Initial model commit
Browse files- config.json +24 -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 +55 -0
- trainer_state.json +681 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForMaskedLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.38.0.dev0",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d896ec994c0f1257c864da336cdb270ff52c37d333d8a8010a0adec25af553a
|
| 3 |
+
size 267954768
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b61fdd1721cddde02e5c9b44dc44abab444041ee5339c9c7eeb77ff1aceb33b
|
| 3 |
+
size 535972218
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0262c33f41012cbd6f2c2e1c1d2ee441ed917ca305d539e54003cf41a55ef078
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f138103487a53a67a03b5f54425825e5c29acd5184bb795b4c677e1677fe9332
|
| 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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1000000000000000019884624838656,
|
| 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 +1,681 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.148005148005148,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 4.9679536679536684e-05,
|
| 14 |
+
"loss": 2.6056,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.13,
|
| 19 |
+
"learning_rate": 4.935778635778636e-05,
|
| 20 |
+
"loss": 2.1389,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 4.9036036036036035e-05,
|
| 26 |
+
"loss": 1.9778,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.26,
|
| 31 |
+
"learning_rate": 4.8714285714285714e-05,
|
| 32 |
+
"loss": 1.8847,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.26,
|
| 37 |
+
"eval_accuracy": 0.6430994438209938,
|
| 38 |
+
"eval_loss": 1.7282191514968872,
|
| 39 |
+
"eval_runtime": 168.5943,
|
| 40 |
+
"eval_samples_per_second": 163.131,
|
| 41 |
+
"eval_steps_per_second": 20.392,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.32,
|
| 46 |
+
"learning_rate": 4.8392535392535393e-05,
|
| 47 |
+
"loss": 1.8149,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.39,
|
| 52 |
+
"learning_rate": 4.807078507078507e-05,
|
| 53 |
+
"loss": 1.7584,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.45,
|
| 58 |
+
"learning_rate": 4.774903474903475e-05,
|
| 59 |
+
"loss": 1.7177,
|
| 60 |
+
"step": 3500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.51,
|
| 64 |
+
"learning_rate": 4.742728442728443e-05,
|
| 65 |
+
"loss": 1.6753,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.51,
|
| 70 |
+
"eval_accuracy": 0.6748989378707684,
|
| 71 |
+
"eval_loss": 1.55081307888031,
|
| 72 |
+
"eval_runtime": 171.3896,
|
| 73 |
+
"eval_samples_per_second": 160.471,
|
| 74 |
+
"eval_steps_per_second": 20.06,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.58,
|
| 79 |
+
"learning_rate": 4.710553410553411e-05,
|
| 80 |
+
"loss": 1.6493,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.64,
|
| 85 |
+
"learning_rate": 4.678378378378379e-05,
|
| 86 |
+
"loss": 1.6196,
|
| 87 |
+
"step": 5000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.71,
|
| 91 |
+
"learning_rate": 4.646203346203347e-05,
|
| 92 |
+
"loss": 1.5848,
|
| 93 |
+
"step": 5500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.77,
|
| 97 |
+
"learning_rate": 4.614028314028314e-05,
|
| 98 |
+
"loss": 1.5664,
|
| 99 |
+
"step": 6000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.77,
|
| 103 |
+
"eval_accuracy": 0.6920701992459631,
|
| 104 |
+
"eval_loss": 1.4559696912765503,
|
| 105 |
+
"eval_runtime": 172.8272,
|
| 106 |
+
"eval_samples_per_second": 159.136,
|
| 107 |
+
"eval_steps_per_second": 19.893,
|
| 108 |
+
"step": 6000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.84,
|
| 112 |
+
"learning_rate": 4.581853281853282e-05,
|
| 113 |
+
"loss": 1.5418,
|
| 114 |
+
"step": 6500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9,
|
| 118 |
+
"learning_rate": 4.54967824967825e-05,
|
| 119 |
+
"loss": 1.5232,
|
| 120 |
+
"step": 7000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.97,
|
| 124 |
+
"learning_rate": 4.517503217503218e-05,
|
| 125 |
+
"loss": 1.5102,
|
| 126 |
+
"step": 7500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.03,
|
| 130 |
+
"learning_rate": 4.4853281853281856e-05,
|
| 131 |
+
"loss": 1.4973,
|
| 132 |
+
"step": 8000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.03,
|
| 136 |
+
"eval_accuracy": 0.7051554952905896,
|
| 137 |
+
"eval_loss": 1.3886678218841553,
|
| 138 |
+
"eval_runtime": 170.2873,
|
| 139 |
+
"eval_samples_per_second": 161.509,
|
| 140 |
+
"eval_steps_per_second": 20.189,
|
| 141 |
+
"step": 8000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.09,
|
| 145 |
+
"learning_rate": 4.4531531531531535e-05,
|
| 146 |
+
"loss": 1.4758,
|
| 147 |
+
"step": 8500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.16,
|
| 151 |
+
"learning_rate": 4.421042471042471e-05,
|
| 152 |
+
"loss": 1.4534,
|
| 153 |
+
"step": 9000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.22,
|
| 157 |
+
"learning_rate": 4.388867438867439e-05,
|
| 158 |
+
"loss": 1.45,
|
| 159 |
+
"step": 9500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.29,
|
| 163 |
+
"learning_rate": 4.356692406692407e-05,
|
| 164 |
+
"loss": 1.4371,
|
| 165 |
+
"step": 10000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.29,
|
| 169 |
+
"eval_accuracy": 0.7145240916645529,
|
| 170 |
+
"eval_loss": 1.3381266593933105,
|
| 171 |
+
"eval_runtime": 171.6166,
|
| 172 |
+
"eval_samples_per_second": 160.258,
|
| 173 |
+
"eval_steps_per_second": 20.033,
|
| 174 |
+
"step": 10000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.35,
|
| 178 |
+
"learning_rate": 4.324517374517374e-05,
|
| 179 |
+
"loss": 1.4315,
|
| 180 |
+
"step": 10500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.42,
|
| 184 |
+
"learning_rate": 4.292342342342343e-05,
|
| 185 |
+
"loss": 1.4166,
|
| 186 |
+
"step": 11000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.48,
|
| 190 |
+
"learning_rate": 4.2602316602316605e-05,
|
| 191 |
+
"loss": 1.4071,
|
| 192 |
+
"step": 11500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.54,
|
| 196 |
+
"learning_rate": 4.228056628056628e-05,
|
| 197 |
+
"loss": 1.3949,
|
| 198 |
+
"step": 12000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.54,
|
| 202 |
+
"eval_accuracy": 0.7217752604656028,
|
| 203 |
+
"eval_loss": 1.3031212091445923,
|
| 204 |
+
"eval_runtime": 171.5333,
|
| 205 |
+
"eval_samples_per_second": 160.336,
|
| 206 |
+
"eval_steps_per_second": 20.043,
|
| 207 |
+
"step": 12000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.61,
|
| 211 |
+
"learning_rate": 4.195881595881596e-05,
|
| 212 |
+
"loss": 1.3929,
|
| 213 |
+
"step": 12500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.67,
|
| 217 |
+
"learning_rate": 4.163770913770914e-05,
|
| 218 |
+
"loss": 1.3755,
|
| 219 |
+
"step": 13000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.74,
|
| 223 |
+
"learning_rate": 4.131595881595882e-05,
|
| 224 |
+
"loss": 1.3731,
|
| 225 |
+
"step": 13500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.8,
|
| 229 |
+
"learning_rate": 4.09942084942085e-05,
|
| 230 |
+
"loss": 1.3656,
|
| 231 |
+
"step": 14000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.8,
|
| 235 |
+
"eval_accuracy": 0.7279450116990841,
|
| 236 |
+
"eval_loss": 1.2706010341644287,
|
| 237 |
+
"eval_runtime": 172.4413,
|
| 238 |
+
"eval_samples_per_second": 159.492,
|
| 239 |
+
"eval_steps_per_second": 19.937,
|
| 240 |
+
"step": 14000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.87,
|
| 244 |
+
"learning_rate": 4.067245817245817e-05,
|
| 245 |
+
"loss": 1.3562,
|
| 246 |
+
"step": 14500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.93,
|
| 250 |
+
"learning_rate": 4.0350707850707856e-05,
|
| 251 |
+
"loss": 1.345,
|
| 252 |
+
"step": 15000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.99,
|
| 256 |
+
"learning_rate": 4.0028957528957535e-05,
|
| 257 |
+
"loss": 1.3401,
|
| 258 |
+
"step": 15500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.06,
|
| 262 |
+
"learning_rate": 3.970720720720721e-05,
|
| 263 |
+
"loss": 1.3271,
|
| 264 |
+
"step": 16000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.06,
|
| 268 |
+
"eval_accuracy": 0.7319083261136123,
|
| 269 |
+
"eval_loss": 1.2469459772109985,
|
| 270 |
+
"eval_runtime": 172.8063,
|
| 271 |
+
"eval_samples_per_second": 159.155,
|
| 272 |
+
"eval_steps_per_second": 19.895,
|
| 273 |
+
"step": 16000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.12,
|
| 277 |
+
"learning_rate": 3.9385456885456886e-05,
|
| 278 |
+
"loss": 1.3179,
|
| 279 |
+
"step": 16500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.19,
|
| 283 |
+
"learning_rate": 3.9064350064350063e-05,
|
| 284 |
+
"loss": 1.3207,
|
| 285 |
+
"step": 17000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.25,
|
| 289 |
+
"learning_rate": 3.874259974259974e-05,
|
| 290 |
+
"loss": 1.3092,
|
| 291 |
+
"step": 17500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.32,
|
| 295 |
+
"learning_rate": 3.842084942084943e-05,
|
| 296 |
+
"loss": 1.3016,
|
| 297 |
+
"step": 18000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.32,
|
| 301 |
+
"eval_accuracy": 0.7369295282061049,
|
| 302 |
+
"eval_loss": 1.2243499755859375,
|
| 303 |
+
"eval_runtime": 171.841,
|
| 304 |
+
"eval_samples_per_second": 160.049,
|
| 305 |
+
"eval_steps_per_second": 20.007,
|
| 306 |
+
"step": 18000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.38,
|
| 310 |
+
"learning_rate": 3.80990990990991e-05,
|
| 311 |
+
"loss": 1.2989,
|
| 312 |
+
"step": 18500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.45,
|
| 316 |
+
"learning_rate": 3.777734877734878e-05,
|
| 317 |
+
"loss": 1.2902,
|
| 318 |
+
"step": 19000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.51,
|
| 322 |
+
"learning_rate": 3.745559845559846e-05,
|
| 323 |
+
"loss": 1.2897,
|
| 324 |
+
"step": 19500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.57,
|
| 328 |
+
"learning_rate": 3.713384813384814e-05,
|
| 329 |
+
"loss": 1.2867,
|
| 330 |
+
"step": 20000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.57,
|
| 334 |
+
"eval_accuracy": 0.7412163432241851,
|
| 335 |
+
"eval_loss": 1.1988307237625122,
|
| 336 |
+
"eval_runtime": 173.4853,
|
| 337 |
+
"eval_samples_per_second": 158.532,
|
| 338 |
+
"eval_steps_per_second": 19.817,
|
| 339 |
+
"step": 20000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.64,
|
| 343 |
+
"learning_rate": 3.681209781209781e-05,
|
| 344 |
+
"loss": 1.2756,
|
| 345 |
+
"step": 20500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.7,
|
| 349 |
+
"learning_rate": 3.6490990990990994e-05,
|
| 350 |
+
"loss": 1.273,
|
| 351 |
+
"step": 21000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.77,
|
| 355 |
+
"learning_rate": 3.616924066924067e-05,
|
| 356 |
+
"loss": 1.2704,
|
| 357 |
+
"step": 21500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.83,
|
| 361 |
+
"learning_rate": 3.5847490347490345e-05,
|
| 362 |
+
"loss": 1.2668,
|
| 363 |
+
"step": 22000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.83,
|
| 367 |
+
"eval_accuracy": 0.7440720045251332,
|
| 368 |
+
"eval_loss": 1.1828033924102783,
|
| 369 |
+
"eval_runtime": 174.2101,
|
| 370 |
+
"eval_samples_per_second": 157.873,
|
| 371 |
+
"eval_steps_per_second": 19.735,
|
| 372 |
+
"step": 22000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.9,
|
| 376 |
+
"learning_rate": 3.552574002574003e-05,
|
| 377 |
+
"loss": 1.2682,
|
| 378 |
+
"step": 22500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.96,
|
| 382 |
+
"learning_rate": 3.52039897039897e-05,
|
| 383 |
+
"loss": 1.2624,
|
| 384 |
+
"step": 23000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.02,
|
| 388 |
+
"learning_rate": 3.488223938223938e-05,
|
| 389 |
+
"loss": 1.2505,
|
| 390 |
+
"step": 23500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.09,
|
| 394 |
+
"learning_rate": 3.4561132561132566e-05,
|
| 395 |
+
"loss": 1.2426,
|
| 396 |
+
"step": 24000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.09,
|
| 400 |
+
"eval_accuracy": 0.7478223153253316,
|
| 401 |
+
"eval_loss": 1.166755199432373,
|
| 402 |
+
"eval_runtime": 174.8548,
|
| 403 |
+
"eval_samples_per_second": 157.29,
|
| 404 |
+
"eval_steps_per_second": 19.662,
|
| 405 |
+
"step": 24000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.15,
|
| 409 |
+
"learning_rate": 3.423938223938224e-05,
|
| 410 |
+
"loss": 1.2337,
|
| 411 |
+
"step": 24500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.22,
|
| 415 |
+
"learning_rate": 3.391763191763192e-05,
|
| 416 |
+
"loss": 1.2389,
|
| 417 |
+
"step": 25000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.28,
|
| 421 |
+
"learning_rate": 3.3595881595881596e-05,
|
| 422 |
+
"loss": 1.2314,
|
| 423 |
+
"step": 25500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.35,
|
| 427 |
+
"learning_rate": 3.3274131274131275e-05,
|
| 428 |
+
"loss": 1.2284,
|
| 429 |
+
"step": 26000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.35,
|
| 433 |
+
"eval_accuracy": 0.7501192662767082,
|
| 434 |
+
"eval_loss": 1.1552441120147705,
|
| 435 |
+
"eval_runtime": 176.5773,
|
| 436 |
+
"eval_samples_per_second": 155.756,
|
| 437 |
+
"eval_steps_per_second": 19.47,
|
| 438 |
+
"step": 26000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.41,
|
| 442 |
+
"learning_rate": 3.2952380952380954e-05,
|
| 443 |
+
"loss": 1.2244,
|
| 444 |
+
"step": 26500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.47,
|
| 448 |
+
"learning_rate": 3.263063063063063e-05,
|
| 449 |
+
"loss": 1.2217,
|
| 450 |
+
"step": 27000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.54,
|
| 454 |
+
"learning_rate": 3.230888030888031e-05,
|
| 455 |
+
"loss": 1.2204,
|
| 456 |
+
"step": 27500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.6,
|
| 460 |
+
"learning_rate": 3.198712998712999e-05,
|
| 461 |
+
"loss": 1.2177,
|
| 462 |
+
"step": 28000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.6,
|
| 466 |
+
"eval_accuracy": 0.7529280009402969,
|
| 467 |
+
"eval_loss": 1.140738606452942,
|
| 468 |
+
"eval_runtime": 175.8979,
|
| 469 |
+
"eval_samples_per_second": 156.358,
|
| 470 |
+
"eval_steps_per_second": 19.545,
|
| 471 |
+
"step": 28000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.67,
|
| 475 |
+
"learning_rate": 3.166537966537967e-05,
|
| 476 |
+
"loss": 1.2126,
|
| 477 |
+
"step": 28500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.73,
|
| 481 |
+
"learning_rate": 3.134427284427285e-05,
|
| 482 |
+
"loss": 1.2123,
|
| 483 |
+
"step": 29000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.8,
|
| 487 |
+
"learning_rate": 3.1022522522522526e-05,
|
| 488 |
+
"loss": 1.2015,
|
| 489 |
+
"step": 29500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.86,
|
| 493 |
+
"learning_rate": 3.07014157014157e-05,
|
| 494 |
+
"loss": 1.2045,
|
| 495 |
+
"step": 30000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.86,
|
| 499 |
+
"eval_accuracy": 0.7548470260547614,
|
| 500 |
+
"eval_loss": 1.1305773258209229,
|
| 501 |
+
"eval_runtime": 177.469,
|
| 502 |
+
"eval_samples_per_second": 154.974,
|
| 503 |
+
"eval_steps_per_second": 19.372,
|
| 504 |
+
"step": 30000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.93,
|
| 508 |
+
"learning_rate": 3.037966537966538e-05,
|
| 509 |
+
"loss": 1.2081,
|
| 510 |
+
"step": 30500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.99,
|
| 514 |
+
"learning_rate": 3.0057915057915058e-05,
|
| 515 |
+
"loss": 1.2009,
|
| 516 |
+
"step": 31000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.05,
|
| 520 |
+
"learning_rate": 2.973616473616474e-05,
|
| 521 |
+
"loss": 1.191,
|
| 522 |
+
"step": 31500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.12,
|
| 526 |
+
"learning_rate": 2.9414414414414416e-05,
|
| 527 |
+
"loss": 1.1901,
|
| 528 |
+
"step": 32000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.12,
|
| 532 |
+
"eval_accuracy": 0.7579209971336668,
|
| 533 |
+
"eval_loss": 1.1146818399429321,
|
| 534 |
+
"eval_runtime": 176.2162,
|
| 535 |
+
"eval_samples_per_second": 156.075,
|
| 536 |
+
"eval_steps_per_second": 19.51,
|
| 537 |
+
"step": 32000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.18,
|
| 541 |
+
"learning_rate": 2.9092664092664095e-05,
|
| 542 |
+
"loss": 1.1939,
|
| 543 |
+
"step": 32500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.25,
|
| 547 |
+
"learning_rate": 2.877091377091377e-05,
|
| 548 |
+
"loss": 1.179,
|
| 549 |
+
"step": 33000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.31,
|
| 553 |
+
"learning_rate": 2.8449163449163453e-05,
|
| 554 |
+
"loss": 1.1831,
|
| 555 |
+
"step": 33500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.38,
|
| 559 |
+
"learning_rate": 2.812741312741313e-05,
|
| 560 |
+
"loss": 1.1801,
|
| 561 |
+
"step": 34000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.38,
|
| 565 |
+
"eval_accuracy": 0.7587203295541968,
|
| 566 |
+
"eval_loss": 1.110528588294983,
|
| 567 |
+
"eval_runtime": 177.1827,
|
| 568 |
+
"eval_samples_per_second": 155.224,
|
| 569 |
+
"eval_steps_per_second": 19.404,
|
| 570 |
+
"step": 34000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.44,
|
| 574 |
+
"learning_rate": 2.7805662805662808e-05,
|
| 575 |
+
"loss": 1.1761,
|
| 576 |
+
"step": 34500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.5,
|
| 580 |
+
"learning_rate": 2.7483912483912483e-05,
|
| 581 |
+
"loss": 1.1767,
|
| 582 |
+
"step": 35000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.57,
|
| 586 |
+
"learning_rate": 2.7162805662805664e-05,
|
| 587 |
+
"loss": 1.166,
|
| 588 |
+
"step": 35500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.63,
|
| 592 |
+
"learning_rate": 2.6841055341055343e-05,
|
| 593 |
+
"loss": 1.167,
|
| 594 |
+
"step": 36000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.63,
|
| 598 |
+
"eval_accuracy": 0.7609539556365092,
|
| 599 |
+
"eval_loss": 1.1016037464141846,
|
| 600 |
+
"eval_runtime": 176.8657,
|
| 601 |
+
"eval_samples_per_second": 155.502,
|
| 602 |
+
"eval_steps_per_second": 19.438,
|
| 603 |
+
"step": 36000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.7,
|
| 607 |
+
"learning_rate": 2.6519305019305018e-05,
|
| 608 |
+
"loss": 1.161,
|
| 609 |
+
"step": 36500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.76,
|
| 613 |
+
"learning_rate": 2.61975546975547e-05,
|
| 614 |
+
"loss": 1.1658,
|
| 615 |
+
"step": 37000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.83,
|
| 619 |
+
"learning_rate": 2.5876447876447878e-05,
|
| 620 |
+
"loss": 1.1656,
|
| 621 |
+
"step": 37500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.89,
|
| 625 |
+
"learning_rate": 2.5554697554697553e-05,
|
| 626 |
+
"loss": 1.1543,
|
| 627 |
+
"step": 38000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 4.89,
|
| 631 |
+
"eval_accuracy": 0.7620338199796781,
|
| 632 |
+
"eval_loss": 1.0933340787887573,
|
| 633 |
+
"eval_runtime": 176.4351,
|
| 634 |
+
"eval_samples_per_second": 155.882,
|
| 635 |
+
"eval_steps_per_second": 19.486,
|
| 636 |
+
"step": 38000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 4.95,
|
| 640 |
+
"learning_rate": 2.5233590733590734e-05,
|
| 641 |
+
"loss": 1.1568,
|
| 642 |
+
"step": 38500
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 5.02,
|
| 646 |
+
"learning_rate": 2.4911840411840413e-05,
|
| 647 |
+
"loss": 1.1591,
|
| 648 |
+
"step": 39000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.08,
|
| 652 |
+
"learning_rate": 2.459009009009009e-05,
|
| 653 |
+
"loss": 1.1485,
|
| 654 |
+
"step": 39500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 5.15,
|
| 658 |
+
"learning_rate": 2.426833976833977e-05,
|
| 659 |
+
"loss": 1.1481,
|
| 660 |
+
"step": 40000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.15,
|
| 664 |
+
"eval_accuracy": 0.7639144921830399,
|
| 665 |
+
"eval_loss": 1.0837804079055786,
|
| 666 |
+
"eval_runtime": 179.9041,
|
| 667 |
+
"eval_samples_per_second": 152.876,
|
| 668 |
+
"eval_steps_per_second": 19.11,
|
| 669 |
+
"step": 40000
|
| 670 |
+
}
|
| 671 |
+
],
|
| 672 |
+
"logging_steps": 500,
|
| 673 |
+
"max_steps": 77700,
|
| 674 |
+
"num_input_tokens_seen": 0,
|
| 675 |
+
"num_train_epochs": 10,
|
| 676 |
+
"save_steps": 2000,
|
| 677 |
+
"total_flos": 1.6967761699709952e+17,
|
| 678 |
+
"train_batch_size": 32,
|
| 679 |
+
"trial_name": null,
|
| 680 |
+
"trial_params": null
|
| 681 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1de5b3ec4a2c8531ca2b480371f1a5d94402246fde794b6ca393ec530f9d9dcd
|
| 3 |
+
size 4728
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|