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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:813dbac8fa97274e3b70cfab4505d0cf98217bbd3b2d9625e4c48e711f7ee71a
|
| 3 |
+
size 997319877
|
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 sha256:326a83ac44b4cb085870abefd7a35886a46642d787bc336ef344978da0292ebb
|
| 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:ca2a6098052f5420268e5519bd00e10332340078658775d4537ceb30ab71817a
|
| 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 sha256:9b4404a5e593daf7e425c8a92c57bc8d6f59c6c97b64a73aae6afdd14574ef05
|
| 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": 2.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -38,11 +38,27 @@
|
|
| 38 |
"eval_samples_per_second": 331.224,
|
| 39 |
"eval_steps_per_second": 23.244,
|
| 40 |
"step": 211
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"max_steps": 1050,
|
| 44 |
"num_train_epochs": 10,
|
| 45 |
-
"total_flos":
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
| 48 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.49069943344752504,
|
| 3 |
+
"best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-316",
|
| 4 |
+
"epoch": 2.995260663507109,
|
| 5 |
+
"global_step": 316,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 38 |
"eval_samples_per_second": 331.224,
|
| 39 |
"eval_steps_per_second": 23.244,
|
| 40 |
"step": 211
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.84,
|
| 44 |
+
"learning_rate": 1.5197568389057753e-05,
|
| 45 |
+
"loss": 0.8144,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7280701754385965,
|
| 51 |
+
"eval_f1_macro": 0.49069943344752504,
|
| 52 |
+
"eval_loss": 0.7686166167259216,
|
| 53 |
+
"eval_runtime": 0.3431,
|
| 54 |
+
"eval_samples_per_second": 332.269,
|
| 55 |
+
"eval_steps_per_second": 23.317,
|
| 56 |
+
"step": 316
|
| 57 |
}
|
| 58 |
],
|
| 59 |
"max_steps": 1050,
|
| 60 |
"num_train_epochs": 10,
|
| 61 |
+
"total_flos": 265093908618240.0,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
| 64 |
}
|
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 sha256:326a83ac44b4cb085870abefd7a35886a46642d787bc336ef344978da0292ebb
|
| 3 |
size 498674357
|
runs/Apr21_00-03-56_jupyter/events.out.tfevents.1713657840.jupyter.2695507.8
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:f7bc2ed98dd8117b474ebb592be0d7ef671f15d40c40af929a3fada626f3897a
|
| 3 |
+
size 5939
|