MohamedAhmedAE
commited on
Commit
•
49c60f9
1
Parent(s):
d647c94
Training in progress, step 10600, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b157da58de763723afba58a487dce4affd5aa4ea8842fbd4da7c7f50fe12697
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b66793c07b1b0a84c67dfb67dabbc667be148932241d1875f1cf4cef5d93cb
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96a19a56fa0d8bb9b191b59d03bf40b790346150a7f3d469cfde615d3a433c9a
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a2e63dae0ad86e6af927f787db5624af1572bceb0832f3c088d78644536e527
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -371,6 +371,13 @@
|
|
371 |
"learning_rate": 1.999988217717089e-05,
|
372 |
"loss": 1.5754,
|
373 |
"step": 10400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 200,
|
@@ -378,7 +385,7 @@
|
|
378 |
"num_input_tokens_seen": 0,
|
379 |
"num_train_epochs": 5,
|
380 |
"save_steps": 200,
|
381 |
-
"total_flos": 1.
|
382 |
"train_batch_size": 1,
|
383 |
"trial_name": null,
|
384 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007882828448086741,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 10600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
371 |
"learning_rate": 1.999988217717089e-05,
|
372 |
"loss": 1.5754,
|
373 |
"step": 10400
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.01,
|
377 |
+
"grad_norm": 1.9017295837402344,
|
378 |
+
"learning_rate": 1.9999877597068942e-05,
|
379 |
+
"loss": 1.572,
|
380 |
+
"step": 10600
|
381 |
}
|
382 |
],
|
383 |
"logging_steps": 200,
|
|
|
385 |
"num_input_tokens_seen": 0,
|
386 |
"num_train_epochs": 5,
|
387 |
"save_steps": 200,
|
388 |
+
"total_flos": 1.3848555079593984e+17,
|
389 |
"train_batch_size": 1,
|
390 |
"trial_name": null,
|
391 |
"trial_params": null
|