zlucia commited on
Commit
f3b0126
1 Parent(s): 56c638c

End of training

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.1433
20
 
21
  ## Model description
22
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 1.094 | 0.34 | 50 | 1.1454 |
54
- | 1.064 | 0.68 | 100 | 1.1266 |
55
- | 1.0163 | 1.02 | 150 | 1.1231 |
56
- | 0.9539 | 1.36 | 200 | 1.1436 |
57
- | 0.9609 | 1.7 | 250 | 1.1433 |
58
 
59
 
60
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1395
20
 
21
  ## Model description
22
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.0974 | 0.34 | 50 | 1.1428 |
54
+ | 1.0626 | 0.68 | 100 | 1.1252 |
55
+ | 1.0209 | 1.02 | 150 | 1.1207 |
56
+ | 0.9509 | 1.36 | 200 | 1.1425 |
57
+ | 0.9616 | 1.7 | 250 | 1.1395 |
58
 
59
 
60
  ### Framework versions
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
 
23
  "q_proj",
24
- "k_proj",
25
- "v_proj",
26
  "down_proj",
27
- "up_proj",
28
- "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "up_proj",
23
+ "v_proj",
24
  "o_proj",
25
+ "gate_proj",
26
  "q_proj",
 
 
27
  "down_proj",
28
+ "k_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:145ad7416eca24755437f8cd9d23332e2960e754a1c4a463da11f8b43c314d87
3
  size 335605144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288bd86ed40ba7e37231e4eb3fb103a40fbd9be5fe490075800aa4cdd6ef5801
3
  size 335605144
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_loss": 1.141337275505066,
4
- "eval_runtime": 15.6641,
5
- "eval_samples_per_second": 16.726,
6
- "eval_steps_per_second": 4.213,
7
- "train_loss": 1.0087233514201885,
8
- "train_runtime": 880.6703,
9
- "train_samples_per_second": 5.35,
10
- "train_steps_per_second": 0.334
11
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_loss": 1.140608787536621,
4
+ "eval_runtime": 15.9495,
5
+ "eval_samples_per_second": 16.427,
6
+ "eval_steps_per_second": 4.138,
7
+ "train_loss": 1.01067645939029,
8
+ "train_runtime": 877.5897,
9
+ "train_samples_per_second": 5.369,
10
+ "train_steps_per_second": 0.335
11
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_loss": 1.141337275505066,
4
- "eval_runtime": 15.6641,
5
- "eval_samples_per_second": 16.726,
6
- "eval_steps_per_second": 4.213
7
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_loss": 1.140608787536621,
4
+ "eval_runtime": 15.9495,
5
+ "eval_samples_per_second": 16.427,
6
+ "eval_steps_per_second": 4.138
7
  }
metrics.json CHANGED
@@ -1 +1 @@
1
- {"run_name": "./output", "train_runtime": 867.3678, "train_samples_per_second": 5.433, "train_steps_per_second": 0.339, "train_loss": 1.0100539411817278, "epoch": 2.0, "eval_loss": 1.141337275505066, "eval_runtime": 15.6641, "eval_samples_per_second": 16.726, "eval_steps_per_second": 4.213}
 
1
+ {"run_name": "./output", "train_runtime": 880.6703, "train_samples_per_second": 5.35, "train_steps_per_second": 0.334, "train_loss": 1.0087233514201885, "epoch": 2.0, "eval_loss": 1.140608787536621, "eval_runtime": 15.9495, "eval_samples_per_second": 16.427, "eval_steps_per_second": 4.138}
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 2.0,
3
- "train_loss": 1.0087233514201885,
4
- "train_runtime": 880.6703,
5
- "train_samples_per_second": 5.35,
6
- "train_steps_per_second": 0.334
7
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "train_loss": 1.01067645939029,
4
+ "train_runtime": 877.5897,
5
+ "train_samples_per_second": 5.369,
6
+ "train_steps_per_second": 0.335
7
  }
trainer_state.json CHANGED
@@ -11,225 +11,225 @@
11
  {
12
  "epoch": 0.07,
13
  "learning_rate": 5e-05,
14
- "loss": 1.1713,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.14,
19
  "learning_rate": 5e-05,
20
- "loss": 1.1363,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.2,
25
  "learning_rate": 5e-05,
26
- "loss": 1.1248,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.27,
31
  "learning_rate": 5e-05,
32
- "loss": 1.0926,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.34,
37
  "learning_rate": 5e-05,
38
- "loss": 1.094,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.34,
43
- "eval_loss": 1.1453776359558105,
44
- "eval_runtime": 15.9789,
45
- "eval_samples_per_second": 16.397,
46
- "eval_steps_per_second": 4.13,
47
  "step": 50
48
  },
49
  {
50
  "epoch": 0.41,
51
  "learning_rate": 5e-05,
52
- "loss": 1.0865,
53
  "step": 60
54
  },
55
  {
56
  "epoch": 0.48,
57
  "learning_rate": 5e-05,
58
- "loss": 1.0746,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 0.54,
63
  "learning_rate": 5e-05,
64
- "loss": 1.1288,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 0.61,
69
  "learning_rate": 5e-05,
70
- "loss": 1.1117,
71
  "step": 90
72
  },
73
  {
74
  "epoch": 0.68,
75
  "learning_rate": 5e-05,
76
- "loss": 1.064,
77
  "step": 100
78
  },
79
  {
80
  "epoch": 0.68,
81
- "eval_loss": 1.1265697479248047,
82
- "eval_runtime": 15.9886,
83
- "eval_samples_per_second": 16.387,
84
- "eval_steps_per_second": 4.128,
85
  "step": 100
86
  },
87
  {
88
  "epoch": 0.75,
89
  "learning_rate": 5e-05,
90
- "loss": 1.0453,
91
  "step": 110
92
  },
93
  {
94
  "epoch": 0.81,
95
  "learning_rate": 5e-05,
96
- "loss": 1.1068,
97
  "step": 120
98
  },
99
  {
100
  "epoch": 0.88,
101
  "learning_rate": 5e-05,
102
- "loss": 1.0914,
103
  "step": 130
104
  },
105
  {
106
  "epoch": 0.95,
107
  "learning_rate": 5e-05,
108
- "loss": 1.0672,
109
  "step": 140
110
  },
111
  {
112
  "epoch": 1.02,
113
  "learning_rate": 5e-05,
114
- "loss": 1.0163,
115
  "step": 150
116
  },
117
  {
118
  "epoch": 1.02,
119
- "eval_loss": 1.1230601072311401,
120
- "eval_runtime": 15.9626,
121
- "eval_samples_per_second": 16.413,
122
- "eval_steps_per_second": 4.135,
123
  "step": 150
124
  },
125
  {
126
  "epoch": 1.09,
127
  "learning_rate": 5e-05,
128
- "loss": 0.943,
129
  "step": 160
130
  },
131
  {
132
  "epoch": 1.15,
133
  "learning_rate": 5e-05,
134
- "loss": 1.0026,
135
  "step": 170
136
  },
137
  {
138
  "epoch": 1.22,
139
  "learning_rate": 5e-05,
140
- "loss": 0.9163,
141
  "step": 180
142
  },
143
  {
144
  "epoch": 1.29,
145
  "learning_rate": 5e-05,
146
- "loss": 0.8891,
147
  "step": 190
148
  },
149
  {
150
  "epoch": 1.36,
151
  "learning_rate": 5e-05,
152
- "loss": 0.9539,
153
  "step": 200
154
  },
155
  {
156
  "epoch": 1.36,
157
- "eval_loss": 1.1436476707458496,
158
- "eval_runtime": 16.0177,
159
- "eval_samples_per_second": 16.357,
160
- "eval_steps_per_second": 4.12,
161
  "step": 200
162
  },
163
  {
164
  "epoch": 1.43,
165
  "learning_rate": 5e-05,
166
- "loss": 0.9251,
167
  "step": 210
168
  },
169
  {
170
  "epoch": 1.49,
171
  "learning_rate": 5e-05,
172
- "loss": 0.8389,
173
  "step": 220
174
  },
175
  {
176
  "epoch": 1.56,
177
  "learning_rate": 5e-05,
178
- "loss": 0.9261,
179
  "step": 230
180
  },
181
  {
182
  "epoch": 1.63,
183
  "learning_rate": 5e-05,
184
- "loss": 0.9326,
185
  "step": 240
186
  },
187
  {
188
  "epoch": 1.7,
189
  "learning_rate": 5e-05,
190
- "loss": 0.9609,
191
  "step": 250
192
  },
193
  {
194
  "epoch": 1.7,
195
- "eval_loss": 1.143343448638916,
196
- "eval_runtime": 16.0196,
197
- "eval_samples_per_second": 16.355,
198
- "eval_steps_per_second": 4.12,
199
  "step": 250
200
  },
201
  {
202
  "epoch": 1.77,
203
  "learning_rate": 5e-05,
204
- "loss": 0.8941,
205
  "step": 260
206
  },
207
  {
208
  "epoch": 1.83,
209
  "learning_rate": 5e-05,
210
- "loss": 0.9774,
211
  "step": 270
212
  },
213
  {
214
  "epoch": 1.9,
215
  "learning_rate": 5e-05,
216
- "loss": 0.8971,
217
  "step": 280
218
  },
219
  {
220
  "epoch": 1.97,
221
  "learning_rate": 5e-05,
222
- "loss": 0.8664,
223
  "step": 290
224
  },
225
  {
226
  "epoch": 2.0,
227
  "step": 294,
228
- "total_flos": 7.138469109576499e+16,
229
- "train_loss": 1.0087233514201885,
230
- "train_runtime": 880.6703,
231
- "train_samples_per_second": 5.35,
232
- "train_steps_per_second": 0.334
233
  }
234
  ],
235
  "logging_steps": 10,
@@ -237,7 +237,7 @@
237
  "num_input_tokens_seen": 0,
238
  "num_train_epochs": 2,
239
  "save_steps": 250,
240
- "total_flos": 7.138469109576499e+16,
241
  "train_batch_size": 4,
242
  "trial_name": null,
243
  "trial_params": null
 
11
  {
12
  "epoch": 0.07,
13
  "learning_rate": 5e-05,
14
+ "loss": 1.1891,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.14,
19
  "learning_rate": 5e-05,
20
+ "loss": 1.1472,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.2,
25
  "learning_rate": 5e-05,
26
+ "loss": 1.1311,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.27,
31
  "learning_rate": 5e-05,
32
+ "loss": 1.1016,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.34,
37
  "learning_rate": 5e-05,
38
+ "loss": 1.0974,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.34,
43
+ "eval_loss": 1.142778754234314,
44
+ "eval_runtime": 15.973,
45
+ "eval_samples_per_second": 16.403,
46
+ "eval_steps_per_second": 4.132,
47
  "step": 50
48
  },
49
  {
50
  "epoch": 0.41,
51
  "learning_rate": 5e-05,
52
+ "loss": 1.0897,
53
  "step": 60
54
  },
55
  {
56
  "epoch": 0.48,
57
  "learning_rate": 5e-05,
58
+ "loss": 1.0727,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 0.54,
63
  "learning_rate": 5e-05,
64
+ "loss": 1.1307,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 0.61,
69
  "learning_rate": 5e-05,
70
+ "loss": 1.1089,
71
  "step": 90
72
  },
73
  {
74
  "epoch": 0.68,
75
  "learning_rate": 5e-05,
76
+ "loss": 1.0626,
77
  "step": 100
78
  },
79
  {
80
  "epoch": 0.68,
81
+ "eval_loss": 1.1251928806304932,
82
+ "eval_runtime": 15.965,
83
+ "eval_samples_per_second": 16.411,
84
+ "eval_steps_per_second": 4.134,
85
  "step": 100
86
  },
87
  {
88
  "epoch": 0.75,
89
  "learning_rate": 5e-05,
90
+ "loss": 1.041,
91
  "step": 110
92
  },
93
  {
94
  "epoch": 0.81,
95
  "learning_rate": 5e-05,
96
+ "loss": 1.1059,
97
  "step": 120
98
  },
99
  {
100
  "epoch": 0.88,
101
  "learning_rate": 5e-05,
102
+ "loss": 1.0942,
103
  "step": 130
104
  },
105
  {
106
  "epoch": 0.95,
107
  "learning_rate": 5e-05,
108
+ "loss": 1.0676,
109
  "step": 140
110
  },
111
  {
112
  "epoch": 1.02,
113
  "learning_rate": 5e-05,
114
+ "loss": 1.0209,
115
  "step": 150
116
  },
117
  {
118
  "epoch": 1.02,
119
+ "eval_loss": 1.1206752061843872,
120
+ "eval_runtime": 16.0175,
121
+ "eval_samples_per_second": 16.357,
122
+ "eval_steps_per_second": 4.12,
123
  "step": 150
124
  },
125
  {
126
  "epoch": 1.09,
127
  "learning_rate": 5e-05,
128
+ "loss": 0.9453,
129
  "step": 160
130
  },
131
  {
132
  "epoch": 1.15,
133
  "learning_rate": 5e-05,
134
+ "loss": 1.0044,
135
  "step": 170
136
  },
137
  {
138
  "epoch": 1.22,
139
  "learning_rate": 5e-05,
140
+ "loss": 0.9175,
141
  "step": 180
142
  },
143
  {
144
  "epoch": 1.29,
145
  "learning_rate": 5e-05,
146
+ "loss": 0.8933,
147
  "step": 190
148
  },
149
  {
150
  "epoch": 1.36,
151
  "learning_rate": 5e-05,
152
+ "loss": 0.9509,
153
  "step": 200
154
  },
155
  {
156
  "epoch": 1.36,
157
+ "eval_loss": 1.142478346824646,
158
+ "eval_runtime": 15.9666,
159
+ "eval_samples_per_second": 16.409,
160
+ "eval_steps_per_second": 4.134,
161
  "step": 200
162
  },
163
  {
164
  "epoch": 1.43,
165
  "learning_rate": 5e-05,
166
+ "loss": 0.9252,
167
  "step": 210
168
  },
169
  {
170
  "epoch": 1.49,
171
  "learning_rate": 5e-05,
172
+ "loss": 0.841,
173
  "step": 220
174
  },
175
  {
176
  "epoch": 1.56,
177
  "learning_rate": 5e-05,
178
+ "loss": 0.9285,
179
  "step": 230
180
  },
181
  {
182
  "epoch": 1.63,
183
  "learning_rate": 5e-05,
184
+ "loss": 0.9325,
185
  "step": 240
186
  },
187
  {
188
  "epoch": 1.7,
189
  "learning_rate": 5e-05,
190
+ "loss": 0.9616,
191
  "step": 250
192
  },
193
  {
194
  "epoch": 1.7,
195
+ "eval_loss": 1.1395381689071655,
196
+ "eval_runtime": 15.961,
197
+ "eval_samples_per_second": 16.415,
198
+ "eval_steps_per_second": 4.135,
199
  "step": 250
200
  },
201
  {
202
  "epoch": 1.77,
203
  "learning_rate": 5e-05,
204
+ "loss": 0.896,
205
  "step": 260
206
  },
207
  {
208
  "epoch": 1.83,
209
  "learning_rate": 5e-05,
210
+ "loss": 0.9771,
211
  "step": 270
212
  },
213
  {
214
  "epoch": 1.9,
215
  "learning_rate": 5e-05,
216
+ "loss": 0.8961,
217
  "step": 280
218
  },
219
  {
220
  "epoch": 1.97,
221
  "learning_rate": 5e-05,
222
+ "loss": 0.8632,
223
  "step": 290
224
  },
225
  {
226
  "epoch": 2.0,
227
  "step": 294,
228
+ "total_flos": 7.196690777643418e+16,
229
+ "train_loss": 1.01067645939029,
230
+ "train_runtime": 877.5897,
231
+ "train_samples_per_second": 5.369,
232
+ "train_steps_per_second": 0.335
233
  }
234
  ],
235
  "logging_steps": 10,
 
237
  "num_input_tokens_seen": 0,
238
  "num_train_epochs": 2,
239
  "save_steps": 250,
240
+ "total_flos": 7.196690777643418e+16,
241
  "train_batch_size": 4,
242
  "trial_name": null,
243
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab2371a464ac761aaa205eccc61ae7ea0d64fef0c315a2db224b7a9181fe0fa
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b7f838de5b7aa39016607bd8e014d82ce38acfa14af4bb34028d36a9f5c6f3
3
  size 6712