MohamedAhmedAE
commited on
Commit
•
9c1858d
1
Parent(s):
a4776e2
Training in progress, step 6600, 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 sha256:23ecbd17698411abba08f800223d4f97c20ce6694fc5497eae762462f06c3ee3
|
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 sha256:8e240a4ccbdf1ba5b7269029cb4c7fbd098170a36530fb8a7924ca7a51629862
|
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 sha256:1fcac68827b9f46f3ac71f10fc39a641a04d0ffa77754feb125895a9297c3035
|
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 sha256:6a5a6b913ef84b8f56bbbc750706d31053f1c2d4afa8b1e983e030aad31a2507
|
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,
|
@@ -231,6 +231,13 @@
|
|
231 |
"learning_rate": 1.999995543968414e-05,
|
232 |
"loss": 1.6274,
|
233 |
"step": 6400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 200,
|
@@ -238,7 +245,7 @@
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 5,
|
240 |
"save_steps": 200,
|
241 |
-
"total_flos": 8.
|
242 |
"train_batch_size": 1,
|
243 |
"trial_name": null,
|
244 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004908176203525707,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 6600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
231 |
"learning_rate": 1.999995543968414e-05,
|
232 |
"loss": 1.6274,
|
233 |
"step": 6400
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0,
|
237 |
+
"grad_norm": 1.9622883796691895,
|
238 |
+
"learning_rate": 1.9999952606205736e-05,
|
239 |
+
"loss": 1.6222,
|
240 |
+
"step": 6600
|
241 |
}
|
242 |
],
|
243 |
"logging_steps": 200,
|
|
|
245 |
"num_input_tokens_seen": 0,
|
246 |
"num_train_epochs": 5,
|
247 |
"save_steps": 200,
|
248 |
+
"total_flos": 8.670264252137472e+16,
|
249 |
"train_batch_size": 1,
|
250 |
"trial_name": null,
|
251 |
"trial_params": null
|