Training in progress, step 2100, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54bb3d2541882c2a5d88cb205eaa23efe91b1af0faa7937fe149082b2a00ede9
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82562273023ff91ad7900512fda5a63cb85c71ec2c54af0a61df26d9c11a5509
|
3 |
size 18902665
|
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 sha256:37d52c1bc6ea42c69efec50a9fdb93109c150d0f5358a667cf5ce03d6e6f892e
|
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:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
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,
|
@@ -287,13 +287,27 @@
|
|
287 |
"eval_samples_per_second": 30.548,
|
288 |
"eval_steps_per_second": 3.822,
|
289 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 100,
|
293 |
"max_steps": 4116,
|
294 |
"num_train_epochs": 3,
|
295 |
"save_steps": 100,
|
296 |
-
"total_flos":
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|
299 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1988422870635986,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2100",
|
4 |
+
"epoch": 1.530054644808743,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
287 |
"eval_samples_per_second": 30.548,
|
288 |
"eval_steps_per_second": 3.822,
|
289 |
"step": 2000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.53,
|
293 |
+
"learning_rate": 0.0002,
|
294 |
+
"loss": 2.177,
|
295 |
+
"step": 2100
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.53,
|
299 |
+
"eval_loss": 2.1988422870635986,
|
300 |
+
"eval_runtime": 205.5358,
|
301 |
+
"eval_samples_per_second": 30.525,
|
302 |
+
"eval_steps_per_second": 3.819,
|
303 |
+
"step": 2100
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 100,
|
307 |
"max_steps": 4116,
|
308 |
"num_train_epochs": 3,
|
309 |
"save_steps": 100,
|
310 |
+
"total_flos": 6.134610229364736e+16,
|
311 |
"trial_name": null,
|
312 |
"trial_params": null
|
313 |
}
|