Johannes Garstenauer commited on
Commit ·
4252ad3
1
Parent(s): 76f6de4
Training in progress, step 1484
Browse files- config.json +0 -8
- last-checkpoint/config.json +0 -8
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/trainer_state.json +18 -5
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- tokenizer.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -8,15 +8,7 @@
|
|
| 8 |
"dim": 768,
|
| 9 |
"dropout": 0.1,
|
| 10 |
"hidden_dim": 3072,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "IRRELEVANT",
|
| 13 |
-
"1": "RELEVANT"
|
| 14 |
-
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"label2id": {
|
| 17 |
-
"IRRELEVANT": 0,
|
| 18 |
-
"RELEVANT": 1
|
| 19 |
-
},
|
| 20 |
"max_position_embeddings": 512,
|
| 21 |
"model_type": "distilbert",
|
| 22 |
"n_heads": 12,
|
|
|
|
| 8 |
"dim": 768,
|
| 9 |
"dropout": 0.1,
|
| 10 |
"hidden_dim": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 512,
|
| 13 |
"model_type": "distilbert",
|
| 14 |
"n_heads": 12,
|
last-checkpoint/config.json
CHANGED
|
@@ -8,15 +8,7 @@
|
|
| 8 |
"dim": 768,
|
| 9 |
"dropout": 0.1,
|
| 10 |
"hidden_dim": 3072,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "IRRELEVANT",
|
| 13 |
-
"1": "RELEVANT"
|
| 14 |
-
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"label2id": {
|
| 17 |
-
"IRRELEVANT": 0,
|
| 18 |
-
"RELEVANT": 1
|
| 19 |
-
},
|
| 20 |
"max_position_embeddings": 512,
|
| 21 |
"model_type": "distilbert",
|
| 22 |
"n_heads": 12,
|
|
|
|
| 8 |
"dim": 768,
|
| 9 |
"dropout": 0.1,
|
| 10 |
"hidden_dim": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 512,
|
| 13 |
"model_type": "distilbert",
|
| 14 |
"n_heads": 12,
|
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 sha256:9896e8d0124d5b60640b7042b8018e3eb1ff58464d4f3428997fbea06aa7afb4
|
| 3 |
+
size 532524613
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 266267309
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a262ac3d9df7d4fb12e6d46105f07d93ea35340e4e9cff0723b93897630a7f
|
| 3 |
size 266267309
|
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:c126e721ff3c6b9747ced437bbbe76b4bc52ffe720acdffd62333dbd482ab9f4
|
| 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:b76e3ce72c19e924a951d5c4e9e39521e9da92ff3a079788c88600432238405a
|
| 3 |
size 627
|
last-checkpoint/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,15 +1,28 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"num_train_epochs": 3,
|
| 12 |
-
"total_flos":
|
| 13 |
"trial_name": null,
|
| 14 |
"trial_params": null
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.15008090614886732,
|
| 5 |
+
"global_step": 1484,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 1.9662891046386194e-05,
|
| 13 |
+
"loss": 0.6969,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 1.9325782092772386e-05,
|
| 19 |
+
"loss": 0.6954,
|
| 20 |
+
"step": 1000
|
| 21 |
+
}
|
| 22 |
+
],
|
| 23 |
+
"max_steps": 29664,
|
| 24 |
"num_train_epochs": 3,
|
| 25 |
+
"total_flos": 2.516244730950451e+16,
|
| 26 |
"trial_name": null,
|
| 27 |
"trial_params": null
|
| 28 |
}
|
last-checkpoint/training_args.bin
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:e8444ef5633d021089a16534c8e413f3aea558064a6d5362f54659c1e09ebcb4
|
| 3 |
+
size 3963
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 266267309
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a262ac3d9df7d4fb12e6d46105f07d93ea35340e4e9cff0723b93897630a7f
|
| 3 |
size 266267309
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
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:e8444ef5633d021089a16534c8e413f3aea558064a6d5362f54659c1e09ebcb4
|
| 3 |
+
size 3963
|