Hugging Face's logo

starlineventures
/
outputs

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
starlineventures commited on
Commit
f573549
·
verified ·
1 Parent(s): 1d314e7

starlineventures/chatgpt

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. all_results.json +5 -5
  5. train_results.json +5 -5
  6. trainer_state.json +202 -34
  7. training_args.bin +1 -1
README.md CHANGED
@@ -36,12 +36,12 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
- - train_batch_size: 3
40
  - eval_batch_size: 16
41
  - seed: 3407
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 1
45
 
46
  ### Training results
47
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
+ - train_batch_size: 2
40
  - eval_batch_size: 16
41
  - seed: 3407
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
 
46
  ### Training results
47
 
adapter_config.json CHANGED
@@ -23,12 +23,12 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "q_proj",
27
  "o_proj",
28
- "down_proj",
29
- "v_proj",
30
- "gate_proj",
31
  "up_proj",
 
 
32
  "k_proj"
33
  ],
34
  "task_type": null,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "gate_proj",
27
  "q_proj",
28
  "o_proj",
 
 
 
29
  "up_proj",
30
+ "v_proj",
31
+ "down_proj",
32
  "k_proj"
33
  ],
34
  "task_type": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e56fad2fc597065040ec21115165f0e05dbe490a73bd27210ea2a44483ce88
3
  size 94422368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac693f0f2fdc993f2404824fc072884724e2e98d9c02080bad726c3d58e8d31d
3
  size 94422368
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5702045314452228,
5
- "train_runtime": 41.5701,
6
- "train_samples_per_second": 4.883,
7
- "train_steps_per_second": 1.636
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.45664438702701743,
5
+ "train_runtime": 139.2627,
6
+ "train_samples_per_second": 4.373,
7
+ "train_steps_per_second": 2.197
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5702045314452228,
5
- "train_runtime": 41.5701,
6
- "train_samples_per_second": 4.883,
7
- "train_steps_per_second": 1.636
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.45664438702701743,
5
+ "train_runtime": 139.2627,
6
+ "train_samples_per_second": 4.373,
7
+ "train_steps_per_second": 2.197
8
  }
trainer_state.json CHANGED
@@ -1,69 +1,237 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 68,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.14705882352941177,
13
- "grad_norm": 8.004534721374512,
14
- "learning_rate": 8.529411764705883e-05,
15
- "loss": 0.8231,
16
  "step": 10
17
  },
18
  {
19
- "epoch": 0.29411764705882354,
20
- "grad_norm": 4.019120693206787,
21
- "learning_rate": 7.058823529411765e-05,
22
- "loss": 0.578,
23
  "step": 20
24
  },
25
  {
26
- "epoch": 0.4411764705882353,
27
- "grad_norm": 5.479783058166504,
28
- "learning_rate": 5.588235294117647e-05,
29
- "loss": 0.5966,
30
  "step": 30
31
  },
32
  {
33
- "epoch": 0.5882352941176471,
34
- "grad_norm": 2.628741979598999,
35
- "learning_rate": 4.11764705882353e-05,
36
- "loss": 0.4605,
37
  "step": 40
38
  },
39
  {
40
- "epoch": 0.7352941176470589,
41
- "grad_norm": 2.3033456802368164,
42
- "learning_rate": 2.647058823529412e-05,
43
- "loss": 0.4407,
44
  "step": 50
45
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  {
47
  "epoch": 0.8823529411764706,
48
- "grad_norm": 2.080810070037842,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  "learning_rate": 1.1764705882352942e-05,
50
- "loss": 0.5047,
51
- "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  },
53
  {
54
- "epoch": 1.0,
55
- "step": 68,
56
  "total_flos": 0.0,
57
- "train_loss": 0.5702045314452228,
58
- "train_runtime": 41.5701,
59
- "train_samples_per_second": 4.883,
60
- "train_steps_per_second": 1.636
61
  }
62
  ],
63
  "logging_steps": 10,
64
- "max_steps": 68,
65
  "num_input_tokens_seen": 0,
66
- "num_train_epochs": 1,
67
  "save_steps": 500,
68
  "stateful_callbacks": {
69
  "TrainerControl": {
@@ -78,7 +246,7 @@
78
  }
79
  },
80
  "total_flos": 0.0,
81
- "train_batch_size": 3,
82
  "trial_name": null,
83
  "trial_params": null
84
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 306,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.09803921568627451,
13
+ "grad_norm": 4.746761322021484,
14
+ "learning_rate": 9.673202614379085e-05,
15
+ "loss": 0.9869,
16
  "step": 10
17
  },
18
  {
19
+ "epoch": 0.19607843137254902,
20
+ "grad_norm": 5.991705417633057,
21
+ "learning_rate": 9.34640522875817e-05,
22
+ "loss": 0.616,
23
  "step": 20
24
  },
25
  {
26
+ "epoch": 0.29411764705882354,
27
+ "grad_norm": 3.076098680496216,
28
+ "learning_rate": 9.019607843137255e-05,
29
+ "loss": 0.5284,
30
  "step": 30
31
  },
32
  {
33
+ "epoch": 0.39215686274509803,
34
+ "grad_norm": 3.2998595237731934,
35
+ "learning_rate": 8.692810457516341e-05,
36
+ "loss": 0.4886,
37
  "step": 40
38
  },
39
  {
40
+ "epoch": 0.49019607843137253,
41
+ "grad_norm": 2.442514657974243,
42
+ "learning_rate": 8.366013071895425e-05,
43
+ "loss": 0.6285,
44
  "step": 50
45
  },
46
+ {
47
+ "epoch": 0.5882352941176471,
48
+ "grad_norm": 2.712733030319214,
49
+ "learning_rate": 8.039215686274511e-05,
50
+ "loss": 0.4081,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.6862745098039216,
55
+ "grad_norm": 3.661532402038574,
56
+ "learning_rate": 7.712418300653595e-05,
57
+ "loss": 0.4035,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.7843137254901961,
62
+ "grad_norm": 3.081589460372925,
63
+ "learning_rate": 7.385620915032681e-05,
64
+ "loss": 0.4408,
65
+ "step": 80
66
+ },
67
  {
68
  "epoch": 0.8823529411764706,
69
+ "grad_norm": 1.6455492973327637,
70
+ "learning_rate": 7.058823529411765e-05,
71
+ "loss": 0.5381,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.9803921568627451,
76
+ "grad_norm": 5.283720970153809,
77
+ "learning_rate": 6.73202614379085e-05,
78
+ "loss": 0.6397,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.0784313725490196,
83
+ "grad_norm": 3.3742055892944336,
84
+ "learning_rate": 6.405228758169934e-05,
85
+ "loss": 0.3739,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.1764705882352942,
90
+ "grad_norm": 1.5715100765228271,
91
+ "learning_rate": 6.078431372549019e-05,
92
+ "loss": 0.4182,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.2745098039215685,
97
+ "grad_norm": 3.0394201278686523,
98
+ "learning_rate": 5.7516339869281044e-05,
99
+ "loss": 0.5015,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.3725490196078431,
104
+ "grad_norm": 3.3617103099823,
105
+ "learning_rate": 5.4248366013071894e-05,
106
+ "loss": 0.4284,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.4705882352941178,
111
+ "grad_norm": 4.484920501708984,
112
+ "learning_rate": 5.0980392156862745e-05,
113
+ "loss": 0.381,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.5686274509803921,
118
+ "grad_norm": 2.6562135219573975,
119
+ "learning_rate": 4.77124183006536e-05,
120
+ "loss": 0.3573,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.6666666666666665,
125
+ "grad_norm": 2.314049005508423,
126
+ "learning_rate": 4.4444444444444447e-05,
127
+ "loss": 0.4173,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.7647058823529411,
132
+ "grad_norm": 1.421838402748108,
133
+ "learning_rate": 4.11764705882353e-05,
134
+ "loss": 0.576,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.8627450980392157,
139
+ "grad_norm": 2.3095510005950928,
140
+ "learning_rate": 3.790849673202614e-05,
141
+ "loss": 0.3533,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.9607843137254903,
146
+ "grad_norm": 2.052910327911377,
147
+ "learning_rate": 3.464052287581699e-05,
148
+ "loss": 0.5017,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.0588235294117645,
153
+ "grad_norm": 1.1552486419677734,
154
+ "learning_rate": 3.137254901960784e-05,
155
+ "loss": 0.3601,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.156862745098039,
160
+ "grad_norm": 3.043320894241333,
161
+ "learning_rate": 2.8104575163398693e-05,
162
+ "loss": 0.3406,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.2549019607843137,
167
+ "grad_norm": 4.259531497955322,
168
+ "learning_rate": 2.4836601307189544e-05,
169
+ "loss": 0.4462,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 2.3529411764705883,
174
+ "grad_norm": 1.8052014112472534,
175
+ "learning_rate": 2.1568627450980395e-05,
176
+ "loss": 0.4161,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 2.450980392156863,
181
+ "grad_norm": 3.096114158630371,
182
+ "learning_rate": 1.8300653594771242e-05,
183
+ "loss": 0.3141,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 2.549019607843137,
188
+ "grad_norm": 1.8495090007781982,
189
+ "learning_rate": 1.5032679738562091e-05,
190
+ "loss": 0.3171,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 2.6470588235294117,
195
+ "grad_norm": 1.7439688444137573,
196
  "learning_rate": 1.1764705882352942e-05,
197
+ "loss": 0.4172,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 2.7450980392156863,
202
+ "grad_norm": 1.6345465183258057,
203
+ "learning_rate": 8.496732026143791e-06,
204
+ "loss": 0.4449,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 2.843137254901961,
209
+ "grad_norm": 1.409085750579834,
210
+ "learning_rate": 5.228758169934641e-06,
211
+ "loss": 0.3413,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 2.9411764705882355,
216
+ "grad_norm": 2.592830181121826,
217
+ "learning_rate": 1.96078431372549e-06,
218
+ "loss": 0.3597,
219
+ "step": 300
220
  },
221
  {
222
+ "epoch": 3.0,
223
+ "step": 306,
224
  "total_flos": 0.0,
225
+ "train_loss": 0.45664438702701743,
226
+ "train_runtime": 139.2627,
227
+ "train_samples_per_second": 4.373,
228
+ "train_steps_per_second": 2.197
229
  }
230
  ],
231
  "logging_steps": 10,
232
+ "max_steps": 306,
233
  "num_input_tokens_seen": 0,
234
+ "num_train_epochs": 3,
235
  "save_steps": 500,
236
  "stateful_callbacks": {
237
  "TrainerControl": {
 
246
  }
247
  },
248
  "total_flos": 0.0,
249
+ "train_batch_size": 2,
250
  "trial_name": null,
251
  "trial_params": null
252
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f5f9f5e571a13c3224a0c95f61204d3992ee84af792bb946098bdaf3e287613
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a462bc1f05b47257fd581a4641ca7c8a1959eda1c6be2e812e7c5d9f10cfee11
3
  size 5432