Training in progress, step 25000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 135998360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80bca253a0f5ca66dc3e39e1ce546bd0defe3bc6421b10a84896e73a3a79706b
|
3 |
size 135998360
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268169559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d566c40915b75ee469c3c4f6352e6e59976f6c1e3d2aab8aecbb14c369ba3494
|
3 |
size 268169559
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d16354864875b00aae19f2df9f099d4e5255f760791cc560d17cb09adeb84c8a
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a963a7b936f55de824412516d865da5a9f6f0018131e283851ae1cda8ff2849
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -343,6 +343,20 @@
|
|
343 |
"eval_samples_per_second": 179.117,
|
344 |
"eval_steps_per_second": 22.395,
|
345 |
"step": 24000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
346 |
}
|
347 |
],
|
348 |
"logging_steps": 1000,
|
@@ -350,7 +364,7 @@
|
|
350 |
"num_input_tokens_seen": 0,
|
351 |
"num_train_epochs": 3,
|
352 |
"save_steps": 1000,
|
353 |
-
"total_flos": 6.
|
354 |
"train_batch_size": 8,
|
355 |
"trial_name": null,
|
356 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.027055351063609123,
|
3 |
+
"best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-25000",
|
4 |
+
"epoch": 2.9836496001909536,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 25000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
343 |
"eval_samples_per_second": 179.117,
|
344 |
"eval_steps_per_second": 22.395,
|
345 |
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.98,
|
349 |
+
"learning_rate": 5.450133269682142e-07,
|
350 |
+
"loss": 0.0115,
|
351 |
+
"step": 25000
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 2.98,
|
355 |
+
"eval_loss": 0.027055351063609123,
|
356 |
+
"eval_runtime": 142.8238,
|
357 |
+
"eval_samples_per_second": 177.856,
|
358 |
+
"eval_steps_per_second": 22.237,
|
359 |
+
"step": 25000
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 1000,
|
|
|
364 |
"num_input_tokens_seen": 0,
|
365 |
"num_train_epochs": 3,
|
366 |
"save_steps": 1000,
|
367 |
+
"total_flos": 6.252295780604789e+16,
|
368 |
"train_batch_size": 8,
|
369 |
"trial_name": null,
|
370 |
"trial_params": null
|