Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-3/checkpoint-2138/model.safetensors +1 -1
- run-3/checkpoint-2138/optimizer.pt +1 -1
- run-3/checkpoint-2138/rng_state.pth +1 -1
- run-3/checkpoint-2138/scheduler.pt +1 -1
- run-3/checkpoint-2138/trainer_state.json +17 -17
- run-3/checkpoint-2138/training_args.bin +1 -1
- runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294598.cab176ec49ea.681.5 +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 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3856f5d52b139f68324c7fde3f7b30f487ee6e7fee6adeb65d95f8f88928dc48
|
| 3 |
size 267832560
|
run-3/checkpoint-2138/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3856f5d52b139f68324c7fde3f7b30f487ee6e7fee6adeb65d95f8f88928dc48
|
| 3 |
size 267832560
|
run-3/checkpoint-2138/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535727290
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e472fbf5f8cc5c472eae2173d310316c60a1b566a27c98944f6e61017eab16f
|
| 3 |
size 535727290
|
run-3/checkpoint-2138/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 sha256:21acd9373ba2636a96a037599a124a8848e64458d7ed9a26ffc24cbd4056b661
|
| 3 |
size 14244
|
run-3/checkpoint-2138/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:f4249bf660aed0d3def9d8b0f79d921f7a157b3f4104064206caa1eaa6c6ede4
|
| 3 |
size 1064
|
run-3/checkpoint-2138/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138",
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
|
@@ -10,35 +10,35 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.23,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.47,
|
| 19 |
-
"learning_rate": 1.
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.7,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.94,
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.0,
|
| 37 |
-
"eval_loss": 0.
|
| 38 |
-
"eval_matthews_correlation": 0.
|
| 39 |
-
"eval_runtime": 0.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 2138
|
| 43 |
}
|
| 44 |
],
|
|
@@ -47,13 +47,13 @@
|
|
| 47 |
"num_input_tokens_seen": 0,
|
| 48 |
"num_train_epochs": 2,
|
| 49 |
"save_steps": 500,
|
| 50 |
-
"total_flos":
|
| 51 |
"train_batch_size": 4,
|
| 52 |
"trial_name": null,
|
| 53 |
"trial_params": {
|
| 54 |
-
"learning_rate":
|
| 55 |
"num_train_epochs": 2,
|
| 56 |
"per_device_train_batch_size": 4,
|
| 57 |
-
"seed":
|
| 58 |
}
|
| 59 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.0463559874942472,
|
| 3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138",
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.23,
|
| 13 |
+
"learning_rate": 1.3504098486610872e-06,
|
| 14 |
+
"loss": 0.6235,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.47,
|
| 19 |
+
"learning_rate": 1.1715949852260916e-06,
|
| 20 |
+
"loss": 0.6084,
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.7,
|
| 25 |
+
"learning_rate": 9.92780121791096e-07,
|
| 26 |
+
"loss": 0.5687,
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.94,
|
| 31 |
+
"learning_rate": 8.139652583561002e-07,
|
| 32 |
+
"loss": 0.5599,
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.0,
|
| 37 |
+
"eval_loss": 0.5971149802207947,
|
| 38 |
+
"eval_matthews_correlation": 0.0463559874942472,
|
| 39 |
+
"eval_runtime": 0.7351,
|
| 40 |
+
"eval_samples_per_second": 1418.884,
|
| 41 |
+
"eval_steps_per_second": 89.786,
|
| 42 |
"step": 2138
|
| 43 |
}
|
| 44 |
],
|
|
|
|
| 47 |
"num_input_tokens_seen": 0,
|
| 48 |
"num_train_epochs": 2,
|
| 49 |
"save_steps": 500,
|
| 50 |
+
"total_flos": 32410011903984.0,
|
| 51 |
"train_batch_size": 4,
|
| 52 |
"trial_name": null,
|
| 53 |
"trial_params": {
|
| 54 |
+
"learning_rate": 1.529224712096083e-06,
|
| 55 |
"num_train_epochs": 2,
|
| 56 |
"per_device_train_batch_size": 4,
|
| 57 |
+
"seed": 5
|
| 58 |
}
|
| 59 |
}
|
run-3/checkpoint-2138/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff0b8762417b71e573ee14cf5d6c55e801af11f299848bcf4bde51f1e4499d53
|
| 3 |
size 4792
|
runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294598.cab176ec49ea.681.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aec5cbcca727aa7079f2bff88b7723e3256d02957fd46f8f12881568ec6a043
|
| 3 |
+
size 5459
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff0b8762417b71e573ee14cf5d6c55e801af11f299848bcf4bde51f1e4499d53
|
| 3 |
size 4792
|