MohamedAhmedAE
commited on
Commit
•
d8d2f90
1
Parent(s):
652792d
Training in progress, step 9000, 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 sha256:9af7b37f06d07ef70d4988ce1f6299893bace9d6a7ba0c9cd136d9ea3fd941fa
|
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:f921cb5d7c6f27660db1f17dd3595cd35f686682075ca581ae6001b538ec16f7
|
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:cf5f888e89f291e2093e87569b5763db1fc85cbdf17ee5606bd0221a799e468a
|
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:aaf2bc4e5abc828d18795c4a133d46fc971f9c25b1fb81b66f19e661f16cda00
|
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,
|
@@ -315,6 +315,13 @@
|
|
315 |
"learning_rate": 1.9999915674072735e-05,
|
316 |
"loss": 1.6099,
|
317 |
"step": 8800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 200,
|
@@ -322,7 +329,7 @@
|
|
322 |
"num_input_tokens_seen": 0,
|
323 |
"num_train_epochs": 5,
|
324 |
"save_steps": 200,
|
325 |
-
"total_flos": 1.
|
326 |
"train_batch_size": 1,
|
327 |
"trial_name": null,
|
328 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006692967550262327,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 9000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"learning_rate": 1.9999915674072735e-05,
|
316 |
"loss": 1.6099,
|
317 |
"step": 8800
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.01,
|
321 |
+
"grad_norm": 2.3625733852386475,
|
322 |
+
"learning_rate": 1.9999911792618627e-05,
|
323 |
+
"loss": 1.5237,
|
324 |
+
"step": 9000
|
325 |
}
|
326 |
],
|
327 |
"logging_steps": 200,
|
|
|
329 |
"num_input_tokens_seen": 0,
|
330 |
"num_train_epochs": 5,
|
331 |
"save_steps": 200,
|
332 |
+
"total_flos": 1.1786109336920064e+17,
|
333 |
"train_batch_size": 1,
|
334 |
"trial_name": null,
|
335 |
"trial_params": null
|