Commit
•
a3f2a5e
1
Parent(s):
2fbcfcc
Training in progress, step 10800, 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 sha256:7ef4eecea3629afcace64b5a917ddd966970bb97958ca98caf3b5b8b8f4cb9f9
|
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:faa46c7ed1d599bf3e19190dd49f7e1e57d3c190ced1afb5d39e58b75b5b6e9d
|
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:d3933564f2de09fa9ed32bd0876590ad1ced5b512ea947850a85c5527075c34c
|
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 sha256:4b9b6db394b3d452474e4549621859e2d2c7908c6ab758c808d3d275e4c68c06
|
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,
|
@@ -378,6 +378,13 @@
|
|
378 |
"learning_rate": 1.9999877597068942e-05,
|
379 |
"loss": 1.572,
|
380 |
"step": 10600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
381 |
}
|
382 |
],
|
383 |
"logging_steps": 200,
|
@@ -385,7 +392,7 @@
|
|
385 |
"num_input_tokens_seen": 0,
|
386 |
"num_train_epochs": 5,
|
387 |
"save_steps": 200,
|
388 |
-
"total_flos": 1.
|
389 |
"train_batch_size": 1,
|
390 |
"trial_name": null,
|
391 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008031561060314793,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 10800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
378 |
"learning_rate": 1.9999877597068942e-05,
|
379 |
"loss": 1.572,
|
380 |
"step": 10600
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.01,
|
384 |
+
"grad_norm": 4.2719645500183105,
|
385 |
+
"learning_rate": 1.9999872929636188e-05,
|
386 |
+
"loss": 1.5997,
|
387 |
+
"step": 10800
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 200,
|
|
|
392 |
"num_input_tokens_seen": 0,
|
393 |
"num_train_epochs": 5,
|
394 |
"save_steps": 200,
|
395 |
+
"total_flos": 1.4106137221472256e+17,
|
396 |
"train_batch_size": 1,
|
397 |
"trial_name": null,
|
398 |
"trial_params": null
|