Training in progress, step 2400, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02f7ef35f5c44722f7a0916299669bf1ea4a015d8557c680696b28164e306535
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:150e1ae552b35cc40720f8b36736d1aa6c0f9c23196b9f5cba8a8cd307091036
|
3 |
size 18902665
|
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 sha256:524dd2e23117d8b443709151f0c30fd7b12f5af14881b8fbb512d42a7c4c2c9a
|
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 sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
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,
|
@@ -329,13 +329,27 @@
|
|
329 |
"eval_samples_per_second": 30.286,
|
330 |
"eval_steps_per_second": 3.789,
|
331 |
"step": 2300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 100,
|
335 |
"max_steps": 4116,
|
336 |
"num_train_epochs": 3,
|
337 |
"save_steps": 100,
|
338 |
-
"total_flos":
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
341 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1605775356292725,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2400",
|
4 |
+
"epoch": 1.748633879781421,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
329 |
"eval_samples_per_second": 30.286,
|
330 |
"eval_steps_per_second": 3.789,
|
331 |
"step": 2300
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.75,
|
335 |
+
"learning_rate": 0.0002,
|
336 |
+
"loss": 2.1581,
|
337 |
+
"step": 2400
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.75,
|
341 |
+
"eval_loss": 2.1605775356292725,
|
342 |
+
"eval_runtime": 207.453,
|
343 |
+
"eval_samples_per_second": 30.243,
|
344 |
+
"eval_steps_per_second": 3.784,
|
345 |
+
"step": 2400
|
346 |
}
|
347 |
],
|
348 |
"logging_steps": 100,
|
349 |
"max_steps": 4116,
|
350 |
"num_train_epochs": 3,
|
351 |
"save_steps": 100,
|
352 |
+
"total_flos": 7.009593112553472e+16,
|
353 |
"trial_name": null,
|
354 |
"trial_params": null
|
355 |
}
|