350219727,
128
+ "logps/rejected": -0.9955471754074097,
129
+ "loss": 0.603,
130
+ "nll_loss": 0.4812262952327728,
131
+ "rewards/accuracies": 0.668749988079071,
132
+ "rewards/chosen": -0.163630872964859,
133
+ "rewards/margins": 0.03547856956720352,
134
+ "rewards/rejected": -0.19910944998264313,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.36,
139
+ "grad_norm": 3.328125,
140
+ "learning_rate": 3.550278821654866e-06,
141
+ "log_odds_chosen": 0.477538526058197,
142
+ "log_odds_ratio": -0.5380920171737671,
143
+ "logits/chosen": -3.194234848022461,
144
+ "logits/rejected": -3.1841280460357666,
145
+ "logps/chosen": -0.8073774576187134,
146
+ "logps/rejected": -1.0695488452911377,
147
+ "loss": 0.5619,
148
+ "nll_loss": 0.47237372398376465,
149
+ "rewards/accuracies": 0.7437499761581421,
150
+ "rewards/chosen": -0.16147547960281372,
151
+ "rewards/margins": 0.05243431776762009,
152
+ "rewards/rejected": -0.2139098197221756,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.41,
157
+ "grad_norm": 3.390625,
158
+ "learning_rate": 3.218268922855452e-06,
159
+ "log_odds_chosen": 0.3934742212295532,
160
+ "log_odds_ratio": -0.598767101764679,
161
+ "logits/chosen": -3.1895227432250977,
162
+ "logits/rejected": -3.173553943634033,
163
+ "logps/chosen": -0.8475399017333984,
164
+ "logps/rejected": -1.0798330307006836,
165
+ "loss": 0.6021,
166
+ "nll_loss": 0.4789814054965973,
167
+ "rewards/accuracies": 0.699999988079071,
168
+ "rewards/chosen": -0.16950799524784088,
169
+ "rewards/margins": 0.046458613127470016,
170
+ "rewards/rejected": -0.2159666121006012,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.45,
175
+ "grad_norm": 2.921875,
176
+ "learning_rate": 2.871768943064129e-06,
177
+ "log_odds_chosen": 0.44187504053115845,
178
+ "log_odds_ratio": -0.5802451372146606,
179
+ "logits/chosen": -3.1786134243011475,
180
+ "logits/rejected": -3.1717491149902344,
181
+ "logps/chosen": -0.8232837915420532,
182
+ "logps/rejected": -1.0571515560150146,
183
+ "loss": 0.5994,
184
+ "nll_loss": 0.49746760725975037,
185
+ "rewards/accuracies": 0.7124999761581421,
186
+ "rewards/chosen": -0.16465675830841064,
187
+ "rewards/margins": 0.046773575246334076,
188
+ "rewards/rejected": -0.21143031120300293,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.5,
193
+ "grad_norm": 3.75,
194
+ "learning_rate": 2.517769039603744e-06,
195
+ "log_odds_chosen": 0.45674100518226624,
196
+ "log_odds_ratio": -0.5514575242996216,
197
+ "logits/chosen": -3.192737102508545,
198
+ "logits/rejected": -3.182710647583008,
199
+ "logps/chosen": -0.7476301789283752,
200
+ "logps/rejected": -0.9913870692253113,
201
+ "loss": 0.5818,
202
+ "nll_loss": 0.4433298707008362,
203
+ "rewards/accuracies": 0.75,
204
+ "rewards/chosen": -0.14952602982521057,
205
+ "rewards/margins": 0.04875140264630318,
206
+ "rewards/rejected": -0.19827742874622345,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.54,
211
+ "grad_norm": 3.34375,
212
+ "learning_rate": 2.163410670372652e-06,
213
+ "log_odds_chosen": 0.4035864770412445,
214
+ "log_odds_ratio": -0.6150745153427124,
215
+ "logits/chosen": -3.193054676055908,
216
+ "logits/rejected": -3.178786277770996,
217
+ "logps/chosen": -0.816441535949707,
218
+ "logps/rejected": -1.0266228914260864,
219
+ "loss": 0.5753,
220
+ "nll_loss": 0.44871068000793457,
221
+ "rewards/accuracies": 0.675000011920929,
222
+ "rewards/chosen": -0.16328832507133484,
223
+ "rewards/margins": 0.042036257684230804,
224
+ "rewards/rejected": -0.20532457530498505,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.59,
229
+ "grad_norm": 3.078125,
230
+ "learning_rate": 1.8158425248197931e-06,
231
+ "log_odds_chosen": 0.3830532431602478,
232
+ "log_odds_ratio": -0.5974889993667603,
233
+ "logits/chosen": -3.196091890335083,
234
+ "logits/rejected": -3.1858651638031006,
235
+ "logps/chosen": -0.8129725456237793,
236
+ "logps/rejected": -1.0201164484024048,
237
+ "loss": 0.5808,
238
+ "nll_loss": 0.4634559154510498,
239
+ "rewards/accuracies": 0.6937500238418579,
240
+ "rewards/chosen": -0.1625945270061493,
241
+ "rewards/margins": 0.041428789496421814,
242
+ "rewards/rejected": -0.20402328670024872,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.63,
247
+ "grad_norm": 3.375,
248
+ "learning_rate": 1.482076309033254e-06,
249
+ "log_odds_chosen": 0.6047395467758179,
250
+ "log_odds_ratio": -0.5417571663856506,
251
+ "logits/chosen": -3.196877956390381,
252
+ "logits/rejected": -3.181436061859131,
253
+ "logps/chosen": -0.7740004062652588,
254
+ "logps/rejected": -1.068457007408142,
255
+ "loss": 0.5764,
256
+ "nll_loss": 0.5040202140808105,
257
+ "rewards/accuracies": 0.7250000238418579,
258
+ "rewards/chosen": -0.15480007231235504,
259
+ "rewards/margins": 0.058891307562589645,
260
+ "rewards/rejected": -0.21369138360023499,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.68,
265
+ "grad_norm": 2.9375,
266
+ "learning_rate": 1.1688452942784592e-06,
267
+ "log_odds_chosen": 0.44741934537887573,
268
+ "log_odds_ratio": -0.5705805420875549,
269
+ "logits/chosen": -3.1841094493865967,
270
+ "logits/rejected": -3.182647705078125,
271
+ "logps/chosen": -0.8209434747695923,
272
+ "logps/rejected": -1.067769169807434,
273
+ "loss": 0.5718,
274
+ "nll_loss": 0.4761679768562317,
275
+ "rewards/accuracies": 0.706250011920929,
276
+ "rewards/chosen": -0.1641887128353119,
277
+ "rewards/margins": 0.04936511814594269,
278
+ "rewards/rejected": -0.21355381608009338,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.72,
283
+ "grad_norm": 3.171875,
284
+ "learning_rate": 8.824684825733865e-07,
285
+ "log_odds_chosen": 0.3429742455482483,
286
+ "log_odds_ratio": -0.6090758442878723,
287
+ "logits/chosen": -3.207231044769287,
288
+ "logits/rejected": -3.193406581878662,
289
+ "logps/chosen": -0.8023210763931274,
290
+ "logps/rejected": -0.9921668767929077,
291
+ "loss": 0.5897,
292
+ "nll_loss": 0.4722462594509125,
293
+ "rewards/accuracies": 0.6937500238418579,
294
+ "rewards/chosen": -0.16046421229839325,
295
+ "rewards/margins": 0.03796914964914322,
296
+ "rewards/rejected": -0.19843336939811707,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.77,
301
+ "grad_norm": 4.25,
302
+ "learning_rate": 6.28723129572247e-07,
303
+ "log_odds_chosen": 0.3038043677806854,
304
+ "log_odds_ratio": -0.6364859342575073,
305
+ "logits/chosen": -3.2201812267303467,
306
+ "logits/rejected": -3.2117972373962402,
307
+ "logps/chosen": -0.7899866104125977,
308
+ "logps/rejected": -0.9470660090446472,
309
+ "loss": 0.614,
310
+ "nll_loss": 0.47518712282180786,
311
+ "rewards/accuracies": 0.6499999761581421,
312
+ "rewards/chosen": -0.15799733996391296,
313
+ "rewards/margins": 0.03141586109995842,
314
+ "rewards/rejected": -0.18941320478916168,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.81,
319
+ "grad_norm": 4.0,
320
+ "learning_rate": 4.127281964319446e-07,
321
+ "log_odds_chosen": 0.42332348227500916,
322
+ "log_odds_ratio": -0.5784670114517212,
323
+ "logits/chosen": -3.194354295730591,
324
+ "logits/rejected": -3.1853244304656982,
325
+ "logps/chosen": -0.7676048278808594,
326
+ "logps/rejected": -0.984086811542511,
327
+ "loss": 0.5862,
328
+ "nll_loss": 0.4467201232910156,
329
+ "rewards/accuracies": 0.6875,
330
+ "rewards/chosen": -0.15352095663547516,
331
+ "rewards/margins": 0.04329640045762062,
332
+ "rewards/rejected": -0.19681736826896667,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.86,
337
+ "grad_norm": 3.15625,
338
+ "learning_rate": 2.388410818585263e-07,
339
+ "log_odds_chosen": 0.47039803862571716,
340
+ "log_odds_ratio": -0.5836545825004578,
341
+ "logits/chosen": -3.205718994140625,
342
+ "logits/rejected": -3.188554286956787,
343
+ "logps/chosen": -0.7774848937988281,
344
+ "logps/rejected": -1.0028108358383179,
345
+ "loss": 0.5743,
346
+ "nll_loss": 0.4325433671474457,
347
+ "rewards/accuracies": 0.706250011920929,
348
+ "rewards/chosen": -0.1554969847202301,
349
+ "rewards/margins": 0.045065198093652725,
350
+ "rewards/rejected": -0.20056216418743134,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.9,
355
+ "grad_norm": 2.9375,
356
+ "learning_rate": 1.1056971762161584e-07,
357
+ "log_odds_chosen": 0.2785649299621582,
358
+ "log_odds_ratio": -0.643887460231781,
359
+ "logits/chosen": -3.1912004947662354,
360
+ "logits/rejected": -3.1815104484558105,
361
+ "logps/chosen": -0.87229984998703,
362
+ "logps/rejected": -1.022983193397522,
363
+ "loss": 0.5796,
364
+ "nll_loss": 0.4835774004459381,
365
+ "rewards/accuracies": 0.6187499761581421,
366
+ "rewards/chosen": -0.17445996403694153,
367
+ "rewards/margins": 0.030136678367853165,
368
+ "rewards/rejected": -0.20459666848182678,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 0.95,
373
+ "grad_norm": 3.03125,
374
+ "learning_rate": 3.050180088809973e-08,
375
+ "log_odds_chosen": 0.30176714062690735,
376
+ "log_odds_ratio": -0.6279340386390686,
377
+ "logits/chosen": -3.187382221221924,
378
+ "logits/rejected": -3.172898054122925,
379
+ "logps/chosen": -0.842138946056366,
380
+ "logps/rejected": -1.0073583126068115,
381
+ "loss": 0.5913,
382
+ "nll_loss": 0.4963778555393219,
383
+ "rewards/accuracies": 0.6625000238418579,
384
+ "rewards/chosen": -0.16842779517173767,
385
+ "rewards/margins": 0.03304388374090195,
386
+ "rewards/rejected": -0.20147165656089783,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 0.99,
391
+ "grad_norm": 3.34375,
392
+ "learning_rate": 2.525910147516131e-10,
393
+ "log_odds_chosen": 0.4221881031990051,
394
+ "log_odds_ratio": -0.5777419805526733,
395
+ "logits/chosen": -3.206446886062622,
396
+ "logits/rejected": -3.1952741146087646,
397
+ "logps/chosen": -0.7956362962722778,
398
+ "logps/rejected": -1.0130151510238647,
399
+ "loss": 0.6099,
400
+ "nll_loss": 0.4894731640815735,
401
+ "rewards/accuracies": 0.731249988079071,
402
+ "rewards/chosen": -0.15912725031375885,
403
+ "rewards/margins": 0.04347577691078186,
404
+ "rewards/rejected": -0.2026030272245407,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 1.0,
409
+ "step": 221,
410
+ "total_flos": 0.0,
411
+ "train_loss": 0.5939142045931579,
412
+ "train_runtime": 4430.1575,
413
+ "train_samples_per_second": 3.195,
414
+ "train_steps_per_second": 0.05
415
+ }
416
+ ],
417
+ "logging_steps": 10,
418
+ "max_steps": 221,
419
+ "num_input_tokens_seen": 0,
420
+ "num_train_epochs": 1,
421
+ "save_steps": 500,
422
+ "total_flos": 0.0,
423
+ "train_batch_size": 8,
424
+ "trial_name": null,
425
+ "trial_params": null
426
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53abe54efe23c00d1af1d9f106b380884bf7732600b98655985f1c38dd6e9439
3
+ size 5496