Training in progress, step 160, 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 9568884
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a9d372a77ae52ead8dd23b6619c8992ab04dc87aebf668822a23f4d328c20ea
|
| 3 |
size 9568884
|
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 sha256:2d1d225f67d11bde290f608a478f50f2fde35c5d5394948e1533977dfc3cb891
|
| 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 sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
|
| 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": 40,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -60,6 +60,21 @@
|
|
| 60 |
"eval_samples_per_second": 45.766,
|
| 61 |
"eval_steps_per_second": 22.888,
|
| 62 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
}
|
| 64 |
],
|
| 65 |
"logging_steps": 40,
|
|
@@ -79,7 +94,7 @@
|
|
| 79 |
"attributes": {}
|
| 80 |
}
|
| 81 |
},
|
| 82 |
-
"total_flos":
|
| 83 |
"train_batch_size": 2,
|
| 84 |
"trial_name": null,
|
| 85 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.05896172094523009,
|
| 5 |
"eval_steps": 40,
|
| 6 |
+
"global_step": 160,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 60 |
"eval_samples_per_second": 45.766,
|
| 61 |
"eval_steps_per_second": 22.888,
|
| 62 |
"step": 120
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.05896172094523009,
|
| 66 |
+
"grad_norm": NaN,
|
| 67 |
+
"learning_rate": 5.000000000000003e-06,
|
| 68 |
+
"loss": 0.0,
|
| 69 |
+
"step": 160
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05896172094523009,
|
| 73 |
+
"eval_loss": NaN,
|
| 74 |
+
"eval_runtime": 98.8283,
|
| 75 |
+
"eval_samples_per_second": 46.252,
|
| 76 |
+
"eval_steps_per_second": 23.131,
|
| 77 |
+
"step": 160
|
| 78 |
}
|
| 79 |
],
|
| 80 |
"logging_steps": 40,
|
|
|
|
| 94 |
"attributes": {}
|
| 95 |
}
|
| 96 |
},
|
| 97 |
+
"total_flos": 7601633234780160.0,
|
| 98 |
"train_batch_size": 2,
|
| 99 |
"trial_name": null,
|
| 100 |
"trial_params": null
|