7000
Browse files- config.json +33 -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 +62 -0
- trainer_state.json +595 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Snowflake/snowflake-arctic-embed-m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "regression",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.40.1",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 30522
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a589d8f297ce0cb1f4669b9b33fe8fcdc1dad90dda103bf5896f6dcd8849e9e9
|
| 3 |
+
size 437955572
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f466bee5090bf14a0f63bf11698d910303fa47c7b4e1bfcec82129d6675dbc2d
|
| 3 |
+
size 4735250
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f29f533dcf5ca51daa42f8c902a3efeaef4392274e0947ca0b572950a8230ea
|
| 3 |
+
size 14180
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80e5dc59d04522e0b163280cdeee9810a4aa398767a7c0437325a0272e0591b6
|
| 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 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 512,
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_to_multiple_of": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"pad_token_type_id": 0,
|
| 53 |
+
"padding_side": "right",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"tokenize_chinese_chars": true,
|
| 58 |
+
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4678440617843855,
|
| 3 |
+
"best_model_checkpoint": "/fsx/anton/cosmopedia/edu_score/bert_snowflake_regression_4/checkpoint-7000",
|
| 4 |
+
"epoch": 4.247572815533981,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 7000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06067961165048544,
|
| 13 |
+
"grad_norm": 0.5638211965560913,
|
| 14 |
+
"learning_rate": 0.0002990898058252427,
|
| 15 |
+
"loss": 0.4753,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12135922330097088,
|
| 20 |
+
"grad_norm": 0.47830212116241455,
|
| 21 |
+
"learning_rate": 0.0002981796116504854,
|
| 22 |
+
"loss": 0.357,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1820388349514563,
|
| 27 |
+
"grad_norm": 0.6941384077072144,
|
| 28 |
+
"learning_rate": 0.0002972694174757281,
|
| 29 |
+
"loss": 0.3542,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.24271844660194175,
|
| 34 |
+
"grad_norm": 0.459163635969162,
|
| 35 |
+
"learning_rate": 0.00029635922330097087,
|
| 36 |
+
"loss": 0.3508,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.30339805825242716,
|
| 41 |
+
"grad_norm": 1.1585971117019653,
|
| 42 |
+
"learning_rate": 0.0002954490291262136,
|
| 43 |
+
"loss": 0.3407,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3640776699029126,
|
| 48 |
+
"grad_norm": 0.6505594849586487,
|
| 49 |
+
"learning_rate": 0.0002945388349514563,
|
| 50 |
+
"loss": 0.3394,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.42475728155339804,
|
| 55 |
+
"grad_norm": 0.9804072976112366,
|
| 56 |
+
"learning_rate": 0.000293628640776699,
|
| 57 |
+
"loss": 0.3435,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4854368932038835,
|
| 62 |
+
"grad_norm": 0.5816351175308228,
|
| 63 |
+
"learning_rate": 0.0002927184466019417,
|
| 64 |
+
"loss": 0.3323,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5461165048543689,
|
| 69 |
+
"grad_norm": 0.6582027673721313,
|
| 70 |
+
"learning_rate": 0.00029180825242718447,
|
| 71 |
+
"loss": 0.3293,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6067961165048543,
|
| 76 |
+
"grad_norm": 0.8432559370994568,
|
| 77 |
+
"learning_rate": 0.0002908980582524271,
|
| 78 |
+
"loss": 0.3337,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6067961165048543,
|
| 83 |
+
"eval_accuracy": 0.6516312117268014,
|
| 84 |
+
"eval_f1_macro": 0.388617225018415,
|
| 85 |
+
"eval_loss": 0.32428401708602905,
|
| 86 |
+
"eval_precision": 0.5273989146868351,
|
| 87 |
+
"eval_recall": 0.3731209274235363,
|
| 88 |
+
"eval_runtime": 63.5791,
|
| 89 |
+
"eval_samples_per_second": 737.144,
|
| 90 |
+
"eval_steps_per_second": 5.772,
|
| 91 |
+
"step": 1000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.6674757281553398,
|
| 95 |
+
"grad_norm": 0.6387248039245605,
|
| 96 |
+
"learning_rate": 0.0002899878640776699,
|
| 97 |
+
"loss": 0.3292,
|
| 98 |
+
"step": 1100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.7281553398058253,
|
| 102 |
+
"grad_norm": 2.0111730098724365,
|
| 103 |
+
"learning_rate": 0.0002890776699029126,
|
| 104 |
+
"loss": 0.3283,
|
| 105 |
+
"step": 1200
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.7888349514563107,
|
| 109 |
+
"grad_norm": 1.0319699048995972,
|
| 110 |
+
"learning_rate": 0.0002881674757281553,
|
| 111 |
+
"loss": 0.3236,
|
| 112 |
+
"step": 1300
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.8495145631067961,
|
| 116 |
+
"grad_norm": 1.194286584854126,
|
| 117 |
+
"learning_rate": 0.000287257281553398,
|
| 118 |
+
"loss": 0.3178,
|
| 119 |
+
"step": 1400
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.9101941747572816,
|
| 123 |
+
"grad_norm": 0.4329046308994293,
|
| 124 |
+
"learning_rate": 0.00028634708737864073,
|
| 125 |
+
"loss": 0.3234,
|
| 126 |
+
"step": 1500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.970873786407767,
|
| 130 |
+
"grad_norm": 0.4490291476249695,
|
| 131 |
+
"learning_rate": 0.0002854368932038835,
|
| 132 |
+
"loss": 0.3148,
|
| 133 |
+
"step": 1600
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.0315533980582525,
|
| 137 |
+
"grad_norm": 1.9341398477554321,
|
| 138 |
+
"learning_rate": 0.0002845266990291262,
|
| 139 |
+
"loss": 0.3157,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0922330097087378,
|
| 144 |
+
"grad_norm": 0.6705629825592041,
|
| 145 |
+
"learning_rate": 0.0002836165048543689,
|
| 146 |
+
"loss": 0.3144,
|
| 147 |
+
"step": 1800
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.1529126213592233,
|
| 151 |
+
"grad_norm": 0.3708420395851135,
|
| 152 |
+
"learning_rate": 0.0002827063106796116,
|
| 153 |
+
"loss": 0.3106,
|
| 154 |
+
"step": 1900
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.2135922330097086,
|
| 158 |
+
"grad_norm": 0.4166070222854614,
|
| 159 |
+
"learning_rate": 0.00028179611650485433,
|
| 160 |
+
"loss": 0.3065,
|
| 161 |
+
"step": 2000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.2135922330097086,
|
| 165 |
+
"eval_accuracy": 0.6756993193505025,
|
| 166 |
+
"eval_f1_macro": 0.4177625223934091,
|
| 167 |
+
"eval_loss": 0.3020932972431183,
|
| 168 |
+
"eval_precision": 0.5208365532058327,
|
| 169 |
+
"eval_recall": 0.3908095186846785,
|
| 170 |
+
"eval_runtime": 63.8686,
|
| 171 |
+
"eval_samples_per_second": 733.803,
|
| 172 |
+
"eval_steps_per_second": 5.746,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.2742718446601942,
|
| 177 |
+
"grad_norm": 0.949810266494751,
|
| 178 |
+
"learning_rate": 0.00028088592233009704,
|
| 179 |
+
"loss": 0.309,
|
| 180 |
+
"step": 2100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.3349514563106797,
|
| 184 |
+
"grad_norm": 0.6933236718177795,
|
| 185 |
+
"learning_rate": 0.00027997572815533975,
|
| 186 |
+
"loss": 0.3039,
|
| 187 |
+
"step": 2200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.395631067961165,
|
| 191 |
+
"grad_norm": 0.4874693751335144,
|
| 192 |
+
"learning_rate": 0.0002790655339805825,
|
| 193 |
+
"loss": 0.3016,
|
| 194 |
+
"step": 2300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.4563106796116505,
|
| 198 |
+
"grad_norm": 0.5307803750038147,
|
| 199 |
+
"learning_rate": 0.0002781553398058252,
|
| 200 |
+
"loss": 0.295,
|
| 201 |
+
"step": 2400
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.516990291262136,
|
| 205 |
+
"grad_norm": 0.7260825634002686,
|
| 206 |
+
"learning_rate": 0.00027724514563106793,
|
| 207 |
+
"loss": 0.298,
|
| 208 |
+
"step": 2500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.5776699029126213,
|
| 212 |
+
"grad_norm": 1.3546072244644165,
|
| 213 |
+
"learning_rate": 0.00027633495145631064,
|
| 214 |
+
"loss": 0.2937,
|
| 215 |
+
"step": 2600
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.6383495145631068,
|
| 219 |
+
"grad_norm": 0.7695233821868896,
|
| 220 |
+
"learning_rate": 0.00027542475728155335,
|
| 221 |
+
"loss": 0.2939,
|
| 222 |
+
"step": 2700
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.6990291262135924,
|
| 226 |
+
"grad_norm": 0.46857160329818726,
|
| 227 |
+
"learning_rate": 0.0002745145631067961,
|
| 228 |
+
"loss": 0.2911,
|
| 229 |
+
"step": 2800
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.7597087378640777,
|
| 233 |
+
"grad_norm": 0.521542489528656,
|
| 234 |
+
"learning_rate": 0.0002736043689320388,
|
| 235 |
+
"loss": 0.2936,
|
| 236 |
+
"step": 2900
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.820388349514563,
|
| 240 |
+
"grad_norm": 1.1797749996185303,
|
| 241 |
+
"learning_rate": 0.00027269417475728154,
|
| 242 |
+
"loss": 0.291,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.820388349514563,
|
| 247 |
+
"eval_accuracy": 0.6800947361683061,
|
| 248 |
+
"eval_f1_macro": 0.43005056999542096,
|
| 249 |
+
"eval_loss": 0.2904761731624603,
|
| 250 |
+
"eval_precision": 0.5283372179121356,
|
| 251 |
+
"eval_recall": 0.40012210038254903,
|
| 252 |
+
"eval_runtime": 63.5697,
|
| 253 |
+
"eval_samples_per_second": 737.253,
|
| 254 |
+
"eval_steps_per_second": 5.773,
|
| 255 |
+
"step": 3000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.8810679611650487,
|
| 259 |
+
"grad_norm": 0.9966709613800049,
|
| 260 |
+
"learning_rate": 0.00027178398058252425,
|
| 261 |
+
"loss": 0.2965,
|
| 262 |
+
"step": 3100
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.941747572815534,
|
| 266 |
+
"grad_norm": 0.40996024012565613,
|
| 267 |
+
"learning_rate": 0.00027087378640776696,
|
| 268 |
+
"loss": 0.2941,
|
| 269 |
+
"step": 3200
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.0024271844660193,
|
| 273 |
+
"grad_norm": 0.5450060367584229,
|
| 274 |
+
"learning_rate": 0.00026996359223300967,
|
| 275 |
+
"loss": 0.2912,
|
| 276 |
+
"step": 3300
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.063106796116505,
|
| 280 |
+
"grad_norm": 0.5307539701461792,
|
| 281 |
+
"learning_rate": 0.0002690533980582524,
|
| 282 |
+
"loss": 0.2872,
|
| 283 |
+
"step": 3400
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.1237864077669903,
|
| 287 |
+
"grad_norm": 0.5863193273544312,
|
| 288 |
+
"learning_rate": 0.00026814320388349514,
|
| 289 |
+
"loss": 0.2929,
|
| 290 |
+
"step": 3500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.1844660194174756,
|
| 294 |
+
"grad_norm": 0.584078311920166,
|
| 295 |
+
"learning_rate": 0.00026723300970873785,
|
| 296 |
+
"loss": 0.2879,
|
| 297 |
+
"step": 3600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.2451456310679614,
|
| 301 |
+
"grad_norm": 0.6381602883338928,
|
| 302 |
+
"learning_rate": 0.00026632281553398056,
|
| 303 |
+
"loss": 0.2892,
|
| 304 |
+
"step": 3700
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.3058252427184467,
|
| 308 |
+
"grad_norm": 0.4760149121284485,
|
| 309 |
+
"learning_rate": 0.00026541262135922327,
|
| 310 |
+
"loss": 0.2863,
|
| 311 |
+
"step": 3800
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.366504854368932,
|
| 315 |
+
"grad_norm": 0.4088296890258789,
|
| 316 |
+
"learning_rate": 0.000264502427184466,
|
| 317 |
+
"loss": 0.2913,
|
| 318 |
+
"step": 3900
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.4271844660194173,
|
| 322 |
+
"grad_norm": 1.3476176261901855,
|
| 323 |
+
"learning_rate": 0.00026359223300970874,
|
| 324 |
+
"loss": 0.2845,
|
| 325 |
+
"step": 4000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.4271844660194173,
|
| 329 |
+
"eval_accuracy": 0.6929182580493738,
|
| 330 |
+
"eval_f1_macro": 0.4442664055274559,
|
| 331 |
+
"eval_loss": 0.280377060174942,
|
| 332 |
+
"eval_precision": 0.5328225535144124,
|
| 333 |
+
"eval_recall": 0.41160029395774395,
|
| 334 |
+
"eval_runtime": 64.199,
|
| 335 |
+
"eval_samples_per_second": 730.027,
|
| 336 |
+
"eval_steps_per_second": 5.717,
|
| 337 |
+
"step": 4000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.487864077669903,
|
| 341 |
+
"grad_norm": 0.6318752765655518,
|
| 342 |
+
"learning_rate": 0.0002626820388349514,
|
| 343 |
+
"loss": 0.2812,
|
| 344 |
+
"step": 4100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.5485436893203883,
|
| 348 |
+
"grad_norm": 0.49435973167419434,
|
| 349 |
+
"learning_rate": 0.00026177184466019416,
|
| 350 |
+
"loss": 0.2803,
|
| 351 |
+
"step": 4200
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.6092233009708736,
|
| 355 |
+
"grad_norm": 0.4300900101661682,
|
| 356 |
+
"learning_rate": 0.00026086165048543687,
|
| 357 |
+
"loss": 0.2853,
|
| 358 |
+
"step": 4300
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.6699029126213594,
|
| 362 |
+
"grad_norm": 0.9545436501502991,
|
| 363 |
+
"learning_rate": 0.0002599514563106796,
|
| 364 |
+
"loss": 0.2813,
|
| 365 |
+
"step": 4400
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.7305825242718447,
|
| 369 |
+
"grad_norm": 0.5803716778755188,
|
| 370 |
+
"learning_rate": 0.0002590412621359223,
|
| 371 |
+
"loss": 0.2838,
|
| 372 |
+
"step": 4500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.79126213592233,
|
| 376 |
+
"grad_norm": 1.4714713096618652,
|
| 377 |
+
"learning_rate": 0.000258131067961165,
|
| 378 |
+
"loss": 0.2814,
|
| 379 |
+
"step": 4600
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.8519417475728153,
|
| 383 |
+
"grad_norm": 0.6767821311950684,
|
| 384 |
+
"learning_rate": 0.00025722087378640777,
|
| 385 |
+
"loss": 0.2741,
|
| 386 |
+
"step": 4700
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.912621359223301,
|
| 390 |
+
"grad_norm": 0.4653462767601013,
|
| 391 |
+
"learning_rate": 0.0002563106796116505,
|
| 392 |
+
"loss": 0.2783,
|
| 393 |
+
"step": 4800
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.9733009708737863,
|
| 397 |
+
"grad_norm": 1.3012775182724,
|
| 398 |
+
"learning_rate": 0.0002554004854368932,
|
| 399 |
+
"loss": 0.283,
|
| 400 |
+
"step": 4900
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.033980582524272,
|
| 404 |
+
"grad_norm": 0.4733451306819916,
|
| 405 |
+
"learning_rate": 0.0002544902912621359,
|
| 406 |
+
"loss": 0.2767,
|
| 407 |
+
"step": 5000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.033980582524272,
|
| 411 |
+
"eval_accuracy": 0.6949666076343696,
|
| 412 |
+
"eval_f1_macro": 0.4524166681181929,
|
| 413 |
+
"eval_loss": 0.2772601842880249,
|
| 414 |
+
"eval_precision": 0.52914110464024,
|
| 415 |
+
"eval_recall": 0.42261704559523156,
|
| 416 |
+
"eval_runtime": 63.4257,
|
| 417 |
+
"eval_samples_per_second": 738.927,
|
| 418 |
+
"eval_steps_per_second": 5.786,
|
| 419 |
+
"step": 5000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.0946601941747574,
|
| 423 |
+
"grad_norm": 0.4103662371635437,
|
| 424 |
+
"learning_rate": 0.0002535800970873786,
|
| 425 |
+
"loss": 0.2796,
|
| 426 |
+
"step": 5100
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.1553398058252426,
|
| 430 |
+
"grad_norm": 0.4195462763309479,
|
| 431 |
+
"learning_rate": 0.0002526699029126213,
|
| 432 |
+
"loss": 0.2757,
|
| 433 |
+
"step": 5200
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.216019417475728,
|
| 437 |
+
"grad_norm": 1.2391552925109863,
|
| 438 |
+
"learning_rate": 0.0002517597087378641,
|
| 439 |
+
"loss": 0.2783,
|
| 440 |
+
"step": 5300
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.2766990291262137,
|
| 444 |
+
"grad_norm": 1.2029412984848022,
|
| 445 |
+
"learning_rate": 0.0002508495145631068,
|
| 446 |
+
"loss": 0.2772,
|
| 447 |
+
"step": 5400
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.337378640776699,
|
| 451 |
+
"grad_norm": 0.5050978660583496,
|
| 452 |
+
"learning_rate": 0.0002499393203883495,
|
| 453 |
+
"loss": 0.2776,
|
| 454 |
+
"step": 5500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 3.3980582524271843,
|
| 458 |
+
"grad_norm": 1.0107412338256836,
|
| 459 |
+
"learning_rate": 0.0002490291262135922,
|
| 460 |
+
"loss": 0.2766,
|
| 461 |
+
"step": 5600
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.45873786407767,
|
| 465 |
+
"grad_norm": 0.4374917149543762,
|
| 466 |
+
"learning_rate": 0.0002481189320388349,
|
| 467 |
+
"loss": 0.2719,
|
| 468 |
+
"step": 5700
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.5194174757281553,
|
| 472 |
+
"grad_norm": 1.6768765449523926,
|
| 473 |
+
"learning_rate": 0.0002472087378640777,
|
| 474 |
+
"loss": 0.2803,
|
| 475 |
+
"step": 5800
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 3.5800970873786406,
|
| 479 |
+
"grad_norm": 0.8120823502540588,
|
| 480 |
+
"learning_rate": 0.0002462985436893204,
|
| 481 |
+
"loss": 0.2723,
|
| 482 |
+
"step": 5900
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.6407766990291264,
|
| 486 |
+
"grad_norm": 1.3967177867889404,
|
| 487 |
+
"learning_rate": 0.0002453883495145631,
|
| 488 |
+
"loss": 0.2796,
|
| 489 |
+
"step": 6000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.6407766990291264,
|
| 493 |
+
"eval_accuracy": 0.7001301555465466,
|
| 494 |
+
"eval_f1_macro": 0.46180498265852127,
|
| 495 |
+
"eval_loss": 0.272257536649704,
|
| 496 |
+
"eval_precision": 0.5281578618931982,
|
| 497 |
+
"eval_recall": 0.4315295129889904,
|
| 498 |
+
"eval_runtime": 63.8213,
|
| 499 |
+
"eval_samples_per_second": 734.347,
|
| 500 |
+
"eval_steps_per_second": 5.75,
|
| 501 |
+
"step": 6000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.7014563106796117,
|
| 505 |
+
"grad_norm": 0.6093985438346863,
|
| 506 |
+
"learning_rate": 0.0002444781553398058,
|
| 507 |
+
"loss": 0.2744,
|
| 508 |
+
"step": 6100
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 3.762135922330097,
|
| 512 |
+
"grad_norm": 0.7282202243804932,
|
| 513 |
+
"learning_rate": 0.00024356796116504852,
|
| 514 |
+
"loss": 0.2715,
|
| 515 |
+
"step": 6200
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.8228155339805827,
|
| 519 |
+
"grad_norm": 1.1341967582702637,
|
| 520 |
+
"learning_rate": 0.00024265776699029123,
|
| 521 |
+
"loss": 0.2709,
|
| 522 |
+
"step": 6300
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 3.883495145631068,
|
| 526 |
+
"grad_norm": 0.8576841354370117,
|
| 527 |
+
"learning_rate": 0.00024174757281553394,
|
| 528 |
+
"loss": 0.275,
|
| 529 |
+
"step": 6400
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 3.9441747572815533,
|
| 533 |
+
"grad_norm": 0.5656840205192566,
|
| 534 |
+
"learning_rate": 0.00024083737864077668,
|
| 535 |
+
"loss": 0.2676,
|
| 536 |
+
"step": 6500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.004854368932039,
|
| 540 |
+
"grad_norm": 0.6544743180274963,
|
| 541 |
+
"learning_rate": 0.0002399271844660194,
|
| 542 |
+
"loss": 0.2734,
|
| 543 |
+
"step": 6600
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.065533980582524,
|
| 547 |
+
"grad_norm": 1.5159205198287964,
|
| 548 |
+
"learning_rate": 0.0002390169902912621,
|
| 549 |
+
"loss": 0.2666,
|
| 550 |
+
"step": 6700
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 4.12621359223301,
|
| 554 |
+
"grad_norm": 0.9112799763679504,
|
| 555 |
+
"learning_rate": 0.00023810679611650483,
|
| 556 |
+
"loss": 0.2646,
|
| 557 |
+
"step": 6800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 4.186893203883495,
|
| 561 |
+
"grad_norm": 0.6971092224121094,
|
| 562 |
+
"learning_rate": 0.00023719660194174754,
|
| 563 |
+
"loss": 0.2681,
|
| 564 |
+
"step": 6900
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.247572815533981,
|
| 568 |
+
"grad_norm": 0.5126680731773376,
|
| 569 |
+
"learning_rate": 0.00023628640776699028,
|
| 570 |
+
"loss": 0.2669,
|
| 571 |
+
"step": 7000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 4.247572815533981,
|
| 575 |
+
"eval_accuracy": 0.7024985597541981,
|
| 576 |
+
"eval_f1_macro": 0.4678440617843855,
|
| 577 |
+
"eval_loss": 0.26851192116737366,
|
| 578 |
+
"eval_precision": 0.5330566032345198,
|
| 579 |
+
"eval_recall": 0.43620949446199525,
|
| 580 |
+
"eval_runtime": 63.9009,
|
| 581 |
+
"eval_samples_per_second": 733.432,
|
| 582 |
+
"eval_steps_per_second": 5.743,
|
| 583 |
+
"step": 7000
|
| 584 |
+
}
|
| 585 |
+
],
|
| 586 |
+
"logging_steps": 100,
|
| 587 |
+
"max_steps": 32960,
|
| 588 |
+
"num_input_tokens_seen": 0,
|
| 589 |
+
"num_train_epochs": 20,
|
| 590 |
+
"save_steps": 1000,
|
| 591 |
+
"total_flos": 4.713992160165028e+17,
|
| 592 |
+
"train_batch_size": 256,
|
| 593 |
+
"trial_name": null,
|
| 594 |
+
"trial_params": null
|
| 595 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efc02ff3cbe38771032be7435dde1ef98e3d99cdd38f1fb9a9c2f710ef949f0b
|
| 3 |
+
size 5048
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|