Training in progress, step 1900, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31466288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c59c9a73081018f9935c7827972a4c96c091e134bec87a67b615ed60a5f241c
|
3 |
size 31466288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62950917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21103e6050d033638c5a313b15a95db6f7f0ee96b52eaab7515f511c5bdf2c1a
|
3 |
size 62950917
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da5eddeaa757c6d016160549ec4b158dd730ee5eb61636139ede6dfade684bcc
|
3 |
size 14575
|
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:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -259,13 +259,27 @@
|
|
259 |
"eval_samples_per_second": 11.288,
|
260 |
"eval_steps_per_second": 1.412,
|
261 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 100,
|
265 |
"max_steps": 4116,
|
266 |
"num_train_epochs": 3,
|
267 |
"save_steps": 100,
|
268 |
-
"total_flos": 4.
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5527715682983398,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1900",
|
4 |
+
"epoch": 1.384335154826958,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
259 |
"eval_samples_per_second": 11.288,
|
260 |
"eval_steps_per_second": 1.412,
|
261 |
"step": 1800
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.38,
|
265 |
+
"learning_rate": 0.0002,
|
266 |
+
"loss": 1.5149,
|
267 |
+
"step": 1900
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.38,
|
271 |
+
"eval_loss": 1.5527715682983398,
|
272 |
+
"eval_runtime": 556.317,
|
273 |
+
"eval_samples_per_second": 11.278,
|
274 |
+
"eval_steps_per_second": 1.411,
|
275 |
+
"step": 1900
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 100,
|
279 |
"max_steps": 4116,
|
280 |
"num_train_epochs": 3,
|
281 |
"save_steps": 100,
|
282 |
+
"total_flos": 4.9544045126846054e+17,
|
283 |
"trial_name": null,
|
284 |
"trial_params": null
|
285 |
}
|