Hugging Face's logo

0x70DA
/
EnabledChat-lora

Text Generation
PyTorch
TensorBoard
Generated from Trainer
Model card Files
xet
Metrics Community
0x70DA commited on
Commit
99e5957
·
1 Parent(s): 3b4cb5c

Training in progress, step 200

Browse files
Files changed (11) hide show
  1. checkpoint-200/optimizer.pt +3 -0
  2. checkpoint-200/pytorch_model.bin +3 -0
  3. checkpoint-200/rng_state.pth +3 -0
  4. checkpoint-200/scaler.pt +3 -0
  5. checkpoint-200/scheduler.pt +3 -0
  6. checkpoint-200/trainer_state.json +264 -0
  7. checkpoint-200/training_args.bin +3 -0
  8. pytorch_model.bin +3 -0
  9. runs/May07_17-47-06_bc858596195a/1683481716.286797/events.out.tfevents.1683481716.bc858596195a.2495.1 +3 -0
  10. runs/May07_17-47-06_bc858596195a/events.out.tfevents.1683481716.bc858596195a.2495.0 +3 -0
  11. training_args.bin +3 -0
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b15da481ecb9da6d1b58cef439c4efb0f56221c87a33fb63e263875822c936
3
+ size 25278853
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de9e367d423f2fbb2a7963afdcdbfa0b304895b262b7d40da95ed25d3015811
3
+ size 12653389
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027af796b517d78c379b0f837723d7f546af00cb42a86507d1c8058c42c2269b
3
+ size 14511
checkpoint-200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
3
+ size 557
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0308641364f6f0574ef0515b5dc85f636f402ee5ab7030ea5ad6f7da6799a20d
3
+ size 627
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.2345943450927734,
3
+ "best_model_checkpoint": "outputs/checkpoint-200",
4
+ "epoch": 0.064,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1e-05,
13
+ "loss": 1.8184,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 2e-05,
19
+ "loss": 1.7858,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 3e-05,
25
+ "loss": 1.7218,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 4e-05,
31
+ "loss": 1.7218,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 5e-05,
37
+ "loss": 1.7009,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 6e-05,
43
+ "loss": 1.6714,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 7e-05,
49
+ "loss": 1.6582,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 8e-05,
55
+ "loss": 1.5659,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 9e-05,
61
+ "loss": 1.5343,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 0.0001,
67
+ "loss": 1.5252,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 0.00011000000000000002,
73
+ "loss": 1.414,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 0.00012,
79
+ "loss": 1.3919,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 0.00013000000000000002,
85
+ "loss": 1.352,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "learning_rate": 0.00014,
91
+ "loss": 1.3762,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.02,
96
+ "learning_rate": 0.00015000000000000001,
97
+ "loss": 1.3238,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.03,
102
+ "learning_rate": 0.00016,
103
+ "loss": 1.3306,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 0.00017,
109
+ "loss": 1.3423,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 0.00018,
115
+ "loss": 1.3199,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.03,
120
+ "learning_rate": 0.00019,
121
+ "loss": 1.3506,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.3315,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.03,
132
+ "learning_rate": 0.0001998921832884097,
133
+ "loss": 1.3142,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.04,
138
+ "learning_rate": 0.00019978436657681943,
139
+ "loss": 1.2994,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.04,
144
+ "learning_rate": 0.00019967654986522912,
145
+ "loss": 1.2972,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 0.00019956873315363883,
151
+ "loss": 1.3135,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.04,
156
+ "learning_rate": 0.00019946091644204851,
157
+ "loss": 1.2903,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.04,
162
+ "learning_rate": 0.00019935309973045823,
163
+ "loss": 1.2783,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "learning_rate": 0.00019924528301886794,
169
+ "loss": 1.3044,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.04,
174
+ "learning_rate": 0.00019913746630727762,
175
+ "loss": 1.2947,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.05,
180
+ "learning_rate": 0.00019902964959568736,
181
+ "loss": 1.2759,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.05,
186
+ "learning_rate": 0.00019892183288409705,
187
+ "loss": 1.2746,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.05,
192
+ "learning_rate": 0.00019881401617250676,
193
+ "loss": 1.2869,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.05,
198
+ "learning_rate": 0.00019870619946091644,
199
+ "loss": 1.26,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.05,
204
+ "learning_rate": 0.00019859838274932616,
205
+ "loss": 1.258,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "learning_rate": 0.00019849056603773587,
211
+ "loss": 1.2649,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "learning_rate": 0.00019838274932614555,
217
+ "loss": 1.2549,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.06,
222
+ "learning_rate": 0.00019827493261455526,
223
+ "loss": 1.2859,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.06,
228
+ "learning_rate": 0.00019816711590296498,
229
+ "loss": 1.2934,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.06,
234
+ "learning_rate": 0.00019805929919137466,
235
+ "loss": 1.3011,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.06,
240
+ "learning_rate": 0.00019795148247978437,
241
+ "loss": 1.2304,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.06,
246
+ "learning_rate": 0.00019784366576819408,
247
+ "loss": 1.2849,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.06,
252
+ "eval_loss": 1.2345943450927734,
253
+ "eval_runtime": 710.2534,
254
+ "eval_samples_per_second": 7.04,
255
+ "eval_steps_per_second": 0.88,
256
+ "step": 200
257
+ }
258
+ ],
259
+ "max_steps": 9375,
260
+ "num_train_epochs": 3,
261
+ "total_flos": 1.19119709995008e+16,
262
+ "trial_name": null,
263
+ "trial_params": null
264
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37558cbc88ba261791fbfa1f320a80e38b6c62c51b94e8ff0512ef16db3ba9ad
3
+ size 3963
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de9e367d423f2fbb2a7963afdcdbfa0b304895b262b7d40da95ed25d3015811
3
+ size 12653389
runs/May07_17-47-06_bc858596195a/1683481716.286797/events.out.tfevents.1683481716.bc858596195a.2495.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52179a2bb19ca09140e93dd7b6918bf80bee1086ee42565e4ec3011bc6cba4f
3
+ size 5873
runs/May07_17-47-06_bc858596195a/events.out.tfevents.1683481716.bc858596195a.2495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45676bd514f77e3d2bbd99fd360f44ab87fbdd25e86b4807242a7b88000c1d3a
3
+ size 10731
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37558cbc88ba261791fbfa1f320a80e38b6c62c51b94e8ff0512ef16db3ba9ad
3
+ size 3963