DuongTrongChi
commited on
Training in progress, step 361, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dacaef364ad77ac1803a72f3736525dd206d7c28282d058f9a9246a1805bf1b0
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abd3846414a209932cf3f9c1ecaa3a5f1a053beebfa2cd6b4a352bc0450a8909
|
3 |
size 50675604
|
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 sha256:358cc543a4dfee9cdbd11d603288fa82292225e6222d3a6078f1df3f3c96f685
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2527,6 +2527,13 @@
|
|
2527 |
"learning_rate": 3.0303030303030305e-06,
|
2528 |
"loss": 1.1291,
|
2529 |
"step": 360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2530 |
}
|
2531 |
],
|
2532 |
"logging_steps": 1,
|
@@ -2546,7 +2553,7 @@
|
|
2546 |
"attributes": {}
|
2547 |
}
|
2548 |
},
|
2549 |
-
"total_flos": 7.
|
2550 |
"train_batch_size": 4,
|
2551 |
"trial_name": null,
|
2552 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.99039780521262,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 361,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2527 |
"learning_rate": 3.0303030303030305e-06,
|
2528 |
"loss": 1.1291,
|
2529 |
"step": 360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.99039780521262,
|
2533 |
+
"grad_norm": 0.08883443474769592,
|
2534 |
+
"learning_rate": 2.2727272727272728e-06,
|
2535 |
+
"loss": 0.9949,
|
2536 |
+
"step": 361
|
2537 |
}
|
2538 |
],
|
2539 |
"logging_steps": 1,
|
|
|
2553 |
"attributes": {}
|
2554 |
}
|
2555 |
},
|
2556 |
+
"total_flos": 7.504897038633492e+17,
|
2557 |
"train_batch_size": 4,
|
2558 |
"trial_name": null,
|
2559 |
"trial_params": null
|