MohamedAhmedAE
commited on
Commit
•
b1a15a7
1
Parent(s):
8c70e82
Training in progress, step 9400, 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 sha256:39e431d6db14e51f3bfd3017080e7c94298c420741f672d6f3148988bcf43745
|
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 sha256:47316673d6aef1c18ee7837cde7ac0a757dd5c2cc276a7a155156bdf8656a755
|
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:f0a546ed2b8311cd8322b8ea0cc1f69ea556efe2ecf55c1d3cb250225b29c7f7
|
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:c7b4d6e372191605987a3472222b6d31492e591157775ac3ab363680ff12d47e
|
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,
|
@@ -329,6 +329,13 @@
|
|
329 |
"learning_rate": 1.9999907823833413e-05,
|
330 |
"loss": 1.5551,
|
331 |
"step": 9200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 200,
|
@@ -336,7 +343,7 @@
|
|
336 |
"num_input_tokens_seen": 0,
|
337 |
"num_train_epochs": 5,
|
338 |
"save_steps": 200,
|
339 |
-
"total_flos": 1.
|
340 |
"train_batch_size": 1,
|
341 |
"trial_name": null,
|
342 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0069904327747184304,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 9400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
329 |
"learning_rate": 1.9999907823833413e-05,
|
330 |
"loss": 1.5551,
|
331 |
"step": 9200
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.01,
|
335 |
+
"grad_norm": 2.759443759918213,
|
336 |
+
"learning_rate": 1.9999903767717127e-05,
|
337 |
+
"loss": 1.5388,
|
338 |
+
"step": 9400
|
339 |
}
|
340 |
],
|
341 |
"logging_steps": 200,
|
|
|
343 |
"num_input_tokens_seen": 0,
|
344 |
"num_train_epochs": 5,
|
345 |
"save_steps": 200,
|
346 |
+
"total_flos": 1.2315378716430336e+17,
|
347 |
"train_batch_size": 1,
|
348 |
"trial_name": null,
|
349 |
"trial_params": null
|