MohamedAhmedAE
commited on
Commit
•
90b404b
1
Parent(s):
e74692a
Training in progress, step 10200, 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 sha256:17ab87b52fe77b0aac85e5c4a2e2c19356beafbdb869980834b2c569fdd8dec2
|
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:a2ed17b033446d9fea3a59eba0464107af299cda4c40efa59a17995b6deae05b
|
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:d67b796360d477d8ece1783942ce085bd8d8c0c2c33afb30f69f41f2fc28a57a
|
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 sha256:322071699a56ddf875d51673dd4754f2d337304fc1c0b6a592a283bd96af5a83
|
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,
|
@@ -357,6 +357,13 @@
|
|
357 |
"learning_rate": 1.9999891075382195e-05,
|
358 |
"loss": 1.5554,
|
359 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 200,
|
@@ -364,7 +371,7 @@
|
|
364 |
"num_input_tokens_seen": 0,
|
365 |
"num_train_epochs": 5,
|
366 |
"save_steps": 200,
|
367 |
-
"total_flos": 1.
|
368 |
"train_batch_size": 1,
|
369 |
"trial_name": null,
|
370 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007585363223630638,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 10200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
357 |
"learning_rate": 1.9999891075382195e-05,
|
358 |
"loss": 1.5554,
|
359 |
"step": 10000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.01,
|
363 |
+
"grad_norm": 3.6852822303771973,
|
364 |
+
"learning_rate": 1.9999886669941987e-05,
|
365 |
+
"loss": 1.5473,
|
366 |
+
"step": 10200
|
367 |
}
|
368 |
],
|
369 |
"logging_steps": 200,
|
|
|
371 |
"num_input_tokens_seen": 0,
|
372 |
"num_train_epochs": 5,
|
373 |
"save_steps": 200,
|
374 |
+
"total_flos": 1.3343348133096653e+17,
|
375 |
"train_batch_size": 1,
|
376 |
"trial_name": null,
|
377 |
"trial_params": null
|