Training in progress, epoch 3, 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 2682482800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7205bc6ef42d3fe5264eee8e9b423c06ed65eb261730c95b173cd46eed841b34
|
| 3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5365108834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a2ff90db3670c76a9736a434b3095e962446788aeeac81efa959d9c377dff7a
|
| 3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c5bbcc855e2d2f1670b318f4813e6c1b2a66567d91cf0f2f810fe4f0b534279
|
| 3 |
size 15006
|
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 sha256:21c1e7c94f4a4d9ecf808ab9f87d13d6452e68cca7a77d136de360bbe5f1bdc5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -37,6 +37,21 @@
|
|
| 37 |
"eval_samples_per_second": 46.53,
|
| 38 |
"eval_steps_per_second": 5.816,
|
| 39 |
"step": 514
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 500,
|
|
@@ -65,7 +80,7 @@
|
|
| 65 |
"attributes": {}
|
| 66 |
}
|
| 67 |
},
|
| 68 |
-
"total_flos":
|
| 69 |
"train_batch_size": 8,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.278564214706421,
|
| 3 |
+
"best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-771",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 771,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 37 |
"eval_samples_per_second": 46.53,
|
| 38 |
"eval_steps_per_second": 5.816,
|
| 39 |
"step": 514
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"grad_norm": 0.5290057063102722,
|
| 44 |
+
"learning_rate": 9.498046875000001e-05,
|
| 45 |
+
"loss": 1.264,
|
| 46 |
+
"step": 771
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_loss": 1.278564214706421,
|
| 51 |
+
"eval_runtime": 9.2918,
|
| 52 |
+
"eval_samples_per_second": 46.493,
|
| 53 |
+
"eval_steps_per_second": 5.812,
|
| 54 |
+
"step": 771
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 500,
|
|
|
|
| 80 |
"attributes": {}
|
| 81 |
}
|
| 82 |
},
|
| 83 |
+
"total_flos": 1.1079859847980646e+17,
|
| 84 |
"train_batch_size": 8,
|
| 85 |
"trial_name": null,
|
| 86 |
"trial_params": null
|