Commit
•
c19ca04
1
Parent(s):
86d11a3
Training in progress, step 10400, 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:e2bbb20e2e294c1c21192f562a8c629ebccc06ad6cd551b6f30c8e039ab4706c
|
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 sha256:8ec42b92ca3eacb4edf3bf7f17472e3af6a7858800cee747ed46bbcad71a1cbe
|
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:e76cdf884e11761c200ac34b58dbb495717e6bde399a5bd34f22ad9223e288af
|
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 sha256:267883072a6671c244f08bafb8d77a7436e4752bd5182174b7eeacf1d55aa425
|
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,
|
@@ -364,6 +364,13 @@
|
|
364 |
"learning_rate": 1.9999886669941987e-05,
|
365 |
"loss": 1.5473,
|
366 |
"step": 10200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
367 |
}
|
368 |
],
|
369 |
"logging_steps": 200,
|
@@ -371,7 +378,7 @@
|
|
371 |
"num_input_tokens_seen": 0,
|
372 |
"num_train_epochs": 5,
|
373 |
"save_steps": 200,
|
374 |
-
"total_flos": 1.
|
375 |
"train_batch_size": 1,
|
376 |
"trial_name": null,
|
377 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007734095835858689,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 10400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
364 |
"learning_rate": 1.9999886669941987e-05,
|
365 |
"loss": 1.5473,
|
366 |
"step": 10200
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.01,
|
370 |
+
"grad_norm": 2.603821039199829,
|
371 |
+
"learning_rate": 1.999988217717089e-05,
|
372 |
+
"loss": 1.5754,
|
373 |
+
"step": 10400
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 200,
|
|
|
378 |
"num_input_tokens_seen": 0,
|
379 |
"num_train_epochs": 5,
|
380 |
"save_steps": 200,
|
381 |
+
"total_flos": 1.3591987236736205e+17,
|
382 |
"train_batch_size": 1,
|
383 |
"trial_name": null,
|
384 |
"trial_params": null
|