Training in progress, step 7260, 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:c215149a346e4745232f75aa29caeb783aacb15981e354da509b579b4a0d88fa
|
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:caa8bc36cccd9f6728d02187da80853064d0e028a44347d9ff4436ffe079a61e
|
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:d1d0cf29234269993f4e76384cf3902e85b7a3a0a14bf1670e9916861bec8ca6
|
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 sha256:43aa4ea8ec04509c3f70158ff7115bf7f80a9a88920a63ab013c5639c724613d
|
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,
|
@@ -2541,6 +2541,13 @@
|
|
2541 |
"learning_rate": 2.2132463751155815e-05,
|
2542 |
"loss": 3.4422,
|
2543 |
"step": 7240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2544 |
}
|
2545 |
],
|
2546 |
"logging_steps": 20,
|
@@ -2548,7 +2555,7 @@
|
|
2548 |
"num_input_tokens_seen": 0,
|
2549 |
"num_train_epochs": 2,
|
2550 |
"save_steps": 20,
|
2551 |
-
"total_flos": 1.
|
2552 |
"train_batch_size": 8,
|
2553 |
"trial_name": null,
|
2554 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5808,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7260,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2541 |
"learning_rate": 2.2132463751155815e-05,
|
2542 |
"loss": 3.4422,
|
2543 |
"step": 7240
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.58,
|
2547 |
+
"grad_norm": 26.5496883392334,
|
2548 |
+
"learning_rate": 2.2089688594844917e-05,
|
2549 |
+
"loss": 3.4953,
|
2550 |
+
"step": 7260
|
2551 |
}
|
2552 |
],
|
2553 |
"logging_steps": 20,
|
|
|
2555 |
"num_input_tokens_seen": 0,
|
2556 |
"num_train_epochs": 2,
|
2557 |
"save_steps": 20,
|
2558 |
+
"total_flos": 1.715896854331392e+16,
|
2559 |
"train_batch_size": 8,
|
2560 |
"trial_name": null,
|
2561 |
"trial_params": null
|