Training in progress, step 2700, 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 sha256:73bf170a4262ebe1fff81baaeeb218372d2e30888e171ac702c009ebd68a8f4a
|
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 sha256:0b1ee60a8dbf6dae548bd961ea1ca9672484fce9c8d9c1cae7edb3f72bdd270e
|
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 sha256:2976c6db6ebcdf9dabf12702a779e061718bd1c4ef8e49e51b66e2a5fcb97d74
|
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:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
|
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,
|
@@ -371,13 +371,27 @@
|
|
371 |
"eval_samples_per_second": 17.745,
|
372 |
"eval_steps_per_second": 2.22,
|
373 |
"step": 2600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 100,
|
377 |
"max_steps": 4116,
|
378 |
"num_train_epochs": 3,
|
379 |
"save_steps": 100,
|
380 |
-
"total_flos": 7.
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.094940423965454,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2700",
|
4 |
+
"epoch": 1.9672131147540983,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
371 |
"eval_samples_per_second": 17.745,
|
372 |
"eval_steps_per_second": 2.22,
|
373 |
"step": 2600
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.97,
|
377 |
+
"learning_rate": 0.0002,
|
378 |
+
"loss": 2.0882,
|
379 |
+
"step": 2700
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 1.97,
|
383 |
+
"eval_loss": 2.094940423965454,
|
384 |
+
"eval_runtime": 353.902,
|
385 |
+
"eval_samples_per_second": 17.728,
|
386 |
+
"eval_steps_per_second": 2.218,
|
387 |
+
"step": 2700
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 100,
|
391 |
"max_steps": 4116,
|
392 |
"num_train_epochs": 3,
|
393 |
"save_steps": 100,
|
394 |
+
"total_flos": 7.934011037632512e+16,
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|