Commit
•
fffa462
1
Parent(s):
d4a8b56
Training in progress, step 30000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +72 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1668076741
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7378cec3d952e350bd0782f3f66d4685e17a260af33a26310893b255a4ef456f
|
3 |
size 1668076741
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 834053717
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faf2486a9aed6db196b4c0c2d69f6b9ce2fe47a70db1927026ee80ceceaa0b78
|
3 |
size 834053717
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6577590482bd95dc8f5fc1b9185d2c76e77162ca88ae8b6a1adbd2a0c1f833f1
|
3 |
size 17641
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcd693cfa252394680d67f0702bcf07e039830fa5cbdfd3fc37f2bc2c7ddcfe5
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb8a20482e53552d32fdf801d3bee556547de0b51c5f96c7d7318698a6a89bd8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -144,11 +144,80 @@
|
|
144 |
"eval_samples_per_second": 22.424,
|
145 |
"eval_steps_per_second": 0.561,
|
146 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"max_steps": 50000,
|
150 |
"num_train_epochs": 9223372036854775807,
|
151 |
-
"total_flos":
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|
154 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6,
|
5 |
+
"global_step": 30000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_samples_per_second": 22.424,
|
145 |
"eval_steps_per_second": 0.561,
|
146 |
"step": 20000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.42,
|
150 |
+
"learning_rate": 2.011372523790927e-05,
|
151 |
+
"loss": 0.8297,
|
152 |
+
"step": 21000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.44,
|
156 |
+
"learning_rate": 1.9171527138850477e-05,
|
157 |
+
"loss": 0.8453,
|
158 |
+
"step": 22000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.46,
|
162 |
+
"learning_rate": 1.8210155373841292e-05,
|
163 |
+
"loss": 0.8384,
|
164 |
+
"step": 23000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.48,
|
168 |
+
"learning_rate": 1.7234746416166368e-05,
|
169 |
+
"loss": 0.828,
|
170 |
+
"step": 24000
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5,
|
174 |
+
"learning_rate": 1.624956548101695e-05,
|
175 |
+
"loss": 0.8226,
|
176 |
+
"step": 25000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.52,
|
180 |
+
"learning_rate": 1.5259912447470205e-05,
|
181 |
+
"loss": 0.8188,
|
182 |
+
"step": 26000
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.54,
|
186 |
+
"learning_rate": 1.4268134252092541e-05,
|
187 |
+
"loss": 0.807,
|
188 |
+
"step": 27000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.56,
|
192 |
+
"learning_rate": 1.3279556319416353e-05,
|
193 |
+
"loss": 0.8235,
|
194 |
+
"step": 28000
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.58,
|
198 |
+
"learning_rate": 1.2298501449209877e-05,
|
199 |
+
"loss": 0.802,
|
200 |
+
"step": 29000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.6,
|
204 |
+
"learning_rate": 1.1330221470267496e-05,
|
205 |
+
"loss": 0.8327,
|
206 |
+
"step": 30000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.6,
|
210 |
+
"eval_accuracy": 0.8488932773912237,
|
211 |
+
"eval_loss": 0.6712204217910767,
|
212 |
+
"eval_runtime": 182.5232,
|
213 |
+
"eval_samples_per_second": 27.394,
|
214 |
+
"eval_steps_per_second": 0.685,
|
215 |
+
"step": 30000
|
216 |
}
|
217 |
],
|
218 |
"max_steps": 50000,
|
219 |
"num_train_epochs": 9223372036854775807,
|
220 |
+
"total_flos": 9.469987651584e+18,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
223 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 834053717
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faf2486a9aed6db196b4c0c2d69f6b9ce2fe47a70db1927026ee80ceceaa0b78
|
3 |
size 834053717
|