Commit
•
8d475d2
1
Parent(s):
14024fd
model upload
Browse files- config.json +67 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +736 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "csebuetnlp/banglabert",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10",
|
| 24 |
+
"11": "LABEL_11",
|
| 25 |
+
"12": "LABEL_12",
|
| 26 |
+
"13": "LABEL_13",
|
| 27 |
+
"14": "LABEL_14",
|
| 28 |
+
"15": "LABEL_15"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"LABEL_0": 0,
|
| 34 |
+
"LABEL_1": 1,
|
| 35 |
+
"LABEL_10": 10,
|
| 36 |
+
"LABEL_11": 11,
|
| 37 |
+
"LABEL_12": 12,
|
| 38 |
+
"LABEL_13": 13,
|
| 39 |
+
"LABEL_14": 14,
|
| 40 |
+
"LABEL_15": 15,
|
| 41 |
+
"LABEL_2": 2,
|
| 42 |
+
"LABEL_3": 3,
|
| 43 |
+
"LABEL_4": 4,
|
| 44 |
+
"LABEL_5": 5,
|
| 45 |
+
"LABEL_6": 6,
|
| 46 |
+
"LABEL_7": 7,
|
| 47 |
+
"LABEL_8": 8,
|
| 48 |
+
"LABEL_9": 9
|
| 49 |
+
},
|
| 50 |
+
"layer_norm_eps": 1e-12,
|
| 51 |
+
"max_position_embeddings": 512,
|
| 52 |
+
"model_type": "electra",
|
| 53 |
+
"num_attention_heads": 12,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"pad_token_id": 0,
|
| 56 |
+
"position_embedding_type": "absolute",
|
| 57 |
+
"problem_type": "single_label_classification",
|
| 58 |
+
"summary_activation": "gelu",
|
| 59 |
+
"summary_last_dropout": 0.1,
|
| 60 |
+
"summary_type": "first",
|
| 61 |
+
"summary_use_proj": true,
|
| 62 |
+
"torch_dtype": "float32",
|
| 63 |
+
"transformers_version": "4.28.0",
|
| 64 |
+
"type_vocab_size": 2,
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"vocab_size": 32000
|
| 67 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2220dac4e654ff3e5bead99234a6eb3854b67d7ef2b37a14c5ce0d85cf9802c
|
| 3 |
+
size 885155077
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:485c31f487c3d6c435d8a4c950cf9c4630e4cfbc10f37d7f55a2c0f6f1f14686
|
| 3 |
+
size 442591989
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5394c5001c71f202613b40c087dccd6e91042e2d7bca7c6efc2e9a6b8662927
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62ed27cc64ae9a3bb244e6e5a43c724c14d79ed561a71664dcfcddb7f88ca76c
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:addf57e86c5a56934ddd72d5eed40ef14e2357605c55b9cc53addab1e75680e7
|
| 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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"full_tokenizer_file": null,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"never_split": null,
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": false,
|
| 14 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,736 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 13500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"eval_f1": 0.9838200292792664,
|
| 13 |
+
"eval_loss": 0.3369638919830322,
|
| 14 |
+
"eval_runtime": 9.8875,
|
| 15 |
+
"eval_samples_per_second": 363.287,
|
| 16 |
+
"eval_steps_per_second": 11.429,
|
| 17 |
+
"step": 225
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"learning_rate": 1.933777777777778e-05,
|
| 22 |
+
"loss": 0.7525,
|
| 23 |
+
"step": 449
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_f1": 0.9947156879317626,
|
| 28 |
+
"eval_loss": 0.06897161155939102,
|
| 29 |
+
"eval_runtime": 9.8175,
|
| 30 |
+
"eval_samples_per_second": 365.878,
|
| 31 |
+
"eval_steps_per_second": 11.51,
|
| 32 |
+
"step": 450
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.5,
|
| 36 |
+
"eval_f1": 0.9963811589436764,
|
| 37 |
+
"eval_loss": 0.02461547963321209,
|
| 38 |
+
"eval_runtime": 9.8704,
|
| 39 |
+
"eval_samples_per_second": 363.916,
|
| 40 |
+
"eval_steps_per_second": 11.448,
|
| 41 |
+
"step": 675
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.0,
|
| 45 |
+
"learning_rate": 1.867555555555556e-05,
|
| 46 |
+
"loss": 0.0421,
|
| 47 |
+
"step": 898
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_f1": 0.9944299040377919,
|
| 52 |
+
"eval_loss": 0.0366971492767334,
|
| 53 |
+
"eval_runtime": 9.8419,
|
| 54 |
+
"eval_samples_per_second": 364.97,
|
| 55 |
+
"eval_steps_per_second": 11.482,
|
| 56 |
+
"step": 900
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.5,
|
| 60 |
+
"eval_f1": 0.9952689302306932,
|
| 61 |
+
"eval_loss": 0.028725871816277504,
|
| 62 |
+
"eval_runtime": 9.8602,
|
| 63 |
+
"eval_samples_per_second": 364.292,
|
| 64 |
+
"eval_steps_per_second": 11.46,
|
| 65 |
+
"step": 1125
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.99,
|
| 69 |
+
"learning_rate": 1.801037037037037e-05,
|
| 70 |
+
"loss": 0.0171,
|
| 71 |
+
"step": 1347
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"eval_f1": 0.9974916981915504,
|
| 76 |
+
"eval_loss": 0.02087334357202053,
|
| 77 |
+
"eval_runtime": 9.8419,
|
| 78 |
+
"eval_samples_per_second": 364.971,
|
| 79 |
+
"eval_steps_per_second": 11.482,
|
| 80 |
+
"step": 1350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.5,
|
| 84 |
+
"eval_f1": 0.9958079825309512,
|
| 85 |
+
"eval_loss": 0.027463000267744064,
|
| 86 |
+
"eval_runtime": 9.8899,
|
| 87 |
+
"eval_samples_per_second": 363.198,
|
| 88 |
+
"eval_steps_per_second": 11.426,
|
| 89 |
+
"step": 1575
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 3.99,
|
| 93 |
+
"learning_rate": 1.7345185185185187e-05,
|
| 94 |
+
"loss": 0.0101,
|
| 95 |
+
"step": 1796
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 4.0,
|
| 99 |
+
"eval_f1": 0.9923778241572203,
|
| 100 |
+
"eval_loss": 0.04307250306010246,
|
| 101 |
+
"eval_runtime": 9.8651,
|
| 102 |
+
"eval_samples_per_second": 364.112,
|
| 103 |
+
"eval_steps_per_second": 11.455,
|
| 104 |
+
"step": 1800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.5,
|
| 108 |
+
"eval_f1": 0.9894604343019209,
|
| 109 |
+
"eval_loss": 0.06550969928503036,
|
| 110 |
+
"eval_runtime": 9.8831,
|
| 111 |
+
"eval_samples_per_second": 363.448,
|
| 112 |
+
"eval_steps_per_second": 11.434,
|
| 113 |
+
"step": 2025
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.99,
|
| 117 |
+
"learning_rate": 1.668e-05,
|
| 118 |
+
"loss": 0.0079,
|
| 119 |
+
"step": 2245
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 5.0,
|
| 123 |
+
"eval_f1": 0.9966504962899037,
|
| 124 |
+
"eval_loss": 0.024906333535909653,
|
| 125 |
+
"eval_runtime": 9.8822,
|
| 126 |
+
"eval_samples_per_second": 363.481,
|
| 127 |
+
"eval_steps_per_second": 11.435,
|
| 128 |
+
"step": 2250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.5,
|
| 132 |
+
"eval_f1": 0.9947052626407842,
|
| 133 |
+
"eval_loss": 0.032973531633615494,
|
| 134 |
+
"eval_runtime": 9.8456,
|
| 135 |
+
"eval_samples_per_second": 364.831,
|
| 136 |
+
"eval_steps_per_second": 11.477,
|
| 137 |
+
"step": 2475
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 5.99,
|
| 141 |
+
"learning_rate": 1.6014814814814815e-05,
|
| 142 |
+
"loss": 0.014,
|
| 143 |
+
"step": 2694
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.0,
|
| 147 |
+
"eval_f1": 0.9958134976155982,
|
| 148 |
+
"eval_loss": 0.025115273892879486,
|
| 149 |
+
"eval_runtime": 9.8838,
|
| 150 |
+
"eval_samples_per_second": 363.422,
|
| 151 |
+
"eval_steps_per_second": 11.433,
|
| 152 |
+
"step": 2700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.5,
|
| 156 |
+
"eval_f1": 0.9963697167771403,
|
| 157 |
+
"eval_loss": 0.014389083720743656,
|
| 158 |
+
"eval_runtime": 9.8519,
|
| 159 |
+
"eval_samples_per_second": 364.599,
|
| 160 |
+
"eval_steps_per_second": 11.47,
|
| 161 |
+
"step": 2925
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.98,
|
| 165 |
+
"learning_rate": 1.534962962962963e-05,
|
| 166 |
+
"loss": 0.0068,
|
| 167 |
+
"step": 3143
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 7.0,
|
| 171 |
+
"eval_f1": 0.9974888410650935,
|
| 172 |
+
"eval_loss": 0.01635473594069481,
|
| 173 |
+
"eval_runtime": 9.8836,
|
| 174 |
+
"eval_samples_per_second": 363.43,
|
| 175 |
+
"eval_steps_per_second": 11.433,
|
| 176 |
+
"step": 3150
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 7.5,
|
| 180 |
+
"eval_f1": 0.9980480978911765,
|
| 181 |
+
"eval_loss": 0.01281055435538292,
|
| 182 |
+
"eval_runtime": 9.8626,
|
| 183 |
+
"eval_samples_per_second": 364.203,
|
| 184 |
+
"eval_steps_per_second": 11.457,
|
| 185 |
+
"step": 3375
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.98,
|
| 189 |
+
"learning_rate": 1.4684444444444445e-05,
|
| 190 |
+
"loss": 0.0018,
|
| 191 |
+
"step": 3592
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 8.0,
|
| 195 |
+
"eval_f1": 0.9966572157308153,
|
| 196 |
+
"eval_loss": 0.021354708820581436,
|
| 197 |
+
"eval_runtime": 9.8914,
|
| 198 |
+
"eval_samples_per_second": 363.144,
|
| 199 |
+
"eval_steps_per_second": 11.424,
|
| 200 |
+
"step": 3600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.5,
|
| 204 |
+
"eval_f1": 0.9969361037754005,
|
| 205 |
+
"eval_loss": 0.019004661589860916,
|
| 206 |
+
"eval_runtime": 9.8255,
|
| 207 |
+
"eval_samples_per_second": 365.578,
|
| 208 |
+
"eval_steps_per_second": 11.501,
|
| 209 |
+
"step": 3825
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 8.98,
|
| 213 |
+
"learning_rate": 1.4020740740740742e-05,
|
| 214 |
+
"loss": 0.0018,
|
| 215 |
+
"step": 4041
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 9.0,
|
| 219 |
+
"eval_f1": 0.9977696305095403,
|
| 220 |
+
"eval_loss": 0.01915433257818222,
|
| 221 |
+
"eval_runtime": 9.847,
|
| 222 |
+
"eval_samples_per_second": 364.78,
|
| 223 |
+
"eval_steps_per_second": 11.476,
|
| 224 |
+
"step": 4050
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 9.5,
|
| 228 |
+
"eval_f1": 0.9963730398525849,
|
| 229 |
+
"eval_loss": 0.02228739485144615,
|
| 230 |
+
"eval_runtime": 9.8515,
|
| 231 |
+
"eval_samples_per_second": 364.615,
|
| 232 |
+
"eval_steps_per_second": 11.47,
|
| 233 |
+
"step": 4275
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 9.98,
|
| 237 |
+
"learning_rate": 1.3355555555555557e-05,
|
| 238 |
+
"loss": 0.0049,
|
| 239 |
+
"step": 4490
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.0,
|
| 243 |
+
"eval_f1": 0.9958423076694589,
|
| 244 |
+
"eval_loss": 0.035607218742370605,
|
| 245 |
+
"eval_runtime": 9.8349,
|
| 246 |
+
"eval_samples_per_second": 365.229,
|
| 247 |
+
"eval_steps_per_second": 11.49,
|
| 248 |
+
"step": 4500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.5,
|
| 252 |
+
"eval_f1": 0.9977709997223315,
|
| 253 |
+
"eval_loss": 0.014773285947740078,
|
| 254 |
+
"eval_runtime": 9.859,
|
| 255 |
+
"eval_samples_per_second": 364.335,
|
| 256 |
+
"eval_steps_per_second": 11.462,
|
| 257 |
+
"step": 4725
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 10.98,
|
| 261 |
+
"learning_rate": 1.2690370370370371e-05,
|
| 262 |
+
"loss": 0.0058,
|
| 263 |
+
"step": 4939
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 11.0,
|
| 267 |
+
"eval_f1": 0.9960966553810828,
|
| 268 |
+
"eval_loss": 0.027824491262435913,
|
| 269 |
+
"eval_runtime": 9.8473,
|
| 270 |
+
"eval_samples_per_second": 364.77,
|
| 271 |
+
"eval_steps_per_second": 11.475,
|
| 272 |
+
"step": 4950
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.5,
|
| 276 |
+
"eval_f1": 0.9958285144673014,
|
| 277 |
+
"eval_loss": 0.034932490438222885,
|
| 278 |
+
"eval_runtime": 9.8384,
|
| 279 |
+
"eval_samples_per_second": 365.101,
|
| 280 |
+
"eval_steps_per_second": 11.486,
|
| 281 |
+
"step": 5175
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 11.97,
|
| 285 |
+
"learning_rate": 1.2025185185185186e-05,
|
| 286 |
+
"loss": 0.004,
|
| 287 |
+
"step": 5388
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 12.0,
|
| 291 |
+
"eval_f1": 0.9958167666486853,
|
| 292 |
+
"eval_loss": 0.03234181925654411,
|
| 293 |
+
"eval_runtime": 9.83,
|
| 294 |
+
"eval_samples_per_second": 365.412,
|
| 295 |
+
"eval_steps_per_second": 11.495,
|
| 296 |
+
"step": 5400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 12.5,
|
| 300 |
+
"eval_f1": 0.9960979327465159,
|
| 301 |
+
"eval_loss": 0.03011472336947918,
|
| 302 |
+
"eval_runtime": 9.9437,
|
| 303 |
+
"eval_samples_per_second": 361.234,
|
| 304 |
+
"eval_steps_per_second": 11.364,
|
| 305 |
+
"step": 5625
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 12.97,
|
| 309 |
+
"learning_rate": 1.136e-05,
|
| 310 |
+
"loss": 0.0002,
|
| 311 |
+
"step": 5837
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 13.0,
|
| 315 |
+
"eval_f1": 0.9966535238124058,
|
| 316 |
+
"eval_loss": 0.028114166110754013,
|
| 317 |
+
"eval_runtime": 9.9673,
|
| 318 |
+
"eval_samples_per_second": 360.379,
|
| 319 |
+
"eval_steps_per_second": 11.337,
|
| 320 |
+
"step": 5850
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 13.5,
|
| 324 |
+
"eval_f1": 0.9963785130348743,
|
| 325 |
+
"eval_loss": 0.031257264316082,
|
| 326 |
+
"eval_runtime": 9.9968,
|
| 327 |
+
"eval_samples_per_second": 359.313,
|
| 328 |
+
"eval_steps_per_second": 11.304,
|
| 329 |
+
"step": 6075
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 13.97,
|
| 333 |
+
"learning_rate": 1.0694814814814815e-05,
|
| 334 |
+
"loss": 0.0001,
|
| 335 |
+
"step": 6286
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 14.0,
|
| 339 |
+
"eval_f1": 0.9963822843309736,
|
| 340 |
+
"eval_loss": 0.026260120794177055,
|
| 341 |
+
"eval_runtime": 9.944,
|
| 342 |
+
"eval_samples_per_second": 361.222,
|
| 343 |
+
"eval_steps_per_second": 11.364,
|
| 344 |
+
"step": 6300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 14.5,
|
| 348 |
+
"eval_f1": 0.9963822843309736,
|
| 349 |
+
"eval_loss": 0.026301411911845207,
|
| 350 |
+
"eval_runtime": 9.9178,
|
| 351 |
+
"eval_samples_per_second": 362.178,
|
| 352 |
+
"eval_steps_per_second": 11.394,
|
| 353 |
+
"step": 6525
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 14.97,
|
| 357 |
+
"learning_rate": 1.0031111111111112e-05,
|
| 358 |
+
"loss": 0.002,
|
| 359 |
+
"step": 6735
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.0,
|
| 363 |
+
"eval_f1": 0.9949833769458274,
|
| 364 |
+
"eval_loss": 0.045748304575681686,
|
| 365 |
+
"eval_runtime": 9.9794,
|
| 366 |
+
"eval_samples_per_second": 359.942,
|
| 367 |
+
"eval_steps_per_second": 11.323,
|
| 368 |
+
"step": 6750
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 15.5,
|
| 372 |
+
"eval_f1": 0.995825155358709,
|
| 373 |
+
"eval_loss": 0.03245578706264496,
|
| 374 |
+
"eval_runtime": 9.9495,
|
| 375 |
+
"eval_samples_per_second": 361.023,
|
| 376 |
+
"eval_steps_per_second": 11.357,
|
| 377 |
+
"step": 6975
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 15.96,
|
| 381 |
+
"learning_rate": 9.365925925925928e-06,
|
| 382 |
+
"loss": 0.0041,
|
| 383 |
+
"step": 7184
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 16.0,
|
| 387 |
+
"eval_f1": 0.9963795479966517,
|
| 388 |
+
"eval_loss": 0.02910827286541462,
|
| 389 |
+
"eval_runtime": 9.9694,
|
| 390 |
+
"eval_samples_per_second": 360.303,
|
| 391 |
+
"eval_steps_per_second": 11.335,
|
| 392 |
+
"step": 7200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.5,
|
| 396 |
+
"eval_f1": 0.9952742268022056,
|
| 397 |
+
"eval_loss": 0.04952191188931465,
|
| 398 |
+
"eval_runtime": 9.9492,
|
| 399 |
+
"eval_samples_per_second": 361.033,
|
| 400 |
+
"eval_steps_per_second": 11.358,
|
| 401 |
+
"step": 7425
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 16.96,
|
| 405 |
+
"learning_rate": 8.700740740740742e-06,
|
| 406 |
+
"loss": 0.0047,
|
| 407 |
+
"step": 7633
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 17.0,
|
| 411 |
+
"eval_f1": 0.9949872709487171,
|
| 412 |
+
"eval_loss": 0.03917469084262848,
|
| 413 |
+
"eval_runtime": 9.9497,
|
| 414 |
+
"eval_samples_per_second": 361.015,
|
| 415 |
+
"eval_steps_per_second": 11.357,
|
| 416 |
+
"step": 7650
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 17.5,
|
| 420 |
+
"eval_f1": 0.9944269801435699,
|
| 421 |
+
"eval_loss": 0.03998776897788048,
|
| 422 |
+
"eval_runtime": 10.0031,
|
| 423 |
+
"eval_samples_per_second": 359.089,
|
| 424 |
+
"eval_steps_per_second": 11.297,
|
| 425 |
+
"step": 7875
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 17.96,
|
| 429 |
+
"learning_rate": 8.035555555555556e-06,
|
| 430 |
+
"loss": 0.0043,
|
| 431 |
+
"step": 8082
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 18.0,
|
| 435 |
+
"eval_f1": 0.9947222403458923,
|
| 436 |
+
"eval_loss": 0.049297936260700226,
|
| 437 |
+
"eval_runtime": 9.9403,
|
| 438 |
+
"eval_samples_per_second": 361.359,
|
| 439 |
+
"eval_steps_per_second": 11.368,
|
| 440 |
+
"step": 8100
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 18.5,
|
| 444 |
+
"eval_f1": 0.9966600284318996,
|
| 445 |
+
"eval_loss": 0.03158922120928764,
|
| 446 |
+
"eval_runtime": 10.0056,
|
| 447 |
+
"eval_samples_per_second": 358.999,
|
| 448 |
+
"eval_steps_per_second": 11.294,
|
| 449 |
+
"step": 8325
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 18.96,
|
| 453 |
+
"learning_rate": 7.370370370370371e-06,
|
| 454 |
+
"loss": 0.0001,
|
| 455 |
+
"step": 8531
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 19.0,
|
| 459 |
+
"eval_f1": 0.9977691843456208,
|
| 460 |
+
"eval_loss": 0.020285602658987045,
|
| 461 |
+
"eval_runtime": 9.9628,
|
| 462 |
+
"eval_samples_per_second": 360.543,
|
| 463 |
+
"eval_steps_per_second": 11.342,
|
| 464 |
+
"step": 8550
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 19.5,
|
| 468 |
+
"eval_f1": 0.9977691843456208,
|
| 469 |
+
"eval_loss": 0.020556360483169556,
|
| 470 |
+
"eval_runtime": 9.9808,
|
| 471 |
+
"eval_samples_per_second": 359.89,
|
| 472 |
+
"eval_steps_per_second": 11.322,
|
| 473 |
+
"step": 8775
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 19.96,
|
| 477 |
+
"learning_rate": 6.705185185185186e-06,
|
| 478 |
+
"loss": 0.0,
|
| 479 |
+
"step": 8980
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 20.0,
|
| 483 |
+
"eval_f1": 0.99749170867917,
|
| 484 |
+
"eval_loss": 0.018523868173360825,
|
| 485 |
+
"eval_runtime": 9.9504,
|
| 486 |
+
"eval_samples_per_second": 360.989,
|
| 487 |
+
"eval_steps_per_second": 11.356,
|
| 488 |
+
"step": 9000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 20.5,
|
| 492 |
+
"eval_f1": 0.99749170867917,
|
| 493 |
+
"eval_loss": 0.01606236957013607,
|
| 494 |
+
"eval_runtime": 9.9683,
|
| 495 |
+
"eval_samples_per_second": 360.341,
|
| 496 |
+
"eval_steps_per_second": 11.336,
|
| 497 |
+
"step": 9225
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 20.95,
|
| 501 |
+
"learning_rate": 6.040000000000001e-06,
|
| 502 |
+
"loss": 0.0008,
|
| 503 |
+
"step": 9429
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 21.0,
|
| 507 |
+
"eval_f1": 0.9961331807425458,
|
| 508 |
+
"eval_loss": 0.027556220069527626,
|
| 509 |
+
"eval_runtime": 9.9439,
|
| 510 |
+
"eval_samples_per_second": 361.228,
|
| 511 |
+
"eval_steps_per_second": 11.364,
|
| 512 |
+
"step": 9450
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 21.5,
|
| 516 |
+
"eval_f1": 0.9974890406034552,
|
| 517 |
+
"eval_loss": 0.022856123745441437,
|
| 518 |
+
"eval_runtime": 9.9718,
|
| 519 |
+
"eval_samples_per_second": 360.218,
|
| 520 |
+
"eval_steps_per_second": 11.332,
|
| 521 |
+
"step": 9675
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 21.95,
|
| 525 |
+
"learning_rate": 5.376296296296297e-06,
|
| 526 |
+
"loss": 0.0015,
|
| 527 |
+
"step": 9878
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 22.0,
|
| 531 |
+
"eval_f1": 0.996655754253198,
|
| 532 |
+
"eval_loss": 0.02840564213693142,
|
| 533 |
+
"eval_runtime": 9.9909,
|
| 534 |
+
"eval_samples_per_second": 359.528,
|
| 535 |
+
"eval_steps_per_second": 11.31,
|
| 536 |
+
"step": 9900
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 22.5,
|
| 540 |
+
"eval_f1": 0.9969386569418872,
|
| 541 |
+
"eval_loss": 0.02319738268852234,
|
| 542 |
+
"eval_runtime": 9.9719,
|
| 543 |
+
"eval_samples_per_second": 360.213,
|
| 544 |
+
"eval_steps_per_second": 11.332,
|
| 545 |
+
"step": 10125
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 22.95,
|
| 549 |
+
"learning_rate": 4.711111111111111e-06,
|
| 550 |
+
"loss": 0.0009,
|
| 551 |
+
"step": 10327
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 23.0,
|
| 555 |
+
"eval_f1": 0.9977709091258657,
|
| 556 |
+
"eval_loss": 0.016745826229453087,
|
| 557 |
+
"eval_runtime": 9.9669,
|
| 558 |
+
"eval_samples_per_second": 360.394,
|
| 559 |
+
"eval_steps_per_second": 11.338,
|
| 560 |
+
"step": 10350
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 23.5,
|
| 564 |
+
"eval_f1": 0.9977709091258657,
|
| 565 |
+
"eval_loss": 0.016933374106884003,
|
| 566 |
+
"eval_runtime": 9.967,
|
| 567 |
+
"eval_samples_per_second": 360.39,
|
| 568 |
+
"eval_steps_per_second": 11.337,
|
| 569 |
+
"step": 10575
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 23.95,
|
| 573 |
+
"learning_rate": 4.045925925925927e-06,
|
| 574 |
+
"loss": 0.0,
|
| 575 |
+
"step": 10776
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 24.0,
|
| 579 |
+
"eval_f1": 0.997211752501557,
|
| 580 |
+
"eval_loss": 0.02103780210018158,
|
| 581 |
+
"eval_runtime": 9.9446,
|
| 582 |
+
"eval_samples_per_second": 361.2,
|
| 583 |
+
"eval_steps_per_second": 11.363,
|
| 584 |
+
"step": 10800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 24.5,
|
| 588 |
+
"eval_f1": 0.997211752501557,
|
| 589 |
+
"eval_loss": 0.02101019211113453,
|
| 590 |
+
"eval_runtime": 9.9889,
|
| 591 |
+
"eval_samples_per_second": 359.6,
|
| 592 |
+
"eval_steps_per_second": 11.313,
|
| 593 |
+
"step": 11025
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 24.94,
|
| 597 |
+
"learning_rate": 3.380740740740741e-06,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 11225
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 25.0,
|
| 603 |
+
"eval_f1": 0.997211752501557,
|
| 604 |
+
"eval_loss": 0.021039091050624847,
|
| 605 |
+
"eval_runtime": 9.9809,
|
| 606 |
+
"eval_samples_per_second": 359.889,
|
| 607 |
+
"eval_steps_per_second": 11.322,
|
| 608 |
+
"step": 11250
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 25.5,
|
| 612 |
+
"eval_f1": 0.997211752501557,
|
| 613 |
+
"eval_loss": 0.021075071766972542,
|
| 614 |
+
"eval_runtime": 9.9783,
|
| 615 |
+
"eval_samples_per_second": 359.981,
|
| 616 |
+
"eval_steps_per_second": 11.325,
|
| 617 |
+
"step": 11475
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 25.94,
|
| 621 |
+
"learning_rate": 2.715555555555556e-06,
|
| 622 |
+
"loss": 0.0,
|
| 623 |
+
"step": 11674
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 26.0,
|
| 627 |
+
"eval_f1": 0.997211752501557,
|
| 628 |
+
"eval_loss": 0.021231742575764656,
|
| 629 |
+
"eval_runtime": 9.9681,
|
| 630 |
+
"eval_samples_per_second": 360.349,
|
| 631 |
+
"eval_steps_per_second": 11.336,
|
| 632 |
+
"step": 11700
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 26.5,
|
| 636 |
+
"eval_f1": 0.997211752501557,
|
| 637 |
+
"eval_loss": 0.021246111020445824,
|
| 638 |
+
"eval_runtime": 9.9808,
|
| 639 |
+
"eval_samples_per_second": 359.893,
|
| 640 |
+
"eval_steps_per_second": 11.322,
|
| 641 |
+
"step": 11925
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 26.94,
|
| 645 |
+
"learning_rate": 2.0503703703703704e-06,
|
| 646 |
+
"loss": 0.0,
|
| 647 |
+
"step": 12123
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 27.0,
|
| 651 |
+
"eval_f1": 0.997211752501557,
|
| 652 |
+
"eval_loss": 0.021242721006274223,
|
| 653 |
+
"eval_runtime": 9.9704,
|
| 654 |
+
"eval_samples_per_second": 360.265,
|
| 655 |
+
"eval_steps_per_second": 11.333,
|
| 656 |
+
"step": 12150
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 27.5,
|
| 660 |
+
"eval_f1": 0.997211752501557,
|
| 661 |
+
"eval_loss": 0.021284321323037148,
|
| 662 |
+
"eval_runtime": 9.9704,
|
| 663 |
+
"eval_samples_per_second": 360.267,
|
| 664 |
+
"eval_steps_per_second": 11.334,
|
| 665 |
+
"step": 12375
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 27.94,
|
| 669 |
+
"learning_rate": 1.3851851851851852e-06,
|
| 670 |
+
"loss": 0.0,
|
| 671 |
+
"step": 12572
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 28.0,
|
| 675 |
+
"eval_f1": 0.9974898648408176,
|
| 676 |
+
"eval_loss": 0.02062426507472992,
|
| 677 |
+
"eval_runtime": 9.9866,
|
| 678 |
+
"eval_samples_per_second": 359.68,
|
| 679 |
+
"eval_steps_per_second": 11.315,
|
| 680 |
+
"step": 12600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 28.5,
|
| 684 |
+
"eval_f1": 0.9974925455517304,
|
| 685 |
+
"eval_loss": 0.014707241207361221,
|
| 686 |
+
"eval_runtime": 10.0028,
|
| 687 |
+
"eval_samples_per_second": 359.098,
|
| 688 |
+
"eval_steps_per_second": 11.297,
|
| 689 |
+
"step": 12825
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 28.94,
|
| 693 |
+
"learning_rate": 7.214814814814814e-07,
|
| 694 |
+
"loss": 0.0004,
|
| 695 |
+
"step": 13021
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 29.0,
|
| 699 |
+
"eval_f1": 0.9974925455517304,
|
| 700 |
+
"eval_loss": 0.015917900949716568,
|
| 701 |
+
"eval_runtime": 10.0109,
|
| 702 |
+
"eval_samples_per_second": 358.81,
|
| 703 |
+
"eval_steps_per_second": 11.288,
|
| 704 |
+
"step": 13050
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 29.5,
|
| 708 |
+
"eval_f1": 0.9974925455517304,
|
| 709 |
+
"eval_loss": 0.015875495970249176,
|
| 710 |
+
"eval_runtime": 10.0428,
|
| 711 |
+
"eval_samples_per_second": 357.669,
|
| 712 |
+
"eval_steps_per_second": 11.252,
|
| 713 |
+
"step": 13275
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 29.93,
|
| 717 |
+
"learning_rate": 5.62962962962963e-08,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 13470
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 30.0,
|
| 723 |
+
"eval_f1": 0.9974925455517304,
|
| 724 |
+
"eval_loss": 0.01589413359761238,
|
| 725 |
+
"eval_runtime": 10.0081,
|
| 726 |
+
"eval_samples_per_second": 358.909,
|
| 727 |
+
"eval_steps_per_second": 11.291,
|
| 728 |
+
"step": 13500
|
| 729 |
+
}
|
| 730 |
+
],
|
| 731 |
+
"max_steps": 13500,
|
| 732 |
+
"num_train_epochs": 30,
|
| 733 |
+
"total_flos": 1.1347301109694464e+17,
|
| 734 |
+
"trial_name": null,
|
| 735 |
+
"trial_params": null
|
| 736 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2d0e7754c6102282b10c1484575c558d2dc92396e47b55c60441d2b923b640
|
| 3 |
+
size 3643
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|