Upload 11 files
Browse files- config.json +35 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +361 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Davit6174/georgian-distilbert-mlm",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0,
|
| 19 |
+
"LABEL_1": 1,
|
| 20 |
+
"LABEL_2": 2
|
| 21 |
+
},
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "distilbert",
|
| 24 |
+
"n_heads": 12,
|
| 25 |
+
"n_layers": 6,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"qa_dropout": 0.1,
|
| 29 |
+
"seq_classif_dropout": 0.2,
|
| 30 |
+
"sinusoidal_pos_embds": false,
|
| 31 |
+
"tie_weights_": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.37.2",
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c005ffe73326c0f1a0caecacf43eaa4840ea0e749c4922792a0a2561c398399
|
| 3 |
+
size 267835644
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979a6d1c7f6c20cbf545c8e0064b7233aab7f997493ea8d1e024dab226c52814
|
| 3 |
+
size 535730554
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49146966fa233318e0182b40a65cb7d1100d138be0297f2502680909d70903bc
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9adde63377a6aa243886ea35d5163440b839c9f4580092fcfa76ba58691794dc
|
| 3 |
+
size 1064
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7875,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.9292134831460674,
|
| 14 |
+
"eval_f1_score": 0.9292134831460674,
|
| 15 |
+
"eval_loss": 0.19579175114631653,
|
| 16 |
+
"eval_runtime": 12.5946,
|
| 17 |
+
"eval_samples_per_second": 70.665,
|
| 18 |
+
"eval_steps_per_second": 1.112,
|
| 19 |
+
"step": 315
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 1.59,
|
| 23 |
+
"learning_rate": 4.682539682539683e-05,
|
| 24 |
+
"loss": 0.2897,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.9235955056179775,
|
| 30 |
+
"eval_f1_score": 0.9235955056179775,
|
| 31 |
+
"eval_loss": 0.2937149703502655,
|
| 32 |
+
"eval_runtime": 12.3147,
|
| 33 |
+
"eval_samples_per_second": 72.272,
|
| 34 |
+
"eval_steps_per_second": 1.137,
|
| 35 |
+
"step": 630
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"eval_accuracy": 0.9348314606741573,
|
| 40 |
+
"eval_f1_score": 0.9348314606741573,
|
| 41 |
+
"eval_loss": 0.34074461460113525,
|
| 42 |
+
"eval_runtime": 12.3763,
|
| 43 |
+
"eval_samples_per_second": 71.912,
|
| 44 |
+
"eval_steps_per_second": 1.131,
|
| 45 |
+
"step": 945
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.17,
|
| 49 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 50 |
+
"loss": 0.0673,
|
| 51 |
+
"step": 1000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"eval_accuracy": 0.9337078651685393,
|
| 56 |
+
"eval_f1_score": 0.9337078651685393,
|
| 57 |
+
"eval_loss": 0.36005520820617676,
|
| 58 |
+
"eval_runtime": 12.1209,
|
| 59 |
+
"eval_samples_per_second": 73.427,
|
| 60 |
+
"eval_steps_per_second": 1.155,
|
| 61 |
+
"step": 1260
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 4.76,
|
| 65 |
+
"learning_rate": 4.047619047619048e-05,
|
| 66 |
+
"loss": 0.0248,
|
| 67 |
+
"step": 1500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 5.0,
|
| 71 |
+
"eval_accuracy": 0.9426966292134832,
|
| 72 |
+
"eval_f1_score": 0.9426966292134832,
|
| 73 |
+
"eval_loss": 0.3878713548183441,
|
| 74 |
+
"eval_runtime": 12.0275,
|
| 75 |
+
"eval_samples_per_second": 73.997,
|
| 76 |
+
"eval_steps_per_second": 1.164,
|
| 77 |
+
"step": 1575
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_accuracy": 0.9404494382022472,
|
| 82 |
+
"eval_f1_score": 0.9404494382022472,
|
| 83 |
+
"eval_loss": 0.40726980566978455,
|
| 84 |
+
"eval_runtime": 12.3482,
|
| 85 |
+
"eval_samples_per_second": 72.075,
|
| 86 |
+
"eval_steps_per_second": 1.134,
|
| 87 |
+
"step": 1890
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.35,
|
| 91 |
+
"learning_rate": 3.730158730158731e-05,
|
| 92 |
+
"loss": 0.0192,
|
| 93 |
+
"step": 2000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.9303370786516854,
|
| 98 |
+
"eval_f1_score": 0.9303370786516854,
|
| 99 |
+
"eval_loss": 0.5313782095909119,
|
| 100 |
+
"eval_runtime": 11.9506,
|
| 101 |
+
"eval_samples_per_second": 74.473,
|
| 102 |
+
"eval_steps_per_second": 1.171,
|
| 103 |
+
"step": 2205
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 7.94,
|
| 107 |
+
"learning_rate": 3.412698412698413e-05,
|
| 108 |
+
"loss": 0.006,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 8.0,
|
| 113 |
+
"eval_accuracy": 0.9426966292134832,
|
| 114 |
+
"eval_f1_score": 0.9426966292134832,
|
| 115 |
+
"eval_loss": 0.4414384067058563,
|
| 116 |
+
"eval_runtime": 12.1778,
|
| 117 |
+
"eval_samples_per_second": 73.084,
|
| 118 |
+
"eval_steps_per_second": 1.15,
|
| 119 |
+
"step": 2520
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 9.0,
|
| 123 |
+
"eval_accuracy": 0.9393258426966292,
|
| 124 |
+
"eval_f1_score": 0.9393258426966292,
|
| 125 |
+
"eval_loss": 0.4911651909351349,
|
| 126 |
+
"eval_runtime": 12.0271,
|
| 127 |
+
"eval_samples_per_second": 74.0,
|
| 128 |
+
"eval_steps_per_second": 1.164,
|
| 129 |
+
"step": 2835
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.52,
|
| 133 |
+
"learning_rate": 3.095238095238095e-05,
|
| 134 |
+
"loss": 0.0035,
|
| 135 |
+
"step": 3000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.0,
|
| 139 |
+
"eval_accuracy": 0.9337078651685393,
|
| 140 |
+
"eval_f1_score": 0.9337078651685393,
|
| 141 |
+
"eval_loss": 0.5025097727775574,
|
| 142 |
+
"eval_runtime": 11.9685,
|
| 143 |
+
"eval_samples_per_second": 74.362,
|
| 144 |
+
"eval_steps_per_second": 1.17,
|
| 145 |
+
"step": 3150
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 11.0,
|
| 149 |
+
"eval_accuracy": 0.9438202247191011,
|
| 150 |
+
"eval_f1_score": 0.9438202247191011,
|
| 151 |
+
"eval_loss": 0.5351067185401917,
|
| 152 |
+
"eval_runtime": 12.1005,
|
| 153 |
+
"eval_samples_per_second": 73.551,
|
| 154 |
+
"eval_steps_per_second": 1.157,
|
| 155 |
+
"step": 3465
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.11,
|
| 159 |
+
"learning_rate": 2.777777777777778e-05,
|
| 160 |
+
"loss": 0.0022,
|
| 161 |
+
"step": 3500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 12.0,
|
| 165 |
+
"eval_accuracy": 0.9337078651685393,
|
| 166 |
+
"eval_f1_score": 0.9337078651685393,
|
| 167 |
+
"eval_loss": 0.6514860987663269,
|
| 168 |
+
"eval_runtime": 12.042,
|
| 169 |
+
"eval_samples_per_second": 73.908,
|
| 170 |
+
"eval_steps_per_second": 1.163,
|
| 171 |
+
"step": 3780
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.7,
|
| 175 |
+
"learning_rate": 2.4603174603174602e-05,
|
| 176 |
+
"loss": 0.0089,
|
| 177 |
+
"step": 4000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.9438202247191011,
|
| 182 |
+
"eval_f1_score": 0.9438202247191011,
|
| 183 |
+
"eval_loss": 0.42843857407569885,
|
| 184 |
+
"eval_runtime": 12.3213,
|
| 185 |
+
"eval_samples_per_second": 72.232,
|
| 186 |
+
"eval_steps_per_second": 1.136,
|
| 187 |
+
"step": 4095
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 14.0,
|
| 191 |
+
"eval_accuracy": 0.9393258426966292,
|
| 192 |
+
"eval_f1_score": 0.9393258426966292,
|
| 193 |
+
"eval_loss": 0.5087563395500183,
|
| 194 |
+
"eval_runtime": 12.0385,
|
| 195 |
+
"eval_samples_per_second": 73.93,
|
| 196 |
+
"eval_steps_per_second": 1.163,
|
| 197 |
+
"step": 4410
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.29,
|
| 201 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 202 |
+
"loss": 0.0125,
|
| 203 |
+
"step": 4500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 15.0,
|
| 207 |
+
"eval_accuracy": 0.9449438202247191,
|
| 208 |
+
"eval_f1_score": 0.9449438202247191,
|
| 209 |
+
"eval_loss": 0.5048856735229492,
|
| 210 |
+
"eval_runtime": 11.9611,
|
| 211 |
+
"eval_samples_per_second": 74.408,
|
| 212 |
+
"eval_steps_per_second": 1.17,
|
| 213 |
+
"step": 4725
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 15.87,
|
| 217 |
+
"learning_rate": 1.8253968253968254e-05,
|
| 218 |
+
"loss": 0.0,
|
| 219 |
+
"step": 5000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"eval_accuracy": 0.9438202247191011,
|
| 224 |
+
"eval_f1_score": 0.9438202247191011,
|
| 225 |
+
"eval_loss": 0.5166943073272705,
|
| 226 |
+
"eval_runtime": 11.932,
|
| 227 |
+
"eval_samples_per_second": 74.589,
|
| 228 |
+
"eval_steps_per_second": 1.173,
|
| 229 |
+
"step": 5040
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 17.0,
|
| 233 |
+
"eval_accuracy": 0.9426966292134832,
|
| 234 |
+
"eval_f1_score": 0.9426966292134832,
|
| 235 |
+
"eval_loss": 0.5239948630332947,
|
| 236 |
+
"eval_runtime": 12.002,
|
| 237 |
+
"eval_samples_per_second": 74.155,
|
| 238 |
+
"eval_steps_per_second": 1.166,
|
| 239 |
+
"step": 5355
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.46,
|
| 243 |
+
"learning_rate": 1.5079365079365079e-05,
|
| 244 |
+
"loss": 0.0,
|
| 245 |
+
"step": 5500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 18.0,
|
| 249 |
+
"eval_accuracy": 0.9426966292134832,
|
| 250 |
+
"eval_f1_score": 0.9426966292134832,
|
| 251 |
+
"eval_loss": 0.5701321363449097,
|
| 252 |
+
"eval_runtime": 12.1342,
|
| 253 |
+
"eval_samples_per_second": 73.347,
|
| 254 |
+
"eval_steps_per_second": 1.154,
|
| 255 |
+
"step": 5670
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.0,
|
| 259 |
+
"eval_accuracy": 0.9382022471910112,
|
| 260 |
+
"eval_f1_score": 0.9382022471910112,
|
| 261 |
+
"eval_loss": 0.5747442245483398,
|
| 262 |
+
"eval_runtime": 12.1144,
|
| 263 |
+
"eval_samples_per_second": 73.466,
|
| 264 |
+
"eval_steps_per_second": 1.156,
|
| 265 |
+
"step": 5985
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 19.05,
|
| 269 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 270 |
+
"loss": 0.0024,
|
| 271 |
+
"step": 6000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 20.0,
|
| 275 |
+
"eval_accuracy": 0.9393258426966292,
|
| 276 |
+
"eval_f1_score": 0.9393258426966292,
|
| 277 |
+
"eval_loss": 0.5525947213172913,
|
| 278 |
+
"eval_runtime": 12.0235,
|
| 279 |
+
"eval_samples_per_second": 74.022,
|
| 280 |
+
"eval_steps_per_second": 1.164,
|
| 281 |
+
"step": 6300
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.63,
|
| 285 |
+
"learning_rate": 8.73015873015873e-06,
|
| 286 |
+
"loss": 0.0013,
|
| 287 |
+
"step": 6500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 21.0,
|
| 291 |
+
"eval_accuracy": 0.9426966292134832,
|
| 292 |
+
"eval_f1_score": 0.9426966292134832,
|
| 293 |
+
"eval_loss": 0.5538011193275452,
|
| 294 |
+
"eval_runtime": 12.0212,
|
| 295 |
+
"eval_samples_per_second": 74.036,
|
| 296 |
+
"eval_steps_per_second": 1.165,
|
| 297 |
+
"step": 6615
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 22.0,
|
| 301 |
+
"eval_accuracy": 0.9426966292134832,
|
| 302 |
+
"eval_f1_score": 0.9426966292134832,
|
| 303 |
+
"eval_loss": 0.5597621202468872,
|
| 304 |
+
"eval_runtime": 12.4264,
|
| 305 |
+
"eval_samples_per_second": 71.622,
|
| 306 |
+
"eval_steps_per_second": 1.127,
|
| 307 |
+
"step": 6930
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 22.22,
|
| 311 |
+
"learning_rate": 5.555555555555556e-06,
|
| 312 |
+
"loss": 0.0,
|
| 313 |
+
"step": 7000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 23.0,
|
| 317 |
+
"eval_accuracy": 0.9415730337078652,
|
| 318 |
+
"eval_f1_score": 0.9415730337078652,
|
| 319 |
+
"eval_loss": 0.5650064945220947,
|
| 320 |
+
"eval_runtime": 12.6304,
|
| 321 |
+
"eval_samples_per_second": 70.465,
|
| 322 |
+
"eval_steps_per_second": 1.108,
|
| 323 |
+
"step": 7245
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.81,
|
| 327 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 328 |
+
"loss": 0.0,
|
| 329 |
+
"step": 7500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 24.0,
|
| 333 |
+
"eval_accuracy": 0.9415730337078652,
|
| 334 |
+
"eval_f1_score": 0.9415730337078652,
|
| 335 |
+
"eval_loss": 0.5530457496643066,
|
| 336 |
+
"eval_runtime": 15.9462,
|
| 337 |
+
"eval_samples_per_second": 55.813,
|
| 338 |
+
"eval_steps_per_second": 0.878,
|
| 339 |
+
"step": 7560
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 25.0,
|
| 343 |
+
"eval_accuracy": 0.9438202247191011,
|
| 344 |
+
"eval_f1_score": 0.9438202247191011,
|
| 345 |
+
"eval_loss": 0.5528258681297302,
|
| 346 |
+
"eval_runtime": 12.7008,
|
| 347 |
+
"eval_samples_per_second": 70.074,
|
| 348 |
+
"eval_steps_per_second": 1.102,
|
| 349 |
+
"step": 7875
|
| 350 |
+
}
|
| 351 |
+
],
|
| 352 |
+
"logging_steps": 500,
|
| 353 |
+
"max_steps": 7875,
|
| 354 |
+
"num_input_tokens_seen": 0,
|
| 355 |
+
"num_train_epochs": 25,
|
| 356 |
+
"save_steps": 500,
|
| 357 |
+
"total_flos": 934453337113386.0,
|
| 358 |
+
"train_batch_size": 16,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34e0247172de1db506bc443c8249c130559eee8e585a5a55c8936f3df08df4f
|
| 3 |
+
size 4664
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|