maxidl commited on
Commit
c0f0b5e
1 Parent(s): 8751caf

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.1
3
+ tags:
4
+ - alignment-handbook
5
+ - generated_from_trainer
6
+ datasets:
7
+ - maxidl/distilabel-capybara-dpo-7k-binarized_en_de
8
+ model-index:
9
+ - name: Mistral-7B-v0.1-capybara-orpo-en-de
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Mistral-7B-v0.1-capybara-orpo-en-de
17
+
18
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the maxidl/distilabel-capybara-dpo-7k-binarized_en_de dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-06
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 32
43
+ - total_train_batch_size: 128
44
+ - total_eval_batch_size: 256
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: inverse_sqrt
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.39.3
57
+ - Pytorch 2.1.2
58
+ - Datasets 2.18.0
59
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.649145109749539,
4
+ "train_runtime": 4268.1705,
5
+ "train_samples": 11530,
6
+ "train_samples_per_second": 8.104,
7
+ "train_steps_per_second": 0.064
8
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
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": true,
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 sha256:056ed418415554f05069301338398b9b9334b179422c0742528d233f95ce257b
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37135ccd1e8747eaee06af0b760d16de278d59067f5eb7c88cf272c879c9730f
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:cd5588779b0dee3055d50ecd18ac217f059f5e9e0c4d99592645f0d914034f93
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/Apr15_17-36-59_ggpu163/events.out.tfevents.1713195547.ggpu163.2260874.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0184086f44b7db1e4f01a23e1266c7843f383abcb5afd1061b8744b6ee8076b4
3
+ size 28511
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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": 1000000000000000019884624838656,
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": 3.0,
3
+ "train_loss": 0.649145109749539,
4
+ "train_runtime": 4268.1705,
5
+ "train_samples": 11530,
6
+ "train_samples_per_second": 8.104,
7
+ "train_steps_per_second": 0.064
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,516 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 273,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "grad_norm": 498.0,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "log_odds_chosen": 0.2863905131816864,
16
+ "log_odds_ratio": -0.5870538949966431,
17
+ "logits/chosen": -2.007096767425537,
18
+ "logits/rejected": -2.008589029312134,
19
+ "logps/chosen": -0.9226220846176147,
20
+ "logps/rejected": -1.105508804321289,
21
+ "loss": 3.8837,
22
+ "nll_loss": 4.084702491760254,
23
+ "rewards/accuracies": 0.7250000238418579,
24
+ "rewards/chosen": -0.04613110423088074,
25
+ "rewards/margins": 0.009144341573119164,
26
+ "rewards/rejected": -0.05527544766664505,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.22,
31
+ "grad_norm": 50.5,
32
+ "learning_rate": 1.0000000000000002e-06,
33
+ "log_odds_chosen": 0.3382885456085205,
34
+ "log_odds_ratio": -0.5765059590339661,
35
+ "logits/chosen": -2.6738319396972656,
36
+ "logits/rejected": -2.6777594089508057,
37
+ "logps/chosen": -0.902550220489502,
38
+ "logps/rejected": -1.1331396102905273,
39
+ "loss": 1.6578,
40
+ "nll_loss": 1.7452325820922852,
41
+ "rewards/accuracies": 0.7749999761581421,
42
+ "rewards/chosen": -0.0451275110244751,
43
+ "rewards/margins": 0.011529467068612576,
44
+ "rewards/rejected": -0.05665697902441025,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.33,
49
+ "grad_norm": 2.140625,
50
+ "learning_rate": 1.5e-06,
51
+ "log_odds_chosen": 0.2815089225769043,
52
+ "log_odds_ratio": -0.5875880122184753,
53
+ "logits/chosen": -2.437102794647217,
54
+ "logits/rejected": -2.4390525817871094,
55
+ "logps/chosen": -0.8905347585678101,
56
+ "logps/rejected": -1.0546678304672241,
57
+ "loss": 0.5865,
58
+ "nll_loss": 0.5374206900596619,
59
+ "rewards/accuracies": 0.7250000238418579,
60
+ "rewards/chosen": -0.044526733458042145,
61
+ "rewards/margins": 0.008206663653254509,
62
+ "rewards/rejected": -0.0527334026992321,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.44,
67
+ "grad_norm": 1.796875,
68
+ "learning_rate": 2.0000000000000003e-06,
69
+ "log_odds_chosen": 0.3029056787490845,
70
+ "log_odds_ratio": -0.6036669611930847,
71
+ "logits/chosen": -2.1445510387420654,
72
+ "logits/rejected": -2.166757583618164,
73
+ "logps/chosen": -0.9048384428024292,
74
+ "logps/rejected": -1.0757750272750854,
75
+ "loss": 0.5633,
76
+ "nll_loss": 0.5419524908065796,
77
+ "rewards/accuracies": 0.7250000238418579,
78
+ "rewards/chosen": -0.04524192586541176,
79
+ "rewards/margins": 0.008546831086277962,
80
+ "rewards/rejected": -0.05378875881433487,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.55,
85
+ "grad_norm": 1.6796875,
86
+ "learning_rate": 2.5e-06,
87
+ "log_odds_chosen": 0.2378097027540207,
88
+ "log_odds_ratio": -0.630806565284729,
89
+ "logits/chosen": -1.8973627090454102,
90
+ "logits/rejected": -1.934752106666565,
91
+ "logps/chosen": -0.8510879278182983,
92
+ "logps/rejected": -1.0084228515625,
93
+ "loss": 0.5498,
94
+ "nll_loss": 0.47691044211387634,
95
+ "rewards/accuracies": 0.675000011920929,
96
+ "rewards/chosen": -0.042554400861263275,
97
+ "rewards/margins": 0.007866747677326202,
98
+ "rewards/rejected": -0.050421155989170074,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.66,
103
+ "grad_norm": 1.7265625,
104
+ "learning_rate": 3e-06,
105
+ "log_odds_chosen": 0.34561508893966675,
106
+ "log_odds_ratio": -0.5882634520530701,
107
+ "logits/chosen": -1.789703369140625,
108
+ "logits/rejected": -1.8299936056137085,
109
+ "logps/chosen": -0.8602263331413269,
110
+ "logps/rejected": -1.0266495943069458,
111
+ "loss": 0.5348,
112
+ "nll_loss": 0.4759138524532318,
113
+ "rewards/accuracies": 0.7749999761581421,
114
+ "rewards/chosen": -0.043011318892240524,
115
+ "rewards/margins": 0.008321164175868034,
116
+ "rewards/rejected": -0.05133248120546341,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.77,
121
+ "grad_norm": 1.5703125,
122
+ "learning_rate": 3.5e-06,
123
+ "log_odds_chosen": 0.306732177734375,
124
+ "log_odds_ratio": -0.6226531267166138,
125
+ "logits/chosen": -1.8786418437957764,
126
+ "logits/rejected": -1.9659067392349243,
127
+ "logps/chosen": -0.8097027540206909,
128
+ "logps/rejected": -0.9237287640571594,
129
+ "loss": 0.5199,
130
+ "nll_loss": 0.47153204679489136,
131
+ "rewards/accuracies": 0.6000000238418579,
132
+ "rewards/chosen": -0.040485139936208725,
133
+ "rewards/margins": 0.005701296962797642,
134
+ "rewards/rejected": -0.04618643969297409,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.88,
139
+ "grad_norm": 1.5703125,
140
+ "learning_rate": 4.000000000000001e-06,
141
+ "log_odds_chosen": 0.46479716897010803,
142
+ "log_odds_ratio": -0.5484603047370911,
143
+ "logits/chosen": -1.894330382347107,
144
+ "logits/rejected": -1.9072799682617188,
145
+ "logps/chosen": -0.8353139758110046,
146
+ "logps/rejected": -1.0923199653625488,
147
+ "loss": 0.5272,
148
+ "nll_loss": 0.49910029768943787,
149
+ "rewards/accuracies": 0.75,
150
+ "rewards/chosen": -0.04176569730043411,
151
+ "rewards/margins": 0.012850301340222359,
152
+ "rewards/rejected": -0.05461599677801132,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.99,
157
+ "grad_norm": 1.5703125,
158
+ "learning_rate": 4.5e-06,
159
+ "log_odds_chosen": 0.46429938077926636,
160
+ "log_odds_ratio": -0.561553418636322,
161
+ "logits/chosen": -1.9992767572402954,
162
+ "logits/rejected": -2.0206494331359863,
163
+ "logps/chosen": -0.7664617300033569,
164
+ "logps/rejected": -0.9973196983337402,
165
+ "loss": 0.5236,
166
+ "nll_loss": 0.47519445419311523,
167
+ "rewards/accuracies": 0.75,
168
+ "rewards/chosen": -0.038323089480400085,
169
+ "rewards/margins": 0.01154289674013853,
170
+ "rewards/rejected": -0.04986598342657089,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 1.1,
175
+ "grad_norm": 1.75,
176
+ "learning_rate": 5e-06,
177
+ "log_odds_chosen": 0.357390433549881,
178
+ "log_odds_ratio": -0.5652999877929688,
179
+ "logits/chosen": -1.8920485973358154,
180
+ "logits/rejected": -1.9230598211288452,
181
+ "logps/chosen": -0.7654845118522644,
182
+ "logps/rejected": -0.9835049510002136,
183
+ "loss": 0.4967,
184
+ "nll_loss": 0.4664408266544342,
185
+ "rewards/accuracies": 0.7250000238418579,
186
+ "rewards/chosen": -0.03827423229813576,
187
+ "rewards/margins": 0.010901018045842648,
188
+ "rewards/rejected": -0.04917524382472038,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 1.21,
193
+ "grad_norm": 1.6015625,
194
+ "learning_rate": 4.767312946227961e-06,
195
+ "log_odds_chosen": 0.2798970341682434,
196
+ "log_odds_ratio": -0.5895387530326843,
197
+ "logits/chosen": -1.9187400341033936,
198
+ "logits/rejected": -1.9244420528411865,
199
+ "logps/chosen": -0.8067512512207031,
200
+ "logps/rejected": -0.9561241269111633,
201
+ "loss": 0.4901,
202
+ "nll_loss": 0.6010779738426208,
203
+ "rewards/accuracies": 0.6499999761581421,
204
+ "rewards/chosen": -0.040337562561035156,
205
+ "rewards/margins": 0.007468645926564932,
206
+ "rewards/rejected": -0.047806207090616226,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 1.32,
211
+ "grad_norm": 1.78125,
212
+ "learning_rate": 4.564354645876385e-06,
213
+ "log_odds_chosen": 0.6895818114280701,
214
+ "log_odds_ratio": -0.45160675048828125,
215
+ "logits/chosen": -1.7748291492462158,
216
+ "logits/rejected": -1.8056682348251343,
217
+ "logps/chosen": -0.7309473752975464,
218
+ "logps/rejected": -1.0976765155792236,
219
+ "loss": 0.4873,
220
+ "nll_loss": 0.4398137629032135,
221
+ "rewards/accuracies": 0.875,
222
+ "rewards/chosen": -0.03654736652970314,
223
+ "rewards/margins": 0.018336456269025803,
224
+ "rewards/rejected": -0.054883819073438644,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 1.43,
229
+ "grad_norm": 1.7890625,
230
+ "learning_rate": 4.385290096535147e-06,
231
+ "log_odds_chosen": 0.658761203289032,
232
+ "log_odds_ratio": -0.47310584783554077,
233
+ "logits/chosen": -1.9612312316894531,
234
+ "logits/rejected": -1.9696747064590454,
235
+ "logps/chosen": -0.7409031987190247,
236
+ "logps/rejected": -1.0737724304199219,
237
+ "loss": 0.4918,
238
+ "nll_loss": 0.43778449296951294,
239
+ "rewards/accuracies": 0.8999999761581421,
240
+ "rewards/chosen": -0.037045158445835114,
241
+ "rewards/margins": 0.016643470153212547,
242
+ "rewards/rejected": -0.05368863418698311,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 1.54,
247
+ "grad_norm": 1.75,
248
+ "learning_rate": 4.2257712736425835e-06,
249
+ "log_odds_chosen": 0.5739403367042542,
250
+ "log_odds_ratio": -0.5177870988845825,
251
+ "logits/chosen": -1.7142318487167358,
252
+ "logits/rejected": -1.7519795894622803,
253
+ "logps/chosen": -0.724389374256134,
254
+ "logps/rejected": -1.0089597702026367,
255
+ "loss": 0.475,
256
+ "nll_loss": 0.4226527214050293,
257
+ "rewards/accuracies": 0.875,
258
+ "rewards/chosen": -0.03621947020292282,
259
+ "rewards/margins": 0.014228522777557373,
260
+ "rewards/rejected": -0.050447989255189896,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 1.65,
265
+ "grad_norm": 1.53125,
266
+ "learning_rate": 4.082482904638631e-06,
267
+ "log_odds_chosen": 0.437107652425766,
268
+ "log_odds_ratio": -0.5386956334114075,
269
+ "logits/chosen": -1.970740556716919,
270
+ "logits/rejected": -2.0762734413146973,
271
+ "logps/chosen": -0.736059308052063,
272
+ "logps/rejected": -0.9635001420974731,
273
+ "loss": 0.4783,
274
+ "nll_loss": 0.4815542697906494,
275
+ "rewards/accuracies": 0.7250000238418579,
276
+ "rewards/chosen": -0.03680296614766121,
277
+ "rewards/margins": 0.011372040025889874,
278
+ "rewards/rejected": -0.04817500710487366,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 1.76,
283
+ "grad_norm": 1.6484375,
284
+ "learning_rate": 3.952847075210474e-06,
285
+ "log_odds_chosen": 0.25039786100387573,
286
+ "log_odds_ratio": -0.6173754334449768,
287
+ "logits/chosen": -1.8762115240097046,
288
+ "logits/rejected": -1.9119548797607422,
289
+ "logps/chosen": -0.8681584596633911,
290
+ "logps/rejected": -1.0069737434387207,
291
+ "loss": 0.4902,
292
+ "nll_loss": 0.4779680371284485,
293
+ "rewards/accuracies": 0.75,
294
+ "rewards/chosen": -0.043407924473285675,
295
+ "rewards/margins": 0.006940762512385845,
296
+ "rewards/rejected": -0.050348687916994095,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 1.87,
301
+ "grad_norm": 1.8046875,
302
+ "learning_rate": 3.834824944236852e-06,
303
+ "log_odds_chosen": 0.8294051885604858,
304
+ "log_odds_ratio": -0.4564356803894043,
305
+ "logits/chosen": -1.9998172521591187,
306
+ "logits/rejected": -2.012346029281616,
307
+ "logps/chosen": -0.7080036997795105,
308
+ "logps/rejected": -1.075842022895813,
309
+ "loss": 0.4728,
310
+ "nll_loss": 0.4948364198207855,
311
+ "rewards/accuracies": 0.824999988079071,
312
+ "rewards/chosen": -0.035400185734033585,
313
+ "rewards/margins": 0.018391914665699005,
314
+ "rewards/rejected": -0.05379210039973259,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 1.98,
319
+ "grad_norm": 1.5234375,
320
+ "learning_rate": 3.72677996249965e-06,
321
+ "log_odds_chosen": 0.6013724207878113,
322
+ "log_odds_ratio": -0.5433425307273865,
323
+ "logits/chosen": -1.8251736164093018,
324
+ "logits/rejected": -1.8962123394012451,
325
+ "logps/chosen": -0.7299692034721375,
326
+ "logps/rejected": -1.0021026134490967,
327
+ "loss": 0.4729,
328
+ "nll_loss": 0.419732004404068,
329
+ "rewards/accuracies": 0.75,
330
+ "rewards/chosen": -0.036498457193374634,
331
+ "rewards/margins": 0.013606672175228596,
332
+ "rewards/rejected": -0.05010513216257095,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 2.09,
337
+ "grad_norm": 1.9921875,
338
+ "learning_rate": 3.6273812505500587e-06,
339
+ "log_odds_chosen": 0.9894807934761047,
340
+ "log_odds_ratio": -0.3992963433265686,
341
+ "logits/chosen": -1.8533046245574951,
342
+ "logits/rejected": -1.8780378103256226,
343
+ "logps/chosen": -0.6669403314590454,
344
+ "logps/rejected": -1.1133853197097778,
345
+ "loss": 0.441,
346
+ "nll_loss": 0.40508294105529785,
347
+ "rewards/accuracies": 0.949999988079071,
348
+ "rewards/chosen": -0.03334701806306839,
349
+ "rewards/margins": 0.02232225239276886,
350
+ "rewards/rejected": -0.05566927045583725,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 2.2,
355
+ "grad_norm": 1.6015625,
356
+ "learning_rate": 3.5355339059327378e-06,
357
+ "log_odds_chosen": 0.7237910032272339,
358
+ "log_odds_ratio": -0.43176889419555664,
359
+ "logits/chosen": -1.7843163013458252,
360
+ "logits/rejected": -1.8297704458236694,
361
+ "logps/chosen": -0.6735831499099731,
362
+ "logps/rejected": -1.0497777462005615,
363
+ "loss": 0.4287,
364
+ "nll_loss": 0.4101743698120117,
365
+ "rewards/accuracies": 0.925000011920929,
366
+ "rewards/chosen": -0.033679161220788956,
367
+ "rewards/margins": 0.01880973018705845,
368
+ "rewards/rejected": -0.052488893270492554,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 2.31,
373
+ "grad_norm": 1.6796875,
374
+ "learning_rate": 3.450327796711771e-06,
375
+ "log_odds_chosen": 0.6548705101013184,
376
+ "log_odds_ratio": -0.4936867654323578,
377
+ "logits/chosen": -1.9768335819244385,
378
+ "logits/rejected": -1.964470624923706,
379
+ "logps/chosen": -0.7660457491874695,
380
+ "logps/rejected": -1.0849239826202393,
381
+ "loss": 0.4251,
382
+ "nll_loss": 0.4697703421115875,
383
+ "rewards/accuracies": 0.824999988079071,
384
+ "rewards/chosen": -0.03830229118466377,
385
+ "rewards/margins": 0.01594390906393528,
386
+ "rewards/rejected": -0.0542462058365345,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 2.42,
391
+ "grad_norm": 1.7109375,
392
+ "learning_rate": 3.3709993123162106e-06,
393
+ "log_odds_chosen": 0.9413236379623413,
394
+ "log_odds_ratio": -0.3946041464805603,
395
+ "logits/chosen": -1.8952887058258057,
396
+ "logits/rejected": -1.9475895166397095,
397
+ "logps/chosen": -0.6552693247795105,
398
+ "logps/rejected": -1.1159121990203857,
399
+ "loss": 0.4313,
400
+ "nll_loss": 0.44144296646118164,
401
+ "rewards/accuracies": 0.925000011920929,
402
+ "rewards/chosen": -0.032763466238975525,
403
+ "rewards/margins": 0.023032139986753464,
404
+ "rewards/rejected": -0.05579560995101929,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 2.53,
409
+ "grad_norm": 1.71875,
410
+ "learning_rate": 3.296902366978936e-06,
411
+ "log_odds_chosen": 0.8275907635688782,
412
+ "log_odds_ratio": -0.4250548481941223,
413
+ "logits/chosen": -1.8575712442398071,
414
+ "logits/rejected": -1.9162076711654663,
415
+ "logps/chosen": -0.6322061419487,
416
+ "logps/rejected": -1.0946836471557617,
417
+ "loss": 0.4229,
418
+ "nll_loss": 0.3766014575958252,
419
+ "rewards/accuracies": 0.824999988079071,
420
+ "rewards/chosen": -0.03161030635237694,
421
+ "rewards/margins": 0.023123880848288536,
422
+ "rewards/rejected": -0.05473419278860092,
423
+ "step": 230
424
+ },
425
+ {
426
+ "epoch": 2.64,
427
+ "grad_norm": 1.828125,
428
+ "learning_rate": 3.2274861218395142e-06,
429
+ "log_odds_chosen": 0.7520133852958679,
430
+ "log_odds_ratio": -0.45257338881492615,
431
+ "logits/chosen": -1.8115984201431274,
432
+ "logits/rejected": -1.8446438312530518,
433
+ "logps/chosen": -0.7262736558914185,
434
+ "logps/rejected": -1.1011757850646973,
435
+ "loss": 0.423,
436
+ "nll_loss": 0.4082041382789612,
437
+ "rewards/accuracies": 0.875,
438
+ "rewards/chosen": -0.03631368279457092,
439
+ "rewards/margins": 0.01874510571360588,
440
+ "rewards/rejected": -0.055058788508176804,
441
+ "step": 240
442
+ },
443
+ {
444
+ "epoch": 2.75,
445
+ "grad_norm": 1.765625,
446
+ "learning_rate": 3.1622776601683796e-06,
447
+ "log_odds_chosen": 0.9655596017837524,
448
+ "log_odds_ratio": -0.42737776041030884,
449
+ "logits/chosen": -1.9757699966430664,
450
+ "logits/rejected": -1.9998546838760376,
451
+ "logps/chosen": -0.6736587285995483,
452
+ "logps/rejected": -1.1431043148040771,
453
+ "loss": 0.4281,
454
+ "nll_loss": 0.4197885990142822,
455
+ "rewards/accuracies": 0.8999999761581421,
456
+ "rewards/chosen": -0.0336829349398613,
457
+ "rewards/margins": 0.023472286760807037,
458
+ "rewards/rejected": -0.057155221700668335,
459
+ "step": 250
460
+ },
461
+ {
462
+ "epoch": 2.86,
463
+ "grad_norm": 1.953125,
464
+ "learning_rate": 3.1008683647302113e-06,
465
+ "log_odds_chosen": 1.018965482711792,
466
+ "log_odds_ratio": -0.3666786551475525,
467
+ "logits/chosen": -1.9215749502182007,
468
+ "logits/rejected": -1.9601131677627563,
469
+ "logps/chosen": -0.5990187525749207,
470
+ "logps/rejected": -1.1184070110321045,
471
+ "loss": 0.421,
472
+ "nll_loss": 0.39652419090270996,
473
+ "rewards/accuracies": 0.925000011920929,
474
+ "rewards/chosen": -0.0299509409815073,
475
+ "rewards/margins": 0.025969412177801132,
476
+ "rewards/rejected": -0.055920351296663284,
477
+ "step": 260
478
+ },
479
+ {
480
+ "epoch": 2.97,
481
+ "grad_norm": 1.84375,
482
+ "learning_rate": 3.0429030972509227e-06,
483
+ "log_odds_chosen": 0.7740264534950256,
484
+ "log_odds_ratio": -0.44708919525146484,
485
+ "logits/chosen": -1.8729135990142822,
486
+ "logits/rejected": -1.9034210443496704,
487
+ "logps/chosen": -0.6478686332702637,
488
+ "logps/rejected": -0.9832038879394531,
489
+ "loss": 0.4251,
490
+ "nll_loss": 0.4181249141693115,
491
+ "rewards/accuracies": 0.8999999761581421,
492
+ "rewards/chosen": -0.0323934331536293,
493
+ "rewards/margins": 0.016766764223575592,
494
+ "rewards/rejected": -0.0491601899266243,
495
+ "step": 270
496
+ },
497
+ {
498
+ "epoch": 3.0,
499
+ "step": 273,
500
+ "total_flos": 0.0,
501
+ "train_loss": 0.649145109749539,
502
+ "train_runtime": 4268.1705,
503
+ "train_samples_per_second": 8.104,
504
+ "train_steps_per_second": 0.064
505
+ }
506
+ ],
507
+ "logging_steps": 10,
508
+ "max_steps": 273,
509
+ "num_input_tokens_seen": 0,
510
+ "num_train_epochs": 3,
511
+ "save_steps": 500,
512
+ "total_flos": 0.0,
513
+ "train_batch_size": 4,
514
+ "trial_name": null,
515
+ "trial_params": null
516
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b00013854d73dd32b49a09ad19cc8651054680a280196abbf9e2866c48d694
3
+ size 5368