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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c01547cabad156253a07bfc83350dadf86119587609f83cbf8848e5690e7c93c
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62d52ded05202d48565ac168cbc0a2f36ff0267389873d0c7e73dbc276708e66
|
3 |
size 39356997
|
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 sha256:1c06d15ff9b633b68ebbf688949ae28d38f1d004fd46f5c3de3aeed397a80edf
|
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": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
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,
|
@@ -287,6 +287,20 @@
|
|
287 |
"eval_samples_per_second": 2.632,
|
288 |
"eval_steps_per_second": 0.33,
|
289 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 100,
|
@@ -294,7 +308,7 @@
|
|
294 |
"num_input_tokens_seen": 0,
|
295 |
"num_train_epochs": 3,
|
296 |
"save_steps": 100,
|
297 |
-
"total_flos": 5.
|
298 |
"trial_name": null,
|
299 |
"trial_params": null
|
300 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9320885539054871,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2100",
|
4 |
+
"epoch": 2.8,
|
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": 2.632,
|
288 |
"eval_steps_per_second": 0.33,
|
289 |
"step": 2000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.8,
|
293 |
+
"learning_rate": 0.0002,
|
294 |
+
"loss": 0.7525,
|
295 |
+
"step": 2100
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 2.8,
|
299 |
+
"eval_loss": 0.9320885539054871,
|
300 |
+
"eval_runtime": 728.1051,
|
301 |
+
"eval_samples_per_second": 2.651,
|
302 |
+
"eval_steps_per_second": 0.332,
|
303 |
+
"step": 2100
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 100,
|
|
|
308 |
"num_input_tokens_seen": 0,
|
309 |
"num_train_epochs": 3,
|
310 |
"save_steps": 100,
|
311 |
+
"total_flos": 5.4402852955938816e+17,
|
312 |
"trial_name": null,
|
313 |
"trial_params": null
|
314 |
}
|