Commit
·
a6423a2
1
Parent(s):
e224651
model
Browse files- config.json +48 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +591 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
| 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 |
+
"id2label": {
|
| 13 |
+
"0": "NEUTRAL",
|
| 14 |
+
"1": "BIT-TOXIC",
|
| 15 |
+
"2": "QUITE-TOXIC",
|
| 16 |
+
"3": "TOXIC",
|
| 17 |
+
"4": "VERY-TOXIC",
|
| 18 |
+
"5": "HIGHLY-TOXIC"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"BIT-TOXIC": 1,
|
| 24 |
+
"HIGHLY-TOXIC": 5,
|
| 25 |
+
"NEUTRAL": 0,
|
| 26 |
+
"QUITE-TOXIC": 2,
|
| 27 |
+
"TOXIC": 3,
|
| 28 |
+
"VERY-TOXIC": 4
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"max_position_embeddings": 512,
|
| 32 |
+
"model_type": "bert",
|
| 33 |
+
"num_attention_heads": 12,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"pooler_fc_size": 768,
|
| 37 |
+
"pooler_num_attention_heads": 12,
|
| 38 |
+
"pooler_num_fc_layers": 3,
|
| 39 |
+
"pooler_size_per_head": 128,
|
| 40 |
+
"pooler_type": "first_token_transform",
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.36.2",
|
| 45 |
+
"type_vocab_size": 2,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 119547
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f4c7696f0cba53d4207583ae9b9a683524102dbfd63ee863773f29d234cb49
|
| 3 |
+
size 711455760
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34a22ef5c0907940797fd5b894119a620fdfd3e246d5b6083f07358e5e2c76b5
|
| 3 |
+
size 1423032570
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be4ae76b8db1a8668ce860e0149170e4ea4f4074988f7a6299bd79133abd4b7f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a844eb31be07bb7a2e7ed0754e6dfef47bac72858c4a8e254dd76d418ba90cb
|
| 3 |
+
size 1064
|
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 |
+
}
|
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 |
+
"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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"full_tokenizer_file": null,
|
| 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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.49082762002944946,
|
| 3 |
+
"best_model_checkpoint": "models/toxic-bert-mbert/checkpoint-380",
|
| 4 |
+
"epoch": 0.41170097508125675,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 380,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 1.968e-05,
|
| 14 |
+
"loss": 1.4487,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_f1": 0.48475671310316976,
|
| 20 |
+
"eval_loss": 1.1357542276382446,
|
| 21 |
+
"eval_runtime": 20.5083,
|
| 22 |
+
"eval_samples_per_second": 270.037,
|
| 23 |
+
"eval_steps_per_second": 11.264,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02,
|
| 28 |
+
"learning_rate": 1.9280000000000002e-05,
|
| 29 |
+
"loss": 1.1897,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"eval_f1": 0.48475671310316976,
|
| 35 |
+
"eval_loss": 1.0628113746643066,
|
| 36 |
+
"eval_runtime": 20.8063,
|
| 37 |
+
"eval_samples_per_second": 266.169,
|
| 38 |
+
"eval_steps_per_second": 11.102,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.8880000000000002e-05,
|
| 44 |
+
"loss": 1.0351,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"eval_f1": 0.48475671310316976,
|
| 50 |
+
"eval_loss": 1.0026295185089111,
|
| 51 |
+
"eval_runtime": 21.4302,
|
| 52 |
+
"eval_samples_per_second": 258.42,
|
| 53 |
+
"eval_steps_per_second": 10.779,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.04,
|
| 58 |
+
"learning_rate": 1.8480000000000003e-05,
|
| 59 |
+
"loss": 0.9274,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.04,
|
| 64 |
+
"eval_f1": 0.602134407148032,
|
| 65 |
+
"eval_loss": 0.8651727437973022,
|
| 66 |
+
"eval_runtime": 21.7252,
|
| 67 |
+
"eval_samples_per_second": 254.911,
|
| 68 |
+
"eval_steps_per_second": 10.633,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 1.8080000000000003e-05,
|
| 74 |
+
"loss": 0.8717,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.05,
|
| 79 |
+
"eval_f1": 0.5878712152620588,
|
| 80 |
+
"eval_loss": 0.8609752058982849,
|
| 81 |
+
"eval_runtime": 21.4208,
|
| 82 |
+
"eval_samples_per_second": 258.534,
|
| 83 |
+
"eval_steps_per_second": 10.784,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.07,
|
| 88 |
+
"learning_rate": 1.768e-05,
|
| 89 |
+
"loss": 0.8187,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.07,
|
| 94 |
+
"eval_f1": 0.6764570688570977,
|
| 95 |
+
"eval_loss": 0.7394715547561646,
|
| 96 |
+
"eval_runtime": 21.8392,
|
| 97 |
+
"eval_samples_per_second": 253.58,
|
| 98 |
+
"eval_steps_per_second": 10.577,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 1.732e-05,
|
| 104 |
+
"loss": 0.8706,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"eval_f1": 0.6850705705176812,
|
| 110 |
+
"eval_loss": 0.7013543844223022,
|
| 111 |
+
"eval_runtime": 21.7795,
|
| 112 |
+
"eval_samples_per_second": 254.276,
|
| 113 |
+
"eval_steps_per_second": 10.606,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09,
|
| 118 |
+
"learning_rate": 1.692e-05,
|
| 119 |
+
"loss": 0.7463,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.09,
|
| 124 |
+
"eval_f1": 0.7283246330984933,
|
| 125 |
+
"eval_loss": 0.665144681930542,
|
| 126 |
+
"eval_runtime": 21.4734,
|
| 127 |
+
"eval_samples_per_second": 257.901,
|
| 128 |
+
"eval_steps_per_second": 10.758,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 1.652e-05,
|
| 134 |
+
"loss": 0.7677,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"eval_f1": 0.6548131465387051,
|
| 140 |
+
"eval_loss": 0.718267560005188,
|
| 141 |
+
"eval_runtime": 21.871,
|
| 142 |
+
"eval_samples_per_second": 253.212,
|
| 143 |
+
"eval_steps_per_second": 10.562,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.11,
|
| 148 |
+
"learning_rate": 1.612e-05,
|
| 149 |
+
"loss": 0.6402,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.11,
|
| 154 |
+
"eval_f1": 0.7153883418869857,
|
| 155 |
+
"eval_loss": 0.6134028434753418,
|
| 156 |
+
"eval_runtime": 21.3946,
|
| 157 |
+
"eval_samples_per_second": 258.85,
|
| 158 |
+
"eval_steps_per_second": 10.797,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 1.5720000000000002e-05,
|
| 164 |
+
"loss": 0.6408,
|
| 165 |
+
"step": 110
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"eval_f1": 0.7200057070545418,
|
| 170 |
+
"eval_loss": 0.6316511034965515,
|
| 171 |
+
"eval_runtime": 21.4218,
|
| 172 |
+
"eval_samples_per_second": 258.521,
|
| 173 |
+
"eval_steps_per_second": 10.783,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.13,
|
| 178 |
+
"learning_rate": 1.5320000000000002e-05,
|
| 179 |
+
"loss": 0.6293,
|
| 180 |
+
"step": 120
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.13,
|
| 184 |
+
"eval_f1": 0.7252309612107771,
|
| 185 |
+
"eval_loss": 0.6177955865859985,
|
| 186 |
+
"eval_runtime": 22.0787,
|
| 187 |
+
"eval_samples_per_second": 250.831,
|
| 188 |
+
"eval_steps_per_second": 10.463,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 1.4920000000000001e-05,
|
| 194 |
+
"loss": 0.5921,
|
| 195 |
+
"step": 130
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.14,
|
| 199 |
+
"eval_f1": 0.718310903510847,
|
| 200 |
+
"eval_loss": 0.6382821798324585,
|
| 201 |
+
"eval_runtime": 21.4528,
|
| 202 |
+
"eval_samples_per_second": 258.148,
|
| 203 |
+
"eval_steps_per_second": 10.768,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.15,
|
| 208 |
+
"learning_rate": 1.4520000000000002e-05,
|
| 209 |
+
"loss": 0.6829,
|
| 210 |
+
"step": 140
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.15,
|
| 214 |
+
"eval_f1": 0.7104650126557948,
|
| 215 |
+
"eval_loss": 0.6063101291656494,
|
| 216 |
+
"eval_runtime": 21.6996,
|
| 217 |
+
"eval_samples_per_second": 255.212,
|
| 218 |
+
"eval_steps_per_second": 10.645,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 1.412e-05,
|
| 224 |
+
"loss": 0.6528,
|
| 225 |
+
"step": 150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.16,
|
| 229 |
+
"eval_f1": 0.7266460816131931,
|
| 230 |
+
"eval_loss": 0.5720272064208984,
|
| 231 |
+
"eval_runtime": 21.3758,
|
| 232 |
+
"eval_samples_per_second": 259.078,
|
| 233 |
+
"eval_steps_per_second": 10.807,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.17,
|
| 238 |
+
"learning_rate": 1.3720000000000002e-05,
|
| 239 |
+
"loss": 0.5472,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.17,
|
| 244 |
+
"eval_f1": 0.7174077954335052,
|
| 245 |
+
"eval_loss": 0.6016837358474731,
|
| 246 |
+
"eval_runtime": 21.9003,
|
| 247 |
+
"eval_samples_per_second": 252.873,
|
| 248 |
+
"eval_steps_per_second": 10.548,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.18,
|
| 253 |
+
"learning_rate": 1.3320000000000001e-05,
|
| 254 |
+
"loss": 0.6625,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.18,
|
| 259 |
+
"eval_f1": 0.7238055756700145,
|
| 260 |
+
"eval_loss": 0.5748048424720764,
|
| 261 |
+
"eval_runtime": 21.4241,
|
| 262 |
+
"eval_samples_per_second": 258.494,
|
| 263 |
+
"eval_steps_per_second": 10.782,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.2,
|
| 268 |
+
"learning_rate": 1.2920000000000002e-05,
|
| 269 |
+
"loss": 0.551,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.2,
|
| 274 |
+
"eval_f1": 0.7216203790293768,
|
| 275 |
+
"eval_loss": 0.5944197177886963,
|
| 276 |
+
"eval_runtime": 21.7253,
|
| 277 |
+
"eval_samples_per_second": 254.91,
|
| 278 |
+
"eval_steps_per_second": 10.633,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 1.252e-05,
|
| 284 |
+
"loss": 0.5633,
|
| 285 |
+
"step": 190
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.21,
|
| 289 |
+
"eval_f1": 0.7591239466384562,
|
| 290 |
+
"eval_loss": 0.5621122717857361,
|
| 291 |
+
"eval_runtime": 21.1932,
|
| 292 |
+
"eval_samples_per_second": 261.31,
|
| 293 |
+
"eval_steps_per_second": 10.9,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.22,
|
| 298 |
+
"learning_rate": 1.2120000000000001e-05,
|
| 299 |
+
"loss": 0.5372,
|
| 300 |
+
"step": 200
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.22,
|
| 304 |
+
"eval_f1": 0.75760072154562,
|
| 305 |
+
"eval_loss": 0.5480858087539673,
|
| 306 |
+
"eval_runtime": 21.2836,
|
| 307 |
+
"eval_samples_per_second": 260.201,
|
| 308 |
+
"eval_steps_per_second": 10.853,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.23,
|
| 313 |
+
"learning_rate": 1.172e-05,
|
| 314 |
+
"loss": 0.6353,
|
| 315 |
+
"step": 210
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.23,
|
| 319 |
+
"eval_f1": 0.7511938652247329,
|
| 320 |
+
"eval_loss": 0.5706632137298584,
|
| 321 |
+
"eval_runtime": 21.8422,
|
| 322 |
+
"eval_samples_per_second": 253.545,
|
| 323 |
+
"eval_steps_per_second": 10.576,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24,
|
| 328 |
+
"learning_rate": 1.132e-05,
|
| 329 |
+
"loss": 0.6332,
|
| 330 |
+
"step": 220
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.24,
|
| 334 |
+
"eval_f1": 0.7614490903091703,
|
| 335 |
+
"eval_loss": 0.5543012022972107,
|
| 336 |
+
"eval_runtime": 21.5696,
|
| 337 |
+
"eval_samples_per_second": 256.75,
|
| 338 |
+
"eval_steps_per_second": 10.71,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.25,
|
| 343 |
+
"learning_rate": 1.0920000000000002e-05,
|
| 344 |
+
"loss": 0.5311,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.25,
|
| 349 |
+
"eval_f1": 0.7432260016931946,
|
| 350 |
+
"eval_loss": 0.5397886633872986,
|
| 351 |
+
"eval_runtime": 21.3122,
|
| 352 |
+
"eval_samples_per_second": 259.851,
|
| 353 |
+
"eval_steps_per_second": 10.839,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.26,
|
| 358 |
+
"learning_rate": 1.0520000000000001e-05,
|
| 359 |
+
"loss": 0.5791,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.26,
|
| 364 |
+
"eval_f1": 0.7434033096243912,
|
| 365 |
+
"eval_loss": 0.5391152501106262,
|
| 366 |
+
"eval_runtime": 21.3796,
|
| 367 |
+
"eval_samples_per_second": 259.032,
|
| 368 |
+
"eval_steps_per_second": 10.805,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.27,
|
| 373 |
+
"learning_rate": 1.0120000000000001e-05,
|
| 374 |
+
"loss": 0.5831,
|
| 375 |
+
"step": 250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.27,
|
| 379 |
+
"eval_f1": 0.763099957359349,
|
| 380 |
+
"eval_loss": 0.5244932174682617,
|
| 381 |
+
"eval_runtime": 21.3101,
|
| 382 |
+
"eval_samples_per_second": 259.877,
|
| 383 |
+
"eval_steps_per_second": 10.84,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.28,
|
| 388 |
+
"learning_rate": 9.72e-06,
|
| 389 |
+
"loss": 0.5453,
|
| 390 |
+
"step": 260
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.28,
|
| 394 |
+
"eval_f1": 0.7585661401268046,
|
| 395 |
+
"eval_loss": 0.5211306214332581,
|
| 396 |
+
"eval_runtime": 21.2639,
|
| 397 |
+
"eval_samples_per_second": 260.442,
|
| 398 |
+
"eval_steps_per_second": 10.863,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.29,
|
| 403 |
+
"learning_rate": 9.32e-06,
|
| 404 |
+
"loss": 0.5087,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.29,
|
| 409 |
+
"eval_f1": 0.7549183270549422,
|
| 410 |
+
"eval_loss": 0.5206575989723206,
|
| 411 |
+
"eval_runtime": 21.5568,
|
| 412 |
+
"eval_samples_per_second": 256.902,
|
| 413 |
+
"eval_steps_per_second": 10.716,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.3,
|
| 418 |
+
"learning_rate": 8.920000000000001e-06,
|
| 419 |
+
"loss": 0.539,
|
| 420 |
+
"step": 280
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.3,
|
| 424 |
+
"eval_f1": 0.7483575758659107,
|
| 425 |
+
"eval_loss": 0.5601561665534973,
|
| 426 |
+
"eval_runtime": 21.7276,
|
| 427 |
+
"eval_samples_per_second": 254.883,
|
| 428 |
+
"eval_steps_per_second": 10.632,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.31,
|
| 433 |
+
"learning_rate": 8.52e-06,
|
| 434 |
+
"loss": 0.502,
|
| 435 |
+
"step": 290
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.31,
|
| 439 |
+
"eval_f1": 0.7497368207624416,
|
| 440 |
+
"eval_loss": 0.5269237160682678,
|
| 441 |
+
"eval_runtime": 21.3645,
|
| 442 |
+
"eval_samples_per_second": 259.215,
|
| 443 |
+
"eval_steps_per_second": 10.812,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.33,
|
| 448 |
+
"learning_rate": 8.120000000000002e-06,
|
| 449 |
+
"loss": 0.5656,
|
| 450 |
+
"step": 300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.33,
|
| 454 |
+
"eval_f1": 0.7490172830029811,
|
| 455 |
+
"eval_loss": 0.5704778432846069,
|
| 456 |
+
"eval_runtime": 21.3309,
|
| 457 |
+
"eval_samples_per_second": 259.623,
|
| 458 |
+
"eval_steps_per_second": 10.829,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.34,
|
| 463 |
+
"learning_rate": 7.72e-06,
|
| 464 |
+
"loss": 0.6157,
|
| 465 |
+
"step": 310
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.34,
|
| 469 |
+
"eval_f1": 0.7610313116302819,
|
| 470 |
+
"eval_loss": 0.5527724027633667,
|
| 471 |
+
"eval_runtime": 21.5886,
|
| 472 |
+
"eval_samples_per_second": 256.524,
|
| 473 |
+
"eval_steps_per_second": 10.7,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.35,
|
| 478 |
+
"learning_rate": 7.32e-06,
|
| 479 |
+
"loss": 0.5262,
|
| 480 |
+
"step": 320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.35,
|
| 484 |
+
"eval_f1": 0.7693956225207979,
|
| 485 |
+
"eval_loss": 0.5064041614532471,
|
| 486 |
+
"eval_runtime": 21.4519,
|
| 487 |
+
"eval_samples_per_second": 258.159,
|
| 488 |
+
"eval_steps_per_second": 10.768,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.36,
|
| 493 |
+
"learning_rate": 6.92e-06,
|
| 494 |
+
"loss": 0.5032,
|
| 495 |
+
"step": 330
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.36,
|
| 499 |
+
"eval_f1": 0.757594480871035,
|
| 500 |
+
"eval_loss": 0.5091240406036377,
|
| 501 |
+
"eval_runtime": 21.5576,
|
| 502 |
+
"eval_samples_per_second": 256.894,
|
| 503 |
+
"eval_steps_per_second": 10.716,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.37,
|
| 508 |
+
"learning_rate": 6.520000000000001e-06,
|
| 509 |
+
"loss": 0.4859,
|
| 510 |
+
"step": 340
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.37,
|
| 514 |
+
"eval_f1": 0.751697533021681,
|
| 515 |
+
"eval_loss": 0.5241729021072388,
|
| 516 |
+
"eval_runtime": 21.6466,
|
| 517 |
+
"eval_samples_per_second": 255.837,
|
| 518 |
+
"eval_steps_per_second": 10.671,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.38,
|
| 523 |
+
"learning_rate": 6.120000000000001e-06,
|
| 524 |
+
"loss": 0.6227,
|
| 525 |
+
"step": 350
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.38,
|
| 529 |
+
"eval_f1": 0.7821857624888272,
|
| 530 |
+
"eval_loss": 0.4922301769256592,
|
| 531 |
+
"eval_runtime": 21.5823,
|
| 532 |
+
"eval_samples_per_second": 256.599,
|
| 533 |
+
"eval_steps_per_second": 10.703,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.39,
|
| 538 |
+
"learning_rate": 5.72e-06,
|
| 539 |
+
"loss": 0.4927,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.39,
|
| 544 |
+
"eval_f1": 0.778530969617547,
|
| 545 |
+
"eval_loss": 0.4920683801174164,
|
| 546 |
+
"eval_runtime": 21.173,
|
| 547 |
+
"eval_samples_per_second": 261.559,
|
| 548 |
+
"eval_steps_per_second": 10.91,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.4,
|
| 553 |
+
"learning_rate": 5.320000000000001e-06,
|
| 554 |
+
"loss": 0.596,
|
| 555 |
+
"step": 370
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4,
|
| 559 |
+
"eval_f1": 0.7737080595193158,
|
| 560 |
+
"eval_loss": 0.509250283241272,
|
| 561 |
+
"eval_runtime": 21.9207,
|
| 562 |
+
"eval_samples_per_second": 252.638,
|
| 563 |
+
"eval_steps_per_second": 10.538,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.41,
|
| 568 |
+
"learning_rate": 4.92e-06,
|
| 569 |
+
"loss": 0.5932,
|
| 570 |
+
"step": 380
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.41,
|
| 574 |
+
"eval_f1": 0.7900070254555186,
|
| 575 |
+
"eval_loss": 0.49082762002944946,
|
| 576 |
+
"eval_runtime": 21.7381,
|
| 577 |
+
"eval_samples_per_second": 254.76,
|
| 578 |
+
"eval_steps_per_second": 10.627,
|
| 579 |
+
"step": 380
|
| 580 |
+
}
|
| 581 |
+
],
|
| 582 |
+
"logging_steps": 10,
|
| 583 |
+
"max_steps": 500,
|
| 584 |
+
"num_input_tokens_seen": 0,
|
| 585 |
+
"num_train_epochs": 1,
|
| 586 |
+
"save_steps": 10,
|
| 587 |
+
"total_flos": 547397542755648.0,
|
| 588 |
+
"train_batch_size": 24,
|
| 589 |
+
"trial_name": null,
|
| 590 |
+
"trial_params": null
|
| 591 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13e1e98689fe171b8a0795459a7b21fd7f54caa699e8895365cb71eb31905978
|
| 3 |
+
size 4728
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|