Training in progress, step 6, 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 37965300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
|
| 3 |
size 37965300
|
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:c374c6562ebbd81ad3d8b3da8ef3358a94d20512db0e27ba8a9f959fd69d8cd7
|
| 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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
|
| 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": 3,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -44,6 +44,35 @@
|
|
| 44 |
"eval_samples_per_second": 4.654,
|
| 45 |
"eval_steps_per_second": 2.331,
|
| 46 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
}
|
| 48 |
],
|
| 49 |
"logging_steps": 1,
|
|
@@ -63,7 +92,7 @@
|
|
| 63 |
"attributes": {}
|
| 64 |
}
|
| 65 |
},
|
| 66 |
-
"total_flos":
|
| 67 |
"train_batch_size": 2,
|
| 68 |
"trial_name": null,
|
| 69 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.004867166903265057,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 6,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 44 |
"eval_samples_per_second": 4.654,
|
| 45 |
"eval_steps_per_second": 2.331,
|
| 46 |
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.0032447779355100387,
|
| 50 |
+
"grad_norm": NaN,
|
| 51 |
+
"learning_rate": 8e-05,
|
| 52 |
+
"loss": 0.0,
|
| 53 |
+
"step": 4
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.004055972419387548,
|
| 57 |
+
"grad_norm": NaN,
|
| 58 |
+
"learning_rate": 0.0001,
|
| 59 |
+
"loss": 0.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.004867166903265057,
|
| 64 |
+
"grad_norm": NaN,
|
| 65 |
+
"learning_rate": 0.00012,
|
| 66 |
+
"loss": 0.0,
|
| 67 |
+
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.004867166903265057,
|
| 71 |
+
"eval_loss": NaN,
|
| 72 |
+
"eval_runtime": 111.4781,
|
| 73 |
+
"eval_samples_per_second": 4.656,
|
| 74 |
+
"eval_steps_per_second": 2.332,
|
| 75 |
+
"step": 6
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 1,
|
|
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
+
"total_flos": 1567522604187648.0,
|
| 96 |
"train_batch_size": 2,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|