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 5
Browse files- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/added_tokens.json +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/config.json +49 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/model.safetensors +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/optimizer.pt +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/rng_state.pth +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/scheduler.pt +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/special_tokens_map.json +15 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/spm.model +3 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/tokenizer.json +0 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/tokenizer_config.json +59 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/trainer_state.json +243 -0
- HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/training_args.bin +3 -0
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/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_5/checkpoint-10290/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12e6c1bd20e52e15a9c2b21e86325cf757778967861b2739b26217c50e4f591f
|
| 3 |
+
size 737728508
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba3b1c3062f6c8dcdb394b5f7df4a475edc2d21c121c553625cf23c5bb460c82
|
| 3 |
+
size 1475580107
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618e03eda38dc82f9f5782bd08c8cc9e4c8b882a61d550bc245fc5e43fd9e7d2
|
| 3 |
+
size 14645
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:875a56e5c0019c6395bfdf39b90d0bdd080e6cccdbac30b8dc2b7d69a8c9c42d
|
| 3 |
+
size 1465
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/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_5/checkpoint-10290/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_5/checkpoint-10290/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/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_5/checkpoint-10290/trainer_state.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": 0.8594509232264335,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10290,
|
| 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": 6.80656623840332,
|
| 15 |
+
"learning_rate": 9.736747484138264e-06,
|
| 16 |
+
"loss": 1.402,
|
| 17 |
+
"step": 1029
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_accuracy": 0.576530612244898,
|
| 22 |
+
"eval_f1": 0.574853960689211,
|
| 23 |
+
"eval_loss": 1.0800668001174927,
|
| 24 |
+
"eval_precision": 0.5788261816159553,
|
| 25 |
+
"eval_recall": 0.576530612244898,
|
| 26 |
+
"eval_roc_auc": NaN,
|
| 27 |
+
"eval_runtime": 35.601,
|
| 28 |
+
"eval_samples_per_second": 231.229,
|
| 29 |
+
"eval_steps_per_second": 7.247,
|
| 30 |
+
"step": 1029
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"grad_norm": 9.89237117767334,
|
| 35 |
+
"learning_rate": 9.654835587095599e-06,
|
| 36 |
+
"loss": 0.9027,
|
| 37 |
+
"step": 2058
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.0,
|
| 41 |
+
"eval_accuracy": 0.7484207968901846,
|
| 42 |
+
"eval_f1": 0.7476547729025828,
|
| 43 |
+
"eval_loss": 0.7617784142494202,
|
| 44 |
+
"eval_precision": 0.7518431672782631,
|
| 45 |
+
"eval_recall": 0.7484207968901846,
|
| 46 |
+
"eval_roc_auc": NaN,
|
| 47 |
+
"eval_runtime": 35.5956,
|
| 48 |
+
"eval_samples_per_second": 231.265,
|
| 49 |
+
"eval_steps_per_second": 7.248,
|
| 50 |
+
"step": 2058
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"grad_norm": 9.707611083984375,
|
| 55 |
+
"learning_rate": 9.444090637441711e-06,
|
| 56 |
+
"loss": 0.6928,
|
| 57 |
+
"step": 3087
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.0,
|
| 61 |
+
"eval_accuracy": 0.7851068999028182,
|
| 62 |
+
"eval_f1": 0.7832374504951297,
|
| 63 |
+
"eval_loss": 0.7101931571960449,
|
| 64 |
+
"eval_precision": 0.7920128847315457,
|
| 65 |
+
"eval_recall": 0.7851068999028182,
|
| 66 |
+
"eval_roc_auc": NaN,
|
| 67 |
+
"eval_runtime": 35.6209,
|
| 68 |
+
"eval_samples_per_second": 231.1,
|
| 69 |
+
"eval_steps_per_second": 7.243,
|
| 70 |
+
"step": 3087
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.0,
|
| 74 |
+
"grad_norm": 10.803573608398438,
|
| 75 |
+
"learning_rate": 9.110185686370767e-06,
|
| 76 |
+
"loss": 0.5828,
|
| 77 |
+
"step": 4116
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.0,
|
| 81 |
+
"eval_accuracy": 0.8179057337220602,
|
| 82 |
+
"eval_f1": 0.8173535749930667,
|
| 83 |
+
"eval_loss": 0.6593535542488098,
|
| 84 |
+
"eval_precision": 0.8221409130759143,
|
| 85 |
+
"eval_recall": 0.8179057337220602,
|
| 86 |
+
"eval_roc_auc": NaN,
|
| 87 |
+
"eval_runtime": 35.5942,
|
| 88 |
+
"eval_samples_per_second": 231.274,
|
| 89 |
+
"eval_steps_per_second": 7.248,
|
| 90 |
+
"step": 4116
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.0,
|
| 94 |
+
"grad_norm": 7.975739002227783,
|
| 95 |
+
"learning_rate": 8.662109133768611e-06,
|
| 96 |
+
"loss": 0.5091,
|
| 97 |
+
"step": 5145
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 5.0,
|
| 101 |
+
"eval_accuracy": 0.8503401360544217,
|
| 102 |
+
"eval_f1": 0.850534759988929,
|
| 103 |
+
"eval_loss": 0.5744812488555908,
|
| 104 |
+
"eval_precision": 0.8520902269806605,
|
| 105 |
+
"eval_recall": 0.8503401360544217,
|
| 106 |
+
"eval_roc_auc": NaN,
|
| 107 |
+
"eval_runtime": 35.5677,
|
| 108 |
+
"eval_samples_per_second": 231.446,
|
| 109 |
+
"eval_steps_per_second": 7.254,
|
| 110 |
+
"step": 5145
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.0,
|
| 114 |
+
"grad_norm": 8.724522590637207,
|
| 115 |
+
"learning_rate": 8.111922769139533e-06,
|
| 116 |
+
"loss": 0.4614,
|
| 117 |
+
"step": 6174
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.0,
|
| 121 |
+
"eval_accuracy": 0.8550777453838678,
|
| 122 |
+
"eval_f1": 0.8549716401986811,
|
| 123 |
+
"eval_loss": 0.5794969797134399,
|
| 124 |
+
"eval_precision": 0.8555356983676137,
|
| 125 |
+
"eval_recall": 0.8550777453838678,
|
| 126 |
+
"eval_roc_auc": NaN,
|
| 127 |
+
"eval_runtime": 35.6056,
|
| 128 |
+
"eval_samples_per_second": 231.199,
|
| 129 |
+
"eval_steps_per_second": 7.246,
|
| 130 |
+
"step": 6174
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"grad_norm": 4.377835273742676,
|
| 135 |
+
"learning_rate": 7.474437079842777e-06,
|
| 136 |
+
"loss": 0.4181,
|
| 137 |
+
"step": 7203
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 7.0,
|
| 141 |
+
"eval_accuracy": 0.8406219630709426,
|
| 142 |
+
"eval_f1": 0.8395410342699746,
|
| 143 |
+
"eval_loss": 0.6411412954330444,
|
| 144 |
+
"eval_precision": 0.8445165901067748,
|
| 145 |
+
"eval_recall": 0.8406219630709426,
|
| 146 |
+
"eval_roc_auc": NaN,
|
| 147 |
+
"eval_runtime": 35.4637,
|
| 148 |
+
"eval_samples_per_second": 232.125,
|
| 149 |
+
"eval_steps_per_second": 7.275,
|
| 150 |
+
"step": 7203
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"grad_norm": 9.616984367370605,
|
| 155 |
+
"learning_rate": 6.766812567028518e-06,
|
| 156 |
+
"loss": 0.3838,
|
| 157 |
+
"step": 8232
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 8.0,
|
| 161 |
+
"eval_accuracy": 0.8516763848396501,
|
| 162 |
+
"eval_f1": 0.8513842649318488,
|
| 163 |
+
"eval_loss": 0.6296998858451843,
|
| 164 |
+
"eval_precision": 0.8544732877629595,
|
| 165 |
+
"eval_recall": 0.8516763848396501,
|
| 166 |
+
"eval_roc_auc": NaN,
|
| 167 |
+
"eval_runtime": 35.5226,
|
| 168 |
+
"eval_samples_per_second": 231.74,
|
| 169 |
+
"eval_steps_per_second": 7.263,
|
| 170 |
+
"step": 8232
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 9.0,
|
| 174 |
+
"grad_norm": 4.073179721832275,
|
| 175 |
+
"learning_rate": 6.008097801464572e-06,
|
| 176 |
+
"loss": 0.3675,
|
| 177 |
+
"step": 9261
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 9.0,
|
| 181 |
+
"eval_accuracy": 0.8402575315840622,
|
| 182 |
+
"eval_f1": 0.839257149097259,
|
| 183 |
+
"eval_loss": 0.6928402185440063,
|
| 184 |
+
"eval_precision": 0.8469105173814502,
|
| 185 |
+
"eval_recall": 0.8402575315840622,
|
| 186 |
+
"eval_roc_auc": NaN,
|
| 187 |
+
"eval_runtime": 35.4873,
|
| 188 |
+
"eval_samples_per_second": 231.971,
|
| 189 |
+
"eval_steps_per_second": 7.27,
|
| 190 |
+
"step": 9261
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.0,
|
| 194 |
+
"grad_norm": 8.766383171081543,
|
| 195 |
+
"learning_rate": 5.218716654346354e-06,
|
| 196 |
+
"loss": 0.3419,
|
| 197 |
+
"step": 10290
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 10.0,
|
| 201 |
+
"eval_accuracy": 0.8594509232264335,
|
| 202 |
+
"eval_f1": 0.8585929935743761,
|
| 203 |
+
"eval_loss": 0.6530036330223083,
|
| 204 |
+
"eval_precision": 0.8622914299313825,
|
| 205 |
+
"eval_recall": 0.8594509232264335,
|
| 206 |
+
"eval_roc_auc": NaN,
|
| 207 |
+
"eval_runtime": 35.4685,
|
| 208 |
+
"eval_samples_per_second": 232.093,
|
| 209 |
+
"eval_steps_per_second": 7.274,
|
| 210 |
+
"step": 10290
|
| 211 |
+
}
|
| 212 |
+
],
|
| 213 |
+
"logging_steps": 500,
|
| 214 |
+
"max_steps": 20580,
|
| 215 |
+
"num_input_tokens_seen": 0,
|
| 216 |
+
"num_train_epochs": 20,
|
| 217 |
+
"save_steps": 500,
|
| 218 |
+
"stateful_callbacks": {
|
| 219 |
+
"EarlyStoppingCallback": {
|
| 220 |
+
"args": {
|
| 221 |
+
"early_stopping_patience": 4,
|
| 222 |
+
"early_stopping_threshold": 0.0
|
| 223 |
+
},
|
| 224 |
+
"attributes": {
|
| 225 |
+
"early_stopping_patience_counter": 0
|
| 226 |
+
}
|
| 227 |
+
},
|
| 228 |
+
"TrainerControl": {
|
| 229 |
+
"args": {
|
| 230 |
+
"should_epoch_stop": false,
|
| 231 |
+
"should_evaluate": false,
|
| 232 |
+
"should_log": false,
|
| 233 |
+
"should_save": true,
|
| 234 |
+
"should_training_stop": false
|
| 235 |
+
},
|
| 236 |
+
"attributes": {}
|
| 237 |
+
}
|
| 238 |
+
},
|
| 239 |
+
"total_flos": 4.3316601001344e+16,
|
| 240 |
+
"train_batch_size": 32,
|
| 241 |
+
"trial_name": null,
|
| 242 |
+
"trial_params": null
|
| 243 |
+
}
|
HF_FT_Carmel_Preprocess3_Data/trial_5/checkpoint-10290/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d94e4fb1930f9885c583a7266441d9c1b4864516406fcc8aac46b5befffb8b70
|
| 3 |
+
size 5777
|