Femboyuwu2000
commited on
Commit
•
4e11a86
1
Parent(s):
6a1b362
Training in progress, step 7220, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04106cea74c9b7217608ed5335434aec139928b980a1d98f13c1d65ad9a2757e
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c17ba484ea8b4f6a5dc4fb01470e7b5de3b2280c1d5dfa43045e816b3035ab
|
3 |
size 7062522
|
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 sha256:515ac92b399b536a4a0990d851348426453ad5a34a8114a85806dc0f2120c04c
|
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 sha256:612c3aa776f0b1615bfed5f7770ad478e4281d699f7ba3dca66036c0a3ba855a
|
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": 2.2217789167362078e-05,
|
2528 |
"loss": 3.4405,
|
2529 |
"step": 7200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2530 |
}
|
2531 |
],
|
2532 |
"logging_steps": 20,
|
@@ -2534,7 +2541,7 @@
|
|
2534 |
"num_input_tokens_seen": 0,
|
2535 |
"num_train_epochs": 2,
|
2536 |
"save_steps": 20,
|
2537 |
-
"total_flos": 1.
|
2538 |
"train_batch_size": 8,
|
2539 |
"trial_name": null,
|
2540 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5776,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7220,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2527 |
"learning_rate": 2.2217789167362078e-05,
|
2528 |
"loss": 3.4405,
|
2529 |
"step": 7200
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.58,
|
2533 |
+
"grad_norm": 34.66562271118164,
|
2534 |
+
"learning_rate": 2.217516409129699e-05,
|
2535 |
+
"loss": 3.5408,
|
2536 |
+
"step": 7220
|
2537 |
}
|
2538 |
],
|
2539 |
"logging_steps": 20,
|
|
|
2541 |
"num_input_tokens_seen": 0,
|
2542 |
"num_train_epochs": 2,
|
2543 |
"save_steps": 20,
|
2544 |
+
"total_flos": 1.7055072218185728e+16,
|
2545 |
"train_batch_size": 8,
|
2546 |
"trial_name": null,
|
2547 |
"trial_params": null
|