Instructions to use CarmelKron/ADV_DL_Project with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CarmelKron/ADV_DL_Project with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CarmelKron/ADV_DL_Project", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload best model from trial 9
Browse files- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/added_tokens.json +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/config.json +49 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/model.safetensors +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/optimizer.pt +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/rng_state.pth +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/scheduler.pt +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/special_tokens_map.json +15 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/spm.model +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/tokenizer.json +0 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/tokenizer_config.json +59 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/trainer_state.json +423 -0
- HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/training_args.bin +3 -0
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"id2label": {
|
| 10 |
+
"0": "LABEL_0",
|
| 11 |
+
"1": "LABEL_1",
|
| 12 |
+
"2": "LABEL_2",
|
| 13 |
+
"3": "LABEL_3",
|
| 14 |
+
"4": "LABEL_4"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3,
|
| 23 |
+
"LABEL_4": 4
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-07,
|
| 26 |
+
"legacy": true,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"max_relative_positions": -1,
|
| 29 |
+
"model_type": "deberta-v2",
|
| 30 |
+
"norm_rel_ebd": "layer_norm",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"pooler_dropout": 0,
|
| 35 |
+
"pooler_hidden_act": "gelu",
|
| 36 |
+
"pooler_hidden_size": 768,
|
| 37 |
+
"pos_att_type": [
|
| 38 |
+
"p2c",
|
| 39 |
+
"c2p"
|
| 40 |
+
],
|
| 41 |
+
"position_biased_input": false,
|
| 42 |
+
"position_buckets": 256,
|
| 43 |
+
"relative_attention": true,
|
| 44 |
+
"share_att_key": true,
|
| 45 |
+
"torch_dtype": "float32",
|
| 46 |
+
"transformers_version": "4.55.2",
|
| 47 |
+
"type_vocab_size": 0,
|
| 48 |
+
"vocab_size": 128100
|
| 49 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67e32a6a03fdb80f713fc15cb51d2db0d764cc25d57db79d95b6aa2091675852
|
| 3 |
+
size 737728508
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c2f3844d7fe40fae306e56ab67f811aa668944dc47b3de9e8355a7706f78d7b
|
| 3 |
+
size 1475580107
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dfac113333823e463ec10796d3ce1cab53d91d97dbdf916b7c2b3184e1dc506
|
| 3 |
+
size 14645
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1ed1a0350cda9da08cc81d5abe0a87214c6b338934584357ddeebc6fd90b5c8
|
| 3 |
+
size 1465
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/trainer_state.json
ADDED
|
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": 0.8500971817298348,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 9785,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 5.558112144470215,
|
| 15 |
+
"learning_rate": 8.417332810177389e-06,
|
| 16 |
+
"loss": 1.4193,
|
| 17 |
+
"step": 515
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_accuracy": 0.5702137998056366,
|
| 22 |
+
"eval_f1": 0.5692306154344411,
|
| 23 |
+
"eval_loss": 1.2191261053085327,
|
| 24 |
+
"eval_precision": 0.5706739549144109,
|
| 25 |
+
"eval_recall": 0.5702137998056366,
|
| 26 |
+
"eval_roc_auc": NaN,
|
| 27 |
+
"eval_runtime": 37.8297,
|
| 28 |
+
"eval_samples_per_second": 217.607,
|
| 29 |
+
"eval_steps_per_second": 13.614,
|
| 30 |
+
"step": 515
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"grad_norm": 8.232677459716797,
|
| 35 |
+
"learning_rate": 8.291531978580723e-06,
|
| 36 |
+
"loss": 1.1175,
|
| 37 |
+
"step": 1030
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.0,
|
| 41 |
+
"eval_accuracy": 0.7031098153547133,
|
| 42 |
+
"eval_f1": 0.7007655946510231,
|
| 43 |
+
"eval_loss": 1.0411858558654785,
|
| 44 |
+
"eval_precision": 0.7064267169663552,
|
| 45 |
+
"eval_recall": 0.7031098153547133,
|
| 46 |
+
"eval_roc_auc": NaN,
|
| 47 |
+
"eval_runtime": 37.7796,
|
| 48 |
+
"eval_samples_per_second": 217.895,
|
| 49 |
+
"eval_steps_per_second": 13.632,
|
| 50 |
+
"step": 1030
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"grad_norm": 10.03100872039795,
|
| 55 |
+
"learning_rate": 8.062218137227657e-06,
|
| 56 |
+
"loss": 0.9696,
|
| 57 |
+
"step": 1545
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.0,
|
| 61 |
+
"eval_accuracy": 0.7546161321671526,
|
| 62 |
+
"eval_f1": 0.7530982932532094,
|
| 63 |
+
"eval_loss": 0.975301206111908,
|
| 64 |
+
"eval_precision": 0.760626168723142,
|
| 65 |
+
"eval_recall": 0.7546161321671526,
|
| 66 |
+
"eval_roc_auc": NaN,
|
| 67 |
+
"eval_runtime": 37.7955,
|
| 68 |
+
"eval_samples_per_second": 217.804,
|
| 69 |
+
"eval_steps_per_second": 13.626,
|
| 70 |
+
"step": 1545
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.0,
|
| 74 |
+
"grad_norm": 7.281851291656494,
|
| 75 |
+
"learning_rate": 7.735222708187771e-06,
|
| 76 |
+
"loss": 0.8916,
|
| 77 |
+
"step": 2060
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.0,
|
| 81 |
+
"eval_accuracy": 0.8002915451895044,
|
| 82 |
+
"eval_f1": 0.8002336100384237,
|
| 83 |
+
"eval_loss": 0.906338632106781,
|
| 84 |
+
"eval_precision": 0.8029534938186172,
|
| 85 |
+
"eval_recall": 0.8002915451895044,
|
| 86 |
+
"eval_roc_auc": NaN,
|
| 87 |
+
"eval_runtime": 37.7477,
|
| 88 |
+
"eval_samples_per_second": 218.079,
|
| 89 |
+
"eval_steps_per_second": 13.643,
|
| 90 |
+
"step": 2060
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.0,
|
| 94 |
+
"grad_norm": 7.478278160095215,
|
| 95 |
+
"learning_rate": 7.318861143988071e-06,
|
| 96 |
+
"loss": 0.8413,
|
| 97 |
+
"step": 2575
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 5.0,
|
| 101 |
+
"eval_accuracy": 0.7971331389698737,
|
| 102 |
+
"eval_f1": 0.7966057944543083,
|
| 103 |
+
"eval_loss": 0.9239436984062195,
|
| 104 |
+
"eval_precision": 0.8047453572692237,
|
| 105 |
+
"eval_recall": 0.7971331389698737,
|
| 106 |
+
"eval_roc_auc": NaN,
|
| 107 |
+
"eval_runtime": 37.8001,
|
| 108 |
+
"eval_samples_per_second": 217.777,
|
| 109 |
+
"eval_steps_per_second": 13.624,
|
| 110 |
+
"step": 2575
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.0,
|
| 114 |
+
"grad_norm": 9.907360076904297,
|
| 115 |
+
"learning_rate": 6.823721466703781e-06,
|
| 116 |
+
"loss": 0.8034,
|
| 117 |
+
"step": 3090
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.0,
|
| 121 |
+
"eval_accuracy": 0.831754130223518,
|
| 122 |
+
"eval_f1": 0.8322278056419339,
|
| 123 |
+
"eval_loss": 0.8634356260299683,
|
| 124 |
+
"eval_precision": 0.8349314594918416,
|
| 125 |
+
"eval_recall": 0.831754130223518,
|
| 126 |
+
"eval_roc_auc": NaN,
|
| 127 |
+
"eval_runtime": 37.9076,
|
| 128 |
+
"eval_samples_per_second": 217.16,
|
| 129 |
+
"eval_steps_per_second": 13.586,
|
| 130 |
+
"step": 3090
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"grad_norm": 6.024265289306641,
|
| 135 |
+
"learning_rate": 6.262395015892101e-06,
|
| 136 |
+
"loss": 0.7725,
|
| 137 |
+
"step": 3605
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 7.0,
|
| 141 |
+
"eval_accuracy": 0.8304178814382897,
|
| 142 |
+
"eval_f1": 0.8303419878734274,
|
| 143 |
+
"eval_loss": 0.8670573234558105,
|
| 144 |
+
"eval_precision": 0.8342245038322631,
|
| 145 |
+
"eval_recall": 0.8304178814382897,
|
| 146 |
+
"eval_roc_auc": NaN,
|
| 147 |
+
"eval_runtime": 37.7741,
|
| 148 |
+
"eval_samples_per_second": 217.927,
|
| 149 |
+
"eval_steps_per_second": 13.634,
|
| 150 |
+
"step": 3605
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"grad_norm": 10.682536125183105,
|
| 155 |
+
"learning_rate": 5.649156252415012e-06,
|
| 156 |
+
"loss": 0.7453,
|
| 157 |
+
"step": 4120
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 8.0,
|
| 161 |
+
"eval_accuracy": 0.8213070942662779,
|
| 162 |
+
"eval_f1": 0.8212500982444025,
|
| 163 |
+
"eval_loss": 0.9185604453086853,
|
| 164 |
+
"eval_precision": 0.8271132923055834,
|
| 165 |
+
"eval_recall": 0.8213070942662779,
|
| 166 |
+
"eval_roc_auc": NaN,
|
| 167 |
+
"eval_runtime": 37.778,
|
| 168 |
+
"eval_samples_per_second": 217.904,
|
| 169 |
+
"eval_steps_per_second": 13.632,
|
| 170 |
+
"step": 4120
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 9.0,
|
| 174 |
+
"grad_norm": 6.34318733215332,
|
| 175 |
+
"learning_rate": 4.999599760699531e-06,
|
| 176 |
+
"loss": 0.7278,
|
| 177 |
+
"step": 4635
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 9.0,
|
| 181 |
+
"eval_accuracy": 0.815354713313897,
|
| 182 |
+
"eval_f1": 0.8140894326498518,
|
| 183 |
+
"eval_loss": 0.9269745945930481,
|
| 184 |
+
"eval_precision": 0.8260331839377416,
|
| 185 |
+
"eval_recall": 0.815354713313897,
|
| 186 |
+
"eval_roc_auc": NaN,
|
| 187 |
+
"eval_runtime": 37.8377,
|
| 188 |
+
"eval_samples_per_second": 217.561,
|
| 189 |
+
"eval_steps_per_second": 13.611,
|
| 190 |
+
"step": 4635
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.0,
|
| 194 |
+
"grad_norm": 3.017087697982788,
|
| 195 |
+
"learning_rate": 4.33024368042219e-06,
|
| 196 |
+
"loss": 0.7096,
|
| 197 |
+
"step": 5150
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 10.0,
|
| 201 |
+
"eval_accuracy": 0.8452380952380952,
|
| 202 |
+
"eval_f1": 0.8447816644269829,
|
| 203 |
+
"eval_loss": 0.8667939305305481,
|
| 204 |
+
"eval_precision": 0.8477436053623723,
|
| 205 |
+
"eval_recall": 0.8452380952380952,
|
| 206 |
+
"eval_roc_auc": NaN,
|
| 207 |
+
"eval_runtime": 37.8683,
|
| 208 |
+
"eval_samples_per_second": 217.385,
|
| 209 |
+
"eval_steps_per_second": 13.6,
|
| 210 |
+
"step": 5150
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.0,
|
| 214 |
+
"grad_norm": 3.7269556522369385,
|
| 215 |
+
"learning_rate": 3.658109652299957e-06,
|
| 216 |
+
"loss": 0.6984,
|
| 217 |
+
"step": 5665
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 11.0,
|
| 221 |
+
"eval_accuracy": 0.841958211856171,
|
| 222 |
+
"eval_f1": 0.8415476710175299,
|
| 223 |
+
"eval_loss": 0.8721299171447754,
|
| 224 |
+
"eval_precision": 0.8449623645824317,
|
| 225 |
+
"eval_recall": 0.841958211856171,
|
| 226 |
+
"eval_roc_auc": NaN,
|
| 227 |
+
"eval_runtime": 37.9157,
|
| 228 |
+
"eval_samples_per_second": 217.113,
|
| 229 |
+
"eval_steps_per_second": 13.583,
|
| 230 |
+
"step": 5665
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 12.0,
|
| 234 |
+
"grad_norm": 3.7326505184173584,
|
| 235 |
+
"learning_rate": 3.0002899599132e-06,
|
| 236 |
+
"loss": 0.6871,
|
| 237 |
+
"step": 6180
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.0,
|
| 241 |
+
"eval_accuracy": 0.847181729834791,
|
| 242 |
+
"eval_f1": 0.8466106694757459,
|
| 243 |
+
"eval_loss": 0.8655446171760559,
|
| 244 |
+
"eval_precision": 0.8495189904538702,
|
| 245 |
+
"eval_recall": 0.847181729834791,
|
| 246 |
+
"eval_roc_auc": NaN,
|
| 247 |
+
"eval_runtime": 37.7619,
|
| 248 |
+
"eval_samples_per_second": 217.997,
|
| 249 |
+
"eval_steps_per_second": 13.638,
|
| 250 |
+
"step": 6180
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 13.0,
|
| 254 |
+
"grad_norm": 6.217965602874756,
|
| 255 |
+
"learning_rate": 2.373512875089546e-06,
|
| 256 |
+
"loss": 0.6775,
|
| 257 |
+
"step": 6695
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 13.0,
|
| 261 |
+
"eval_accuracy": 0.8436588921282799,
|
| 262 |
+
"eval_f1": 0.843049851632682,
|
| 263 |
+
"eval_loss": 0.8765755295753479,
|
| 264 |
+
"eval_precision": 0.8461543882148126,
|
| 265 |
+
"eval_recall": 0.8436588921282799,
|
| 266 |
+
"eval_roc_auc": NaN,
|
| 267 |
+
"eval_runtime": 37.8117,
|
| 268 |
+
"eval_samples_per_second": 217.71,
|
| 269 |
+
"eval_steps_per_second": 13.62,
|
| 270 |
+
"step": 6695
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 14.0,
|
| 274 |
+
"grad_norm": 7.1924591064453125,
|
| 275 |
+
"learning_rate": 1.7937172600607028e-06,
|
| 276 |
+
"loss": 0.6692,
|
| 277 |
+
"step": 7210
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 14.0,
|
| 281 |
+
"eval_accuracy": 0.8456025267249757,
|
| 282 |
+
"eval_f1": 0.8447769322123251,
|
| 283 |
+
"eval_loss": 0.8750342130661011,
|
| 284 |
+
"eval_precision": 0.8478356896102327,
|
| 285 |
+
"eval_recall": 0.8456025267249757,
|
| 286 |
+
"eval_roc_auc": NaN,
|
| 287 |
+
"eval_runtime": 37.7763,
|
| 288 |
+
"eval_samples_per_second": 217.915,
|
| 289 |
+
"eval_steps_per_second": 13.633,
|
| 290 |
+
"step": 7210
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 15.0,
|
| 294 |
+
"grad_norm": 5.0120110511779785,
|
| 295 |
+
"learning_rate": 1.2756472442057663e-06,
|
| 296 |
+
"loss": 0.663,
|
| 297 |
+
"step": 7725
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 15.0,
|
| 301 |
+
"eval_accuracy": 0.8453595724003887,
|
| 302 |
+
"eval_f1": 0.8446776063557639,
|
| 303 |
+
"eval_loss": 0.8758830428123474,
|
| 304 |
+
"eval_precision": 0.8477575898104898,
|
| 305 |
+
"eval_recall": 0.8453595724003887,
|
| 306 |
+
"eval_roc_auc": NaN,
|
| 307 |
+
"eval_runtime": 37.8196,
|
| 308 |
+
"eval_samples_per_second": 217.665,
|
| 309 |
+
"eval_steps_per_second": 13.617,
|
| 310 |
+
"step": 7725
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 16.0,
|
| 314 |
+
"grad_norm": 11.924120903015137,
|
| 315 |
+
"learning_rate": 8.324772827003197e-07,
|
| 316 |
+
"loss": 0.6565,
|
| 317 |
+
"step": 8240
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 16.0,
|
| 321 |
+
"eval_accuracy": 0.8486394557823129,
|
| 322 |
+
"eval_f1": 0.8480349809458595,
|
| 323 |
+
"eval_loss": 0.8735076189041138,
|
| 324 |
+
"eval_precision": 0.8500301298006432,
|
| 325 |
+
"eval_recall": 0.8486394557823129,
|
| 326 |
+
"eval_roc_auc": NaN,
|
| 327 |
+
"eval_runtime": 37.7497,
|
| 328 |
+
"eval_samples_per_second": 218.068,
|
| 329 |
+
"eval_steps_per_second": 13.642,
|
| 330 |
+
"step": 8240
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.0,
|
| 334 |
+
"grad_norm": 4.6612348556518555,
|
| 335 |
+
"learning_rate": 4.7547713178258506e-07,
|
| 336 |
+
"loss": 0.657,
|
| 337 |
+
"step": 8755
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 17.0,
|
| 341 |
+
"eval_accuracy": 0.8459669582118562,
|
| 342 |
+
"eval_f1": 0.8452751227681518,
|
| 343 |
+
"eval_loss": 0.8765075206756592,
|
| 344 |
+
"eval_precision": 0.8475525311833207,
|
| 345 |
+
"eval_recall": 0.8459669582118562,
|
| 346 |
+
"eval_roc_auc": NaN,
|
| 347 |
+
"eval_runtime": 37.8329,
|
| 348 |
+
"eval_samples_per_second": 217.588,
|
| 349 |
+
"eval_steps_per_second": 13.612,
|
| 350 |
+
"step": 8755
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 18.0,
|
| 354 |
+
"grad_norm": 7.9603190422058105,
|
| 355 |
+
"learning_rate": 2.1372526027338365e-07,
|
| 356 |
+
"loss": 0.6519,
|
| 357 |
+
"step": 9270
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.0,
|
| 361 |
+
"eval_accuracy": 0.8436588921282799,
|
| 362 |
+
"eval_f1": 0.8428520068385834,
|
| 363 |
+
"eval_loss": 0.8832859396934509,
|
| 364 |
+
"eval_precision": 0.845684783693064,
|
| 365 |
+
"eval_recall": 0.8436588921282799,
|
| 366 |
+
"eval_roc_auc": NaN,
|
| 367 |
+
"eval_runtime": 37.8928,
|
| 368 |
+
"eval_samples_per_second": 217.244,
|
| 369 |
+
"eval_steps_per_second": 13.591,
|
| 370 |
+
"step": 9270
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 19.0,
|
| 374 |
+
"grad_norm": 9.929984092712402,
|
| 375 |
+
"learning_rate": 5.3877985258798145e-08,
|
| 376 |
+
"loss": 0.6526,
|
| 377 |
+
"step": 9785
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 19.0,
|
| 381 |
+
"eval_accuracy": 0.8500971817298348,
|
| 382 |
+
"eval_f1": 0.8493918056264033,
|
| 383 |
+
"eval_loss": 0.8758156895637512,
|
| 384 |
+
"eval_precision": 0.85158355523026,
|
| 385 |
+
"eval_recall": 0.8500971817298348,
|
| 386 |
+
"eval_roc_auc": NaN,
|
| 387 |
+
"eval_runtime": 37.8551,
|
| 388 |
+
"eval_samples_per_second": 217.461,
|
| 389 |
+
"eval_steps_per_second": 13.604,
|
| 390 |
+
"step": 9785
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"logging_steps": 500,
|
| 394 |
+
"max_steps": 10300,
|
| 395 |
+
"num_input_tokens_seen": 0,
|
| 396 |
+
"num_train_epochs": 20,
|
| 397 |
+
"save_steps": 500,
|
| 398 |
+
"stateful_callbacks": {
|
| 399 |
+
"EarlyStoppingCallback": {
|
| 400 |
+
"args": {
|
| 401 |
+
"early_stopping_patience": 4,
|
| 402 |
+
"early_stopping_threshold": 0.0
|
| 403 |
+
},
|
| 404 |
+
"attributes": {
|
| 405 |
+
"early_stopping_patience_counter": 0
|
| 406 |
+
}
|
| 407 |
+
},
|
| 408 |
+
"TrainerControl": {
|
| 409 |
+
"args": {
|
| 410 |
+
"should_epoch_stop": false,
|
| 411 |
+
"should_evaluate": false,
|
| 412 |
+
"should_log": false,
|
| 413 |
+
"should_save": true,
|
| 414 |
+
"should_training_stop": false
|
| 415 |
+
},
|
| 416 |
+
"attributes": {}
|
| 417 |
+
}
|
| 418 |
+
},
|
| 419 |
+
"total_flos": 8.23015419025536e+16,
|
| 420 |
+
"train_batch_size": 16,
|
| 421 |
+
"trial_name": null,
|
| 422 |
+
"trial_params": null
|
| 423 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_9/checkpoint-9785/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f8ab3c0643c0abd6a396c57cae5b77386927158338087a0321d2d239020ba7
|
| 3 |
+
size 5777
|