Training in progress, epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-4l35az4b/checkpoint-84/config.json +36 -0
- run-4l35az4b/checkpoint-84/model.safetensors +3 -0
- run-4l35az4b/checkpoint-84/optimizer.pt +3 -0
- run-4l35az4b/checkpoint-84/rng_state.pth +3 -0
- run-4l35az4b/checkpoint-84/scheduler.pt +3 -0
- run-4l35az4b/checkpoint-84/special_tokens_map.json +7 -0
- run-4l35az4b/checkpoint-84/tokenizer.json +0 -0
- run-4l35az4b/checkpoint-84/tokenizer_config.json +56 -0
- run-4l35az4b/checkpoint-84/trainer_state.json +51 -0
- run-4l35az4b/checkpoint-84/training_args.bin +3 -0
- run-4l35az4b/checkpoint-84/vocab.txt +0 -0
- run-sgvshopq/checkpoint-334/config.json +36 -0
- run-sgvshopq/checkpoint-334/model.safetensors +3 -0
- run-sgvshopq/checkpoint-334/optimizer.pt +3 -0
- run-sgvshopq/checkpoint-334/rng_state.pth +3 -0
- run-sgvshopq/checkpoint-334/scheduler.pt +3 -0
- run-sgvshopq/checkpoint-334/special_tokens_map.json +7 -0
- run-sgvshopq/checkpoint-334/tokenizer.json +0 -0
- run-sgvshopq/checkpoint-334/tokenizer_config.json +56 -0
- run-sgvshopq/checkpoint-334/trainer_state.json +60 -0
- run-sgvshopq/checkpoint-334/training_args.bin +3 -0
- run-sgvshopq/checkpoint-334/vocab.txt +0 -0
- run-sgvshopq/checkpoint-501/config.json +36 -0
- run-sgvshopq/checkpoint-501/model.safetensors +3 -0
- run-sgvshopq/checkpoint-501/optimizer.pt +3 -0
- run-sgvshopq/checkpoint-501/rng_state.pth +3 -0
- run-sgvshopq/checkpoint-501/scheduler.pt +3 -0
- run-sgvshopq/checkpoint-501/special_tokens_map.json +7 -0
- run-sgvshopq/checkpoint-501/tokenizer.json +0 -0
- run-sgvshopq/checkpoint-501/tokenizer_config.json +56 -0
- run-sgvshopq/checkpoint-501/trainer_state.json +76 -0
- run-sgvshopq/checkpoint-501/training_args.bin +3 -0
- run-sgvshopq/checkpoint-501/vocab.txt +0 -0
- run-sgvshopq/checkpoint-668/config.json +36 -0
- run-sgvshopq/checkpoint-668/model.safetensors +3 -0
- run-sgvshopq/checkpoint-668/optimizer.pt +3 -0
- run-sgvshopq/checkpoint-668/rng_state.pth +3 -0
- run-sgvshopq/checkpoint-668/scheduler.pt +3 -0
- run-sgvshopq/checkpoint-668/special_tokens_map.json +7 -0
- run-sgvshopq/checkpoint-668/tokenizer.json +0 -0
- run-sgvshopq/checkpoint-668/tokenizer_config.json +56 -0
- run-sgvshopq/checkpoint-668/trainer_state.json +85 -0
- run-sgvshopq/checkpoint-668/training_args.bin +3 -0
- run-sgvshopq/checkpoint-668/vocab.txt +0 -0
- run-sgvshopq/checkpoint-835/config.json +36 -0
- run-sgvshopq/checkpoint-835/model.safetensors +3 -0
- run-sgvshopq/checkpoint-835/optimizer.pt +3 -0
- run-sgvshopq/checkpoint-835/rng_state.pth +3 -0
- run-sgvshopq/checkpoint-835/scheduler.pt +3 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267838720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b674f25ded57ebf21f027e819429e0ebd48f4f0f60757952bc5281c6055705f8
|
| 3 |
size 267838720
|
run-4l35az4b/checkpoint-84/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Business",
|
| 12 |
+
"1": "Personal",
|
| 13 |
+
"2": "Government",
|
| 14 |
+
"3": "Others"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Business": 0,
|
| 19 |
+
"Government": 2,
|
| 20 |
+
"Others": 3,
|
| 21 |
+
"Personal": 1
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
run-4l35az4b/checkpoint-84/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b674f25ded57ebf21f027e819429e0ebd48f4f0f60757952bc5281c6055705f8
|
| 3 |
+
size 267838720
|
run-4l35az4b/checkpoint-84/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3ba7ff386a4c348e368ddbc5d297cddd08ff82e946f56172ed2a27f7c5e6e3b
|
| 3 |
+
size 535739578
|
run-4l35az4b/checkpoint-84/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afff510158e72710fbb8fac16812c79c500369dfcefe8df73832191bdab380f4
|
| 3 |
+
size 14244
|
run-4l35az4b/checkpoint-84/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a74cd353d999cd08709c613f025b00438fece76a26541db2f55964d5846996e
|
| 3 |
+
size 1064
|
run-4l35az4b/checkpoint-84/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-4l35az4b/checkpoint-84/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-4l35az4b/checkpoint-84/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
run-4l35az4b/checkpoint-84/trainer_state.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 84,
|
| 3 |
+
"best_metric": 0.9333333333333333,
|
| 4 |
+
"best_model_checkpoint": "website_prediction_model/run-4l35az4b/checkpoint-84",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 84,
|
| 8 |
+
"is_hyper_param_search": true,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.9333333333333333,
|
| 15 |
+
"eval_loss": 0.306448757648468,
|
| 16 |
+
"eval_runtime": 0.7576,
|
| 17 |
+
"eval_samples_per_second": 98.996,
|
| 18 |
+
"eval_steps_per_second": 6.6,
|
| 19 |
+
"step": 84
|
| 20 |
+
}
|
| 21 |
+
],
|
| 22 |
+
"logging_steps": 500,
|
| 23 |
+
"max_steps": 168,
|
| 24 |
+
"num_input_tokens_seen": 0,
|
| 25 |
+
"num_train_epochs": 2,
|
| 26 |
+
"save_steps": 500,
|
| 27 |
+
"stateful_callbacks": {
|
| 28 |
+
"TrainerControl": {
|
| 29 |
+
"args": {
|
| 30 |
+
"should_epoch_stop": false,
|
| 31 |
+
"should_evaluate": false,
|
| 32 |
+
"should_log": false,
|
| 33 |
+
"should_save": true,
|
| 34 |
+
"should_training_stop": false
|
| 35 |
+
},
|
| 36 |
+
"attributes": {}
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"total_flos": 0,
|
| 40 |
+
"train_batch_size": 8,
|
| 41 |
+
"trial_name": null,
|
| 42 |
+
"trial_params": {
|
| 43 |
+
"_wandb": {},
|
| 44 |
+
"assignments": {},
|
| 45 |
+
"learning_rate": 7.418475718661359e-05,
|
| 46 |
+
"metric": "eval/loss",
|
| 47 |
+
"num_train_epochs": 2,
|
| 48 |
+
"per_device_train_batch_size": 8,
|
| 49 |
+
"seed": 9
|
| 50 |
+
}
|
| 51 |
+
}
|
run-4l35az4b/checkpoint-84/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57deca4086c25b751c8273099eb9f10148f808b8084f39c5f3ea1db5a0e64ef4
|
| 3 |
+
size 5304
|
run-4l35az4b/checkpoint-84/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-334/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Business",
|
| 12 |
+
"1": "Personal",
|
| 13 |
+
"2": "Government",
|
| 14 |
+
"3": "Others"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Business": 0,
|
| 19 |
+
"Government": 2,
|
| 20 |
+
"Others": 3,
|
| 21 |
+
"Personal": 1
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
run-sgvshopq/checkpoint-334/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78da642b0bca7cea970d4db5b9f8ea323ad4e6f64269662f195b2359b9e2223d
|
| 3 |
+
size 267838720
|
run-sgvshopq/checkpoint-334/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b31721ad3c5c97882f9aa8b8064e0c08556cabc813c738a84f302e0ca133f1f
|
| 3 |
+
size 535739578
|
run-sgvshopq/checkpoint-334/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea5bf3cc7eacb0ce1dfd362939b14040175a6f2da4db1bb31b28a961825f119
|
| 3 |
+
size 14244
|
run-sgvshopq/checkpoint-334/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e138f317e46eab7f35b83ff8c67f4bc63c5cbbe69b6fbfe312966d0e6d4e237d
|
| 3 |
+
size 1064
|
run-sgvshopq/checkpoint-334/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-sgvshopq/checkpoint-334/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-334/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
run-sgvshopq/checkpoint-334/trainer_state.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 167,
|
| 3 |
+
"best_metric": 0.9333333333333333,
|
| 4 |
+
"best_model_checkpoint": "website_prediction_model/run-sgvshopq/checkpoint-167",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 334,
|
| 8 |
+
"is_hyper_param_search": true,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.9333333333333333,
|
| 15 |
+
"eval_loss": 0.3241618275642395,
|
| 16 |
+
"eval_runtime": 0.7614,
|
| 17 |
+
"eval_samples_per_second": 98.503,
|
| 18 |
+
"eval_steps_per_second": 6.567,
|
| 19 |
+
"step": 167
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.92,
|
| 24 |
+
"eval_loss": 0.4100591540336609,
|
| 25 |
+
"eval_runtime": 0.7651,
|
| 26 |
+
"eval_samples_per_second": 98.031,
|
| 27 |
+
"eval_steps_per_second": 6.535,
|
| 28 |
+
"step": 334
|
| 29 |
+
}
|
| 30 |
+
],
|
| 31 |
+
"logging_steps": 500,
|
| 32 |
+
"max_steps": 835,
|
| 33 |
+
"num_input_tokens_seen": 0,
|
| 34 |
+
"num_train_epochs": 5,
|
| 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": 0,
|
| 49 |
+
"train_batch_size": 4,
|
| 50 |
+
"trial_name": null,
|
| 51 |
+
"trial_params": {
|
| 52 |
+
"_wandb": {},
|
| 53 |
+
"assignments": {},
|
| 54 |
+
"learning_rate": 5.207464397831743e-05,
|
| 55 |
+
"metric": "eval/loss",
|
| 56 |
+
"num_train_epochs": 5,
|
| 57 |
+
"per_device_train_batch_size": 4,
|
| 58 |
+
"seed": 2
|
| 59 |
+
}
|
| 60 |
+
}
|
run-sgvshopq/checkpoint-334/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7be1702138e1071acaefa1fe9267dc149c7295ba57326c5725d4b5bcc2e156f
|
| 3 |
+
size 5304
|
run-sgvshopq/checkpoint-334/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-501/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Business",
|
| 12 |
+
"1": "Personal",
|
| 13 |
+
"2": "Government",
|
| 14 |
+
"3": "Others"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Business": 0,
|
| 19 |
+
"Government": 2,
|
| 20 |
+
"Others": 3,
|
| 21 |
+
"Personal": 1
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
run-sgvshopq/checkpoint-501/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:848fa07a33ccaab6e1de29b83822abe447abb28355a02bebc8ab8956338c4a08
|
| 3 |
+
size 267838720
|
run-sgvshopq/checkpoint-501/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfb44e6a800719448cc82af03a576cdff7d0191ff504495b94c7efd2f8ae86b0
|
| 3 |
+
size 535739578
|
run-sgvshopq/checkpoint-501/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07b1a1a97fd1950b7b4ccea607f9951fc6e50f89c524264ee820319562f235dc
|
| 3 |
+
size 14244
|
run-sgvshopq/checkpoint-501/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a92831e2d40f7ed8789dabc7543e5cba513152b6289af5159011338de7332c75
|
| 3 |
+
size 1064
|
run-sgvshopq/checkpoint-501/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-sgvshopq/checkpoint-501/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-501/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
run-sgvshopq/checkpoint-501/trainer_state.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 501,
|
| 3 |
+
"best_metric": 0.96,
|
| 4 |
+
"best_model_checkpoint": "website_prediction_model/run-sgvshopq/checkpoint-501",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 501,
|
| 8 |
+
"is_hyper_param_search": true,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.9333333333333333,
|
| 15 |
+
"eval_loss": 0.3241618275642395,
|
| 16 |
+
"eval_runtime": 0.7614,
|
| 17 |
+
"eval_samples_per_second": 98.503,
|
| 18 |
+
"eval_steps_per_second": 6.567,
|
| 19 |
+
"step": 167
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.92,
|
| 24 |
+
"eval_loss": 0.4100591540336609,
|
| 25 |
+
"eval_runtime": 0.7651,
|
| 26 |
+
"eval_samples_per_second": 98.031,
|
| 27 |
+
"eval_steps_per_second": 6.535,
|
| 28 |
+
"step": 334
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.9940119760479043,
|
| 32 |
+
"grad_norm": 0.2577260136604309,
|
| 33 |
+
"learning_rate": 2.0199942947474583e-05,
|
| 34 |
+
"loss": 0.3069,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"eval_accuracy": 0.96,
|
| 40 |
+
"eval_loss": 0.2778964340686798,
|
| 41 |
+
"eval_runtime": 0.7752,
|
| 42 |
+
"eval_samples_per_second": 96.751,
|
| 43 |
+
"eval_steps_per_second": 6.45,
|
| 44 |
+
"step": 501
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"logging_steps": 500,
|
| 48 |
+
"max_steps": 835,
|
| 49 |
+
"num_input_tokens_seen": 0,
|
| 50 |
+
"num_train_epochs": 5,
|
| 51 |
+
"save_steps": 500,
|
| 52 |
+
"stateful_callbacks": {
|
| 53 |
+
"TrainerControl": {
|
| 54 |
+
"args": {
|
| 55 |
+
"should_epoch_stop": false,
|
| 56 |
+
"should_evaluate": false,
|
| 57 |
+
"should_log": false,
|
| 58 |
+
"should_save": true,
|
| 59 |
+
"should_training_stop": false
|
| 60 |
+
},
|
| 61 |
+
"attributes": {}
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"total_flos": 177491946576000.0,
|
| 65 |
+
"train_batch_size": 4,
|
| 66 |
+
"trial_name": null,
|
| 67 |
+
"trial_params": {
|
| 68 |
+
"_wandb": {},
|
| 69 |
+
"assignments": {},
|
| 70 |
+
"learning_rate": 5.207464397831743e-05,
|
| 71 |
+
"metric": "eval/loss",
|
| 72 |
+
"num_train_epochs": 5,
|
| 73 |
+
"per_device_train_batch_size": 4,
|
| 74 |
+
"seed": 2
|
| 75 |
+
}
|
| 76 |
+
}
|
run-sgvshopq/checkpoint-501/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7be1702138e1071acaefa1fe9267dc149c7295ba57326c5725d4b5bcc2e156f
|
| 3 |
+
size 5304
|
run-sgvshopq/checkpoint-501/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-668/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Business",
|
| 12 |
+
"1": "Personal",
|
| 13 |
+
"2": "Government",
|
| 14 |
+
"3": "Others"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Business": 0,
|
| 19 |
+
"Government": 2,
|
| 20 |
+
"Others": 3,
|
| 21 |
+
"Personal": 1
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
run-sgvshopq/checkpoint-668/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4be934c475c9d0915034e5fc6b4746e9a002598f945d2274dba8f2d36afe1f22
|
| 3 |
+
size 267838720
|
run-sgvshopq/checkpoint-668/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e52fa984e65d1c4a5b901efb7d4c017bb215bfb81174674e6f34b1a4667f89f
|
| 3 |
+
size 535739578
|
run-sgvshopq/checkpoint-668/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6392508246df30b38b20abcc6d85516cd245c093e6eccaf9004adfee7af3a286
|
| 3 |
+
size 14244
|
run-sgvshopq/checkpoint-668/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:213317b083a875c996999d790e761c65535bb3427ea55bb2227fa697fa7dbeed
|
| 3 |
+
size 1064
|
run-sgvshopq/checkpoint-668/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-sgvshopq/checkpoint-668/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-668/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
run-sgvshopq/checkpoint-668/trainer_state.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 501,
|
| 3 |
+
"best_metric": 0.96,
|
| 4 |
+
"best_model_checkpoint": "website_prediction_model/run-sgvshopq/checkpoint-501",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 668,
|
| 8 |
+
"is_hyper_param_search": true,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.9333333333333333,
|
| 15 |
+
"eval_loss": 0.3241618275642395,
|
| 16 |
+
"eval_runtime": 0.7614,
|
| 17 |
+
"eval_samples_per_second": 98.503,
|
| 18 |
+
"eval_steps_per_second": 6.567,
|
| 19 |
+
"step": 167
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.92,
|
| 24 |
+
"eval_loss": 0.4100591540336609,
|
| 25 |
+
"eval_runtime": 0.7651,
|
| 26 |
+
"eval_samples_per_second": 98.031,
|
| 27 |
+
"eval_steps_per_second": 6.535,
|
| 28 |
+
"step": 334
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.9940119760479043,
|
| 32 |
+
"grad_norm": 0.2577260136604309,
|
| 33 |
+
"learning_rate": 2.0199942947474583e-05,
|
| 34 |
+
"loss": 0.3069,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"eval_accuracy": 0.96,
|
| 40 |
+
"eval_loss": 0.2778964340686798,
|
| 41 |
+
"eval_runtime": 0.7752,
|
| 42 |
+
"eval_samples_per_second": 96.751,
|
| 43 |
+
"eval_steps_per_second": 6.45,
|
| 44 |
+
"step": 501
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.0,
|
| 48 |
+
"eval_accuracy": 0.96,
|
| 49 |
+
"eval_loss": 0.29343634843826294,
|
| 50 |
+
"eval_runtime": 0.7633,
|
| 51 |
+
"eval_samples_per_second": 98.253,
|
| 52 |
+
"eval_steps_per_second": 6.55,
|
| 53 |
+
"step": 668
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"logging_steps": 500,
|
| 57 |
+
"max_steps": 835,
|
| 58 |
+
"num_input_tokens_seen": 0,
|
| 59 |
+
"num_train_epochs": 5,
|
| 60 |
+
"save_steps": 500,
|
| 61 |
+
"stateful_callbacks": {
|
| 62 |
+
"TrainerControl": {
|
| 63 |
+
"args": {
|
| 64 |
+
"should_epoch_stop": false,
|
| 65 |
+
"should_evaluate": false,
|
| 66 |
+
"should_log": false,
|
| 67 |
+
"should_save": true,
|
| 68 |
+
"should_training_stop": false
|
| 69 |
+
},
|
| 70 |
+
"attributes": {}
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"total_flos": 177491946576000.0,
|
| 74 |
+
"train_batch_size": 4,
|
| 75 |
+
"trial_name": null,
|
| 76 |
+
"trial_params": {
|
| 77 |
+
"_wandb": {},
|
| 78 |
+
"assignments": {},
|
| 79 |
+
"learning_rate": 5.207464397831743e-05,
|
| 80 |
+
"metric": "eval/loss",
|
| 81 |
+
"num_train_epochs": 5,
|
| 82 |
+
"per_device_train_batch_size": 4,
|
| 83 |
+
"seed": 2
|
| 84 |
+
}
|
| 85 |
+
}
|
run-sgvshopq/checkpoint-668/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7be1702138e1071acaefa1fe9267dc149c7295ba57326c5725d4b5bcc2e156f
|
| 3 |
+
size 5304
|
run-sgvshopq/checkpoint-668/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-sgvshopq/checkpoint-835/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Business",
|
| 12 |
+
"1": "Personal",
|
| 13 |
+
"2": "Government",
|
| 14 |
+
"3": "Others"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Business": 0,
|
| 19 |
+
"Government": 2,
|
| 20 |
+
"Others": 3,
|
| 21 |
+
"Personal": 1
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
run-sgvshopq/checkpoint-835/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:770cdcc25e7c41338d1ae57aef6b47f00173c66f163135204703cca22882acbe
|
| 3 |
+
size 267838720
|
run-sgvshopq/checkpoint-835/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7fc92e2e3b6027e85527860250fc74708ba085e197491e2edf11607e7764a0c
|
| 3 |
+
size 535739578
|
run-sgvshopq/checkpoint-835/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d48495e05d8a325bfaa9655ac7bdce2386d4fadacf20d4c71b92958ba461c2c4
|
| 3 |
+
size 14244
|
run-sgvshopq/checkpoint-835/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:945ebaea3fe8bc90d8538817aa3bc81cf69ab02c6a5adf8a9bd61c8d29700ab9
|
| 3 |
+
size 1064
|