burtenshaw HF staff commited on
Commit
b00caa3
1 Parent(s): 19b09a0

Upload folder using huggingface_hub

Browse files
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.38.2"
6
+ }
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db68417c4e59a7c907c4e46f1673f7b306d0cc02ef9d81744bf5ce751726054
3
+ size 1239173352
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee378caf0b6044a995c1da5fa6dbda30f90f1f25c8893151b8d36caba588fc4c
3
+ size 3712103866
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3467c4019f073fb3f78d725769757ba01dead7ee9368a54406b5d0eaf146581d
3
+ size 1239279449
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c733f603eddfbf8aea2db46dfb96d2d44052ea3c8d772ba82a9011002700581
3
+ size 14244
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bdfdc58f49ec10c0300671170c8cd13c1079080b9e9c4c20632dae81d91bd64
3
+ size 1064
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/trainer_state.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8604190945625305,
3
+ "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1687,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "grad_norm": 800.0,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 18.0938,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.06,
20
+ "grad_norm": 23.5,
21
+ "learning_rate": 5e-06,
22
+ "loss": 6.3163,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.09,
27
+ "grad_norm": 50.75,
28
+ "learning_rate": 4.987763947682049e-06,
29
+ "loss": 0.9927,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.12,
34
+ "grad_norm": 19.0,
35
+ "learning_rate": 4.951175567509258e-06,
36
+ "loss": 1.0442,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.15,
41
+ "grad_norm": 13.625,
42
+ "learning_rate": 4.890593017348846e-06,
43
+ "loss": 0.9387,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.18,
48
+ "grad_norm": 66.5,
49
+ "learning_rate": 4.806609330203466e-06,
50
+ "loss": 0.97,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "grad_norm": 22.5,
56
+ "learning_rate": 4.700046609104932e-06,
57
+ "loss": 0.9789,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.24,
62
+ "grad_norm": 11.625,
63
+ "learning_rate": 4.5719479796776466e-06,
64
+ "loss": 0.8951,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.27,
69
+ "grad_norm": 51.0,
70
+ "learning_rate": 4.423567379146835e-06,
71
+ "loss": 1.0329,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.3,
76
+ "grad_norm": 13.9375,
77
+ "learning_rate": 4.256357281745347e-06,
78
+ "loss": 1.0507,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.33,
83
+ "grad_norm": 15.0625,
84
+ "learning_rate": 4.071954480673098e-06,
85
+ "loss": 0.8861,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.36,
90
+ "grad_norm": 33.75,
91
+ "learning_rate": 3.872164065787287e-06,
92
+ "loss": 0.8826,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "grad_norm": 16.875,
98
+ "learning_rate": 3.6589417538632477e-06,
99
+ "loss": 1.0443,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.41,
104
+ "grad_norm": 17.25,
105
+ "learning_rate": 3.4343747443922253e-06,
106
+ "loss": 0.9825,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.44,
111
+ "grad_norm": 10.1875,
112
+ "learning_rate": 3.2006612883156387e-06,
113
+ "loss": 0.8588,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.47,
118
+ "grad_norm": 18.5,
119
+ "learning_rate": 2.960089169694257e-06,
120
+ "loss": 0.86,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.5,
125
+ "grad_norm": 34.0,
126
+ "learning_rate": 2.7150133109518347e-06,
127
+ "loss": 0.8479,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.53,
132
+ "grad_norm": 17.25,
133
+ "learning_rate": 2.4678327209119225e-06,
134
+ "loss": 0.8909,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.56,
139
+ "grad_norm": 19.625,
140
+ "learning_rate": 2.220967011279888e-06,
141
+ "loss": 0.8326,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.59,
146
+ "grad_norm": 15.6875,
147
+ "learning_rate": 1.976832711446584e-06,
148
+ "loss": 0.9614,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.62,
153
+ "grad_norm": 28.0,
154
+ "learning_rate": 1.737819613464305e-06,
155
+ "loss": 0.751,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.65,
160
+ "grad_norm": 17.125,
161
+ "learning_rate": 1.506267378750319e-06,
162
+ "loss": 0.9322,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.68,
167
+ "grad_norm": 20.125,
168
+ "learning_rate": 1.2844426355112658e-06,
169
+ "loss": 0.7542,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.71,
174
+ "grad_norm": 21.5,
175
+ "learning_rate": 1.0745167910780963e-06,
176
+ "loss": 0.8321,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.74,
181
+ "grad_norm": 14.25,
182
+ "learning_rate": 8.785447763431101e-07,
183
+ "loss": 0.87,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.77,
188
+ "grad_norm": 15.25,
189
+ "learning_rate": 6.984449303664287e-07,
190
+ "loss": 0.8061,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.8,
195
+ "grad_norm": 20.375,
196
+ "learning_rate": 5.359802220583124e-07,
197
+ "loss": 0.8294,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.83,
202
+ "grad_norm": 12.5625,
203
+ "learning_rate": 3.9274099275530384e-07,
204
+ "loss": 0.9622,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.86,
209
+ "grad_norm": 16.75,
210
+ "learning_rate": 2.7012938862039123e-07,
211
+ "loss": 0.8932,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.89,
216
+ "grad_norm": 13.75,
217
+ "learning_rate": 1.6934563525596053e-07,
218
+ "loss": 0.9018,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.92,
223
+ "grad_norm": 26.75,
224
+ "learning_rate": 9.137628888518491e-08,
225
+ "loss": 0.9468,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.95,
230
+ "grad_norm": 18.75,
231
+ "learning_rate": 3.698457910917608e-08,
232
+ "loss": 0.8617,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.98,
237
+ "grad_norm": 13.125,
238
+ "learning_rate": 6.702937773119533e-09,
239
+ "loss": 0.8404,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 1.0,
244
+ "eval_loss": 0.8604190945625305,
245
+ "eval_runtime": 87.9192,
246
+ "eval_samples_per_second": 4.277,
247
+ "eval_steps_per_second": 2.138,
248
+ "step": 1687
249
+ }
250
+ ],
251
+ "logging_steps": 50,
252
+ "max_steps": 1687,
253
+ "num_input_tokens_seen": 0,
254
+ "num_train_epochs": 1,
255
+ "save_steps": 500,
256
+ "total_flos": 1.2782603635523584e+16,
257
+ "train_batch_size": 2,
258
+ "trial_name": null,
259
+ "trial_params": null
260
+ }
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845a3f0102c29d18010ceb5d819cd67e9156eea7d9342492ecb920d1ca74b6ac
3
+ size 5048
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.38.2"
6
+ }
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db68417c4e59a7c907c4e46f1673f7b306d0cc02ef9d81744bf5ce751726054
3
+ size 1239173352
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845a3f0102c29d18010ceb5d819cd67e9156eea7d9342492ecb920d1ca74b6ac
3
+ size 5048