MohamedAhmedAE
commited on
Commit
•
0688d7e
1
Parent(s):
1a4d075
Training in progress, step 8200, 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 sha256:783309b92bf904a4987195d65f9c3e49a0a7df8a83abb12055e5dba735e35ba3
|
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:c2c0aba8b4efcec01add15ebdb21629b6fb824568690d50ff04fee5ba95bce6f
|
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:a6e69560bad23a6fb4e8cc5cd668902a0c825d77164f5297a8878eeef71f6dbf
|
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 sha256:612d436028557394444e8286b0ca62afad5efea9ac857621a2bc4c96f8a94c3b
|
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,
|
@@ -287,6 +287,13 @@
|
|
287 |
"learning_rate": 1.9999930326577432e-05,
|
288 |
"loss": 1.5593,
|
289 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 200,
|
@@ -294,7 +301,7 @@
|
|
294 |
"num_input_tokens_seen": 0,
|
295 |
"num_train_epochs": 5,
|
296 |
"save_steps": 200,
|
297 |
-
"total_flos": 1.
|
298 |
"train_batch_size": 1,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00609803710135012,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 8200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
287 |
"learning_rate": 1.9999930326577432e-05,
|
288 |
"loss": 1.5593,
|
289 |
"step": 8000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.01,
|
293 |
+
"grad_norm": 2.441413640975952,
|
294 |
+
"learning_rate": 1.999992679444808e-05,
|
295 |
+
"loss": 1.5118,
|
296 |
+
"step": 8200
|
297 |
}
|
298 |
],
|
299 |
"logging_steps": 200,
|
|
|
301 |
"num_input_tokens_seen": 0,
|
302 |
"num_train_epochs": 5,
|
303 |
"save_steps": 200,
|
304 |
+
"total_flos": 1.0738682585918669e+17,
|
305 |
"train_batch_size": 1,
|
306 |
"trial_name": null,
|
307 |
"trial_params": null
|