Add sentence-level checkpoint
Browse files- checkpoint-11250/config.json +33 -0
- checkpoint-11250/model.safetensors +3 -0
- checkpoint-11250/optimizer.pt +3 -0
- checkpoint-11250/rng_state.pth +3 -0
- checkpoint-11250/scheduler.pt +3 -0
- checkpoint-11250/special_tokens_map.json +37 -0
- checkpoint-11250/tokenizer.json +0 -0
- checkpoint-11250/tokenizer_config.json +58 -0
- checkpoint-11250/trainer_state.json +433 -0
- checkpoint-11250/training_args.bin +3 -0
- checkpoint-11250/vocab.txt +0 -0
- config.json +33 -0
- model.safetensors +3 -0
- runs/May21_09-02-37_pttrainer/events.out.tfevents.1747818159.pttrainer +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-11250/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/jupyter/pt-train/models/pt-ai-detector",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pooler_fc_size": 768,
|
| 22 |
+
"pooler_num_attention_heads": 12,
|
| 23 |
+
"pooler_num_fc_layers": 3,
|
| 24 |
+
"pooler_size_per_head": 128,
|
| 25 |
+
"pooler_type": "first_token_transform",
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.48.3",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 29794
|
| 33 |
+
}
|
checkpoint-11250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb3758f1430cc3f87eae126140915744ef3a170d68ef2c9523bfbdb26d23200c
|
| 3 |
+
size 435722224
|
checkpoint-11250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:084e5ea5a08dc25d79c4ba422abbaffe1d2a63842670a8e5faffcbb278dce862
|
| 3 |
+
size 871565963
|
checkpoint-11250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3472c0eb73a718473691f1e6f0a5a4758ecc8c500147fa67749a0a91771cd00d
|
| 3 |
+
size 14645
|
checkpoint-11250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c32da73705eae98f430d64a119daddc7f19894095d0d8000ee0c78108dbc3d97
|
| 3 |
+
size 1465
|
checkpoint-11250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-11250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
checkpoint-11250/trainer_state.json
ADDED
|
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03605493903160095,
|
| 3 |
+
"best_model_checkpoint": "/home/jupyter/pt-train/models/pt-ai-detector-sent/checkpoint-11250",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.017777777777777778,
|
| 13 |
+
"grad_norm": 0.2309582382440567,
|
| 14 |
+
"learning_rate": 9.825777777777779e-06,
|
| 15 |
+
"loss": 1.1561,
|
| 16 |
+
"step": 200
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.035555555555555556,
|
| 20 |
+
"grad_norm": 0.12385065108537674,
|
| 21 |
+
"learning_rate": 9.648000000000001e-06,
|
| 22 |
+
"loss": 0.1037,
|
| 23 |
+
"step": 400
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05333333333333334,
|
| 27 |
+
"grad_norm": 1.04470694065094,
|
| 28 |
+
"learning_rate": 9.470222222222222e-06,
|
| 29 |
+
"loss": 0.0954,
|
| 30 |
+
"step": 600
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07111111111111111,
|
| 34 |
+
"grad_norm": 0.06991372257471085,
|
| 35 |
+
"learning_rate": 9.292444444444445e-06,
|
| 36 |
+
"loss": 0.0774,
|
| 37 |
+
"step": 800
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08888888888888889,
|
| 41 |
+
"grad_norm": 0.7150733470916748,
|
| 42 |
+
"learning_rate": 9.114666666666668e-06,
|
| 43 |
+
"loss": 0.0644,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10666666666666667,
|
| 48 |
+
"grad_norm": 10.402215003967285,
|
| 49 |
+
"learning_rate": 8.93688888888889e-06,
|
| 50 |
+
"loss": 0.0759,
|
| 51 |
+
"step": 1200
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12444444444444444,
|
| 55 |
+
"grad_norm": 16.095781326293945,
|
| 56 |
+
"learning_rate": 8.76e-06,
|
| 57 |
+
"loss": 0.0708,
|
| 58 |
+
"step": 1400
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14222222222222222,
|
| 62 |
+
"grad_norm": 0.015104565769433975,
|
| 63 |
+
"learning_rate": 8.582222222222223e-06,
|
| 64 |
+
"loss": 0.072,
|
| 65 |
+
"step": 1600
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16,
|
| 69 |
+
"grad_norm": 0.05716638267040253,
|
| 70 |
+
"learning_rate": 8.404444444444444e-06,
|
| 71 |
+
"loss": 0.0583,
|
| 72 |
+
"step": 1800
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17777777777777778,
|
| 76 |
+
"grad_norm": 0.18205951154232025,
|
| 77 |
+
"learning_rate": 8.226666666666667e-06,
|
| 78 |
+
"loss": 0.0471,
|
| 79 |
+
"step": 2000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19555555555555557,
|
| 83 |
+
"grad_norm": 0.010154439136385918,
|
| 84 |
+
"learning_rate": 8.04888888888889e-06,
|
| 85 |
+
"loss": 0.047,
|
| 86 |
+
"step": 2200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21333333333333335,
|
| 90 |
+
"grad_norm": 0.016992947086691856,
|
| 91 |
+
"learning_rate": 7.871111111111112e-06,
|
| 92 |
+
"loss": 0.0563,
|
| 93 |
+
"step": 2400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2311111111111111,
|
| 97 |
+
"grad_norm": 18.458301544189453,
|
| 98 |
+
"learning_rate": 7.693333333333333e-06,
|
| 99 |
+
"loss": 0.0491,
|
| 100 |
+
"step": 2600
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.24888888888888888,
|
| 104 |
+
"grad_norm": 0.12355442345142365,
|
| 105 |
+
"learning_rate": 7.515555555555556e-06,
|
| 106 |
+
"loss": 0.0612,
|
| 107 |
+
"step": 2800
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26666666666666666,
|
| 111 |
+
"grad_norm": 0.027129609137773514,
|
| 112 |
+
"learning_rate": 7.337777777777778e-06,
|
| 113 |
+
"loss": 0.0545,
|
| 114 |
+
"step": 3000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28444444444444444,
|
| 118 |
+
"grad_norm": 16.13323211669922,
|
| 119 |
+
"learning_rate": 7.16e-06,
|
| 120 |
+
"loss": 0.0608,
|
| 121 |
+
"step": 3200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3022222222222222,
|
| 125 |
+
"grad_norm": 0.0006109599489718676,
|
| 126 |
+
"learning_rate": 6.982222222222223e-06,
|
| 127 |
+
"loss": 0.0336,
|
| 128 |
+
"step": 3400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.32,
|
| 132 |
+
"grad_norm": 5.837182998657227,
|
| 133 |
+
"learning_rate": 6.8044444444444444e-06,
|
| 134 |
+
"loss": 0.0485,
|
| 135 |
+
"step": 3600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3377777777777778,
|
| 139 |
+
"grad_norm": 2.619032859802246,
|
| 140 |
+
"learning_rate": 6.626666666666667e-06,
|
| 141 |
+
"loss": 0.0454,
|
| 142 |
+
"step": 3800
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35555555555555557,
|
| 146 |
+
"grad_norm": 0.10736280679702759,
|
| 147 |
+
"learning_rate": 6.448888888888889e-06,
|
| 148 |
+
"loss": 0.0562,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.37333333333333335,
|
| 153 |
+
"grad_norm": 0.010529163293540478,
|
| 154 |
+
"learning_rate": 6.271111111111111e-06,
|
| 155 |
+
"loss": 0.0397,
|
| 156 |
+
"step": 4200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.39111111111111113,
|
| 160 |
+
"grad_norm": 7.122026443481445,
|
| 161 |
+
"learning_rate": 6.093333333333333e-06,
|
| 162 |
+
"loss": 0.0455,
|
| 163 |
+
"step": 4400
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4088888888888889,
|
| 167 |
+
"grad_norm": 14.466997146606445,
|
| 168 |
+
"learning_rate": 5.915555555555556e-06,
|
| 169 |
+
"loss": 0.0437,
|
| 170 |
+
"step": 4600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4266666666666667,
|
| 174 |
+
"grad_norm": 0.011481579393148422,
|
| 175 |
+
"learning_rate": 5.737777777777778e-06,
|
| 176 |
+
"loss": 0.0365,
|
| 177 |
+
"step": 4800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4444444444444444,
|
| 181 |
+
"grad_norm": 0.09981393069028854,
|
| 182 |
+
"learning_rate": 5.560000000000001e-06,
|
| 183 |
+
"loss": 0.0373,
|
| 184 |
+
"step": 5000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4622222222222222,
|
| 188 |
+
"grad_norm": 0.0657946765422821,
|
| 189 |
+
"learning_rate": 5.382222222222223e-06,
|
| 190 |
+
"loss": 0.0444,
|
| 191 |
+
"step": 5200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.48,
|
| 195 |
+
"grad_norm": 1.3812452554702759,
|
| 196 |
+
"learning_rate": 5.204444444444445e-06,
|
| 197 |
+
"loss": 0.0336,
|
| 198 |
+
"step": 5400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.49777777777777776,
|
| 202 |
+
"grad_norm": 0.032792165875434875,
|
| 203 |
+
"learning_rate": 5.026666666666667e-06,
|
| 204 |
+
"loss": 0.039,
|
| 205 |
+
"step": 5600
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5155555555555555,
|
| 209 |
+
"grad_norm": 1.433627963066101,
|
| 210 |
+
"learning_rate": 4.848888888888889e-06,
|
| 211 |
+
"loss": 0.0347,
|
| 212 |
+
"step": 5800
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5333333333333333,
|
| 216 |
+
"grad_norm": 18.49650001525879,
|
| 217 |
+
"learning_rate": 4.6711111111111115e-06,
|
| 218 |
+
"loss": 0.0421,
|
| 219 |
+
"step": 6000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5511111111111111,
|
| 223 |
+
"grad_norm": 0.15248766541481018,
|
| 224 |
+
"learning_rate": 4.493333333333333e-06,
|
| 225 |
+
"loss": 0.0466,
|
| 226 |
+
"step": 6200
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5688888888888889,
|
| 230 |
+
"grad_norm": 1.2822659015655518,
|
| 231 |
+
"learning_rate": 4.315555555555556e-06,
|
| 232 |
+
"loss": 0.0397,
|
| 233 |
+
"step": 6400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5866666666666667,
|
| 237 |
+
"grad_norm": 0.04721234738826752,
|
| 238 |
+
"learning_rate": 4.1377777777777784e-06,
|
| 239 |
+
"loss": 0.0419,
|
| 240 |
+
"step": 6600
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6044444444444445,
|
| 244 |
+
"grad_norm": 0.04303908720612526,
|
| 245 |
+
"learning_rate": 3.96e-06,
|
| 246 |
+
"loss": 0.0405,
|
| 247 |
+
"step": 6800
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6222222222222222,
|
| 251 |
+
"grad_norm": 0.009814753197133541,
|
| 252 |
+
"learning_rate": 3.782222222222223e-06,
|
| 253 |
+
"loss": 0.0304,
|
| 254 |
+
"step": 7000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.64,
|
| 258 |
+
"grad_norm": 0.25008726119995117,
|
| 259 |
+
"learning_rate": 3.604444444444445e-06,
|
| 260 |
+
"loss": 0.0397,
|
| 261 |
+
"step": 7200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6577777777777778,
|
| 265 |
+
"grad_norm": 0.00500706909224391,
|
| 266 |
+
"learning_rate": 3.426666666666667e-06,
|
| 267 |
+
"loss": 0.0369,
|
| 268 |
+
"step": 7400
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6755555555555556,
|
| 272 |
+
"grad_norm": 0.0132444491609931,
|
| 273 |
+
"learning_rate": 3.2488888888888894e-06,
|
| 274 |
+
"loss": 0.0314,
|
| 275 |
+
"step": 7600
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6933333333333334,
|
| 279 |
+
"grad_norm": 5.168927192687988,
|
| 280 |
+
"learning_rate": 3.072e-06,
|
| 281 |
+
"loss": 0.0382,
|
| 282 |
+
"step": 7800
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7111111111111111,
|
| 286 |
+
"grad_norm": 7.176743507385254,
|
| 287 |
+
"learning_rate": 2.8951111111111114e-06,
|
| 288 |
+
"loss": 0.0476,
|
| 289 |
+
"step": 8000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7288888888888889,
|
| 293 |
+
"grad_norm": 0.0021492040250450373,
|
| 294 |
+
"learning_rate": 2.7173333333333336e-06,
|
| 295 |
+
"loss": 0.0368,
|
| 296 |
+
"step": 8200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7466666666666667,
|
| 300 |
+
"grad_norm": 0.006746188271790743,
|
| 301 |
+
"learning_rate": 2.539555555555556e-06,
|
| 302 |
+
"loss": 0.0382,
|
| 303 |
+
"step": 8400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7644444444444445,
|
| 307 |
+
"grad_norm": 0.005719976499676704,
|
| 308 |
+
"learning_rate": 2.361777777777778e-06,
|
| 309 |
+
"loss": 0.0297,
|
| 310 |
+
"step": 8600
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7822222222222223,
|
| 314 |
+
"grad_norm": 0.04104682430624962,
|
| 315 |
+
"learning_rate": 2.184e-06,
|
| 316 |
+
"loss": 0.0379,
|
| 317 |
+
"step": 8800
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8,
|
| 321 |
+
"grad_norm": 0.009711818769574165,
|
| 322 |
+
"learning_rate": 2.0062222222222224e-06,
|
| 323 |
+
"loss": 0.0323,
|
| 324 |
+
"step": 9000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8177777777777778,
|
| 328 |
+
"grad_norm": 0.03058827668428421,
|
| 329 |
+
"learning_rate": 1.8284444444444445e-06,
|
| 330 |
+
"loss": 0.0456,
|
| 331 |
+
"step": 9200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8355555555555556,
|
| 335 |
+
"grad_norm": 0.009686224162578583,
|
| 336 |
+
"learning_rate": 1.6506666666666667e-06,
|
| 337 |
+
"loss": 0.0321,
|
| 338 |
+
"step": 9400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8533333333333334,
|
| 342 |
+
"grad_norm": 0.03049510158598423,
|
| 343 |
+
"learning_rate": 1.472888888888889e-06,
|
| 344 |
+
"loss": 0.0308,
|
| 345 |
+
"step": 9600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8711111111111111,
|
| 349 |
+
"grad_norm": 0.12437938898801804,
|
| 350 |
+
"learning_rate": 1.295111111111111e-06,
|
| 351 |
+
"loss": 0.0384,
|
| 352 |
+
"step": 9800
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8888888888888888,
|
| 356 |
+
"grad_norm": 0.012638283893465996,
|
| 357 |
+
"learning_rate": 1.1173333333333335e-06,
|
| 358 |
+
"loss": 0.0328,
|
| 359 |
+
"step": 10000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9066666666666666,
|
| 363 |
+
"grad_norm": 0.061814695596694946,
|
| 364 |
+
"learning_rate": 9.395555555555557e-07,
|
| 365 |
+
"loss": 0.0415,
|
| 366 |
+
"step": 10200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9244444444444444,
|
| 370 |
+
"grad_norm": 0.0710972398519516,
|
| 371 |
+
"learning_rate": 7.617777777777779e-07,
|
| 372 |
+
"loss": 0.025,
|
| 373 |
+
"step": 10400
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9422222222222222,
|
| 377 |
+
"grad_norm": 17.15258026123047,
|
| 378 |
+
"learning_rate": 5.84e-07,
|
| 379 |
+
"loss": 0.0346,
|
| 380 |
+
"step": 10600
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.96,
|
| 384 |
+
"grad_norm": 0.21364516019821167,
|
| 385 |
+
"learning_rate": 4.062222222222222e-07,
|
| 386 |
+
"loss": 0.0291,
|
| 387 |
+
"step": 10800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9777777777777777,
|
| 391 |
+
"grad_norm": 0.24612575769424438,
|
| 392 |
+
"learning_rate": 2.2844444444444446e-07,
|
| 393 |
+
"loss": 0.0304,
|
| 394 |
+
"step": 11000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9955555555555555,
|
| 398 |
+
"grad_norm": 1.2707738876342773,
|
| 399 |
+
"learning_rate": 5.066666666666667e-08,
|
| 400 |
+
"loss": 0.0288,
|
| 401 |
+
"step": 11200
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.0,
|
| 405 |
+
"eval_loss": 0.03605493903160095,
|
| 406 |
+
"eval_runtime": 22.7203,
|
| 407 |
+
"eval_samples_per_second": 880.272,
|
| 408 |
+
"eval_steps_per_second": 55.017,
|
| 409 |
+
"step": 11250
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 200,
|
| 413 |
+
"max_steps": 11250,
|
| 414 |
+
"num_input_tokens_seen": 0,
|
| 415 |
+
"num_train_epochs": 1,
|
| 416 |
+
"save_steps": 500,
|
| 417 |
+
"stateful_callbacks": {
|
| 418 |
+
"TrainerControl": {
|
| 419 |
+
"args": {
|
| 420 |
+
"should_epoch_stop": false,
|
| 421 |
+
"should_evaluate": false,
|
| 422 |
+
"should_log": false,
|
| 423 |
+
"should_save": true,
|
| 424 |
+
"should_training_stop": true
|
| 425 |
+
},
|
| 426 |
+
"attributes": {}
|
| 427 |
+
}
|
| 428 |
+
},
|
| 429 |
+
"total_flos": 7865326777845120.0,
|
| 430 |
+
"train_batch_size": 16,
|
| 431 |
+
"trial_name": null,
|
| 432 |
+
"trial_params": null
|
| 433 |
+
}
|
checkpoint-11250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69451857894e617a46b89c1e519f0949a4d2b04eceb9f19f6af7aa335fe8649
|
| 3 |
+
size 5841
|
checkpoint-11250/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/jupyter/pt-train/models/pt-ai-detector",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pooler_fc_size": 768,
|
| 22 |
+
"pooler_num_attention_heads": 12,
|
| 23 |
+
"pooler_num_fc_layers": 3,
|
| 24 |
+
"pooler_size_per_head": 128,
|
| 25 |
+
"pooler_type": "first_token_transform",
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.48.3",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 29794
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb3758f1430cc3f87eae126140915744ef3a170d68ef2c9523bfbdb26d23200c
|
| 3 |
+
size 435722224
|
runs/May21_09-02-37_pttrainer/events.out.tfevents.1747818159.pttrainer
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bfdd748e6355b0bfe168f6fa559e3113c768bb8ac02848a7d28b0055dbb051c
|
| 3 |
+
size 17829
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69451857894e617a46b89c1e519f0949a4d2b04eceb9f19f6af7aa335fe8649
|
| 3 |
+
size 5841
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|