Joeran Bosma
commited on
Commit
·
7f8facc
1
Parent(s):
1885037
Initial release
Browse files- all_results.json +15 -0
- config.json +27 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +1327 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8339330300923873,
|
| 4 |
+
"eval_loss": 0.6957311034202576,
|
| 5 |
+
"eval_runtime": 1565.0818,
|
| 6 |
+
"eval_samples": 103187,
|
| 7 |
+
"eval_samples_per_second": 65.931,
|
| 8 |
+
"eval_steps_per_second": 4.121,
|
| 9 |
+
"perplexity": 2.005174528132345,
|
| 10 |
+
"train_loss": 1.3247782011802152,
|
| 11 |
+
"train_runtime": 514233.1245,
|
| 12 |
+
"train_samples": 824387,
|
| 13 |
+
"train_samples_per_second": 16.031,
|
| 14 |
+
"train_steps_per_second": 0.063
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.29.0.dev0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8339330300923873,
|
| 4 |
+
"eval_loss": 0.6957311034202576,
|
| 5 |
+
"eval_runtime": 1565.0818,
|
| 6 |
+
"eval_samples": 103187,
|
| 7 |
+
"eval_samples_per_second": 65.931,
|
| 8 |
+
"eval_steps_per_second": 4.121,
|
| 9 |
+
"perplexity": 2.005174528132345
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:017c10485db3bd7f54b214f34587e8c8047b10a4519a4f369ec61ccf2ca7cb76
|
| 3 |
+
size 498863417
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": {
|
| 9 |
+
"__type": "AddedToken",
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"model_max_length": 512,
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 20 |
+
"trim_offsets": true,
|
| 21 |
+
"unk_token": "<unk>"
|
| 22 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.3247782011802152,
|
| 4 |
+
"train_runtime": 514233.1245,
|
| 5 |
+
"train_samples": 824387,
|
| 6 |
+
"train_samples_per_second": 16.031,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6948868632316589,
|
| 3 |
+
"best_model_checkpoint": "/output/zgt-roberta-base-finetuned-Gu21schedule-BS256-10ep/checkpoint-31926",
|
| 4 |
+
"epoch": 9.999029597282872,
|
| 5 |
+
"global_step": 32200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"eval_accuracy": 0.15792088093844922,
|
| 13 |
+
"eval_loss": 6.227477550506592,
|
| 14 |
+
"eval_runtime": 1564.1073,
|
| 15 |
+
"eval_samples_per_second": 65.972,
|
| 16 |
+
"eval_steps_per_second": 4.124,
|
| 17 |
+
"step": 313
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.16,
|
| 21 |
+
"learning_rate": 9.316770186335403e-05,
|
| 22 |
+
"loss": 7.1011,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.19,
|
| 27 |
+
"eval_accuracy": 0.17130737364600243,
|
| 28 |
+
"eval_loss": 6.035614967346191,
|
| 29 |
+
"eval_runtime": 1566.1128,
|
| 30 |
+
"eval_samples_per_second": 65.887,
|
| 31 |
+
"eval_steps_per_second": 4.118,
|
| 32 |
+
"step": 626
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"eval_accuracy": 0.15421966595333422,
|
| 37 |
+
"eval_loss": 5.970716953277588,
|
| 38 |
+
"eval_runtime": 1567.0923,
|
| 39 |
+
"eval_samples_per_second": 65.846,
|
| 40 |
+
"eval_steps_per_second": 4.116,
|
| 41 |
+
"step": 939
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.31,
|
| 45 |
+
"learning_rate": 0.00018633540372670805,
|
| 46 |
+
"loss": 6.0182,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.39,
|
| 51 |
+
"eval_accuracy": 0.17392094665213684,
|
| 52 |
+
"eval_loss": 5.876271724700928,
|
| 53 |
+
"eval_runtime": 1568.897,
|
| 54 |
+
"eval_samples_per_second": 65.77,
|
| 55 |
+
"eval_steps_per_second": 4.111,
|
| 56 |
+
"step": 1252
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.47,
|
| 60 |
+
"learning_rate": 0.0002795031055900621,
|
| 61 |
+
"loss": 5.8908,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.49,
|
| 66 |
+
"eval_accuracy": 0.17560553688955177,
|
| 67 |
+
"eval_loss": 5.8265557289123535,
|
| 68 |
+
"eval_runtime": 1564.0767,
|
| 69 |
+
"eval_samples_per_second": 65.973,
|
| 70 |
+
"eval_steps_per_second": 4.124,
|
| 71 |
+
"step": 1565
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.58,
|
| 75 |
+
"eval_accuracy": 0.1755758633601614,
|
| 76 |
+
"eval_loss": 5.785298824310303,
|
| 77 |
+
"eval_runtime": 1563.8448,
|
| 78 |
+
"eval_samples_per_second": 65.983,
|
| 79 |
+
"eval_steps_per_second": 4.124,
|
| 80 |
+
"step": 1878
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.62,
|
| 84 |
+
"learning_rate": 0.0003726708074534161,
|
| 85 |
+
"loss": 5.8105,
|
| 86 |
+
"step": 2000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.68,
|
| 90 |
+
"eval_accuracy": 0.1851031730080446,
|
| 91 |
+
"eval_loss": 5.230679988861084,
|
| 92 |
+
"eval_runtime": 1563.8141,
|
| 93 |
+
"eval_samples_per_second": 65.984,
|
| 94 |
+
"eval_steps_per_second": 4.125,
|
| 95 |
+
"step": 2191
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.78,
|
| 99 |
+
"learning_rate": 0.0004658385093167702,
|
| 100 |
+
"loss": 4.8469,
|
| 101 |
+
"step": 2500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.78,
|
| 105 |
+
"eval_accuracy": 0.49302250475931464,
|
| 106 |
+
"eval_loss": 2.994337320327759,
|
| 107 |
+
"eval_runtime": 1564.1944,
|
| 108 |
+
"eval_samples_per_second": 65.968,
|
| 109 |
+
"eval_steps_per_second": 4.124,
|
| 110 |
+
"step": 2504
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.87,
|
| 114 |
+
"eval_accuracy": 0.6404133912717029,
|
| 115 |
+
"eval_loss": 1.8836123943328857,
|
| 116 |
+
"eval_runtime": 1565.3247,
|
| 117 |
+
"eval_samples_per_second": 65.921,
|
| 118 |
+
"eval_steps_per_second": 4.121,
|
| 119 |
+
"step": 2817
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.93,
|
| 123 |
+
"learning_rate": 0.0005590062111801242,
|
| 124 |
+
"loss": 2.2431,
|
| 125 |
+
"step": 3000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.97,
|
| 129 |
+
"eval_accuracy": 0.6801897739457411,
|
| 130 |
+
"eval_loss": 1.6012158393859863,
|
| 131 |
+
"eval_runtime": 1567.0654,
|
| 132 |
+
"eval_samples_per_second": 65.847,
|
| 133 |
+
"eval_steps_per_second": 4.116,
|
| 134 |
+
"step": 3130
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.07,
|
| 138 |
+
"eval_accuracy": 0.7009936840521221,
|
| 139 |
+
"eval_loss": 1.4589687585830688,
|
| 140 |
+
"eval_runtime": 1567.9702,
|
| 141 |
+
"eval_samples_per_second": 65.809,
|
| 142 |
+
"eval_steps_per_second": 4.114,
|
| 143 |
+
"step": 3443
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.09,
|
| 147 |
+
"learning_rate": 0.0005942028985507245,
|
| 148 |
+
"loss": 1.618,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.17,
|
| 153 |
+
"eval_accuracy": 0.7143850078266079,
|
| 154 |
+
"eval_loss": 1.3708570003509521,
|
| 155 |
+
"eval_runtime": 1567.3868,
|
| 156 |
+
"eval_samples_per_second": 65.834,
|
| 157 |
+
"eval_steps_per_second": 4.115,
|
| 158 |
+
"step": 3756
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.24,
|
| 162 |
+
"learning_rate": 0.0005838509316770186,
|
| 163 |
+
"loss": 1.436,
|
| 164 |
+
"step": 4000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.26,
|
| 168 |
+
"eval_accuracy": 0.725278557944805,
|
| 169 |
+
"eval_loss": 1.2998367547988892,
|
| 170 |
+
"eval_runtime": 1564.9997,
|
| 171 |
+
"eval_samples_per_second": 65.934,
|
| 172 |
+
"eval_steps_per_second": 4.121,
|
| 173 |
+
"step": 4069
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.36,
|
| 177 |
+
"eval_accuracy": 0.7341513279268731,
|
| 178 |
+
"eval_loss": 1.2506020069122314,
|
| 179 |
+
"eval_runtime": 1565.2355,
|
| 180 |
+
"eval_samples_per_second": 65.924,
|
| 181 |
+
"eval_steps_per_second": 4.121,
|
| 182 |
+
"step": 4382
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.4,
|
| 186 |
+
"learning_rate": 0.0005734989648033125,
|
| 187 |
+
"loss": 1.3344,
|
| 188 |
+
"step": 4500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.46,
|
| 192 |
+
"eval_accuracy": 0.7414229730121367,
|
| 193 |
+
"eval_loss": 1.2084842920303345,
|
| 194 |
+
"eval_runtime": 1564.6672,
|
| 195 |
+
"eval_samples_per_second": 65.948,
|
| 196 |
+
"eval_steps_per_second": 4.122,
|
| 197 |
+
"step": 4695
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.55,
|
| 201 |
+
"learning_rate": 0.0005631469979296066,
|
| 202 |
+
"loss": 1.2678,
|
| 203 |
+
"step": 5000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.56,
|
| 207 |
+
"eval_accuracy": 0.7460624134488423,
|
| 208 |
+
"eval_loss": 1.1799527406692505,
|
| 209 |
+
"eval_runtime": 1565.6909,
|
| 210 |
+
"eval_samples_per_second": 65.905,
|
| 211 |
+
"eval_steps_per_second": 4.12,
|
| 212 |
+
"step": 5008
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.65,
|
| 216 |
+
"eval_accuracy": 0.7513162543657942,
|
| 217 |
+
"eval_loss": 1.1497138738632202,
|
| 218 |
+
"eval_runtime": 1565.9769,
|
| 219 |
+
"eval_samples_per_second": 65.893,
|
| 220 |
+
"eval_steps_per_second": 4.119,
|
| 221 |
+
"step": 5321
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.71,
|
| 225 |
+
"learning_rate": 0.0005527950310559006,
|
| 226 |
+
"loss": 1.2183,
|
| 227 |
+
"step": 5500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.75,
|
| 231 |
+
"eval_accuracy": 0.7555471802775164,
|
| 232 |
+
"eval_loss": 1.1244266033172607,
|
| 233 |
+
"eval_runtime": 1565.313,
|
| 234 |
+
"eval_samples_per_second": 65.921,
|
| 235 |
+
"eval_steps_per_second": 4.121,
|
| 236 |
+
"step": 5634
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.85,
|
| 240 |
+
"eval_accuracy": 0.7586796535932161,
|
| 241 |
+
"eval_loss": 1.1065826416015625,
|
| 242 |
+
"eval_runtime": 1565.5955,
|
| 243 |
+
"eval_samples_per_second": 65.909,
|
| 244 |
+
"eval_steps_per_second": 4.12,
|
| 245 |
+
"step": 5947
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.86,
|
| 249 |
+
"learning_rate": 0.0005424430641821946,
|
| 250 |
+
"loss": 1.1764,
|
| 251 |
+
"step": 6000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.94,
|
| 255 |
+
"eval_accuracy": 0.7621753158952852,
|
| 256 |
+
"eval_loss": 1.0877457857131958,
|
| 257 |
+
"eval_runtime": 1565.477,
|
| 258 |
+
"eval_samples_per_second": 65.914,
|
| 259 |
+
"eval_steps_per_second": 4.12,
|
| 260 |
+
"step": 6260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.02,
|
| 264 |
+
"learning_rate": 0.0005320910973084886,
|
| 265 |
+
"loss": 1.1481,
|
| 266 |
+
"step": 6500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.04,
|
| 270 |
+
"eval_accuracy": 0.7653308256390273,
|
| 271 |
+
"eval_loss": 1.069921851158142,
|
| 272 |
+
"eval_runtime": 1565.5751,
|
| 273 |
+
"eval_samples_per_second": 65.91,
|
| 274 |
+
"eval_steps_per_second": 4.12,
|
| 275 |
+
"step": 6573
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.14,
|
| 279 |
+
"eval_accuracy": 0.7669783269978627,
|
| 280 |
+
"eval_loss": 1.059142827987671,
|
| 281 |
+
"eval_runtime": 1564.7195,
|
| 282 |
+
"eval_samples_per_second": 65.946,
|
| 283 |
+
"eval_steps_per_second": 4.122,
|
| 284 |
+
"step": 6886
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.17,
|
| 288 |
+
"learning_rate": 0.0005217391304347826,
|
| 289 |
+
"loss": 1.1169,
|
| 290 |
+
"step": 7000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.24,
|
| 294 |
+
"eval_accuracy": 0.7701243077960133,
|
| 295 |
+
"eval_loss": 1.0415377616882324,
|
| 296 |
+
"eval_runtime": 1565.3407,
|
| 297 |
+
"eval_samples_per_second": 65.92,
|
| 298 |
+
"eval_steps_per_second": 4.121,
|
| 299 |
+
"step": 7199
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.33,
|
| 303 |
+
"learning_rate": 0.0005113871635610765,
|
| 304 |
+
"loss": 1.0953,
|
| 305 |
+
"step": 7500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.33,
|
| 309 |
+
"eval_accuracy": 0.7718881473585557,
|
| 310 |
+
"eval_loss": 1.0299146175384521,
|
| 311 |
+
"eval_runtime": 1565.1494,
|
| 312 |
+
"eval_samples_per_second": 65.928,
|
| 313 |
+
"eval_steps_per_second": 4.121,
|
| 314 |
+
"step": 7512
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.43,
|
| 318 |
+
"eval_accuracy": 0.7742740416938212,
|
| 319 |
+
"eval_loss": 1.0169405937194824,
|
| 320 |
+
"eval_runtime": 1565.1719,
|
| 321 |
+
"eval_samples_per_second": 65.927,
|
| 322 |
+
"eval_steps_per_second": 4.121,
|
| 323 |
+
"step": 7825
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.48,
|
| 327 |
+
"learning_rate": 0.0005010351966873705,
|
| 328 |
+
"loss": 1.0743,
|
| 329 |
+
"step": 8000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.53,
|
| 333 |
+
"eval_accuracy": 0.7762836729268914,
|
| 334 |
+
"eval_loss": 1.006744146347046,
|
| 335 |
+
"eval_runtime": 1565.0712,
|
| 336 |
+
"eval_samples_per_second": 65.931,
|
| 337 |
+
"eval_steps_per_second": 4.121,
|
| 338 |
+
"step": 8138
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.62,
|
| 342 |
+
"eval_accuracy": 0.7780289191145969,
|
| 343 |
+
"eval_loss": 0.9963796734809875,
|
| 344 |
+
"eval_runtime": 1564.7218,
|
| 345 |
+
"eval_samples_per_second": 65.946,
|
| 346 |
+
"eval_steps_per_second": 4.122,
|
| 347 |
+
"step": 8451
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.64,
|
| 351 |
+
"learning_rate": 0.0004906832298136645,
|
| 352 |
+
"loss": 1.0582,
|
| 353 |
+
"step": 8500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.72,
|
| 357 |
+
"eval_accuracy": 0.7799966088129119,
|
| 358 |
+
"eval_loss": 0.9861342310905457,
|
| 359 |
+
"eval_runtime": 1564.6716,
|
| 360 |
+
"eval_samples_per_second": 65.948,
|
| 361 |
+
"eval_steps_per_second": 4.122,
|
| 362 |
+
"step": 8764
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.79,
|
| 366 |
+
"learning_rate": 0.00048033126293995856,
|
| 367 |
+
"loss": 1.0401,
|
| 368 |
+
"step": 9000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.82,
|
| 372 |
+
"eval_accuracy": 0.7818533899689635,
|
| 373 |
+
"eval_loss": 0.9751449227333069,
|
| 374 |
+
"eval_runtime": 1564.9804,
|
| 375 |
+
"eval_samples_per_second": 65.935,
|
| 376 |
+
"eval_steps_per_second": 4.121,
|
| 377 |
+
"step": 9077
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.92,
|
| 381 |
+
"eval_accuracy": 0.7830731640909905,
|
| 382 |
+
"eval_loss": 0.9680520296096802,
|
| 383 |
+
"eval_runtime": 1565.4431,
|
| 384 |
+
"eval_samples_per_second": 65.916,
|
| 385 |
+
"eval_steps_per_second": 4.12,
|
| 386 |
+
"step": 9390
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.95,
|
| 390 |
+
"learning_rate": 0.00046997929606625255,
|
| 391 |
+
"loss": 1.0262,
|
| 392 |
+
"step": 9500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.01,
|
| 396 |
+
"eval_accuracy": 0.7843024373004699,
|
| 397 |
+
"eval_loss": 0.9606424570083618,
|
| 398 |
+
"eval_runtime": 1565.1725,
|
| 399 |
+
"eval_samples_per_second": 65.927,
|
| 400 |
+
"eval_steps_per_second": 4.121,
|
| 401 |
+
"step": 9703
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.11,
|
| 405 |
+
"learning_rate": 0.0004596273291925466,
|
| 406 |
+
"loss": 1.0093,
|
| 407 |
+
"step": 10000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.11,
|
| 411 |
+
"eval_accuracy": 0.7858115501363246,
|
| 412 |
+
"eval_loss": 0.9535852670669556,
|
| 413 |
+
"eval_runtime": 1564.8587,
|
| 414 |
+
"eval_samples_per_second": 65.94,
|
| 415 |
+
"eval_steps_per_second": 4.122,
|
| 416 |
+
"step": 10016
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.21,
|
| 420 |
+
"eval_accuracy": 0.7874158219284931,
|
| 421 |
+
"eval_loss": 0.9444663524627686,
|
| 422 |
+
"eval_runtime": 1564.7558,
|
| 423 |
+
"eval_samples_per_second": 65.944,
|
| 424 |
+
"eval_steps_per_second": 4.122,
|
| 425 |
+
"step": 10329
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.26,
|
| 429 |
+
"learning_rate": 0.0004492753623188405,
|
| 430 |
+
"loss": 0.995,
|
| 431 |
+
"step": 10500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.3,
|
| 435 |
+
"eval_accuracy": 0.7884454282264995,
|
| 436 |
+
"eval_loss": 0.9367947578430176,
|
| 437 |
+
"eval_runtime": 1565.5731,
|
| 438 |
+
"eval_samples_per_second": 65.91,
|
| 439 |
+
"eval_steps_per_second": 4.12,
|
| 440 |
+
"step": 10642
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.4,
|
| 444 |
+
"eval_accuracy": 0.7902011668190658,
|
| 445 |
+
"eval_loss": 0.9284105896949768,
|
| 446 |
+
"eval_runtime": 1564.8586,
|
| 447 |
+
"eval_samples_per_second": 65.94,
|
| 448 |
+
"eval_steps_per_second": 4.122,
|
| 449 |
+
"step": 10955
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.42,
|
| 453 |
+
"learning_rate": 0.0004389233954451345,
|
| 454 |
+
"loss": 0.983,
|
| 455 |
+
"step": 11000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.5,
|
| 459 |
+
"eval_accuracy": 0.7912236011775762,
|
| 460 |
+
"eval_loss": 0.9227182269096375,
|
| 461 |
+
"eval_runtime": 1564.9848,
|
| 462 |
+
"eval_samples_per_second": 65.935,
|
| 463 |
+
"eval_steps_per_second": 4.121,
|
| 464 |
+
"step": 11268
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.57,
|
| 468 |
+
"learning_rate": 0.00042857142857142855,
|
| 469 |
+
"loss": 0.9728,
|
| 470 |
+
"step": 11500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.6,
|
| 474 |
+
"eval_accuracy": 0.7926902278847275,
|
| 475 |
+
"eval_loss": 0.9144140481948853,
|
| 476 |
+
"eval_runtime": 1564.605,
|
| 477 |
+
"eval_samples_per_second": 65.951,
|
| 478 |
+
"eval_steps_per_second": 4.122,
|
| 479 |
+
"step": 11581
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.69,
|
| 483 |
+
"eval_accuracy": 0.7936642140619866,
|
| 484 |
+
"eval_loss": 0.9096552133560181,
|
| 485 |
+
"eval_runtime": 1565.1262,
|
| 486 |
+
"eval_samples_per_second": 65.929,
|
| 487 |
+
"eval_steps_per_second": 4.121,
|
| 488 |
+
"step": 11894
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.73,
|
| 492 |
+
"learning_rate": 0.00041821946169772254,
|
| 493 |
+
"loss": 0.9632,
|
| 494 |
+
"step": 12000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.79,
|
| 498 |
+
"eval_accuracy": 0.7947595817774112,
|
| 499 |
+
"eval_loss": 0.9028408527374268,
|
| 500 |
+
"eval_runtime": 1564.7786,
|
| 501 |
+
"eval_samples_per_second": 65.944,
|
| 502 |
+
"eval_steps_per_second": 4.122,
|
| 503 |
+
"step": 12207
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.88,
|
| 507 |
+
"learning_rate": 0.0004078674948240166,
|
| 508 |
+
"loss": 0.953,
|
| 509 |
+
"step": 12500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 3.89,
|
| 513 |
+
"eval_accuracy": 0.7958614481801236,
|
| 514 |
+
"eval_loss": 0.896992564201355,
|
| 515 |
+
"eval_runtime": 1564.1136,
|
| 516 |
+
"eval_samples_per_second": 65.972,
|
| 517 |
+
"eval_steps_per_second": 4.124,
|
| 518 |
+
"step": 12520
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.99,
|
| 522 |
+
"eval_accuracy": 0.796848649990296,
|
| 523 |
+
"eval_loss": 0.8908724188804626,
|
| 524 |
+
"eval_runtime": 1564.2284,
|
| 525 |
+
"eval_samples_per_second": 65.967,
|
| 526 |
+
"eval_steps_per_second": 4.123,
|
| 527 |
+
"step": 12833
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 4.04,
|
| 531 |
+
"learning_rate": 0.0003975155279503105,
|
| 532 |
+
"loss": 0.9414,
|
| 533 |
+
"step": 13000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.08,
|
| 537 |
+
"eval_accuracy": 0.797744672086327,
|
| 538 |
+
"eval_loss": 0.8873794674873352,
|
| 539 |
+
"eval_runtime": 1565.739,
|
| 540 |
+
"eval_samples_per_second": 65.903,
|
| 541 |
+
"eval_steps_per_second": 4.119,
|
| 542 |
+
"step": 13146
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.18,
|
| 546 |
+
"eval_accuracy": 0.7986036425092956,
|
| 547 |
+
"eval_loss": 0.881266713142395,
|
| 548 |
+
"eval_runtime": 1565.4321,
|
| 549 |
+
"eval_samples_per_second": 65.916,
|
| 550 |
+
"eval_steps_per_second": 4.12,
|
| 551 |
+
"step": 13459
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.19,
|
| 555 |
+
"learning_rate": 0.0003871635610766045,
|
| 556 |
+
"loss": 0.9287,
|
| 557 |
+
"step": 13500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 4.28,
|
| 561 |
+
"eval_accuracy": 0.7999304297565917,
|
| 562 |
+
"eval_loss": 0.8743026852607727,
|
| 563 |
+
"eval_runtime": 1564.903,
|
| 564 |
+
"eval_samples_per_second": 65.938,
|
| 565 |
+
"eval_steps_per_second": 4.122,
|
| 566 |
+
"step": 13772
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.35,
|
| 570 |
+
"learning_rate": 0.00037681159420289854,
|
| 571 |
+
"loss": 0.9219,
|
| 572 |
+
"step": 14000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.37,
|
| 576 |
+
"eval_accuracy": 0.80051802299604,
|
| 577 |
+
"eval_loss": 0.8717477917671204,
|
| 578 |
+
"eval_runtime": 1565.3161,
|
| 579 |
+
"eval_samples_per_second": 65.921,
|
| 580 |
+
"eval_steps_per_second": 4.121,
|
| 581 |
+
"step": 14085
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.47,
|
| 585 |
+
"eval_accuracy": 0.801263244223999,
|
| 586 |
+
"eval_loss": 0.8662565350532532,
|
| 587 |
+
"eval_runtime": 1564.6984,
|
| 588 |
+
"eval_samples_per_second": 65.947,
|
| 589 |
+
"eval_steps_per_second": 4.122,
|
| 590 |
+
"step": 14398
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.5,
|
| 594 |
+
"learning_rate": 0.0003664596273291925,
|
| 595 |
+
"loss": 0.9137,
|
| 596 |
+
"step": 14500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.57,
|
| 600 |
+
"eval_accuracy": 0.8024215648096065,
|
| 601 |
+
"eval_loss": 0.8607039451599121,
|
| 602 |
+
"eval_runtime": 1565.2999,
|
| 603 |
+
"eval_samples_per_second": 65.922,
|
| 604 |
+
"eval_steps_per_second": 4.121,
|
| 605 |
+
"step": 14711
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.66,
|
| 609 |
+
"learning_rate": 0.0003561076604554865,
|
| 610 |
+
"loss": 0.9062,
|
| 611 |
+
"step": 15000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.67,
|
| 615 |
+
"eval_accuracy": 0.80312043845701,
|
| 616 |
+
"eval_loss": 0.8565826416015625,
|
| 617 |
+
"eval_runtime": 1566.6554,
|
| 618 |
+
"eval_samples_per_second": 65.865,
|
| 619 |
+
"eval_steps_per_second": 4.117,
|
| 620 |
+
"step": 15024
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.76,
|
| 624 |
+
"eval_accuracy": 0.8044941042086672,
|
| 625 |
+
"eval_loss": 0.8497495055198669,
|
| 626 |
+
"eval_runtime": 1566.3382,
|
| 627 |
+
"eval_samples_per_second": 65.878,
|
| 628 |
+
"eval_steps_per_second": 4.118,
|
| 629 |
+
"step": 15337
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.81,
|
| 633 |
+
"learning_rate": 0.0003457556935817805,
|
| 634 |
+
"loss": 0.8978,
|
| 635 |
+
"step": 15500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.86,
|
| 639 |
+
"eval_accuracy": 0.8053608800858211,
|
| 640 |
+
"eval_loss": 0.8438310623168945,
|
| 641 |
+
"eval_runtime": 1565.4433,
|
| 642 |
+
"eval_samples_per_second": 65.916,
|
| 643 |
+
"eval_steps_per_second": 4.12,
|
| 644 |
+
"step": 15650
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.96,
|
| 648 |
+
"eval_accuracy": 0.8064097453094475,
|
| 649 |
+
"eval_loss": 0.8402115702629089,
|
| 650 |
+
"eval_runtime": 1565.8792,
|
| 651 |
+
"eval_samples_per_second": 65.897,
|
| 652 |
+
"eval_steps_per_second": 4.119,
|
| 653 |
+
"step": 15963
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.97,
|
| 657 |
+
"learning_rate": 0.0003354037267080745,
|
| 658 |
+
"loss": 0.8907,
|
| 659 |
+
"step": 16000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.05,
|
| 663 |
+
"eval_accuracy": 0.8072085264677659,
|
| 664 |
+
"eval_loss": 0.8345613479614258,
|
| 665 |
+
"eval_runtime": 1565.4826,
|
| 666 |
+
"eval_samples_per_second": 65.914,
|
| 667 |
+
"eval_steps_per_second": 4.12,
|
| 668 |
+
"step": 16276
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 5.12,
|
| 672 |
+
"learning_rate": 0.0003250517598343685,
|
| 673 |
+
"loss": 0.8791,
|
| 674 |
+
"step": 16500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.15,
|
| 678 |
+
"eval_accuracy": 0.8079710854147522,
|
| 679 |
+
"eval_loss": 0.8311530947685242,
|
| 680 |
+
"eval_runtime": 1565.3772,
|
| 681 |
+
"eval_samples_per_second": 65.918,
|
| 682 |
+
"eval_steps_per_second": 4.12,
|
| 683 |
+
"step": 16589
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 5.25,
|
| 687 |
+
"eval_accuracy": 0.808113472692542,
|
| 688 |
+
"eval_loss": 0.8312503695487976,
|
| 689 |
+
"eval_runtime": 1564.9419,
|
| 690 |
+
"eval_samples_per_second": 65.937,
|
| 691 |
+
"eval_steps_per_second": 4.122,
|
| 692 |
+
"step": 16902
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 5.28,
|
| 696 |
+
"learning_rate": 0.00031469979296066245,
|
| 697 |
+
"loss": 0.8713,
|
| 698 |
+
"step": 17000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 5.35,
|
| 702 |
+
"eval_accuracy": 0.8089870028151737,
|
| 703 |
+
"eval_loss": 0.8246920108795166,
|
| 704 |
+
"eval_runtime": 1566.1653,
|
| 705 |
+
"eval_samples_per_second": 65.885,
|
| 706 |
+
"eval_steps_per_second": 4.118,
|
| 707 |
+
"step": 17215
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 5.43,
|
| 711 |
+
"learning_rate": 0.0003043478260869565,
|
| 712 |
+
"loss": 0.866,
|
| 713 |
+
"step": 17500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.44,
|
| 717 |
+
"eval_accuracy": 0.8100817167380647,
|
| 718 |
+
"eval_loss": 0.8203573822975159,
|
| 719 |
+
"eval_runtime": 1563.7507,
|
| 720 |
+
"eval_samples_per_second": 65.987,
|
| 721 |
+
"eval_steps_per_second": 4.125,
|
| 722 |
+
"step": 17528
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 5.54,
|
| 726 |
+
"eval_accuracy": 0.8106388454645975,
|
| 727 |
+
"eval_loss": 0.8163631558418274,
|
| 728 |
+
"eval_runtime": 1563.2024,
|
| 729 |
+
"eval_samples_per_second": 66.01,
|
| 730 |
+
"eval_steps_per_second": 4.126,
|
| 731 |
+
"step": 17841
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 5.59,
|
| 735 |
+
"learning_rate": 0.0002939958592132505,
|
| 736 |
+
"loss": 0.8607,
|
| 737 |
+
"step": 18000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.64,
|
| 741 |
+
"eval_accuracy": 0.8114071774300123,
|
| 742 |
+
"eval_loss": 0.8129469752311707,
|
| 743 |
+
"eval_runtime": 1563.1261,
|
| 744 |
+
"eval_samples_per_second": 66.013,
|
| 745 |
+
"eval_steps_per_second": 4.126,
|
| 746 |
+
"step": 18154
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 5.73,
|
| 750 |
+
"eval_accuracy": 0.8122062364179543,
|
| 751 |
+
"eval_loss": 0.808627724647522,
|
| 752 |
+
"eval_runtime": 1564.3551,
|
| 753 |
+
"eval_samples_per_second": 65.961,
|
| 754 |
+
"eval_steps_per_second": 4.123,
|
| 755 |
+
"step": 18467
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 5.74,
|
| 759 |
+
"learning_rate": 0.00028364389233954447,
|
| 760 |
+
"loss": 0.8534,
|
| 761 |
+
"step": 18500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 5.83,
|
| 765 |
+
"eval_accuracy": 0.8128903362394657,
|
| 766 |
+
"eval_loss": 0.8055641651153564,
|
| 767 |
+
"eval_runtime": 1563.7512,
|
| 768 |
+
"eval_samples_per_second": 65.987,
|
| 769 |
+
"eval_steps_per_second": 4.125,
|
| 770 |
+
"step": 18780
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 5.9,
|
| 774 |
+
"learning_rate": 0.0002732919254658385,
|
| 775 |
+
"loss": 0.8448,
|
| 776 |
+
"step": 19000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 5.93,
|
| 780 |
+
"eval_accuracy": 0.8134494722363886,
|
| 781 |
+
"eval_loss": 0.8019941449165344,
|
| 782 |
+
"eval_runtime": 1563.2984,
|
| 783 |
+
"eval_samples_per_second": 66.006,
|
| 784 |
+
"eval_steps_per_second": 4.126,
|
| 785 |
+
"step": 19093
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 6.03,
|
| 789 |
+
"eval_accuracy": 0.8143192139194421,
|
| 790 |
+
"eval_loss": 0.7982867956161499,
|
| 791 |
+
"eval_runtime": 1563.6693,
|
| 792 |
+
"eval_samples_per_second": 65.99,
|
| 793 |
+
"eval_steps_per_second": 4.125,
|
| 794 |
+
"step": 19406
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 6.06,
|
| 798 |
+
"learning_rate": 0.0002629399585921325,
|
| 799 |
+
"loss": 0.8391,
|
| 800 |
+
"step": 19500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 6.12,
|
| 804 |
+
"eval_accuracy": 0.8147886522353383,
|
| 805 |
+
"eval_loss": 0.7949500679969788,
|
| 806 |
+
"eval_runtime": 1563.7961,
|
| 807 |
+
"eval_samples_per_second": 65.985,
|
| 808 |
+
"eval_steps_per_second": 4.125,
|
| 809 |
+
"step": 19719
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 6.21,
|
| 813 |
+
"learning_rate": 0.0002525879917184265,
|
| 814 |
+
"loss": 0.8304,
|
| 815 |
+
"step": 20000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 6.22,
|
| 819 |
+
"eval_accuracy": 0.8155781682195781,
|
| 820 |
+
"eval_loss": 0.7908634543418884,
|
| 821 |
+
"eval_runtime": 1563.2059,
|
| 822 |
+
"eval_samples_per_second": 66.01,
|
| 823 |
+
"eval_steps_per_second": 4.126,
|
| 824 |
+
"step": 20032
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 6.32,
|
| 828 |
+
"eval_accuracy": 0.816149684044946,
|
| 829 |
+
"eval_loss": 0.7888238430023193,
|
| 830 |
+
"eval_runtime": 1565.7848,
|
| 831 |
+
"eval_samples_per_second": 65.901,
|
| 832 |
+
"eval_steps_per_second": 4.119,
|
| 833 |
+
"step": 20345
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 6.37,
|
| 837 |
+
"learning_rate": 0.00024223602484472047,
|
| 838 |
+
"loss": 0.825,
|
| 839 |
+
"step": 20500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 6.41,
|
| 843 |
+
"eval_accuracy": 0.8167946967773272,
|
| 844 |
+
"eval_loss": 0.7858228087425232,
|
| 845 |
+
"eval_runtime": 1565.9773,
|
| 846 |
+
"eval_samples_per_second": 65.893,
|
| 847 |
+
"eval_steps_per_second": 4.119,
|
| 848 |
+
"step": 20658
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 6.51,
|
| 852 |
+
"eval_accuracy": 0.8174543786608812,
|
| 853 |
+
"eval_loss": 0.7798792123794556,
|
| 854 |
+
"eval_runtime": 1566.9273,
|
| 855 |
+
"eval_samples_per_second": 65.853,
|
| 856 |
+
"eval_steps_per_second": 4.116,
|
| 857 |
+
"step": 20971
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 6.52,
|
| 861 |
+
"learning_rate": 0.00023188405797101448,
|
| 862 |
+
"loss": 0.8198,
|
| 863 |
+
"step": 21000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 6.61,
|
| 867 |
+
"eval_accuracy": 0.818135156601779,
|
| 868 |
+
"eval_loss": 0.7765618562698364,
|
| 869 |
+
"eval_runtime": 1568.3727,
|
| 870 |
+
"eval_samples_per_second": 65.792,
|
| 871 |
+
"eval_steps_per_second": 4.113,
|
| 872 |
+
"step": 21284
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 6.68,
|
| 876 |
+
"learning_rate": 0.00022153209109730847,
|
| 877 |
+
"loss": 0.8139,
|
| 878 |
+
"step": 21500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 6.71,
|
| 882 |
+
"eval_accuracy": 0.8189553029778005,
|
| 883 |
+
"eval_loss": 0.7735697627067566,
|
| 884 |
+
"eval_runtime": 1567.9384,
|
| 885 |
+
"eval_samples_per_second": 65.811,
|
| 886 |
+
"eval_steps_per_second": 4.114,
|
| 887 |
+
"step": 21597
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 6.8,
|
| 891 |
+
"eval_accuracy": 0.8195096365262311,
|
| 892 |
+
"eval_loss": 0.7705960273742676,
|
| 893 |
+
"eval_runtime": 1568.1878,
|
| 894 |
+
"eval_samples_per_second": 65.8,
|
| 895 |
+
"eval_steps_per_second": 4.113,
|
| 896 |
+
"step": 21910
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 6.83,
|
| 900 |
+
"learning_rate": 0.00021118012422360248,
|
| 901 |
+
"loss": 0.8094,
|
| 902 |
+
"step": 22000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 6.9,
|
| 906 |
+
"eval_accuracy": 0.8200746154831311,
|
| 907 |
+
"eval_loss": 0.7673328518867493,
|
| 908 |
+
"eval_runtime": 1567.3958,
|
| 909 |
+
"eval_samples_per_second": 65.833,
|
| 910 |
+
"eval_steps_per_second": 4.115,
|
| 911 |
+
"step": 22223
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 6.99,
|
| 915 |
+
"learning_rate": 0.00020082815734989647,
|
| 916 |
+
"loss": 0.8032,
|
| 917 |
+
"step": 22500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 7.0,
|
| 921 |
+
"eval_accuracy": 0.8205203976743998,
|
| 922 |
+
"eval_loss": 0.764415979385376,
|
| 923 |
+
"eval_runtime": 1567.2437,
|
| 924 |
+
"eval_samples_per_second": 65.84,
|
| 925 |
+
"eval_steps_per_second": 4.116,
|
| 926 |
+
"step": 22536
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 7.1,
|
| 930 |
+
"eval_accuracy": 0.8215158231256271,
|
| 931 |
+
"eval_loss": 0.7607036232948303,
|
| 932 |
+
"eval_runtime": 1568.907,
|
| 933 |
+
"eval_samples_per_second": 65.77,
|
| 934 |
+
"eval_steps_per_second": 4.111,
|
| 935 |
+
"step": 22849
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 7.14,
|
| 939 |
+
"learning_rate": 0.00019047619047619045,
|
| 940 |
+
"loss": 0.794,
|
| 941 |
+
"step": 23000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 7.19,
|
| 945 |
+
"eval_accuracy": 0.8218634447758527,
|
| 946 |
+
"eval_loss": 0.7578034996986389,
|
| 947 |
+
"eval_runtime": 1562.4876,
|
| 948 |
+
"eval_samples_per_second": 66.04,
|
| 949 |
+
"eval_steps_per_second": 4.128,
|
| 950 |
+
"step": 23162
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 7.29,
|
| 954 |
+
"eval_accuracy": 0.8225726120979496,
|
| 955 |
+
"eval_loss": 0.7539456486701965,
|
| 956 |
+
"eval_runtime": 1563.2377,
|
| 957 |
+
"eval_samples_per_second": 66.009,
|
| 958 |
+
"eval_steps_per_second": 4.126,
|
| 959 |
+
"step": 23475
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 7.3,
|
| 963 |
+
"learning_rate": 0.00018012422360248444,
|
| 964 |
+
"loss": 0.7891,
|
| 965 |
+
"step": 23500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 7.39,
|
| 969 |
+
"eval_accuracy": 0.8229123629611099,
|
| 970 |
+
"eval_loss": 0.751589298248291,
|
| 971 |
+
"eval_runtime": 1562.2621,
|
| 972 |
+
"eval_samples_per_second": 66.05,
|
| 973 |
+
"eval_steps_per_second": 4.129,
|
| 974 |
+
"step": 23788
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 7.45,
|
| 978 |
+
"learning_rate": 0.00016977225672877845,
|
| 979 |
+
"loss": 0.7854,
|
| 980 |
+
"step": 24000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 7.48,
|
| 984 |
+
"eval_accuracy": 0.8234190549813617,
|
| 985 |
+
"eval_loss": 0.7492088079452515,
|
| 986 |
+
"eval_runtime": 1562.6896,
|
| 987 |
+
"eval_samples_per_second": 66.032,
|
| 988 |
+
"eval_steps_per_second": 4.127,
|
| 989 |
+
"step": 24101
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 7.58,
|
| 993 |
+
"eval_accuracy": 0.823868769101777,
|
| 994 |
+
"eval_loss": 0.7464490532875061,
|
| 995 |
+
"eval_runtime": 1563.2351,
|
| 996 |
+
"eval_samples_per_second": 66.009,
|
| 997 |
+
"eval_steps_per_second": 4.126,
|
| 998 |
+
"step": 24414
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 7.61,
|
| 1002 |
+
"learning_rate": 0.00015942028985507247,
|
| 1003 |
+
"loss": 0.7813,
|
| 1004 |
+
"step": 24500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 7.68,
|
| 1008 |
+
"eval_accuracy": 0.8245509114698386,
|
| 1009 |
+
"eval_loss": 0.7424126863479614,
|
| 1010 |
+
"eval_runtime": 1563.6491,
|
| 1011 |
+
"eval_samples_per_second": 65.991,
|
| 1012 |
+
"eval_steps_per_second": 4.125,
|
| 1013 |
+
"step": 24727
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 7.76,
|
| 1017 |
+
"learning_rate": 0.00014906832298136645,
|
| 1018 |
+
"loss": 0.7757,
|
| 1019 |
+
"step": 25000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 7.78,
|
| 1023 |
+
"eval_accuracy": 0.8252597131033751,
|
| 1024 |
+
"eval_loss": 0.7401213049888611,
|
| 1025 |
+
"eval_runtime": 1563.1841,
|
| 1026 |
+
"eval_samples_per_second": 66.011,
|
| 1027 |
+
"eval_steps_per_second": 4.126,
|
| 1028 |
+
"step": 25040
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 7.87,
|
| 1032 |
+
"eval_accuracy": 0.8254715067571893,
|
| 1033 |
+
"eval_loss": 0.7378228306770325,
|
| 1034 |
+
"eval_runtime": 1563.1126,
|
| 1035 |
+
"eval_samples_per_second": 66.014,
|
| 1036 |
+
"eval_steps_per_second": 4.126,
|
| 1037 |
+
"step": 25353
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 7.92,
|
| 1041 |
+
"learning_rate": 0.00013871635610766044,
|
| 1042 |
+
"loss": 0.7722,
|
| 1043 |
+
"step": 25500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 7.97,
|
| 1047 |
+
"eval_accuracy": 0.8263812114502447,
|
| 1048 |
+
"eval_loss": 0.734555184841156,
|
| 1049 |
+
"eval_runtime": 1563.3264,
|
| 1050 |
+
"eval_samples_per_second": 66.005,
|
| 1051 |
+
"eval_steps_per_second": 4.126,
|
| 1052 |
+
"step": 25666
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 8.07,
|
| 1056 |
+
"eval_accuracy": 0.8266910048907001,
|
| 1057 |
+
"eval_loss": 0.7316432595252991,
|
| 1058 |
+
"eval_runtime": 1565.1422,
|
| 1059 |
+
"eval_samples_per_second": 65.928,
|
| 1060 |
+
"eval_steps_per_second": 4.121,
|
| 1061 |
+
"step": 25979
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 8.07,
|
| 1065 |
+
"learning_rate": 0.00012836438923395443,
|
| 1066 |
+
"loss": 0.765,
|
| 1067 |
+
"step": 26000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 8.16,
|
| 1071 |
+
"eval_accuracy": 0.8270383479169559,
|
| 1072 |
+
"eval_loss": 0.7292919754981995,
|
| 1073 |
+
"eval_runtime": 1563.9337,
|
| 1074 |
+
"eval_samples_per_second": 65.979,
|
| 1075 |
+
"eval_steps_per_second": 4.124,
|
| 1076 |
+
"step": 26292
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 8.23,
|
| 1080 |
+
"learning_rate": 0.00011801242236024844,
|
| 1081 |
+
"loss": 0.7584,
|
| 1082 |
+
"step": 26500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 8.26,
|
| 1086 |
+
"eval_accuracy": 0.8277969783059648,
|
| 1087 |
+
"eval_loss": 0.7266284227371216,
|
| 1088 |
+
"eval_runtime": 1566.4843,
|
| 1089 |
+
"eval_samples_per_second": 65.872,
|
| 1090 |
+
"eval_steps_per_second": 4.118,
|
| 1091 |
+
"step": 26605
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 8.36,
|
| 1095 |
+
"eval_accuracy": 0.8280860122956746,
|
| 1096 |
+
"eval_loss": 0.7245298624038696,
|
| 1097 |
+
"eval_runtime": 1564.0929,
|
| 1098 |
+
"eval_samples_per_second": 65.972,
|
| 1099 |
+
"eval_steps_per_second": 4.124,
|
| 1100 |
+
"step": 26918
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 8.38,
|
| 1104 |
+
"learning_rate": 0.00010766045548654244,
|
| 1105 |
+
"loss": 0.7565,
|
| 1106 |
+
"step": 27000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 8.46,
|
| 1110 |
+
"eval_accuracy": 0.8286899161017834,
|
| 1111 |
+
"eval_loss": 0.7209280729293823,
|
| 1112 |
+
"eval_runtime": 1567.5209,
|
| 1113 |
+
"eval_samples_per_second": 65.828,
|
| 1114 |
+
"eval_steps_per_second": 4.115,
|
| 1115 |
+
"step": 27231
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 8.54,
|
| 1119 |
+
"learning_rate": 9.730848861283643e-05,
|
| 1120 |
+
"loss": 0.7506,
|
| 1121 |
+
"step": 27500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 8.55,
|
| 1125 |
+
"eval_accuracy": 0.829094583836786,
|
| 1126 |
+
"eval_loss": 0.7193953990936279,
|
| 1127 |
+
"eval_runtime": 1567.7556,
|
| 1128 |
+
"eval_samples_per_second": 65.818,
|
| 1129 |
+
"eval_steps_per_second": 4.114,
|
| 1130 |
+
"step": 27544
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 8.65,
|
| 1134 |
+
"eval_accuracy": 0.8296025421755568,
|
| 1135 |
+
"eval_loss": 0.7171857357025146,
|
| 1136 |
+
"eval_runtime": 1567.618,
|
| 1137 |
+
"eval_samples_per_second": 65.824,
|
| 1138 |
+
"eval_steps_per_second": 4.115,
|
| 1139 |
+
"step": 27857
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 8.69,
|
| 1143 |
+
"learning_rate": 8.695652173913043e-05,
|
| 1144 |
+
"loss": 0.7469,
|
| 1145 |
+
"step": 28000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 8.75,
|
| 1149 |
+
"eval_accuracy": 0.8297588118895532,
|
| 1150 |
+
"eval_loss": 0.715788722038269,
|
| 1151 |
+
"eval_runtime": 1568.2621,
|
| 1152 |
+
"eval_samples_per_second": 65.797,
|
| 1153 |
+
"eval_steps_per_second": 4.113,
|
| 1154 |
+
"step": 28170
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 8.84,
|
| 1158 |
+
"eval_accuracy": 0.8303201783553539,
|
| 1159 |
+
"eval_loss": 0.7129087448120117,
|
| 1160 |
+
"eval_runtime": 1566.51,
|
| 1161 |
+
"eval_samples_per_second": 65.871,
|
| 1162 |
+
"eval_steps_per_second": 4.117,
|
| 1163 |
+
"step": 28483
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 8.85,
|
| 1167 |
+
"learning_rate": 7.660455486542441e-05,
|
| 1168 |
+
"loss": 0.7434,
|
| 1169 |
+
"step": 28500
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 8.94,
|
| 1173 |
+
"eval_accuracy": 0.8310723013027939,
|
| 1174 |
+
"eval_loss": 0.7107537984848022,
|
| 1175 |
+
"eval_runtime": 1565.7298,
|
| 1176 |
+
"eval_samples_per_second": 65.903,
|
| 1177 |
+
"eval_steps_per_second": 4.119,
|
| 1178 |
+
"step": 28796
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 9.01,
|
| 1182 |
+
"learning_rate": 6.625258799171841e-05,
|
| 1183 |
+
"loss": 0.7395,
|
| 1184 |
+
"step": 29000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 9.04,
|
| 1188 |
+
"eval_accuracy": 0.8311976533176414,
|
| 1189 |
+
"eval_loss": 0.7103267908096313,
|
| 1190 |
+
"eval_runtime": 1566.6592,
|
| 1191 |
+
"eval_samples_per_second": 65.864,
|
| 1192 |
+
"eval_steps_per_second": 4.117,
|
| 1193 |
+
"step": 29109
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 9.14,
|
| 1197 |
+
"eval_accuracy": 0.831599738008909,
|
| 1198 |
+
"eval_loss": 0.7076959609985352,
|
| 1199 |
+
"eval_runtime": 1563.475,
|
| 1200 |
+
"eval_samples_per_second": 65.998,
|
| 1201 |
+
"eval_steps_per_second": 4.125,
|
| 1202 |
+
"step": 29422
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 9.16,
|
| 1206 |
+
"learning_rate": 5.5900621118012414e-05,
|
| 1207 |
+
"loss": 0.7327,
|
| 1208 |
+
"step": 29500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 9.23,
|
| 1212 |
+
"eval_accuracy": 0.8318789165507281,
|
| 1213 |
+
"eval_loss": 0.7060185074806213,
|
| 1214 |
+
"eval_runtime": 1563.2277,
|
| 1215 |
+
"eval_samples_per_second": 66.009,
|
| 1216 |
+
"eval_steps_per_second": 4.126,
|
| 1217 |
+
"step": 29735
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 9.32,
|
| 1221 |
+
"learning_rate": 4.554865424430642e-05,
|
| 1222 |
+
"loss": 0.7294,
|
| 1223 |
+
"step": 30000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 9.33,
|
| 1227 |
+
"eval_accuracy": 0.8324941188917658,
|
| 1228 |
+
"eval_loss": 0.7029792070388794,
|
| 1229 |
+
"eval_runtime": 1563.5398,
|
| 1230 |
+
"eval_samples_per_second": 65.996,
|
| 1231 |
+
"eval_steps_per_second": 4.125,
|
| 1232 |
+
"step": 30048
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 9.43,
|
| 1236 |
+
"eval_accuracy": 0.832804502850609,
|
| 1237 |
+
"eval_loss": 0.7012088298797607,
|
| 1238 |
+
"eval_runtime": 1563.5997,
|
| 1239 |
+
"eval_samples_per_second": 65.993,
|
| 1240 |
+
"eval_steps_per_second": 4.125,
|
| 1241 |
+
"step": 30361
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 9.47,
|
| 1245 |
+
"learning_rate": 3.5196687370600414e-05,
|
| 1246 |
+
"loss": 0.7277,
|
| 1247 |
+
"step": 30500
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 9.53,
|
| 1251 |
+
"eval_accuracy": 0.8329869074323458,
|
| 1252 |
+
"eval_loss": 0.7000030875205994,
|
| 1253 |
+
"eval_runtime": 1563.8346,
|
| 1254 |
+
"eval_samples_per_second": 65.983,
|
| 1255 |
+
"eval_steps_per_second": 4.124,
|
| 1256 |
+
"step": 30674
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 9.62,
|
| 1260 |
+
"eval_accuracy": 0.8334238360274034,
|
| 1261 |
+
"eval_loss": 0.6988800764083862,
|
| 1262 |
+
"eval_runtime": 1563.4183,
|
| 1263 |
+
"eval_samples_per_second": 66.001,
|
| 1264 |
+
"eval_steps_per_second": 4.126,
|
| 1265 |
+
"step": 30987
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 9.63,
|
| 1269 |
+
"learning_rate": 2.4844720496894407e-05,
|
| 1270 |
+
"loss": 0.7237,
|
| 1271 |
+
"step": 31000
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 9.72,
|
| 1275 |
+
"eval_accuracy": 0.8335258711989345,
|
| 1276 |
+
"eval_loss": 0.6981679201126099,
|
| 1277 |
+
"eval_runtime": 1564.2656,
|
| 1278 |
+
"eval_samples_per_second": 65.965,
|
| 1279 |
+
"eval_steps_per_second": 4.123,
|
| 1280 |
+
"step": 31300
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 9.78,
|
| 1284 |
+
"learning_rate": 1.4492753623188405e-05,
|
| 1285 |
+
"loss": 0.7233,
|
| 1286 |
+
"step": 31500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 9.82,
|
| 1290 |
+
"eval_accuracy": 0.8338284368943191,
|
| 1291 |
+
"eval_loss": 0.6956919431686401,
|
| 1292 |
+
"eval_runtime": 1565.7206,
|
| 1293 |
+
"eval_samples_per_second": 65.904,
|
| 1294 |
+
"eval_steps_per_second": 4.12,
|
| 1295 |
+
"step": 31613
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 9.91,
|
| 1299 |
+
"eval_accuracy": 0.8342045312252818,
|
| 1300 |
+
"eval_loss": 0.6948868632316589,
|
| 1301 |
+
"eval_runtime": 1564.1555,
|
| 1302 |
+
"eval_samples_per_second": 65.97,
|
| 1303 |
+
"eval_steps_per_second": 4.124,
|
| 1304 |
+
"step": 31926
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 9.94,
|
| 1308 |
+
"learning_rate": 4.140786749482401e-06,
|
| 1309 |
+
"loss": 0.7196,
|
| 1310 |
+
"step": 32000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 10.0,
|
| 1314 |
+
"step": 32200,
|
| 1315 |
+
"total_flos": 2.1701190649823816e+18,
|
| 1316 |
+
"train_loss": 1.3247782011802152,
|
| 1317 |
+
"train_runtime": 514233.1245,
|
| 1318 |
+
"train_samples_per_second": 16.031,
|
| 1319 |
+
"train_steps_per_second": 0.063
|
| 1320 |
+
}
|
| 1321 |
+
],
|
| 1322 |
+
"max_steps": 32200,
|
| 1323 |
+
"num_train_epochs": 10,
|
| 1324 |
+
"total_flos": 2.1701190649823816e+18,
|
| 1325 |
+
"trial_name": null,
|
| 1326 |
+
"trial_params": null
|
| 1327 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c7584a71694e95aea09111d0473f31f59583aa247deafe06abc4f114529773a
|
| 3 |
+
size 3963
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|