MohamedAhmedAE
commited on
Commit
•
e13e325
1
Parent(s):
93bbebf
Training in progress, step 7800, 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 sha256:8230b48ad5d2d47bded13d0b4a225a6fe458e88f0dfffee4ef6138e3578b7cb7
|
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:a3ebd683f88765c7f3684d4f1b999d5a7d937536c2acc21fbea1dd5a504ff4c8
|
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 sha256:5815229928c679da2154333af4c0852e138211519132990800c387aec8269b78
|
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 sha256:3961966af58db2c2b54115da864b0f30cc2f3fd3fe289e5c948d2dbcbffbe9d4
|
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,
|
@@ -273,6 +273,13 @@
|
|
273 |
"learning_rate": 1.9999937128842296e-05,
|
274 |
"loss": 1.6411,
|
275 |
"step": 7600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 200,
|
@@ -280,7 +287,7 @@
|
|
280 |
"num_input_tokens_seen": 0,
|
281 |
"num_train_epochs": 5,
|
282 |
"save_steps": 200,
|
283 |
-
"total_flos":
|
284 |
"train_batch_size": 1,
|
285 |
"trial_name": null,
|
286 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005800571876894017,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 7800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
273 |
"learning_rate": 1.9999937128842296e-05,
|
274 |
"loss": 1.6411,
|
275 |
"step": 7600
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.01,
|
279 |
+
"grad_norm": 4.499472141265869,
|
280 |
+
"learning_rate": 1.9999933771375512e-05,
|
281 |
+
"loss": 1.5566,
|
282 |
+
"step": 7800
|
283 |
}
|
284 |
],
|
285 |
"logging_steps": 200,
|
|
|
287 |
"num_input_tokens_seen": 0,
|
288 |
"num_train_epochs": 5,
|
289 |
"save_steps": 200,
|
290 |
+
"total_flos": 1.0229934649090867e+17,
|
291 |
"train_batch_size": 1,
|
292 |
"trial_name": null,
|
293 |
"trial_params": null
|