Upload 10 files
Browse files- sketch/cls_score.json +0 -0
- sketch/config.json +31 -0
- sketch/model.safetensors +3 -0
- sketch/sketch_eval_results.txt +10 -0
- sketch/special_tokens_map.json +7 -0
- sketch/tokenizer.json +0 -0
- sketch/tokenizer_config.json +55 -0
- sketch/trainer_state.json +432 -0
- sketch/training_args.bin +3 -0
- sketch/vocab.txt +0 -0
sketch/cls_score.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sketch/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/electra-base-discriminator",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 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": "electra",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"summary_activation": "gelu",
|
| 23 |
+
"summary_last_dropout": 0.1,
|
| 24 |
+
"summary_type": "first",
|
| 25 |
+
"summary_use_proj": true,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.41.2",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
sketch/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42fc04e6b976a242dc088e8c5f7cbeeb6e1992e0054fbeca1c78ba40602551c0
|
| 3 |
+
size 437959248
|
sketch/sketch_eval_results.txt
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
***** Eval results *****
|
| 2 |
+
2024-06-16 18:21:32.231566epoch = 10.0
|
| 3 |
+
eval_accuracy = 0.831397777592113
|
| 4 |
+
eval_f1 = 0.8103383458646617
|
| 5 |
+
eval_precision = 0.9280947255113025
|
| 6 |
+
eval_recall = 0.7190992493744788
|
| 7 |
+
eval_runtime = 50.2235
|
| 8 |
+
eval_samples_per_second = 238.315
|
| 9 |
+
eval_steps_per_second = 3.743
|
| 10 |
+
|
sketch/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 |
+
}
|
sketch/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sketch/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
sketch/trainer_state.json
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24509803921568626,
|
| 13 |
+
"grad_norm": 2.2194137573242188,
|
| 14 |
+
"learning_rate": 4.901960784313726e-06,
|
| 15 |
+
"loss": 0.6351,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.49019607843137253,
|
| 20 |
+
"grad_norm": 5.901831150054932,
|
| 21 |
+
"learning_rate": 9.803921568627451e-06,
|
| 22 |
+
"loss": 0.4992,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7352941176470589,
|
| 27 |
+
"grad_norm": 5.434150695800781,
|
| 28 |
+
"learning_rate": 1.4705882352941179e-05,
|
| 29 |
+
"loss": 0.3933,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9803921568627451,
|
| 34 |
+
"grad_norm": 6.714095115661621,
|
| 35 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 36 |
+
"loss": 0.3433,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.795555184225917,
|
| 42 |
+
"eval_f1": 0.758320987654321,
|
| 43 |
+
"eval_precision": 0.9295399515738498,
|
| 44 |
+
"eval_recall": 0.6403669724770642,
|
| 45 |
+
"eval_runtime": 50.1487,
|
| 46 |
+
"eval_samples_per_second": 238.67,
|
| 47 |
+
"eval_steps_per_second": 3.749,
|
| 48 |
+
"step": 2040
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.2254901960784315,
|
| 52 |
+
"grad_norm": 4.650435924530029,
|
| 53 |
+
"learning_rate": 1.9501089324618738e-05,
|
| 54 |
+
"loss": 0.2707,
|
| 55 |
+
"step": 2500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.4705882352941178,
|
| 59 |
+
"grad_norm": 5.975987434387207,
|
| 60 |
+
"learning_rate": 1.8956427015250548e-05,
|
| 61 |
+
"loss": 0.2568,
|
| 62 |
+
"step": 3000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.715686274509804,
|
| 66 |
+
"grad_norm": 4.295902729034424,
|
| 67 |
+
"learning_rate": 1.8413943355119828e-05,
|
| 68 |
+
"loss": 0.2396,
|
| 69 |
+
"step": 3500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.9607843137254903,
|
| 73 |
+
"grad_norm": 4.352377414703369,
|
| 74 |
+
"learning_rate": 1.7869281045751637e-05,
|
| 75 |
+
"loss": 0.2253,
|
| 76 |
+
"step": 4000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.0,
|
| 80 |
+
"eval_accuracy": 0.821873172361935,
|
| 81 |
+
"eval_f1": 0.7964094728800611,
|
| 82 |
+
"eval_precision": 0.9314272950636587,
|
| 83 |
+
"eval_recall": 0.69557964970809,
|
| 84 |
+
"eval_runtime": 50.0719,
|
| 85 |
+
"eval_samples_per_second": 239.036,
|
| 86 |
+
"eval_steps_per_second": 3.755,
|
| 87 |
+
"step": 4080
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.2058823529411766,
|
| 91 |
+
"grad_norm": 8.222220420837402,
|
| 92 |
+
"learning_rate": 1.7324618736383444e-05,
|
| 93 |
+
"loss": 0.1567,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.450980392156863,
|
| 98 |
+
"grad_norm": 8.841856956481934,
|
| 99 |
+
"learning_rate": 1.677995642701525e-05,
|
| 100 |
+
"loss": 0.1406,
|
| 101 |
+
"step": 5000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.696078431372549,
|
| 105 |
+
"grad_norm": 5.413289546966553,
|
| 106 |
+
"learning_rate": 1.6236383442265798e-05,
|
| 107 |
+
"loss": 0.1379,
|
| 108 |
+
"step": 5500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.9411764705882355,
|
| 112 |
+
"grad_norm": 6.019312381744385,
|
| 113 |
+
"learning_rate": 1.5691721132897604e-05,
|
| 114 |
+
"loss": 0.1406,
|
| 115 |
+
"step": 6000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.0,
|
| 119 |
+
"eval_accuracy": 0.8236277049043362,
|
| 120 |
+
"eval_f1": 0.7998103366524419,
|
| 121 |
+
"eval_precision": 0.9268131868131868,
|
| 122 |
+
"eval_recall": 0.7034195162635529,
|
| 123 |
+
"eval_runtime": 50.1875,
|
| 124 |
+
"eval_samples_per_second": 238.486,
|
| 125 |
+
"eval_steps_per_second": 3.746,
|
| 126 |
+
"step": 6120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.186274509803922,
|
| 130 |
+
"grad_norm": 4.456413269042969,
|
| 131 |
+
"learning_rate": 1.5148148148148149e-05,
|
| 132 |
+
"loss": 0.0954,
|
| 133 |
+
"step": 6500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 3.431372549019608,
|
| 137 |
+
"grad_norm": 3.628704786300659,
|
| 138 |
+
"learning_rate": 1.4603485838779959e-05,
|
| 139 |
+
"loss": 0.0892,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.6764705882352944,
|
| 144 |
+
"grad_norm": 2.9508347511291504,
|
| 145 |
+
"learning_rate": 1.4058823529411765e-05,
|
| 146 |
+
"loss": 0.0919,
|
| 147 |
+
"step": 7500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.9215686274509802,
|
| 151 |
+
"grad_norm": 6.59318208694458,
|
| 152 |
+
"learning_rate": 1.3514161220043573e-05,
|
| 153 |
+
"loss": 0.0873,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 4.0,
|
| 158 |
+
"eval_accuracy": 0.8282229091820537,
|
| 159 |
+
"eval_f1": 0.808351976137211,
|
| 160 |
+
"eval_precision": 0.9161208535812381,
|
| 161 |
+
"eval_recall": 0.7232693911592994,
|
| 162 |
+
"eval_runtime": 50.5224,
|
| 163 |
+
"eval_samples_per_second": 236.905,
|
| 164 |
+
"eval_steps_per_second": 3.721,
|
| 165 |
+
"step": 8160
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.166666666666667,
|
| 169 |
+
"grad_norm": 2.5619020462036133,
|
| 170 |
+
"learning_rate": 1.2969498910675382e-05,
|
| 171 |
+
"loss": 0.0696,
|
| 172 |
+
"step": 8500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 4.411764705882353,
|
| 176 |
+
"grad_norm": 6.823647499084473,
|
| 177 |
+
"learning_rate": 1.242483660130719e-05,
|
| 178 |
+
"loss": 0.0564,
|
| 179 |
+
"step": 9000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.6568627450980395,
|
| 183 |
+
"grad_norm": 7.367131233215332,
|
| 184 |
+
"learning_rate": 1.1880174291939e-05,
|
| 185 |
+
"loss": 0.0608,
|
| 186 |
+
"step": 9500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 4.901960784313726,
|
| 190 |
+
"grad_norm": 1.920448660850525,
|
| 191 |
+
"learning_rate": 1.1335511982570806e-05,
|
| 192 |
+
"loss": 0.0642,
|
| 193 |
+
"step": 10000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 5.0,
|
| 197 |
+
"eval_accuracy": 0.8349903918456011,
|
| 198 |
+
"eval_f1": 0.8161593595829842,
|
| 199 |
+
"eval_precision": 0.9233361415332771,
|
| 200 |
+
"eval_recall": 0.7312760633861551,
|
| 201 |
+
"eval_runtime": 50.2334,
|
| 202 |
+
"eval_samples_per_second": 238.268,
|
| 203 |
+
"eval_steps_per_second": 3.743,
|
| 204 |
+
"step": 10200
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.147058823529412,
|
| 208 |
+
"grad_norm": 0.24896511435508728,
|
| 209 |
+
"learning_rate": 1.0790849673202614e-05,
|
| 210 |
+
"loss": 0.0484,
|
| 211 |
+
"step": 10500
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 5.392156862745098,
|
| 215 |
+
"grad_norm": 0.1454085409641266,
|
| 216 |
+
"learning_rate": 1.0248366013071896e-05,
|
| 217 |
+
"loss": 0.0428,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.637254901960784,
|
| 222 |
+
"grad_norm": 0.20693035423755646,
|
| 223 |
+
"learning_rate": 9.703703703703703e-06,
|
| 224 |
+
"loss": 0.0422,
|
| 225 |
+
"step": 11500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 5.882352941176471,
|
| 229 |
+
"grad_norm": 7.705965518951416,
|
| 230 |
+
"learning_rate": 9.159041394335513e-06,
|
| 231 |
+
"loss": 0.0439,
|
| 232 |
+
"step": 12000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 6.0,
|
| 236 |
+
"eval_accuracy": 0.82078703316902,
|
| 237 |
+
"eval_f1": 0.7939283312518013,
|
| 238 |
+
"eval_precision": 0.9361123697326688,
|
| 239 |
+
"eval_recall": 0.6892410341951626,
|
| 240 |
+
"eval_runtime": 50.1119,
|
| 241 |
+
"eval_samples_per_second": 238.846,
|
| 242 |
+
"eval_steps_per_second": 3.752,
|
| 243 |
+
"step": 12240
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.127450980392156,
|
| 247 |
+
"grad_norm": 3.6634812355041504,
|
| 248 |
+
"learning_rate": 8.614379084967321e-06,
|
| 249 |
+
"loss": 0.0368,
|
| 250 |
+
"step": 12500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 6.372549019607844,
|
| 254 |
+
"grad_norm": 0.9099088311195374,
|
| 255 |
+
"learning_rate": 8.069716775599129e-06,
|
| 256 |
+
"loss": 0.0299,
|
| 257 |
+
"step": 13000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 6.617647058823529,
|
| 261 |
+
"grad_norm": 4.98677921295166,
|
| 262 |
+
"learning_rate": 7.5250544662309376e-06,
|
| 263 |
+
"loss": 0.0305,
|
| 264 |
+
"step": 13500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.862745098039216,
|
| 268 |
+
"grad_norm": 1.047827124595642,
|
| 269 |
+
"learning_rate": 6.9803921568627454e-06,
|
| 270 |
+
"loss": 0.0322,
|
| 271 |
+
"step": 14000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 7.0,
|
| 275 |
+
"eval_accuracy": 0.8311471300860557,
|
| 276 |
+
"eval_f1": 0.8085630387420669,
|
| 277 |
+
"eval_precision": 0.9355545813239807,
|
| 278 |
+
"eval_recall": 0.7119266055045872,
|
| 279 |
+
"eval_runtime": 50.2076,
|
| 280 |
+
"eval_samples_per_second": 238.39,
|
| 281 |
+
"eval_steps_per_second": 3.744,
|
| 282 |
+
"step": 14280
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.107843137254902,
|
| 286 |
+
"grad_norm": 4.889837741851807,
|
| 287 |
+
"learning_rate": 6.435729847494554e-06,
|
| 288 |
+
"loss": 0.0278,
|
| 289 |
+
"step": 14500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.352941176470588,
|
| 293 |
+
"grad_norm": 0.027428582310676575,
|
| 294 |
+
"learning_rate": 5.891067538126363e-06,
|
| 295 |
+
"loss": 0.0242,
|
| 296 |
+
"step": 15000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.598039215686274,
|
| 300 |
+
"grad_norm": 15.176671981811523,
|
| 301 |
+
"learning_rate": 5.34640522875817e-06,
|
| 302 |
+
"loss": 0.0216,
|
| 303 |
+
"step": 15500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.8431372549019605,
|
| 307 |
+
"grad_norm": 0.10369198769330978,
|
| 308 |
+
"learning_rate": 4.801742919389979e-06,
|
| 309 |
+
"loss": 0.0241,
|
| 310 |
+
"step": 16000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.0,
|
| 314 |
+
"eval_accuracy": 0.8279722616759964,
|
| 315 |
+
"eval_f1": 0.8052586777641162,
|
| 316 |
+
"eval_precision": 0.9298820445609436,
|
| 317 |
+
"eval_recall": 0.710091743119266,
|
| 318 |
+
"eval_runtime": 50.123,
|
| 319 |
+
"eval_samples_per_second": 238.792,
|
| 320 |
+
"eval_steps_per_second": 3.751,
|
| 321 |
+
"step": 16320
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 8.088235294117647,
|
| 325 |
+
"grad_norm": 6.414863109588623,
|
| 326 |
+
"learning_rate": 4.2570806100217874e-06,
|
| 327 |
+
"loss": 0.0223,
|
| 328 |
+
"step": 16500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 8.333333333333334,
|
| 332 |
+
"grad_norm": 7.71334981918335,
|
| 333 |
+
"learning_rate": 3.7135076252723314e-06,
|
| 334 |
+
"loss": 0.0161,
|
| 335 |
+
"step": 17000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 8.57843137254902,
|
| 339 |
+
"grad_norm": 6.453121662139893,
|
| 340 |
+
"learning_rate": 3.1688453159041397e-06,
|
| 341 |
+
"loss": 0.0191,
|
| 342 |
+
"step": 17500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 8.823529411764707,
|
| 346 |
+
"grad_norm": 17.10112762451172,
|
| 347 |
+
"learning_rate": 2.624183006535948e-06,
|
| 348 |
+
"loss": 0.0182,
|
| 349 |
+
"step": 18000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 9.0,
|
| 353 |
+
"eval_accuracy": 0.8256328849527947,
|
| 354 |
+
"eval_f1": 0.8022738038844149,
|
| 355 |
+
"eval_precision": 0.9285087719298246,
|
| 356 |
+
"eval_recall": 0.706255212677231,
|
| 357 |
+
"eval_runtime": 50.0398,
|
| 358 |
+
"eval_samples_per_second": 239.19,
|
| 359 |
+
"eval_steps_per_second": 3.757,
|
| 360 |
+
"step": 18360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 9.068627450980392,
|
| 364 |
+
"grad_norm": 0.027658773586153984,
|
| 365 |
+
"learning_rate": 2.0795206971677563e-06,
|
| 366 |
+
"loss": 0.0179,
|
| 367 |
+
"step": 18500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 9.313725490196079,
|
| 371 |
+
"grad_norm": 0.012034358456730843,
|
| 372 |
+
"learning_rate": 1.5348583877995642e-06,
|
| 373 |
+
"loss": 0.0142,
|
| 374 |
+
"step": 19000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 9.558823529411764,
|
| 378 |
+
"grad_norm": 0.053181909024715424,
|
| 379 |
+
"learning_rate": 9.923747276688455e-07,
|
| 380 |
+
"loss": 0.0117,
|
| 381 |
+
"step": 19500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 9.803921568627452,
|
| 385 |
+
"grad_norm": 0.0060155196115374565,
|
| 386 |
+
"learning_rate": 4.477124183006536e-07,
|
| 387 |
+
"loss": 0.0125,
|
| 388 |
+
"step": 20000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 10.0,
|
| 392 |
+
"eval_accuracy": 0.831397777592113,
|
| 393 |
+
"eval_f1": 0.8103383458646617,
|
| 394 |
+
"eval_precision": 0.9280947255113025,
|
| 395 |
+
"eval_recall": 0.7190992493744788,
|
| 396 |
+
"eval_runtime": 50.2235,
|
| 397 |
+
"eval_samples_per_second": 238.315,
|
| 398 |
+
"eval_steps_per_second": 3.743,
|
| 399 |
+
"step": 20400
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 10.0,
|
| 403 |
+
"step": 20400,
|
| 404 |
+
"total_flos": 3.433678205764608e+17,
|
| 405 |
+
"train_loss": 0.1127255682851754,
|
| 406 |
+
"train_runtime": 14662.5965,
|
| 407 |
+
"train_samples_per_second": 89.004,
|
| 408 |
+
"train_steps_per_second": 1.391
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"logging_steps": 500,
|
| 412 |
+
"max_steps": 20400,
|
| 413 |
+
"num_input_tokens_seen": 0,
|
| 414 |
+
"num_train_epochs": 10,
|
| 415 |
+
"save_steps": 5000,
|
| 416 |
+
"stateful_callbacks": {
|
| 417 |
+
"TrainerControl": {
|
| 418 |
+
"args": {
|
| 419 |
+
"should_epoch_stop": false,
|
| 420 |
+
"should_evaluate": false,
|
| 421 |
+
"should_log": false,
|
| 422 |
+
"should_save": true,
|
| 423 |
+
"should_training_stop": false
|
| 424 |
+
},
|
| 425 |
+
"attributes": {}
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"total_flos": 3.433678205764608e+17,
|
| 429 |
+
"train_batch_size": 64,
|
| 430 |
+
"trial_name": null,
|
| 431 |
+
"trial_params": null
|
| 432 |
+
}
|
sketch/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe9bba43f581225319e9bf9748c1a32355e5b612f6b61d90f7370956d30d4e0d
|
| 3 |
+
size 4667
|
sketch/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|