Training in progress, step 26, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43122580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05030e503b160bc7361b19d6d4e584f44e3e6bdbf1dc770eded719f4f73c8c04
|
| 3 |
size 43122580
|
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:b4a54a07c0698958332d5189e11a9b414061c5c0cc1dc498ca427cf69ec68650
|
| 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 sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
|
| 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": 13,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -30,6 +30,21 @@
|
|
| 30 |
"eval_samples_per_second": 27.491,
|
| 31 |
"eval_steps_per_second": 13.746,
|
| 32 |
"step": 13
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
}
|
| 34 |
],
|
| 35 |
"logging_steps": 10,
|
|
@@ -49,7 +64,7 @@
|
|
| 49 |
"attributes": {}
|
| 50 |
}
|
| 51 |
},
|
| 52 |
-
"total_flos":
|
| 53 |
"train_batch_size": 2,
|
| 54 |
"trial_name": null,
|
| 55 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.009690644800596348,
|
| 5 |
"eval_steps": 13,
|
| 6 |
+
"global_step": 26,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 30 |
"eval_samples_per_second": 27.491,
|
| 31 |
"eval_steps_per_second": 13.746,
|
| 32 |
"step": 13
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.007454342154304882,
|
| 36 |
+
"grad_norm": NaN,
|
| 37 |
+
"learning_rate": 0.00015000000000000001,
|
| 38 |
+
"loss": 0.0,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.009690644800596348,
|
| 43 |
+
"eval_loss": NaN,
|
| 44 |
+
"eval_runtime": 41.1615,
|
| 45 |
+
"eval_samples_per_second": 27.453,
|
| 46 |
+
"eval_steps_per_second": 13.726,
|
| 47 |
+
"step": 26
|
| 48 |
}
|
| 49 |
],
|
| 50 |
"logging_steps": 10,
|
|
|
|
| 64 |
"attributes": {}
|
| 65 |
}
|
| 66 |
},
|
| 67 |
+
"total_flos": 5389459591790592.0,
|
| 68 |
"train_batch_size": 2,
|
| 69 |
"trial_name": null,
|
| 70 |
"trial_params": null
|