Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-120/model.safetensors +1 -1
- run-0/checkpoint-120/optimizer.pt +1 -1
- run-0/checkpoint-120/scaler.pt +3 -0
- run-0/checkpoint-120/trainer_state.json +8 -8
- run-0/checkpoint-120/training_args.bin +1 -1
- runs/Oct26_17-22-45_49ca29516c75/events.out.tfevents.1761500015.49ca29516c75.609.3 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598898116
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a25ab4189f57cefa6683da318b62f0b56c4bf241725450d7afa7aa7bd191bc
|
| 3 |
size 598898116
|
run-0/checkpoint-120/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598898116
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a25ab4189f57cefa6683da318b62f0b56c4bf241725450d7afa7aa7bd191bc
|
| 3 |
size 598898116
|
run-0/checkpoint-120/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1197886411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c52c7c0ed3b89bc5e989c0acacdae089b1db48616ba21cf0d6f584c35607776
|
| 3 |
size 1197886411
|
run-0/checkpoint-120/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf3b5533a1f7c51903a394b9b37628068b69e8f1df609e7f470770e608906ee7
|
| 3 |
+
size 1383
|
run-0/checkpoint-120/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"best_global_step": 120,
|
| 3 |
-
"best_metric": 0.
|
| 4 |
"best_model_checkpoint": "student_modernBERT_clinc_oos/run-0/checkpoint-120",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
@@ -11,11 +11,11 @@
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss":
|
| 16 |
-
"eval_runtime":
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second":
|
| 19 |
"step": 120
|
| 20 |
}
|
| 21 |
],
|
|
@@ -40,8 +40,8 @@
|
|
| 40 |
"train_batch_size": 32,
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": {
|
| 43 |
-
"alpha": 0.
|
| 44 |
"num_train_epochs": 6,
|
| 45 |
-
"temperature":
|
| 46 |
}
|
| 47 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_global_step": 120,
|
| 3 |
+
"best_metric": 0.5541935483870968,
|
| 4 |
"best_model_checkpoint": "student_modernBERT_clinc_oos/run-0/checkpoint-120",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.5541935483870968,
|
| 15 |
+
"eval_loss": 1.7238802909851074,
|
| 16 |
+
"eval_runtime": 7.0038,
|
| 17 |
+
"eval_samples_per_second": 442.616,
|
| 18 |
+
"eval_steps_per_second": 13.85,
|
| 19 |
"step": 120
|
| 20 |
}
|
| 21 |
],
|
|
|
|
| 40 |
"train_batch_size": 32,
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": {
|
| 43 |
+
"alpha": 0.17839594203233045,
|
| 44 |
"num_train_epochs": 6,
|
| 45 |
+
"temperature": 13
|
| 46 |
}
|
| 47 |
}
|
run-0/checkpoint-120/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:defea8818495be5704f8f89261e105141cdc7770477d9f23e5c577ed2e3f7868
|
| 3 |
size 5905
|
runs/Oct26_17-22-45_49ca29516c75/events.out.tfevents.1761500015.49ca29516c75.609.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d10ad5f4a31fa75d8b78a7171923f134d188e4d4ef68a3901eeb6e97e549951
|
| 3 |
+
size 13538
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:defea8818495be5704f8f89261e105141cdc7770477d9f23e5c577ed2e3f7868
|
| 3 |
size 5905
|