Upload 6 files
Browse files- config.json +33 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +38 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"adapters": {
|
| 4 |
+
"adapters": {},
|
| 5 |
+
"config_map": {},
|
| 6 |
+
"fusion_config_map": {},
|
| 7 |
+
"fusions": {}
|
| 8 |
+
},
|
| 9 |
+
"architectures": [
|
| 10 |
+
"BertForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"hidden_act": "gelu",
|
| 16 |
+
"hidden_dropout_prob": 0.1,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.17.0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 30522
|
| 33 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11e81b7b15d1770b5a67be004c0628636b460bc76e433b9c31d0d9c6a6fa22d6
|
| 3 |
+
size 14657
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd0592c4add983bc4eb7a950d9caad1e9f61c3447737fa0fbd5baa44ed701456
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e74c8ceacf53818f8f5fab954954d21588684ae757b03ec33700c68a21150dd
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 48,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": {
|
| 13 |
+
"accuracy": 0.8645833333333334
|
| 14 |
+
},
|
| 15 |
+
"eval_loss": 0.3641645908355713,
|
| 16 |
+
"eval_runtime": 1.6644,
|
| 17 |
+
"eval_samples_per_second": 57.68,
|
| 18 |
+
"eval_steps_per_second": 3.605,
|
| 19 |
+
"step": 24
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": {
|
| 24 |
+
"accuracy": 0.7916666666666666
|
| 25 |
+
},
|
| 26 |
+
"eval_loss": 0.5475189685821533,
|
| 27 |
+
"eval_runtime": 1.6598,
|
| 28 |
+
"eval_samples_per_second": 57.838,
|
| 29 |
+
"eval_steps_per_second": 3.615,
|
| 30 |
+
"step": 48
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"max_steps": 240,
|
| 34 |
+
"num_train_epochs": 10,
|
| 35 |
+
"total_flos": 202069290516480.0,
|
| 36 |
+
"trial_name": null,
|
| 37 |
+
"trial_params": null
|
| 38 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29a76027b5fe39b33ec7425a28b666ebbd153f5fb6c4e92a5b391b488b45afad
|
| 3 |
+
size 2991
|