Hugging Face's logo

saneowl
/
finetuned_state_checkpoints

Model card Files
xet
 Community
saneowl commited on
Commit
121892f
·
verified ·
1 Parent(s): d8e315e

Upload 5 files

Browse files
Files changed (5) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scaler.pt +3 -0
  4. scheduler.pt +3 -0
  5. trainer_state.json +244 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee5d199a037419ea136ec83e8f5e11cd8313445779ab92a0ba13db677eddce3
3
+ size 14454143663
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e828e16cc2008fb3eb29819627408ea8c2702ed8894d77c6487a8dbccc3c7ac5
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.007653061224489796,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00025510204081632655,
14
+ "grad_norm": 2.689539670944214,
15
+ "learning_rate": 1.9995e-05,
16
+ "loss": 8.2037,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.0005102040816326531,
21
+ "grad_norm": 2.3293910026550293,
22
+ "learning_rate": 1.9989897959183675e-05,
23
+ "loss": 6.9309,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0007653061224489796,
28
+ "grad_norm": 2.9805541038513184,
29
+ "learning_rate": 1.9984795918367347e-05,
30
+ "loss": 6.6153,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.0010204081632653062,
35
+ "grad_norm": 2.419286012649536,
36
+ "learning_rate": 1.9979693877551025e-05,
37
+ "loss": 6.3907,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.0012755102040816326,
42
+ "grad_norm": 2.8373420238494873,
43
+ "learning_rate": 1.9974591836734696e-05,
44
+ "loss": 6.2331,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.001530612244897959,
49
+ "grad_norm": 3.41703462600708,
50
+ "learning_rate": 1.9969489795918367e-05,
51
+ "loss": 6.0079,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.0017857142857142857,
56
+ "grad_norm": 1.9326502084732056,
57
+ "learning_rate": 1.996438775510204e-05,
58
+ "loss": 6.8421,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.0020408163265306124,
63
+ "grad_norm": 1.9628627300262451,
64
+ "learning_rate": 1.9959285714285716e-05,
65
+ "loss": 6.7932,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.002295918367346939,
70
+ "grad_norm": 1.8839755058288574,
71
+ "learning_rate": 1.995418367346939e-05,
72
+ "loss": 6.6473,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.002551020408163265,
77
+ "grad_norm": 2.1319727897644043,
78
+ "learning_rate": 1.9949081632653062e-05,
79
+ "loss": 6.5281,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.0028061224489795917,
84
+ "grad_norm": 2.1496269702911377,
85
+ "learning_rate": 1.9943979591836737e-05,
86
+ "loss": 6.417,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.003061224489795918,
91
+ "grad_norm": 1.9443697929382324,
92
+ "learning_rate": 1.993887755102041e-05,
93
+ "loss": 6.3274,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.0033163265306122448,
98
+ "grad_norm": 2.0376827716827393,
99
+ "learning_rate": 1.9933775510204082e-05,
100
+ "loss": 6.2191,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.0035714285714285713,
105
+ "grad_norm": 2.2743828296661377,
106
+ "learning_rate": 1.9928673469387757e-05,
107
+ "loss": 6.1371,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.003826530612244898,
112
+ "grad_norm": 1.8305890560150146,
113
+ "learning_rate": 1.992357142857143e-05,
114
+ "loss": 6.0537,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.004081632653061225,
119
+ "grad_norm": 2.600226402282715,
120
+ "learning_rate": 1.9918469387755103e-05,
121
+ "loss": 6.0223,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.004336734693877551,
126
+ "grad_norm": 2.161254644393921,
127
+ "learning_rate": 1.9913367346938777e-05,
128
+ "loss": 6.0193,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.004591836734693878,
133
+ "grad_norm": 2.131312131881714,
134
+ "learning_rate": 1.990826530612245e-05,
135
+ "loss": 5.9072,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.004846938775510204,
140
+ "grad_norm": 2.2562108039855957,
141
+ "learning_rate": 1.9903163265306123e-05,
142
+ "loss": 5.8881,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.00510204081632653,
147
+ "grad_norm": 2.4200196266174316,
148
+ "learning_rate": 1.9898061224489798e-05,
149
+ "loss": 5.7981,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.005357142857142857,
154
+ "grad_norm": 2.1939544677734375,
155
+ "learning_rate": 1.989295918367347e-05,
156
+ "loss": 5.776,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.005612244897959183,
161
+ "grad_norm": 2.1955156326293945,
162
+ "learning_rate": 1.9887857142857147e-05,
163
+ "loss": 5.7542,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.00586734693877551,
168
+ "grad_norm": 2.50158953666687,
169
+ "learning_rate": 1.9882755102040818e-05,
170
+ "loss": 5.6729,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.006122448979591836,
175
+ "grad_norm": 2.2941956520080566,
176
+ "learning_rate": 1.9877653061224493e-05,
177
+ "loss": 5.5944,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.006377551020408163,
182
+ "grad_norm": 2.183966875076294,
183
+ "learning_rate": 1.9872551020408164e-05,
184
+ "loss": 5.634,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.0066326530612244895,
189
+ "grad_norm": 2.238250732421875,
190
+ "learning_rate": 1.986744897959184e-05,
191
+ "loss": 5.5691,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.0068877551020408165,
196
+ "grad_norm": 2.298186779022217,
197
+ "learning_rate": 1.9862346938775513e-05,
198
+ "loss": 5.5623,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.007142857142857143,
203
+ "grad_norm": 2.208320379257202,
204
+ "learning_rate": 1.9857244897959184e-05,
205
+ "loss": 5.4931,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.00739795918367347,
210
+ "grad_norm": 2.469818353652954,
211
+ "learning_rate": 1.985214285714286e-05,
212
+ "loss": 5.4935,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.007653061224489796,
217
+ "grad_norm": 2.56227445602417,
218
+ "learning_rate": 1.9847040816326533e-05,
219
+ "loss": 5.4278,
220
+ "step": 1500
221
+ }
222
+ ],
223
+ "logging_steps": 50,
224
+ "max_steps": 196000,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 9223372036854775807,
227
+ "save_steps": 500,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": false
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 1.24857511575552e+17,
241
+ "train_batch_size": 2,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }