Training in progress, step 3100, 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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:085a2ebfd04a3809d12b0e3db225b58bc970a83b1089d0a63600fcfc200ecdba
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bdab217ef76511669f78840feecc999ecc4aaa34ffbda530e89db33f056d9c5
|
3 |
size 39356997
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02564141f65d6796fc22bd626e526e8aed02bce0651ca616957fae586fbe037
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.9039433002471924,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
4 |
-
"epoch": 4.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -427,6 +427,20 @@
|
|
427 |
"eval_samples_per_second": 2.495,
|
428 |
"eval_steps_per_second": 0.313,
|
429 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
430 |
}
|
431 |
],
|
432 |
"logging_steps": 100,
|
@@ -434,7 +448,7 @@
|
|
434 |
"num_input_tokens_seen": 0,
|
435 |
"num_train_epochs": 5,
|
436 |
"save_steps": 100,
|
437 |
-
"total_flos":
|
438 |
"trial_name": null,
|
439 |
"trial_params": null
|
440 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.9039433002471924,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
4 |
+
"epoch": 4.133333333333334,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
427 |
"eval_samples_per_second": 2.495,
|
428 |
"eval_steps_per_second": 0.313,
|
429 |
"step": 3000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 4.13,
|
433 |
+
"learning_rate": 0.0002,
|
434 |
+
"loss": 0.6845,
|
435 |
+
"step": 3100
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 4.13,
|
439 |
+
"eval_loss": 0.906529426574707,
|
440 |
+
"eval_runtime": 784.1515,
|
441 |
+
"eval_samples_per_second": 2.461,
|
442 |
+
"eval_steps_per_second": 0.309,
|
443 |
+
"step": 3100
|
444 |
}
|
445 |
],
|
446 |
"logging_steps": 100,
|
|
|
448 |
"num_input_tokens_seen": 0,
|
449 |
"num_train_epochs": 5,
|
450 |
"save_steps": 100,
|
451 |
+
"total_flos": 8.029294478933606e+17,
|
452 |
"trial_name": null,
|
453 |
"trial_params": null
|
454 |
}
|