Training in progress, epoch 1
Browse files- config.json +25 -0
- model.safetensors +3 -0
- run-0/checkpoint-94/config.json +25 -0
- run-0/checkpoint-94/model.safetensors +3 -0
- run-0/checkpoint-94/optimizer.pt +3 -0
- run-0/checkpoint-94/rng_state.pth +3 -0
- run-0/checkpoint-94/scheduler.pt +3 -0
- run-0/checkpoint-94/trainer_state.json +49 -0
- run-0/checkpoint-94/training_args.bin +3 -0
- runs/Sep25_10-49-38_40a6cf7e9f4d/events.out.tfevents.1727261380.40a6cf7e9f4d.32062.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
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,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73e847162584a63fc2b5ba5e89709a11e8088b406ea094129b0c68313a2d0e39
|
3 |
+
size 267832560
|
run-0/checkpoint-94/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
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,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-94/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73e847162584a63fc2b5ba5e89709a11e8088b406ea094129b0c68313a2d0e39
|
3 |
+
size 267832560
|
run-0/checkpoint-94/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dedc9c913ac72ae75dde16317029fbcdba37f17ccb5288fe8d30b960316e946b
|
3 |
+
size 535727290
|
run-0/checkpoint-94/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:860d4da9b4711ea90de7843aa6dbd8802334208c5a3fa704b27d144f453970b1
|
3 |
+
size 14244
|
run-0/checkpoint-94/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78d906d3f670d90721f6ec9d218b83d88f860c9da1c15bf209ca03b5489217dd
|
3 |
+
size 1064
|
run-0/checkpoint-94/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 94,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.8344827586206897,
|
14 |
+
"eval_f1": 0.8345990695128626,
|
15 |
+
"eval_loss": 0.36505451798439026,
|
16 |
+
"eval_precision": 0.8347741140987747,
|
17 |
+
"eval_recall": 0.8344827586206897,
|
18 |
+
"eval_runtime": 6.2346,
|
19 |
+
"eval_samples_per_second": 162.801,
|
20 |
+
"eval_steps_per_second": 20.37,
|
21 |
+
"step": 94
|
22 |
+
}
|
23 |
+
],
|
24 |
+
"logging_steps": 500,
|
25 |
+
"max_steps": 188,
|
26 |
+
"num_input_tokens_seen": 0,
|
27 |
+
"num_train_epochs": 2,
|
28 |
+
"save_steps": 500,
|
29 |
+
"stateful_callbacks": {
|
30 |
+
"TrainerControl": {
|
31 |
+
"args": {
|
32 |
+
"should_epoch_stop": false,
|
33 |
+
"should_evaluate": false,
|
34 |
+
"should_log": false,
|
35 |
+
"should_save": true,
|
36 |
+
"should_training_stop": false
|
37 |
+
},
|
38 |
+
"attributes": {}
|
39 |
+
}
|
40 |
+
},
|
41 |
+
"total_flos": 0,
|
42 |
+
"train_batch_size": 32,
|
43 |
+
"trial_name": null,
|
44 |
+
"trial_params": {
|
45 |
+
"learning_rate": 3.9540891862156024e-05,
|
46 |
+
"num_train_epochs": 2,
|
47 |
+
"per_device_train_batch_size": 32
|
48 |
+
}
|
49 |
+
}
|
run-0/checkpoint-94/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6208cda24d8fa7973d51f688e4629da400fdd1e533b33bcb3230b504718b42
|
3 |
+
size 5240
|
runs/Sep25_10-49-38_40a6cf7e9f4d/events.out.tfevents.1727261380.40a6cf7e9f4d.32062.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:769295d2508a1274574caa73ac0478fe5d092df64ccfc8c5936bc5a08bb5db2a
|
3 |
+
size 5331
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6208cda24d8fa7973d51f688e4629da400fdd1e533b33bcb3230b504718b42
|
3 |
+
size 5240
|