Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-716/model.safetensors +1 -1
- run-1/checkpoint-716/optimizer.pt +1 -1
- run-1/checkpoint-716/rng_state.pth +2 -2
- run-1/checkpoint-716/scheduler.pt +1 -1
- run-1/checkpoint-716/training_args.bin +1 -1
- run-2/checkpoint-179/config.json +25 -0
- run-2/checkpoint-179/model.safetensors +3 -0
- run-2/checkpoint-179/optimizer.pt +3 -0
- run-2/checkpoint-179/rng_state.pth +3 -0
- run-2/checkpoint-179/scheduler.pt +3 -0
- run-2/checkpoint-179/special_tokens_map.json +7 -0
- run-2/checkpoint-179/tokenizer_config.json +57 -0
- run-2/checkpoint-179/trainer_state.json +35 -0
- run-2/checkpoint-179/training_args.bin +3 -0
- run-2/checkpoint-179/vocab.txt +0 -0
- runs/Mar09_20-46-55_12ef847df42e/events.out.tfevents.1710018092.12ef847df42e.11821.5 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2821aed8ad53a1b4125cce904f99586c69649435ced6b40b75870d96cf717833
|
| 3 |
size 267832560
|
run-1/checkpoint-716/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a786a267e3d420ca32cfb33e30e25ee6d6c786a51a341f824db9b545f95049
|
| 3 |
size 267832560
|
run-1/checkpoint-716/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535727290
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73e78c5b3308f8aa3cf93c87911488ccb466ca6609cbf41f3b37ad35602548ea
|
| 3 |
size 535727290
|
run-1/checkpoint-716/rng_state.pth
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:ae3da6582620bcfe156dce31519e10c6f672ba3ba51a71ef28eb294e691b2530
|
| 3 |
+
size 14244
|
run-1/checkpoint-716/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44d89e311ccded1d69c6bf810a821968678e0606577aa7cde55f63cb8e4b2bb6
|
| 3 |
size 1064
|
run-1/checkpoint-716/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb08b78a879b2a9b7abbbaf6e8ab5cc5cddbc616d40fcf027dd248408bd13c4e
|
| 3 |
size 4920
|
run-2/checkpoint-179/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": "4.38.2",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
run-2/checkpoint-179/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2821aed8ad53a1b4125cce904f99586c69649435ced6b40b75870d96cf717833
|
| 3 |
+
size 267832560
|
run-2/checkpoint-179/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7802637dc0863cbbdcb8e6eb9f7878bf9a179dcec43f03da926895a7ad6b201a
|
| 3 |
+
size 535727290
|
run-2/checkpoint-179/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15bd7eab532ffea089b3ecd205042dfdc9bbc5a043c59135bae94a6fd9442f81
|
| 3 |
+
size 14244
|
run-2/checkpoint-179/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f210aa56319def83ddcbfad1ac50b2a99c668fa00db8ad6c56ca12b010802e3
|
| 3 |
+
size 1064
|
run-2/checkpoint-179/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-2/checkpoint-179/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-2/checkpoint-179/trainer_state.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5979160666465759,
|
| 3 |
+
"best_model_checkpoint": "./results/run-2/checkpoint-179",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 179,
|
| 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": 0.6590277777777779,
|
| 14 |
+
"eval_loss": 0.5979160666465759,
|
| 15 |
+
"eval_runtime": 5.582,
|
| 16 |
+
"eval_samples_per_second": 171.087,
|
| 17 |
+
"eval_steps_per_second": 21.498,
|
| 18 |
+
"step": 179
|
| 19 |
+
}
|
| 20 |
+
],
|
| 21 |
+
"logging_steps": 500,
|
| 22 |
+
"max_steps": 358,
|
| 23 |
+
"num_input_tokens_seen": 0,
|
| 24 |
+
"num_train_epochs": 2,
|
| 25 |
+
"save_steps": 500,
|
| 26 |
+
"total_flos": 0,
|
| 27 |
+
"train_batch_size": 16,
|
| 28 |
+
"trial_name": null,
|
| 29 |
+
"trial_params": {
|
| 30 |
+
"learning_rate": 6.581247532366931e-05,
|
| 31 |
+
"num_train_epochs": 2,
|
| 32 |
+
"per_device_train_batch_size": 16,
|
| 33 |
+
"seed": 16
|
| 34 |
+
}
|
| 35 |
+
}
|
run-2/checkpoint-179/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0c633ed7e3612a5e5d297d29173201510ab737bc2800b9f5e33be1dfb865b9d
|
| 3 |
+
size 4920
|
run-2/checkpoint-179/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/Mar09_20-46-55_12ef847df42e/events.out.tfevents.1710018092.12ef847df42e.11821.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64d7fe889bf1beccc4c86568ee201c86e288fec6cc75917af7f179fcc2bda2b
|
| 3 |
+
size 5439
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0c633ed7e3612a5e5d297d29173201510ab737bc2800b9f5e33be1dfb865b9d
|
| 3 |
size 4920
|