Training in progress, step 2900, 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:e81834b3b8ce8a84668f373441f0d50637fb84cd037399793dbd007eae58e5f5
|
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:b9c1215701e6b6e5b69da3135df5870e6f8747aed9e256a4eb58e36b25200add
|
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 sha256:4661af03204b37126651ed054d902327a755c23a1b8ab409aa9200fc8c97a842
|
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 sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 3.
|
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,
|
@@ -399,6 +399,20 @@
|
|
399 |
"eval_samples_per_second": 2.482,
|
400 |
"eval_steps_per_second": 0.311,
|
401 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 100,
|
@@ -406,7 +420,7 @@
|
|
406 |
"num_input_tokens_seen": 0,
|
407 |
"num_train_epochs": 5,
|
408 |
"save_steps": 100,
|
409 |
-
"total_flos": 7.
|
410 |
"trial_name": null,
|
411 |
"trial_params": null
|
412 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9069462418556213,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2900",
|
4 |
+
"epoch": 3.8666666666666667,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
399 |
"eval_samples_per_second": 2.482,
|
400 |
"eval_steps_per_second": 0.311,
|
401 |
"step": 2800
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.87,
|
405 |
+
"learning_rate": 0.0002,
|
406 |
+
"loss": 0.7222,
|
407 |
+
"step": 2900
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 3.87,
|
411 |
+
"eval_loss": 0.9069462418556213,
|
412 |
+
"eval_runtime": 778.8375,
|
413 |
+
"eval_samples_per_second": 2.478,
|
414 |
+
"eval_steps_per_second": 0.311,
|
415 |
+
"step": 2900
|
416 |
}
|
417 |
],
|
418 |
"logging_steps": 100,
|
|
|
420 |
"num_input_tokens_seen": 0,
|
421 |
"num_train_epochs": 5,
|
422 |
"save_steps": 100,
|
423 |
+
"total_flos": 7.511437778626253e+17,
|
424 |
"trial_name": null,
|
425 |
"trial_params": null
|
426 |
}
|