Initial model upload
Browse files- config.json +52 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- trainer_state.json +270 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../model/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "\u043e\u0442\u0435\u0446",
|
| 12 |
+
"1": "\u043c\u0430\u0442\u044c",
|
| 13 |
+
"2": "\u0440\u0435\u0431\u0435\u043d\u043e\u043a",
|
| 14 |
+
"3": "\u0441\u0443\u043f\u0440\u0443\u0433",
|
| 15 |
+
"4": "\u0431\u044b\u0432\u0448\u0438\u0439 \u0441\u0443\u043f\u0440\u0443\u0433",
|
| 16 |
+
"5": "\u043e \u0441\u0435\u0431\u0435"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"\u0431\u044b\u0432\u0448\u0438\u0439 \u0441\u0443\u043f\u0440\u0443\u0433": 4,
|
| 22 |
+
"\u043c\u0430\u0442\u044c": 1,
|
| 23 |
+
"\u043e \u0441\u0435\u0431\u0435": 5,
|
| 24 |
+
"\u043e\u0442\u0435\u0446": 0,
|
| 25 |
+
"\u0440\u0435\u0431\u0435\u043d\u043e\u043a": 2,
|
| 26 |
+
"\u0441\u0443\u043f\u0440\u0443\u0433": 3
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-07,
|
| 29 |
+
"legacy": true,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"max_relative_positions": -1,
|
| 32 |
+
"model_type": "deberta-v2",
|
| 33 |
+
"norm_rel_ebd": "layer_norm",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"pooler_dropout": 0,
|
| 38 |
+
"pooler_hidden_act": "gelu",
|
| 39 |
+
"pooler_hidden_size": 1024,
|
| 40 |
+
"pos_att_type": [
|
| 41 |
+
"p2c",
|
| 42 |
+
"c2p"
|
| 43 |
+
],
|
| 44 |
+
"position_biased_input": false,
|
| 45 |
+
"position_buckets": 256,
|
| 46 |
+
"relative_attention": true,
|
| 47 |
+
"share_att_key": true,
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.47.0",
|
| 50 |
+
"type_vocab_size": 0,
|
| 51 |
+
"vocab_size": 128100
|
| 52 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd763dfe8e85c866e6bd66f50809d9d54abce16f01859bae8100bc92ed5f69e
|
| 3 |
+
size 1740320848
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09bc7a04cb1c04fd2bf390ada3ea92d968b99d16473546daf9bf211097dd45d0
|
| 3 |
+
size 210016058
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ec1c04ea978711253e617f503c8e9a897c2b598c232debda0e8460cead38768
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2966c532a4eaa51eb66d10c1d97075ad2d534019e8d79c43ed0464fef1781368
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 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": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"split_by_punct": false,
|
| 57 |
+
"stride": 0,
|
| 58 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]",
|
| 62 |
+
"vocab_type": "spm"
|
| 63 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03780783340334892,
|
| 3 |
+
"best_model_checkpoint": "./results3/checkpoint-2400",
|
| 4 |
+
"epoch": 3.864734299516908,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.322061191626409,
|
| 13 |
+
"grad_norm": 7.461069583892822,
|
| 14 |
+
"learning_rate": 6.666666666666667e-07,
|
| 15 |
+
"loss": 1.8012,
|
| 16 |
+
"step": 200
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.322061191626409,
|
| 20 |
+
"eval_accuracy": 0.18971061093247588,
|
| 21 |
+
"eval_f1": 0.10189049057972092,
|
| 22 |
+
"eval_loss": 1.7812345027923584,
|
| 23 |
+
"eval_precision": 0.12844515990912814,
|
| 24 |
+
"eval_recall": 0.18971061093247588,
|
| 25 |
+
"eval_runtime": 5.7225,
|
| 26 |
+
"eval_samples_per_second": 108.693,
|
| 27 |
+
"eval_steps_per_second": 27.261,
|
| 28 |
+
"step": 200
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.644122383252818,
|
| 32 |
+
"grad_norm": 6.918825149536133,
|
| 33 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 34 |
+
"loss": 1.7688,
|
| 35 |
+
"step": 400
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.644122383252818,
|
| 39 |
+
"eval_accuracy": 0.26688102893890675,
|
| 40 |
+
"eval_f1": 0.21143076934540506,
|
| 41 |
+
"eval_loss": 1.7484790086746216,
|
| 42 |
+
"eval_precision": 0.48251637799958924,
|
| 43 |
+
"eval_recall": 0.26688102893890675,
|
| 44 |
+
"eval_runtime": 5.841,
|
| 45 |
+
"eval_samples_per_second": 106.489,
|
| 46 |
+
"eval_steps_per_second": 26.708,
|
| 47 |
+
"step": 400
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.966183574879227,
|
| 51 |
+
"grad_norm": 6.153536319732666,
|
| 52 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 53 |
+
"loss": 1.7475,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.966183574879227,
|
| 58 |
+
"eval_accuracy": 0.5353697749196141,
|
| 59 |
+
"eval_f1": 0.5292630942880905,
|
| 60 |
+
"eval_loss": 1.6678913831710815,
|
| 61 |
+
"eval_precision": 0.5777595640628179,
|
| 62 |
+
"eval_recall": 0.5353697749196141,
|
| 63 |
+
"eval_runtime": 5.7676,
|
| 64 |
+
"eval_samples_per_second": 107.844,
|
| 65 |
+
"eval_steps_per_second": 27.048,
|
| 66 |
+
"step": 600
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.288244766505636,
|
| 70 |
+
"grad_norm": 10.906112670898438,
|
| 71 |
+
"learning_rate": 2.666666666666667e-06,
|
| 72 |
+
"loss": 1.6323,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.288244766505636,
|
| 77 |
+
"eval_accuracy": 0.6109324758842444,
|
| 78 |
+
"eval_f1": 0.584022217728586,
|
| 79 |
+
"eval_loss": 1.4518650770187378,
|
| 80 |
+
"eval_precision": 0.6770832871589993,
|
| 81 |
+
"eval_recall": 0.6109324758842444,
|
| 82 |
+
"eval_runtime": 5.7252,
|
| 83 |
+
"eval_samples_per_second": 108.643,
|
| 84 |
+
"eval_steps_per_second": 27.248,
|
| 85 |
+
"step": 800
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.6103059581320451,
|
| 89 |
+
"grad_norm": 11.212413787841797,
|
| 90 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 91 |
+
"loss": 1.3569,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.6103059581320451,
|
| 96 |
+
"eval_accuracy": 0.6672025723472669,
|
| 97 |
+
"eval_f1": 0.6448086526662313,
|
| 98 |
+
"eval_loss": 1.0713452100753784,
|
| 99 |
+
"eval_precision": 0.7227579722788608,
|
| 100 |
+
"eval_recall": 0.6672025723472669,
|
| 101 |
+
"eval_runtime": 5.8441,
|
| 102 |
+
"eval_samples_per_second": 106.433,
|
| 103 |
+
"eval_steps_per_second": 26.694,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.9323671497584543,
|
| 108 |
+
"grad_norm": 10.077208518981934,
|
| 109 |
+
"learning_rate": 4.000000000000001e-06,
|
| 110 |
+
"loss": 0.9744,
|
| 111 |
+
"step": 1200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.9323671497584543,
|
| 115 |
+
"eval_accuracy": 0.8360128617363344,
|
| 116 |
+
"eval_f1": 0.8313516450563994,
|
| 117 |
+
"eval_loss": 0.6114147901535034,
|
| 118 |
+
"eval_precision": 0.8485064229080279,
|
| 119 |
+
"eval_recall": 0.8360128617363344,
|
| 120 |
+
"eval_runtime": 5.7667,
|
| 121 |
+
"eval_samples_per_second": 107.861,
|
| 122 |
+
"eval_steps_per_second": 27.052,
|
| 123 |
+
"step": 1200
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.2544283413848634,
|
| 127 |
+
"grad_norm": 3.6660408973693848,
|
| 128 |
+
"learning_rate": 4.666666666666667e-06,
|
| 129 |
+
"loss": 0.5969,
|
| 130 |
+
"step": 1400
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.2544283413848634,
|
| 134 |
+
"eval_accuracy": 0.9180064308681672,
|
| 135 |
+
"eval_f1": 0.9171911311305204,
|
| 136 |
+
"eval_loss": 0.29916083812713623,
|
| 137 |
+
"eval_precision": 0.9217784712222669,
|
| 138 |
+
"eval_recall": 0.9180064308681672,
|
| 139 |
+
"eval_runtime": 5.8166,
|
| 140 |
+
"eval_samples_per_second": 106.936,
|
| 141 |
+
"eval_steps_per_second": 26.82,
|
| 142 |
+
"step": 1400
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.576489533011272,
|
| 146 |
+
"grad_norm": 3.6452574729919434,
|
| 147 |
+
"learning_rate": 4.994440868783523e-06,
|
| 148 |
+
"loss": 0.3187,
|
| 149 |
+
"step": 1600
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.576489533011272,
|
| 153 |
+
"eval_accuracy": 0.9453376205787781,
|
| 154 |
+
"eval_f1": 0.94523522766866,
|
| 155 |
+
"eval_loss": 0.1684405654668808,
|
| 156 |
+
"eval_precision": 0.951570696538466,
|
| 157 |
+
"eval_recall": 0.9453376205787781,
|
| 158 |
+
"eval_runtime": 5.7215,
|
| 159 |
+
"eval_samples_per_second": 108.712,
|
| 160 |
+
"eval_steps_per_second": 27.265,
|
| 161 |
+
"step": 1600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.898550724637681,
|
| 165 |
+
"grad_norm": 0.2801424562931061,
|
| 166 |
+
"learning_rate": 4.950116048011739e-06,
|
| 167 |
+
"loss": 0.1856,
|
| 168 |
+
"step": 1800
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.898550724637681,
|
| 172 |
+
"eval_accuracy": 0.9726688102893891,
|
| 173 |
+
"eval_f1": 0.9726543269299354,
|
| 174 |
+
"eval_loss": 0.0953439399600029,
|
| 175 |
+
"eval_precision": 0.9736809257583791,
|
| 176 |
+
"eval_recall": 0.9726688102893891,
|
| 177 |
+
"eval_runtime": 5.7237,
|
| 178 |
+
"eval_samples_per_second": 108.672,
|
| 179 |
+
"eval_steps_per_second": 27.255,
|
| 180 |
+
"step": 1800
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.2206119162640903,
|
| 184 |
+
"grad_norm": 0.754078209400177,
|
| 185 |
+
"learning_rate": 4.862254033772164e-06,
|
| 186 |
+
"loss": 0.1113,
|
| 187 |
+
"step": 2000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.2206119162640903,
|
| 191 |
+
"eval_accuracy": 0.9823151125401929,
|
| 192 |
+
"eval_f1": 0.9823107313578804,
|
| 193 |
+
"eval_loss": 0.05166807398200035,
|
| 194 |
+
"eval_precision": 0.9823692945184218,
|
| 195 |
+
"eval_recall": 0.9823151125401929,
|
| 196 |
+
"eval_runtime": 5.6315,
|
| 197 |
+
"eval_samples_per_second": 110.451,
|
| 198 |
+
"eval_steps_per_second": 27.702,
|
| 199 |
+
"step": 2000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.542673107890499,
|
| 203 |
+
"grad_norm": 0.2094874083995819,
|
| 204 |
+
"learning_rate": 4.7324160849755856e-06,
|
| 205 |
+
"loss": 0.0492,
|
| 206 |
+
"step": 2200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.542673107890499,
|
| 210 |
+
"eval_accuracy": 0.9855305466237942,
|
| 211 |
+
"eval_f1": 0.9855078289074475,
|
| 212 |
+
"eval_loss": 0.04900892823934555,
|
| 213 |
+
"eval_precision": 0.9855788271208662,
|
| 214 |
+
"eval_recall": 0.9855305466237942,
|
| 215 |
+
"eval_runtime": 5.7859,
|
| 216 |
+
"eval_samples_per_second": 107.503,
|
| 217 |
+
"eval_steps_per_second": 26.962,
|
| 218 |
+
"step": 2200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.864734299516908,
|
| 222 |
+
"grad_norm": 0.26868194341659546,
|
| 223 |
+
"learning_rate": 4.562909349440899e-06,
|
| 224 |
+
"loss": 0.0584,
|
| 225 |
+
"step": 2400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.864734299516908,
|
| 229 |
+
"eval_accuracy": 0.9855305466237942,
|
| 230 |
+
"eval_f1": 0.9855183714453405,
|
| 231 |
+
"eval_loss": 0.03780783340334892,
|
| 232 |
+
"eval_precision": 0.9856657355462896,
|
| 233 |
+
"eval_recall": 0.9855305466237942,
|
| 234 |
+
"eval_runtime": 5.7375,
|
| 235 |
+
"eval_samples_per_second": 108.409,
|
| 236 |
+
"eval_steps_per_second": 27.189,
|
| 237 |
+
"step": 2400
|
| 238 |
+
}
|
| 239 |
+
],
|
| 240 |
+
"logging_steps": 200,
|
| 241 |
+
"max_steps": 6210,
|
| 242 |
+
"num_input_tokens_seen": 0,
|
| 243 |
+
"num_train_epochs": 10,
|
| 244 |
+
"save_steps": 200,
|
| 245 |
+
"stateful_callbacks": {
|
| 246 |
+
"EarlyStoppingCallback": {
|
| 247 |
+
"args": {
|
| 248 |
+
"early_stopping_patience": 3,
|
| 249 |
+
"early_stopping_threshold": 0.0
|
| 250 |
+
},
|
| 251 |
+
"attributes": {
|
| 252 |
+
"early_stopping_patience_counter": 0
|
| 253 |
+
}
|
| 254 |
+
},
|
| 255 |
+
"TrainerControl": {
|
| 256 |
+
"args": {
|
| 257 |
+
"should_epoch_stop": false,
|
| 258 |
+
"should_evaluate": false,
|
| 259 |
+
"should_log": false,
|
| 260 |
+
"should_save": true,
|
| 261 |
+
"should_training_stop": false
|
| 262 |
+
},
|
| 263 |
+
"attributes": {}
|
| 264 |
+
}
|
| 265 |
+
},
|
| 266 |
+
"total_flos": 383614021649664.0,
|
| 267 |
+
"train_batch_size": 4,
|
| 268 |
+
"trial_name": null,
|
| 269 |
+
"trial_params": null
|
| 270 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c065fc0c8ef5911d83c5bd37ed6bf30478028d63d9361ae1826f528ca5cf4aa
|
| 3 |
+
size 5304
|