Commit
•
723b076
1
Parent(s):
407dfa9
Training in progress, step 11200, 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:e978a3dd631581b3085b0ba38c6e47c5baef5e3766e2ff1b44fe2bab4c83f0b4
|
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:cdc657b03435bb6036ff9119a02ab148c9d23c955e9af628c8f81d4a57890a66
|
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 sha256:2c99279038b507bc5d43a7a4b5bc357533051098093ca7eb76dbe75fa2a95d6f
|
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 sha256:1c195caf8ca639dd51bdc47a7a6d637f5c72f6cdcb49eec092ef0892b56f6e72
|
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,
|
@@ -392,6 +392,13 @@
|
|
392 |
"learning_rate": 1.9999868174872666e-05,
|
393 |
"loss": 1.533,
|
394 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
395 |
}
|
396 |
],
|
397 |
"logging_steps": 200,
|
@@ -399,7 +406,7 @@
|
|
399 |
"num_input_tokens_seen": 0,
|
400 |
"num_train_epochs": 5,
|
401 |
"save_steps": 200,
|
402 |
-
"total_flos": 1.
|
403 |
"train_batch_size": 1,
|
404 |
"trial_name": null,
|
405 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008329026284770896,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 11200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
392 |
"learning_rate": 1.9999868174872666e-05,
|
393 |
"loss": 1.533,
|
394 |
"step": 11000
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.01,
|
398 |
+
"grad_norm": 4.553364276885986,
|
399 |
+
"learning_rate": 1.9999863357206127e-05,
|
400 |
+
"loss": 1.5328,
|
401 |
+
"step": 11200
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 200,
|
|
|
406 |
"num_input_tokens_seen": 0,
|
407 |
"num_train_epochs": 5,
|
408 |
"save_steps": 200,
|
409 |
+
"total_flos": 1.463004983428055e+17,
|
410 |
"train_batch_size": 1,
|
411 |
"trial_name": null,
|
412 |
"trial_params": null
|