Training in progress, step 5, 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 26498
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae9eb09c0a92d3cec58c8aa83c51dcbb8bc5b40ee212a0c4733565b58390f2cb
|
| 3 |
size 26498
|
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:ec4a9005df5a5390088500321a6c73e8931d27938b229b188b070f417f1eed22
|
| 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 sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
|
| 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": 2,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -59,6 +59,13 @@
|
|
| 59 |
"eval_samples_per_second": 213.909,
|
| 60 |
"eval_steps_per_second": 107.402,
|
| 61 |
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"logging_steps": 1,
|
|
@@ -73,12 +80,12 @@
|
|
| 73 |
"should_evaluate": false,
|
| 74 |
"should_log": false,
|
| 75 |
"should_save": true,
|
| 76 |
-
"should_training_stop":
|
| 77 |
},
|
| 78 |
"attributes": {}
|
| 79 |
}
|
| 80 |
},
|
| 81 |
-
"total_flos":
|
| 82 |
"train_batch_size": 2,
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0353356890459364,
|
| 5 |
"eval_steps": 2,
|
| 6 |
+
"global_step": 5,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 59 |
"eval_samples_per_second": 213.909,
|
| 60 |
"eval_steps_per_second": 107.402,
|
| 61 |
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.0353356890459364,
|
| 65 |
+
"grad_norm": NaN,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 0.0,
|
| 68 |
+
"step": 5
|
| 69 |
}
|
| 70 |
],
|
| 71 |
"logging_steps": 1,
|
|
|
|
| 80 |
"should_evaluate": false,
|
| 81 |
"should_log": false,
|
| 82 |
"should_save": true,
|
| 83 |
+
"should_training_stop": true
|
| 84 |
},
|
| 85 |
"attributes": {}
|
| 86 |
}
|
| 87 |
},
|
| 88 |
+
"total_flos": 3631153152.0,
|
| 89 |
"train_batch_size": 2,
|
| 90 |
"trial_name": null,
|
| 91 |
"trial_params": null
|