Training in progress, step 500, checkpoint
Browse files
last-checkpoint/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2,
|
23 |
+
"LABEL_3": 3,
|
24 |
+
"LABEL_4": 4
|
25 |
+
},
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "distilbert",
|
28 |
+
"n_heads": 12,
|
29 |
+
"n_layers": 6,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"qa_dropout": 0.1,
|
33 |
+
"seq_classif_dropout": 0.2,
|
34 |
+
"sinusoidal_pos_embds": false,
|
35 |
+
"tie_weights_": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.44.2",
|
38 |
+
"vocab_size": 30522
|
39 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a49ce476ce25fb8f59f194b7ee8dcbd54c7ed9b29498db44d64d455c49fe720
|
3 |
+
size 267841796
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dda8f9a2635a73ea6ece3ba5bfea39916c1a581c9ee7bf67f6a93a025eaa77e2
|
3 |
+
size 535745722
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e42af4289e0114191fc9e8ce7f1b2330a011f00b6431a48cc3c602a486780b82
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27e1abe568f79c654af9f14796de50d6057468072e44df705c1a8d292ff6bcd7
|
3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.1796199083328247,
|
3 |
+
"best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
|
4 |
+
"epoch": 0.16,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.16,
|
13 |
+
"grad_norm": 3.1486153602600098,
|
14 |
+
"learning_rate": 2.133105802047782e-06,
|
15 |
+
"loss": 1.5322,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.16,
|
20 |
+
"eval_accuracy": 0.6822207084468664,
|
21 |
+
"eval_f1": 0.6711737667050809,
|
22 |
+
"eval_loss": 1.1796199083328247,
|
23 |
+
"eval_precision": 0.6833120550639381,
|
24 |
+
"eval_recall": 0.6822207084468664,
|
25 |
+
"eval_runtime": 134.8614,
|
26 |
+
"eval_samples_per_second": 108.852,
|
27 |
+
"eval_steps_per_second": 0.853,
|
28 |
+
"step": 500
|
29 |
+
}
|
30 |
+
],
|
31 |
+
"logging_steps": 500,
|
32 |
+
"max_steps": 9375,
|
33 |
+
"num_input_tokens_seen": 0,
|
34 |
+
"num_train_epochs": 3,
|
35 |
+
"save_steps": 500,
|
36 |
+
"stateful_callbacks": {
|
37 |
+
"TrainerControl": {
|
38 |
+
"args": {
|
39 |
+
"should_epoch_stop": false,
|
40 |
+
"should_evaluate": false,
|
41 |
+
"should_log": false,
|
42 |
+
"should_save": true,
|
43 |
+
"should_training_stop": false
|
44 |
+
},
|
45 |
+
"attributes": {}
|
46 |
+
}
|
47 |
+
},
|
48 |
+
"total_flos": 2119591772160000.0,
|
49 |
+
"train_batch_size": 32,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80840a874d0517d96566f685f49eddb6929ee834dcb1aae19a32a27f7e050d80
|
3 |
+
size 5240
|