Hossein Ghorbanfekr
commited on
Commit
•
5a8c26c
1
Parent(s):
fabe43e
first version of GEOberje base model and tokenizer
Browse files- config.json +26 -0
- generation_config.json +5 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +719 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GroNLP/bert-base-dutch-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 3,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.34.0.dev0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30073
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 3,
|
| 4 |
+
"transformers_version": "4.34.0.dev0"
|
| 5 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc38eb5cfa7c84be805ac8c79b8b60660b46dc0d382a7d55fdb108077a2cc07e
|
| 3 |
+
size 873520581
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae4540e3a4e364c70c06d8514d63ca3bdfca8f103c1df8c4d896ff84ac3d4c0
|
| 3 |
+
size 436745013
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:313c0b317057e20f1196cc6b353f1dc56e4e5e8ee19eb7cf8e4af0a3905f4112
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a65bcf181720c4bb1063c4bcf5f9008975b112f9a87b7b1edff2a7384fade15c
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"additional_special_tokens": [],
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": true,
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.675777792930603,
|
| 3 |
+
"best_model_checkpoint": "trainer/checkpoint-372428",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 396200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 2.2513,
|
| 15 |
+
"step": 7924
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 1.2939835786819458,
|
| 20 |
+
"eval_runtime": 37.6044,
|
| 21 |
+
"eval_samples_per_second": 749.168,
|
| 22 |
+
"eval_steps_per_second": 23.428,
|
| 23 |
+
"step": 7924
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 4e-05,
|
| 28 |
+
"loss": 1.3752,
|
| 29 |
+
"step": 15848
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 1.1416432857513428,
|
| 34 |
+
"eval_runtime": 37.8169,
|
| 35 |
+
"eval_samples_per_second": 744.958,
|
| 36 |
+
"eval_steps_per_second": 23.296,
|
| 37 |
+
"step": 15848
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.0,
|
| 41 |
+
"learning_rate": 4.9473684210526315e-05,
|
| 42 |
+
"loss": 1.2436,
|
| 43 |
+
"step": 23772
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 1.0676215887069702,
|
| 48 |
+
"eval_runtime": 37.7184,
|
| 49 |
+
"eval_samples_per_second": 746.904,
|
| 50 |
+
"eval_steps_per_second": 23.357,
|
| 51 |
+
"step": 23772
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"learning_rate": 4.842105263157895e-05,
|
| 56 |
+
"loss": 1.1458,
|
| 57 |
+
"step": 31696
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_loss": 0.9978280067443848,
|
| 62 |
+
"eval_runtime": 36.3705,
|
| 63 |
+
"eval_samples_per_second": 774.584,
|
| 64 |
+
"eval_steps_per_second": 24.223,
|
| 65 |
+
"step": 31696
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.0,
|
| 69 |
+
"learning_rate": 4.736842105263158e-05,
|
| 70 |
+
"loss": 1.0841,
|
| 71 |
+
"step": 39620
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_loss": 0.9508912563323975,
|
| 76 |
+
"eval_runtime": 36.5102,
|
| 77 |
+
"eval_samples_per_second": 771.62,
|
| 78 |
+
"eval_steps_per_second": 24.13,
|
| 79 |
+
"step": 39620
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.0,
|
| 83 |
+
"learning_rate": 4.6315789473684214e-05,
|
| 84 |
+
"loss": 1.0386,
|
| 85 |
+
"step": 47544
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6.0,
|
| 89 |
+
"eval_loss": 0.9356514811515808,
|
| 90 |
+
"eval_runtime": 36.323,
|
| 91 |
+
"eval_samples_per_second": 775.598,
|
| 92 |
+
"eval_steps_per_second": 24.255,
|
| 93 |
+
"step": 47544
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"learning_rate": 4.5263157894736846e-05,
|
| 98 |
+
"loss": 0.9989,
|
| 99 |
+
"step": 55468
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"eval_loss": 0.9180737137794495,
|
| 104 |
+
"eval_runtime": 36.4427,
|
| 105 |
+
"eval_samples_per_second": 773.05,
|
| 106 |
+
"eval_steps_per_second": 24.175,
|
| 107 |
+
"step": 55468
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"learning_rate": 4.421052631578947e-05,
|
| 112 |
+
"loss": 0.9686,
|
| 113 |
+
"step": 63392
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 0.8952454328536987,
|
| 118 |
+
"eval_runtime": 36.1822,
|
| 119 |
+
"eval_samples_per_second": 778.615,
|
| 120 |
+
"eval_steps_per_second": 24.349,
|
| 121 |
+
"step": 63392
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 9.0,
|
| 125 |
+
"learning_rate": 4.3157894736842105e-05,
|
| 126 |
+
"loss": 0.9426,
|
| 127 |
+
"step": 71316
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 9.0,
|
| 131 |
+
"eval_loss": 0.8876378536224365,
|
| 132 |
+
"eval_runtime": 36.5182,
|
| 133 |
+
"eval_samples_per_second": 771.451,
|
| 134 |
+
"eval_steps_per_second": 24.125,
|
| 135 |
+
"step": 71316
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.0,
|
| 139 |
+
"learning_rate": 4.210526315789474e-05,
|
| 140 |
+
"loss": 0.9198,
|
| 141 |
+
"step": 79240
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.0,
|
| 145 |
+
"eval_loss": 0.8818822503089905,
|
| 146 |
+
"eval_runtime": 36.3065,
|
| 147 |
+
"eval_samples_per_second": 775.949,
|
| 148 |
+
"eval_steps_per_second": 24.266,
|
| 149 |
+
"step": 79240
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 11.0,
|
| 153 |
+
"learning_rate": 4.105263157894737e-05,
|
| 154 |
+
"loss": 0.9053,
|
| 155 |
+
"step": 87164
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.0,
|
| 159 |
+
"eval_loss": 0.8349147439002991,
|
| 160 |
+
"eval_runtime": 36.3771,
|
| 161 |
+
"eval_samples_per_second": 774.444,
|
| 162 |
+
"eval_steps_per_second": 24.219,
|
| 163 |
+
"step": 87164
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 12.0,
|
| 167 |
+
"learning_rate": 4e-05,
|
| 168 |
+
"loss": 0.8881,
|
| 169 |
+
"step": 95088
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 12.0,
|
| 173 |
+
"eval_loss": 0.8407663702964783,
|
| 174 |
+
"eval_runtime": 36.4047,
|
| 175 |
+
"eval_samples_per_second": 773.857,
|
| 176 |
+
"eval_steps_per_second": 24.2,
|
| 177 |
+
"step": 95088
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 3.894736842105263e-05,
|
| 182 |
+
"loss": 0.8704,
|
| 183 |
+
"step": 103012
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_loss": 0.8339666128158569,
|
| 188 |
+
"eval_runtime": 36.314,
|
| 189 |
+
"eval_samples_per_second": 775.79,
|
| 190 |
+
"eval_steps_per_second": 24.261,
|
| 191 |
+
"step": 103012
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"learning_rate": 3.789473684210527e-05,
|
| 196 |
+
"loss": 0.8533,
|
| 197 |
+
"step": 110936
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 0.8264057636260986,
|
| 202 |
+
"eval_runtime": 36.2648,
|
| 203 |
+
"eval_samples_per_second": 776.841,
|
| 204 |
+
"eval_steps_per_second": 24.294,
|
| 205 |
+
"step": 110936
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"learning_rate": 3.6842105263157895e-05,
|
| 210 |
+
"loss": 0.8418,
|
| 211 |
+
"step": 118860
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 15.0,
|
| 215 |
+
"eval_loss": 0.8100990653038025,
|
| 216 |
+
"eval_runtime": 36.5073,
|
| 217 |
+
"eval_samples_per_second": 771.682,
|
| 218 |
+
"eval_steps_per_second": 24.132,
|
| 219 |
+
"step": 118860
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"learning_rate": 3.578947368421053e-05,
|
| 224 |
+
"loss": 0.8307,
|
| 225 |
+
"step": 126784
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.0,
|
| 229 |
+
"eval_loss": 0.8106787800788879,
|
| 230 |
+
"eval_runtime": 36.2767,
|
| 231 |
+
"eval_samples_per_second": 776.586,
|
| 232 |
+
"eval_steps_per_second": 24.286,
|
| 233 |
+
"step": 126784
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 17.0,
|
| 237 |
+
"learning_rate": 3.473684210526316e-05,
|
| 238 |
+
"loss": 0.815,
|
| 239 |
+
"step": 134708
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.0,
|
| 243 |
+
"eval_loss": 0.7991083264350891,
|
| 244 |
+
"eval_runtime": 36.2711,
|
| 245 |
+
"eval_samples_per_second": 776.707,
|
| 246 |
+
"eval_steps_per_second": 24.289,
|
| 247 |
+
"step": 134708
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 18.0,
|
| 251 |
+
"learning_rate": 3.368421052631579e-05,
|
| 252 |
+
"loss": 0.8015,
|
| 253 |
+
"step": 142632
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_loss": 0.7952774167060852,
|
| 258 |
+
"eval_runtime": 37.5556,
|
| 259 |
+
"eval_samples_per_second": 750.142,
|
| 260 |
+
"eval_steps_per_second": 23.459,
|
| 261 |
+
"step": 142632
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"learning_rate": 3.2631578947368426e-05,
|
| 266 |
+
"loss": 0.7894,
|
| 267 |
+
"step": 150556
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 19.0,
|
| 271 |
+
"eval_loss": 0.7720882296562195,
|
| 272 |
+
"eval_runtime": 36.9729,
|
| 273 |
+
"eval_samples_per_second": 761.964,
|
| 274 |
+
"eval_steps_per_second": 23.828,
|
| 275 |
+
"step": 150556
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"learning_rate": 3.157894736842105e-05,
|
| 280 |
+
"loss": 0.7789,
|
| 281 |
+
"step": 158480
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"eval_loss": 0.7802249789237976,
|
| 286 |
+
"eval_runtime": 37.1298,
|
| 287 |
+
"eval_samples_per_second": 758.744,
|
| 288 |
+
"eval_steps_per_second": 23.728,
|
| 289 |
+
"step": 158480
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.0,
|
| 293 |
+
"learning_rate": 3.0526315789473684e-05,
|
| 294 |
+
"loss": 0.7678,
|
| 295 |
+
"step": 166404
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 21.0,
|
| 299 |
+
"eval_loss": 0.7610885500907898,
|
| 300 |
+
"eval_runtime": 36.2573,
|
| 301 |
+
"eval_samples_per_second": 777.002,
|
| 302 |
+
"eval_steps_per_second": 24.299,
|
| 303 |
+
"step": 166404
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"learning_rate": 2.9473684210526314e-05,
|
| 308 |
+
"loss": 0.7534,
|
| 309 |
+
"step": 174328
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.0,
|
| 313 |
+
"eval_loss": 0.782088577747345,
|
| 314 |
+
"eval_runtime": 37.4893,
|
| 315 |
+
"eval_samples_per_second": 751.467,
|
| 316 |
+
"eval_steps_per_second": 23.5,
|
| 317 |
+
"step": 174328
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 23.0,
|
| 321 |
+
"learning_rate": 2.842105263157895e-05,
|
| 322 |
+
"loss": 0.7502,
|
| 323 |
+
"step": 182252
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.0,
|
| 327 |
+
"eval_loss": 0.7673630714416504,
|
| 328 |
+
"eval_runtime": 36.6312,
|
| 329 |
+
"eval_samples_per_second": 769.07,
|
| 330 |
+
"eval_steps_per_second": 24.051,
|
| 331 |
+
"step": 182252
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 24.0,
|
| 335 |
+
"learning_rate": 2.7368421052631583e-05,
|
| 336 |
+
"loss": 0.7345,
|
| 337 |
+
"step": 190176
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.0,
|
| 341 |
+
"eval_loss": 0.7627705335617065,
|
| 342 |
+
"eval_runtime": 37.0149,
|
| 343 |
+
"eval_samples_per_second": 761.099,
|
| 344 |
+
"eval_steps_per_second": 23.801,
|
| 345 |
+
"step": 190176
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 350 |
+
"loss": 0.7264,
|
| 351 |
+
"step": 198100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 25.0,
|
| 355 |
+
"eval_loss": 0.7561437487602234,
|
| 356 |
+
"eval_runtime": 37.2677,
|
| 357 |
+
"eval_samples_per_second": 755.937,
|
| 358 |
+
"eval_steps_per_second": 23.64,
|
| 359 |
+
"step": 198100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 26.0,
|
| 363 |
+
"learning_rate": 2.5263157894736845e-05,
|
| 364 |
+
"loss": 0.7142,
|
| 365 |
+
"step": 206024
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 26.0,
|
| 369 |
+
"eval_loss": 0.7509896159172058,
|
| 370 |
+
"eval_runtime": 37.3161,
|
| 371 |
+
"eval_samples_per_second": 754.956,
|
| 372 |
+
"eval_steps_per_second": 23.609,
|
| 373 |
+
"step": 206024
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 27.0,
|
| 377 |
+
"learning_rate": 2.4210526315789474e-05,
|
| 378 |
+
"loss": 0.7018,
|
| 379 |
+
"step": 213948
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 27.0,
|
| 383 |
+
"eval_loss": 0.7464780807495117,
|
| 384 |
+
"eval_runtime": 36.7538,
|
| 385 |
+
"eval_samples_per_second": 766.505,
|
| 386 |
+
"eval_steps_per_second": 23.97,
|
| 387 |
+
"step": 213948
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.0,
|
| 391 |
+
"learning_rate": 2.3157894736842107e-05,
|
| 392 |
+
"loss": 0.6897,
|
| 393 |
+
"step": 221872
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.0,
|
| 397 |
+
"eval_loss": 0.7344001531600952,
|
| 398 |
+
"eval_runtime": 37.0652,
|
| 399 |
+
"eval_samples_per_second": 760.066,
|
| 400 |
+
"eval_steps_per_second": 23.769,
|
| 401 |
+
"step": 221872
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"learning_rate": 2.2105263157894736e-05,
|
| 406 |
+
"loss": 0.682,
|
| 407 |
+
"step": 229796
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 29.0,
|
| 411 |
+
"eval_loss": 0.7429642081260681,
|
| 412 |
+
"eval_runtime": 37.2732,
|
| 413 |
+
"eval_samples_per_second": 755.824,
|
| 414 |
+
"eval_steps_per_second": 23.636,
|
| 415 |
+
"step": 229796
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 30.0,
|
| 419 |
+
"learning_rate": 2.105263157894737e-05,
|
| 420 |
+
"loss": 0.6754,
|
| 421 |
+
"step": 237720
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 30.0,
|
| 425 |
+
"eval_loss": 0.7481978535652161,
|
| 426 |
+
"eval_runtime": 37.0222,
|
| 427 |
+
"eval_samples_per_second": 760.949,
|
| 428 |
+
"eval_steps_per_second": 23.797,
|
| 429 |
+
"step": 237720
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 31.0,
|
| 433 |
+
"learning_rate": 2e-05,
|
| 434 |
+
"loss": 0.6679,
|
| 435 |
+
"step": 245644
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 31.0,
|
| 439 |
+
"eval_loss": 0.7224923968315125,
|
| 440 |
+
"eval_runtime": 37.2439,
|
| 441 |
+
"eval_samples_per_second": 756.419,
|
| 442 |
+
"eval_steps_per_second": 23.655,
|
| 443 |
+
"step": 245644
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 1.8947368421052634e-05,
|
| 448 |
+
"loss": 0.6566,
|
| 449 |
+
"step": 253568
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.0,
|
| 453 |
+
"eval_loss": 0.715844452381134,
|
| 454 |
+
"eval_runtime": 36.5457,
|
| 455 |
+
"eval_samples_per_second": 770.871,
|
| 456 |
+
"eval_steps_per_second": 24.107,
|
| 457 |
+
"step": 253568
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 33.0,
|
| 461 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 462 |
+
"loss": 0.6492,
|
| 463 |
+
"step": 261492
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 33.0,
|
| 467 |
+
"eval_loss": 0.7234057188034058,
|
| 468 |
+
"eval_runtime": 36.3822,
|
| 469 |
+
"eval_samples_per_second": 774.335,
|
| 470 |
+
"eval_steps_per_second": 24.215,
|
| 471 |
+
"step": 261492
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 34.0,
|
| 475 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 476 |
+
"loss": 0.642,
|
| 477 |
+
"step": 269416
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 34.0,
|
| 481 |
+
"eval_loss": 0.7132413983345032,
|
| 482 |
+
"eval_runtime": 36.3793,
|
| 483 |
+
"eval_samples_per_second": 774.396,
|
| 484 |
+
"eval_steps_per_second": 24.217,
|
| 485 |
+
"step": 269416
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.0,
|
| 489 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 490 |
+
"loss": 0.6342,
|
| 491 |
+
"step": 277340
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 35.0,
|
| 495 |
+
"eval_loss": 0.7007443904876709,
|
| 496 |
+
"eval_runtime": 36.3032,
|
| 497 |
+
"eval_samples_per_second": 776.02,
|
| 498 |
+
"eval_steps_per_second": 24.268,
|
| 499 |
+
"step": 277340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"learning_rate": 1.4736842105263157e-05,
|
| 504 |
+
"loss": 0.6236,
|
| 505 |
+
"step": 285264
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 36.0,
|
| 509 |
+
"eval_loss": 0.69706791639328,
|
| 510 |
+
"eval_runtime": 37.0755,
|
| 511 |
+
"eval_samples_per_second": 759.854,
|
| 512 |
+
"eval_steps_per_second": 23.762,
|
| 513 |
+
"step": 285264
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 37.0,
|
| 517 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 518 |
+
"loss": 0.6146,
|
| 519 |
+
"step": 293188
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 37.0,
|
| 523 |
+
"eval_loss": 0.6900755167007446,
|
| 524 |
+
"eval_runtime": 36.5007,
|
| 525 |
+
"eval_samples_per_second": 771.822,
|
| 526 |
+
"eval_steps_per_second": 24.137,
|
| 527 |
+
"step": 293188
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 38.0,
|
| 531 |
+
"learning_rate": 1.2631578947368422e-05,
|
| 532 |
+
"loss": 0.6087,
|
| 533 |
+
"step": 301112
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.0,
|
| 537 |
+
"eval_loss": 0.6962341666221619,
|
| 538 |
+
"eval_runtime": 36.6631,
|
| 539 |
+
"eval_samples_per_second": 768.402,
|
| 540 |
+
"eval_steps_per_second": 24.03,
|
| 541 |
+
"step": 301112
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 39.0,
|
| 545 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 546 |
+
"loss": 0.5989,
|
| 547 |
+
"step": 309036
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 39.0,
|
| 551 |
+
"eval_loss": 0.7045713067054749,
|
| 552 |
+
"eval_runtime": 36.6758,
|
| 553 |
+
"eval_samples_per_second": 768.136,
|
| 554 |
+
"eval_steps_per_second": 24.021,
|
| 555 |
+
"step": 309036
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 40.0,
|
| 559 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 560 |
+
"loss": 0.5924,
|
| 561 |
+
"step": 316960
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"eval_loss": 0.6984645128250122,
|
| 566 |
+
"eval_runtime": 36.7394,
|
| 567 |
+
"eval_samples_per_second": 766.807,
|
| 568 |
+
"eval_steps_per_second": 23.98,
|
| 569 |
+
"step": 316960
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 41.0,
|
| 573 |
+
"learning_rate": 9.473684210526317e-06,
|
| 574 |
+
"loss": 0.5827,
|
| 575 |
+
"step": 324884
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 41.0,
|
| 579 |
+
"eval_loss": 0.6994604468345642,
|
| 580 |
+
"eval_runtime": 36.8305,
|
| 581 |
+
"eval_samples_per_second": 764.91,
|
| 582 |
+
"eval_steps_per_second": 23.92,
|
| 583 |
+
"step": 324884
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 42.0,
|
| 587 |
+
"learning_rate": 8.421052631578948e-06,
|
| 588 |
+
"loss": 0.5731,
|
| 589 |
+
"step": 332808
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 42.0,
|
| 593 |
+
"eval_loss": 0.6827645301818848,
|
| 594 |
+
"eval_runtime": 36.7809,
|
| 595 |
+
"eval_samples_per_second": 765.941,
|
| 596 |
+
"eval_steps_per_second": 23.953,
|
| 597 |
+
"step": 332808
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 43.0,
|
| 601 |
+
"learning_rate": 7.3684210526315784e-06,
|
| 602 |
+
"loss": 0.5718,
|
| 603 |
+
"step": 340732
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 43.0,
|
| 607 |
+
"eval_loss": 0.7020975947380066,
|
| 608 |
+
"eval_runtime": 36.6627,
|
| 609 |
+
"eval_samples_per_second": 768.411,
|
| 610 |
+
"eval_steps_per_second": 24.03,
|
| 611 |
+
"step": 340732
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 44.0,
|
| 615 |
+
"learning_rate": 6.315789473684211e-06,
|
| 616 |
+
"loss": 0.5663,
|
| 617 |
+
"step": 348656
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 44.0,
|
| 621 |
+
"eval_loss": 0.6774910092353821,
|
| 622 |
+
"eval_runtime": 36.8941,
|
| 623 |
+
"eval_samples_per_second": 763.59,
|
| 624 |
+
"eval_steps_per_second": 23.879,
|
| 625 |
+
"step": 348656
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 45.0,
|
| 629 |
+
"learning_rate": 5.263157894736842e-06,
|
| 630 |
+
"loss": 0.5575,
|
| 631 |
+
"step": 356580
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.0,
|
| 635 |
+
"eval_loss": 0.683965265750885,
|
| 636 |
+
"eval_runtime": 36.8405,
|
| 637 |
+
"eval_samples_per_second": 764.703,
|
| 638 |
+
"eval_steps_per_second": 23.914,
|
| 639 |
+
"step": 356580
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 46.0,
|
| 643 |
+
"learning_rate": 4.210526315789474e-06,
|
| 644 |
+
"loss": 0.5524,
|
| 645 |
+
"step": 364504
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 46.0,
|
| 649 |
+
"eval_loss": 0.6812577247619629,
|
| 650 |
+
"eval_runtime": 36.3196,
|
| 651 |
+
"eval_samples_per_second": 775.669,
|
| 652 |
+
"eval_steps_per_second": 24.257,
|
| 653 |
+
"step": 364504
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 47.0,
|
| 657 |
+
"learning_rate": 3.1578947368421056e-06,
|
| 658 |
+
"loss": 0.5499,
|
| 659 |
+
"step": 372428
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 47.0,
|
| 663 |
+
"eval_loss": 0.675777792930603,
|
| 664 |
+
"eval_runtime": 36.282,
|
| 665 |
+
"eval_samples_per_second": 776.473,
|
| 666 |
+
"eval_steps_per_second": 24.282,
|
| 667 |
+
"step": 372428
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 48.0,
|
| 671 |
+
"learning_rate": 2.105263157894737e-06,
|
| 672 |
+
"loss": 0.541,
|
| 673 |
+
"step": 380352
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 48.0,
|
| 677 |
+
"eval_loss": 0.678913950920105,
|
| 678 |
+
"eval_runtime": 36.4409,
|
| 679 |
+
"eval_samples_per_second": 773.087,
|
| 680 |
+
"eval_steps_per_second": 24.176,
|
| 681 |
+
"step": 380352
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 49.0,
|
| 685 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 686 |
+
"loss": 0.5372,
|
| 687 |
+
"step": 388276
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 49.0,
|
| 691 |
+
"eval_loss": 0.6796761155128479,
|
| 692 |
+
"eval_runtime": 36.5663,
|
| 693 |
+
"eval_samples_per_second": 770.435,
|
| 694 |
+
"eval_steps_per_second": 24.093,
|
| 695 |
+
"step": 388276
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 50.0,
|
| 699 |
+
"learning_rate": 0.0,
|
| 700 |
+
"loss": 0.535,
|
| 701 |
+
"step": 396200
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 50.0,
|
| 705 |
+
"eval_loss": 0.6791965365409851,
|
| 706 |
+
"eval_runtime": 36.555,
|
| 707 |
+
"eval_samples_per_second": 770.674,
|
| 708 |
+
"eval_steps_per_second": 24.101,
|
| 709 |
+
"step": 396200
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 500,
|
| 713 |
+
"max_steps": 396200,
|
| 714 |
+
"num_train_epochs": 50,
|
| 715 |
+
"save_steps": 500,
|
| 716 |
+
"total_flos": 7.079826371258392e+17,
|
| 717 |
+
"trial_name": null,
|
| 718 |
+
"trial_params": null
|
| 719 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e77c050ffc8aa60501d4002695e5a1361e07452365b0d224aeeab04e33ad83f
|
| 3 |
+
size 4027
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|