chujiezheng commited on
Commit
8560714
·
verified ·
1 Parent(s): b86cef2

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "train_loss": 0.5926835913407175,
4
+ "train_runtime": 2430.0992,
5
+ "train_samples": 12227,
6
+ "train_samples_per_second": 5.031,
7
+ "train_steps_per_second": 0.039
8
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
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 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.39.3"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b3fe0b8e2d688b72c6fc82d11709c58b37880d4b71448f3bf0cd784e79fe32
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:caf77239690682593738edf3b52607d23a17797cfa94b055d9a754ca79fcfebf
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e196fb011f134078f2774d9904341a265bbe6c970fe04037074d95594c0e2c4
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/Apr17_01-40-59_pluslab01-a100.cs.ucla.edu/events.out.tfevents.1713343334.pluslab01-a100.cs.ucla.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5de2ab1007d975ca2709786d0d3dd4d5de215d17c974fee83fea9ef3b0be03
3
+ size 18616
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_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": 0.99,
3
+ "train_loss": 0.5926835913407175,
4
+ "train_runtime": 2430.0992,
5
+ "train_samples": 12227,
6
+ "train_samples_per_second": 5.031,
7
+ "train_steps_per_second": 0.039
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9921671018276762,
5
+ "eval_steps": 500,
6
+ "global_step": 95,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 6.531803428424505,
14
+ "learning_rate": 1.5000000000000002e-07,
15
+ "logits/chosen": -2.851747512817383,
16
+ "logits/rejected": -2.833996534347534,
17
+ "logps/chosen": -165.70089721679688,
18
+ "logps/rejected": -198.857666015625,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.05,
28
+ "grad_norm": 5.945146082388948,
29
+ "learning_rate": 7.5e-07,
30
+ "logits/chosen": -2.7703874111175537,
31
+ "logits/rejected": -2.773144006729126,
32
+ "logps/chosen": -171.2422332763672,
33
+ "logps/rejected": -172.52732849121094,
34
+ "loss": 0.6929,
35
+ "rewards/accuracies": 0.3984375,
36
+ "rewards/chosen": 0.001207518856972456,
37
+ "rewards/margins": 0.00034020940074697137,
38
+ "rewards/rejected": 0.0008673094562254846,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "grad_norm": 7.177620483727426,
44
+ "learning_rate": 1.5e-06,
45
+ "logits/chosen": -2.7866053581237793,
46
+ "logits/rejected": -2.7954766750335693,
47
+ "logps/chosen": -186.5630340576172,
48
+ "logps/rejected": -192.17149353027344,
49
+ "loss": 0.6878,
50
+ "rewards/accuracies": 0.625,
51
+ "rewards/chosen": 0.038089457899332047,
52
+ "rewards/margins": 0.011779792606830597,
53
+ "rewards/rejected": 0.02630966529250145,
54
+ "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.16,
58
+ "grad_norm": 8.417917120076636,
59
+ "learning_rate": 1.4872298247629265e-06,
60
+ "logits/chosen": -2.824795722961426,
61
+ "logits/rejected": -2.8347983360290527,
62
+ "logps/chosen": -197.54190063476562,
63
+ "logps/rejected": -192.82992553710938,
64
+ "loss": 0.6676,
65
+ "rewards/accuracies": 0.6000000238418579,
66
+ "rewards/chosen": 0.02421323023736477,
67
+ "rewards/margins": 0.06345993280410767,
68
+ "rewards/rejected": -0.03924670070409775,
69
+ "step": 15
70
+ },
71
+ {
72
+ "epoch": 0.21,
73
+ "grad_norm": 9.10298055209343,
74
+ "learning_rate": 1.4493541720532668e-06,
75
+ "logits/chosen": -2.7853965759277344,
76
+ "logits/rejected": -2.7954306602478027,
77
+ "logps/chosen": -172.51913452148438,
78
+ "logps/rejected": -199.7716522216797,
79
+ "loss": 0.6292,
80
+ "rewards/accuracies": 0.699999988079071,
81
+ "rewards/chosen": -0.0377628356218338,
82
+ "rewards/margins": 0.16324351727962494,
83
+ "rewards/rejected": -0.20100633800029755,
84
+ "step": 20
85
+ },
86
+ {
87
+ "epoch": 0.26,
88
+ "grad_norm": 10.051372999934031,
89
+ "learning_rate": 1.3876628517972108e-06,
90
+ "logits/chosen": -2.7528138160705566,
91
+ "logits/rejected": -2.7506392002105713,
92
+ "logps/chosen": -147.0410919189453,
93
+ "logps/rejected": -184.7159423828125,
94
+ "loss": 0.6228,
95
+ "rewards/accuracies": 0.643750011920929,
96
+ "rewards/chosen": -0.15569067001342773,
97
+ "rewards/margins": 0.19696763157844543,
98
+ "rewards/rejected": -0.3526582419872284,
99
+ "step": 25
100
+ },
101
+ {
102
+ "epoch": 0.31,
103
+ "grad_norm": 11.47609664425213,
104
+ "learning_rate": 1.3042566879154944e-06,
105
+ "logits/chosen": -2.77292799949646,
106
+ "logits/rejected": -2.770139217376709,
107
+ "logps/chosen": -189.57742309570312,
108
+ "logps/rejected": -228.9635467529297,
109
+ "loss": 0.6066,
110
+ "rewards/accuracies": 0.7437499761581421,
111
+ "rewards/chosen": -0.3009790778160095,
112
+ "rewards/margins": 0.33582720160484314,
113
+ "rewards/rejected": -0.6368061900138855,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.37,
118
+ "grad_norm": 14.051983189813676,
119
+ "learning_rate": 1.2019759772844424e-06,
120
+ "logits/chosen": -2.8096296787261963,
121
+ "logits/rejected": -2.8017215728759766,
122
+ "logps/chosen": -245.0883026123047,
123
+ "logps/rejected": -281.6932067871094,
124
+ "loss": 0.602,
125
+ "rewards/accuracies": 0.5874999761581421,
126
+ "rewards/chosen": -0.5381699800491333,
127
+ "rewards/margins": 0.27634209394454956,
128
+ "rewards/rejected": -0.8145120739936829,
129
+ "step": 35
130
+ },
131
+ {
132
+ "epoch": 0.42,
133
+ "grad_norm": 16.49665781047947,
134
+ "learning_rate": 1.0843037668324039e-06,
135
+ "logits/chosen": -2.690340042114258,
136
+ "logits/rejected": -2.703282356262207,
137
+ "logps/chosen": -204.72268676757812,
138
+ "logps/rejected": -264.89361572265625,
139
+ "loss": 0.5792,
140
+ "rewards/accuracies": 0.65625,
141
+ "rewards/chosen": -0.7186366319656372,
142
+ "rewards/margins": 0.4523038864135742,
143
+ "rewards/rejected": -1.1709405183792114,
144
+ "step": 40
145
+ },
146
+ {
147
+ "epoch": 0.47,
148
+ "grad_norm": 18.566501994693994,
149
+ "learning_rate": 9.552472425540623e-07,
150
+ "logits/chosen": -2.699636936187744,
151
+ "logits/rejected": -2.7163338661193848,
152
+ "logps/chosen": -291.1601257324219,
153
+ "logps/rejected": -333.49310302734375,
154
+ "loss": 0.6088,
155
+ "rewards/accuracies": 0.6937500238418579,
156
+ "rewards/chosen": -1.0251235961914062,
157
+ "rewards/margins": 0.493073046207428,
158
+ "rewards/rejected": -1.518196702003479,
159
+ "step": 45
160
+ },
161
+ {
162
+ "epoch": 0.52,
163
+ "grad_norm": 20.128869617238305,
164
+ "learning_rate": 8.192012695974766e-07,
165
+ "logits/chosen": -2.689870595932007,
166
+ "logits/rejected": -2.6908297538757324,
167
+ "logps/chosen": -252.3955078125,
168
+ "logps/rejected": -331.952880859375,
169
+ "loss": 0.577,
170
+ "rewards/accuracies": 0.71875,
171
+ "rewards/chosen": -0.780690610408783,
172
+ "rewards/margins": 0.6397809982299805,
173
+ "rewards/rejected": -1.4204715490341187,
174
+ "step": 50
175
+ },
176
+ {
177
+ "epoch": 0.57,
178
+ "grad_norm": 17.347634723380718,
179
+ "learning_rate": 6.807987304025236e-07,
180
+ "logits/chosen": -2.582890748977661,
181
+ "logits/rejected": -2.5895731449127197,
182
+ "logps/chosen": -216.3740234375,
183
+ "logps/rejected": -272.9044494628906,
184
+ "loss": 0.5676,
185
+ "rewards/accuracies": 0.643750011920929,
186
+ "rewards/chosen": -0.6826119422912598,
187
+ "rewards/margins": 0.5186464190483093,
188
+ "rewards/rejected": -1.2012584209442139,
189
+ "step": 55
190
+ },
191
+ {
192
+ "epoch": 0.63,
193
+ "grad_norm": 18.207607616337743,
194
+ "learning_rate": 5.447527574459379e-07,
195
+ "logits/chosen": -2.615662097930908,
196
+ "logits/rejected": -2.612374782562256,
197
+ "logps/chosen": -263.39892578125,
198
+ "logps/rejected": -343.30780029296875,
199
+ "loss": 0.556,
200
+ "rewards/accuracies": 0.706250011920929,
201
+ "rewards/chosen": -0.9144086837768555,
202
+ "rewards/margins": 0.5602952241897583,
203
+ "rewards/rejected": -1.4747039079666138,
204
+ "step": 60
205
+ },
206
+ {
207
+ "epoch": 0.68,
208
+ "grad_norm": 17.920968395292732,
209
+ "learning_rate": 4.1569623316759636e-07,
210
+ "logits/chosen": -2.603685140609741,
211
+ "logits/rejected": -2.6156582832336426,
212
+ "logps/chosen": -278.8509216308594,
213
+ "logps/rejected": -348.4021911621094,
214
+ "loss": 0.5707,
215
+ "rewards/accuracies": 0.7124999761581421,
216
+ "rewards/chosen": -1.1677374839782715,
217
+ "rewards/margins": 0.6181171536445618,
218
+ "rewards/rejected": -1.7858545780181885,
219
+ "step": 65
220
+ },
221
+ {
222
+ "epoch": 0.73,
223
+ "grad_norm": 21.60317231649874,
224
+ "learning_rate": 2.980240227155578e-07,
225
+ "logits/chosen": -2.530977725982666,
226
+ "logits/rejected": -2.538461208343506,
227
+ "logps/chosen": -298.65631103515625,
228
+ "logps/rejected": -345.4963684082031,
229
+ "loss": 0.5603,
230
+ "rewards/accuracies": 0.6499999761581421,
231
+ "rewards/chosen": -1.2151950597763062,
232
+ "rewards/margins": 0.5020937323570251,
233
+ "rewards/rejected": -1.7172887325286865,
234
+ "step": 70
235
+ },
236
+ {
237
+ "epoch": 0.78,
238
+ "grad_norm": 23.519516498457133,
239
+ "learning_rate": 1.9574331208450578e-07,
240
+ "logits/chosen": -2.4647083282470703,
241
+ "logits/rejected": -2.457724094390869,
242
+ "logps/chosen": -297.4154052734375,
243
+ "logps/rejected": -408.7651062011719,
244
+ "loss": 0.5333,
245
+ "rewards/accuracies": 0.71875,
246
+ "rewards/chosen": -1.2555583715438843,
247
+ "rewards/margins": 0.9959794282913208,
248
+ "rewards/rejected": -2.251537799835205,
249
+ "step": 75
250
+ },
251
+ {
252
+ "epoch": 0.84,
253
+ "grad_norm": 24.189874157051893,
254
+ "learning_rate": 1.1233714820278951e-07,
255
+ "logits/chosen": -2.415569305419922,
256
+ "logits/rejected": -2.409623384475708,
257
+ "logps/chosen": -286.6866455078125,
258
+ "logps/rejected": -374.3118591308594,
259
+ "loss": 0.5319,
260
+ "rewards/accuracies": 0.737500011920929,
261
+ "rewards/chosen": -1.1869741678237915,
262
+ "rewards/margins": 0.8028388023376465,
263
+ "rewards/rejected": -1.9898128509521484,
264
+ "step": 80
265
+ },
266
+ {
267
+ "epoch": 0.89,
268
+ "grad_norm": 27.1421302316283,
269
+ "learning_rate": 5.064582794673323e-08,
270
+ "logits/chosen": -2.463069438934326,
271
+ "logits/rejected": -2.4618234634399414,
272
+ "logps/chosen": -291.75006103515625,
273
+ "logps/rejected": -380.35186767578125,
274
+ "loss": 0.5565,
275
+ "rewards/accuracies": 0.6937500238418579,
276
+ "rewards/chosen": -1.315664529800415,
277
+ "rewards/margins": 0.7988798022270203,
278
+ "rewards/rejected": -2.11454439163208,
279
+ "step": 85
280
+ },
281
+ {
282
+ "epoch": 0.94,
283
+ "grad_norm": 24.52916506686646,
284
+ "learning_rate": 1.2770175237073662e-08,
285
+ "logits/chosen": -2.391339063644409,
286
+ "logits/rejected": -2.3986663818359375,
287
+ "logps/chosen": -315.0043640136719,
288
+ "logps/rejected": -409.3547668457031,
289
+ "loss": 0.552,
290
+ "rewards/accuracies": 0.699999988079071,
291
+ "rewards/chosen": -1.4606488943099976,
292
+ "rewards/margins": 0.8770757913589478,
293
+ "rewards/rejected": -2.337724447250366,
294
+ "step": 90
295
+ },
296
+ {
297
+ "epoch": 0.99,
298
+ "grad_norm": 31.400140337371543,
299
+ "learning_rate": 0.0,
300
+ "logits/chosen": -2.4539380073547363,
301
+ "logits/rejected": -2.4629311561584473,
302
+ "logps/chosen": -328.31024169921875,
303
+ "logps/rejected": -411.2120056152344,
304
+ "loss": 0.5588,
305
+ "rewards/accuracies": 0.6937500238418579,
306
+ "rewards/chosen": -1.4270151853561401,
307
+ "rewards/margins": 0.8573243021965027,
308
+ "rewards/rejected": -2.284339666366577,
309
+ "step": 95
310
+ },
311
+ {
312
+ "epoch": 0.99,
313
+ "step": 95,
314
+ "total_flos": 0.0,
315
+ "train_loss": 0.5926835913407175,
316
+ "train_runtime": 2430.0992,
317
+ "train_samples_per_second": 5.031,
318
+ "train_steps_per_second": 0.039
319
+ }
320
+ ],
321
+ "logging_steps": 5,
322
+ "max_steps": 95,
323
+ "num_input_tokens_seen": 0,
324
+ "num_train_epochs": 1,
325
+ "save_steps": 500,
326
+ "total_flos": 0.0,
327
+ "train_batch_size": 8,
328
+ "trial_name": null,
329
+ "trial_params": null
330
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0478d792cfae10fc7ebfa7c431c0a1b26ecfca6f361acd5688e99143a38bc6
3
+ size 6200