Commit
•
cc3f2d1
1
Parent(s):
d796eb7
Training in progress, step 11000, 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 sha256:42f79bcb4242acb92a4f7cb2331724557b975405cdb310b6f75cdab5cb0cf2d0
|
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 sha256:93139c8c08d09e4868b40bea372b7bdcca69c0d3b509b09aa1126e67ca651e8b
|
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 sha256:9a20da3a65d158b87b649074348cf08fe7936ff41d5f292d89b1fa2048fa05d5
|
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:e17c3aa03d4452fd561bbc9a7830a63b2db80786a84498fe104eef97b6075f39
|
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,
|
@@ -385,6 +385,13 @@
|
|
385 |
"learning_rate": 1.9999872929636188e-05,
|
386 |
"loss": 1.5997,
|
387 |
"step": 10800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 200,
|
@@ -392,7 +399,7 @@
|
|
392 |
"num_input_tokens_seen": 0,
|
393 |
"num_train_epochs": 5,
|
394 |
"save_steps": 200,
|
395 |
-
"total_flos": 1.
|
396 |
"train_batch_size": 1,
|
397 |
"trial_name": null,
|
398 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008180293672542844,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 11000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
385 |
"learning_rate": 1.9999872929636188e-05,
|
386 |
"loss": 1.5997,
|
387 |
"step": 10800
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.01,
|
391 |
+
"grad_norm": 3.612062454223633,
|
392 |
+
"learning_rate": 1.9999868174872666e-05,
|
393 |
+
"loss": 1.533,
|
394 |
+
"step": 11000
|
395 |
}
|
396 |
],
|
397 |
"logging_steps": 200,
|
|
|
399 |
"num_input_tokens_seen": 0,
|
400 |
"num_train_epochs": 5,
|
401 |
"save_steps": 200,
|
402 |
+
"total_flos": 1.4349700301888717e+17,
|
403 |
"train_batch_size": 1,
|
404 |
"trial_name": null,
|
405 |
"trial_params": null
|