Training in progress, epoch 2
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 997319621
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d368d077a0f444a0992c017207945d7447e79b57de30f24df1bd30ac7d4e58cf
|
| 3 |
size 997319621
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498674357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:757180f5847e6e6e8adc313dea5ce34782c19436414b11183013431c12c89f61
|
| 3 |
size 498674357
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:190ec63f1eff039dd063347cda3f4ca17867f19ff6206e72f252578f29b0a5aa
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8630ed6b65e3550515505b33e335b0d86561e79d9eaa57ead62028ad30608d0e
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-
|
| 4 |
-
"epoch": 0
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -22,11 +22,27 @@
|
|
| 22 |
"eval_samples_per_second": 329.861,
|
| 23 |
"eval_steps_per_second": 23.148,
|
| 24 |
"step": 105
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"max_steps": 1050,
|
| 28 |
"num_train_epochs": 10,
|
| 29 |
-
"total_flos":
|
| 30 |
"trial_name": null,
|
| 31 |
"trial_params": null
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.32540006346615896,
|
| 3 |
+
"best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-211",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 211,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 22 |
"eval_samples_per_second": 329.861,
|
| 23 |
"eval_steps_per_second": 23.148,
|
| 24 |
"step": 105
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.9,
|
| 28 |
+
"learning_rate": 1.7223910840932118e-05,
|
| 29 |
+
"loss": 1.0405,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.6842105263157895,
|
| 35 |
+
"eval_f1_macro": 0.32540006346615896,
|
| 36 |
+
"eval_loss": 0.9257992506027222,
|
| 37 |
+
"eval_runtime": 0.3473,
|
| 38 |
+
"eval_samples_per_second": 328.201,
|
| 39 |
+
"eval_steps_per_second": 23.032,
|
| 40 |
+
"step": 211
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"max_steps": 1050,
|
| 44 |
"num_train_epochs": 10,
|
| 45 |
+
"total_flos": 177618674535264.0,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
| 48 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498674357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:757180f5847e6e6e8adc313dea5ce34782c19436414b11183013431c12c89f61
|
| 3 |
size 498674357
|
runs/Apr20_23-56-38_jupyter/events.out.tfevents.1713657402.jupyter.2695507.6
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d656c80c2e480e10e021e9249c6e707aa6cb23ea8b0e70d0f93bf74508986d6b
|
| 3 |
+
size 5407
|