Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +54 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +83 -0
- trainer_state.json +573 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<unk>NOTUSED": 32005
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "camembert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CamembertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 6,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6",
|
| 21 |
+
"7": "LABEL_7",
|
| 22 |
+
"8": "LABEL_8",
|
| 23 |
+
"9": "LABEL_9",
|
| 24 |
+
"10": "LABEL_10"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"LABEL_0": 0,
|
| 30 |
+
"LABEL_1": 1,
|
| 31 |
+
"LABEL_10": 10,
|
| 32 |
+
"LABEL_2": 2,
|
| 33 |
+
"LABEL_3": 3,
|
| 34 |
+
"LABEL_4": 4,
|
| 35 |
+
"LABEL_5": 5,
|
| 36 |
+
"LABEL_6": 6,
|
| 37 |
+
"LABEL_7": 7,
|
| 38 |
+
"LABEL_8": 8,
|
| 39 |
+
"LABEL_9": 9
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-05,
|
| 42 |
+
"max_position_embeddings": 514,
|
| 43 |
+
"model_type": "camembert",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"output_past": true,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.45.2",
|
| 51 |
+
"type_vocab_size": 1,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 32005
|
| 54 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b4c0188433a097d5f6aca79f2e1f235a3e7e965c5a9fbaa8cdfd3599e453651
|
| 3 |
+
size 440183196
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ba5f882155067722ae2b0cd9deb26218fda591ee9dfebe54fced3af73eeffa
|
| 3 |
+
size 680665594
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9824539445e632bf778aeb058b52a3648df9a5e704d2bdc7956848504ea60527
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:749896e251d426ea8371bc9e22e15df847827603e6810847330cc4e4134e75d1
|
| 3 |
+
size 1064
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
| 3 |
+
size 810912
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED",
|
| 5 |
+
"<unk>NOTUSED"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"cls_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"mask_token": {
|
| 11 |
+
"content": "<mask>",
|
| 12 |
+
"lstrip": true,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"unk_token": "<unk>"
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>NOTUSED",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>NOTUSED",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 36 |
+
"content": "<s>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"6": {
|
| 44 |
+
"content": "</s>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32004": {
|
| 52 |
+
"content": "<mask>",
|
| 53 |
+
"lstrip": true,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32005": {
|
| 60 |
+
"content": "<unk>NOTUSED",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"additional_special_tokens": [
|
| 69 |
+
"<s>NOTUSED",
|
| 70 |
+
"</s>NOTUSED",
|
| 71 |
+
"<unk>NOTUSED"
|
| 72 |
+
],
|
| 73 |
+
"bos_token": "<s>",
|
| 74 |
+
"clean_up_tokenization_spaces": false,
|
| 75 |
+
"cls_token": "<s>",
|
| 76 |
+
"eos_token": "</s>",
|
| 77 |
+
"mask_token": "<mask>",
|
| 78 |
+
"model_max_length": 512,
|
| 79 |
+
"pad_token": "<pad>",
|
| 80 |
+
"sep_token": "</s>",
|
| 81 |
+
"tokenizer_class": "CamembertTokenizer",
|
| 82 |
+
"unk_token": "<unk>"
|
| 83 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.012820512820513,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2670940170940171,
|
| 13 |
+
"grad_norm": 0.11774194240570068,
|
| 14 |
+
"learning_rate": 4.9809218559218565e-05,
|
| 15 |
+
"loss": 0.246,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2670940170940171,
|
| 20 |
+
"eval_f1": 0.5214187643020595,
|
| 21 |
+
"eval_loss": 0.03276558592915535,
|
| 22 |
+
"eval_precision": 0.5067158868528732,
|
| 23 |
+
"eval_recall": 0.5370003770739065,
|
| 24 |
+
"eval_runtime": 119.6438,
|
| 25 |
+
"eval_samples_per_second": 123.349,
|
| 26 |
+
"eval_steps_per_second": 3.861,
|
| 27 |
+
"step": 500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.5341880341880342,
|
| 31 |
+
"grad_norm": 0.042453471571207047,
|
| 32 |
+
"learning_rate": 4.961843711843712e-05,
|
| 33 |
+
"loss": 0.0238,
|
| 34 |
+
"step": 1000
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.5341880341880342,
|
| 38 |
+
"eval_f1": 0.6635963067112459,
|
| 39 |
+
"eval_loss": 0.01632688380777836,
|
| 40 |
+
"eval_precision": 0.6257568797761723,
|
| 41 |
+
"eval_recall": 0.7063065610859729,
|
| 42 |
+
"eval_runtime": 125.2059,
|
| 43 |
+
"eval_samples_per_second": 117.87,
|
| 44 |
+
"eval_steps_per_second": 3.69,
|
| 45 |
+
"step": 1000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.8012820512820513,
|
| 49 |
+
"grad_norm": 0.024465590715408325,
|
| 50 |
+
"learning_rate": 4.9427655677655683e-05,
|
| 51 |
+
"loss": 0.0127,
|
| 52 |
+
"step": 1500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.8012820512820513,
|
| 56 |
+
"eval_f1": 0.9185966204705558,
|
| 57 |
+
"eval_loss": 0.007961403578519821,
|
| 58 |
+
"eval_precision": 0.8978039780397804,
|
| 59 |
+
"eval_recall": 0.9403751885369532,
|
| 60 |
+
"eval_runtime": 214.5953,
|
| 61 |
+
"eval_samples_per_second": 68.771,
|
| 62 |
+
"eval_steps_per_second": 2.153,
|
| 63 |
+
"step": 1500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.0683760683760684,
|
| 67 |
+
"grad_norm": 0.06622592359781265,
|
| 68 |
+
"learning_rate": 4.923687423687424e-05,
|
| 69 |
+
"loss": 0.0063,
|
| 70 |
+
"step": 2000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.0683760683760684,
|
| 74 |
+
"eval_f1": 0.9344357210681118,
|
| 75 |
+
"eval_loss": 0.005176798906177282,
|
| 76 |
+
"eval_precision": 0.9185448253881529,
|
| 77 |
+
"eval_recall": 0.9508861236802413,
|
| 78 |
+
"eval_runtime": 215.2423,
|
| 79 |
+
"eval_samples_per_second": 68.565,
|
| 80 |
+
"eval_steps_per_second": 2.146,
|
| 81 |
+
"step": 2000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.3354700854700854,
|
| 85 |
+
"grad_norm": 0.048759885132312775,
|
| 86 |
+
"learning_rate": 4.9046092796092795e-05,
|
| 87 |
+
"loss": 0.0041,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.3354700854700854,
|
| 92 |
+
"eval_f1": 0.9516508609641868,
|
| 93 |
+
"eval_loss": 0.0035495704505592585,
|
| 94 |
+
"eval_precision": 0.9410165430164509,
|
| 95 |
+
"eval_recall": 0.9625282805429864,
|
| 96 |
+
"eval_runtime": 215.3598,
|
| 97 |
+
"eval_samples_per_second": 68.527,
|
| 98 |
+
"eval_steps_per_second": 2.145,
|
| 99 |
+
"step": 2500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.6025641025641026,
|
| 103 |
+
"grad_norm": 0.04741215705871582,
|
| 104 |
+
"learning_rate": 4.885531135531136e-05,
|
| 105 |
+
"loss": 0.003,
|
| 106 |
+
"step": 3000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.6025641025641026,
|
| 110 |
+
"eval_f1": 0.9602090789225843,
|
| 111 |
+
"eval_loss": 0.002707522828131914,
|
| 112 |
+
"eval_precision": 0.9593056078283778,
|
| 113 |
+
"eval_recall": 0.9611142533936652,
|
| 114 |
+
"eval_runtime": 215.7177,
|
| 115 |
+
"eval_samples_per_second": 68.413,
|
| 116 |
+
"eval_steps_per_second": 2.142,
|
| 117 |
+
"step": 3000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.8696581196581197,
|
| 121 |
+
"grad_norm": 0.022911719977855682,
|
| 122 |
+
"learning_rate": 4.8664529914529914e-05,
|
| 123 |
+
"loss": 0.0024,
|
| 124 |
+
"step": 3500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.8696581196581197,
|
| 128 |
+
"eval_f1": 0.9571561338289963,
|
| 129 |
+
"eval_loss": 0.0023886554408818483,
|
| 130 |
+
"eval_precision": 0.9438233137829912,
|
| 131 |
+
"eval_recall": 0.9708710407239819,
|
| 132 |
+
"eval_runtime": 205.5029,
|
| 133 |
+
"eval_samples_per_second": 71.814,
|
| 134 |
+
"eval_steps_per_second": 2.248,
|
| 135 |
+
"step": 3500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.1367521367521367,
|
| 139 |
+
"grad_norm": 0.05229872837662697,
|
| 140 |
+
"learning_rate": 4.8473748473748476e-05,
|
| 141 |
+
"loss": 0.0018,
|
| 142 |
+
"step": 4000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.1367521367521367,
|
| 146 |
+
"eval_f1": 0.9639815719670529,
|
| 147 |
+
"eval_loss": 0.0022004263009876013,
|
| 148 |
+
"eval_precision": 0.9518886131789358,
|
| 149 |
+
"eval_recall": 0.9763857466063348,
|
| 150 |
+
"eval_runtime": 217.5053,
|
| 151 |
+
"eval_samples_per_second": 67.851,
|
| 152 |
+
"eval_steps_per_second": 2.124,
|
| 153 |
+
"step": 4000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.4038461538461537,
|
| 157 |
+
"grad_norm": 0.04928997904062271,
|
| 158 |
+
"learning_rate": 4.828296703296704e-05,
|
| 159 |
+
"loss": 0.0013,
|
| 160 |
+
"step": 4500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.4038461538461537,
|
| 164 |
+
"eval_f1": 0.9693363629974934,
|
| 165 |
+
"eval_loss": 0.0017703943885862827,
|
| 166 |
+
"eval_precision": 0.9635356028500908,
|
| 167 |
+
"eval_recall": 0.9752073906485671,
|
| 168 |
+
"eval_runtime": 205.3479,
|
| 169 |
+
"eval_samples_per_second": 71.868,
|
| 170 |
+
"eval_steps_per_second": 2.25,
|
| 171 |
+
"step": 4500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.6709401709401708,
|
| 175 |
+
"grad_norm": 0.03343936800956726,
|
| 176 |
+
"learning_rate": 4.8092185592185595e-05,
|
| 177 |
+
"loss": 0.0014,
|
| 178 |
+
"step": 5000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.6709401709401708,
|
| 182 |
+
"eval_f1": 0.9706270005648653,
|
| 183 |
+
"eval_loss": 0.001739403698593378,
|
| 184 |
+
"eval_precision": 0.9693493794659647,
|
| 185 |
+
"eval_recall": 0.9719079939668175,
|
| 186 |
+
"eval_runtime": 204.7418,
|
| 187 |
+
"eval_samples_per_second": 72.081,
|
| 188 |
+
"eval_steps_per_second": 2.257,
|
| 189 |
+
"step": 5000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.9380341880341883,
|
| 193 |
+
"grad_norm": 0.07879549264907837,
|
| 194 |
+
"learning_rate": 4.790140415140416e-05,
|
| 195 |
+
"loss": 0.0013,
|
| 196 |
+
"step": 5500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.9380341880341883,
|
| 200 |
+
"eval_f1": 0.9702524596250233,
|
| 201 |
+
"eval_loss": 0.0016117716440930963,
|
| 202 |
+
"eval_precision": 0.9555301645338209,
|
| 203 |
+
"eval_recall": 0.985435520361991,
|
| 204 |
+
"eval_runtime": 216.8331,
|
| 205 |
+
"eval_samples_per_second": 68.062,
|
| 206 |
+
"eval_steps_per_second": 2.131,
|
| 207 |
+
"step": 5500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.2051282051282053,
|
| 211 |
+
"grad_norm": 0.14366598427295685,
|
| 212 |
+
"learning_rate": 4.771062271062271e-05,
|
| 213 |
+
"loss": 0.0008,
|
| 214 |
+
"step": 6000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.2051282051282053,
|
| 218 |
+
"eval_f1": 0.977527028941032,
|
| 219 |
+
"eval_loss": 0.001418485539034009,
|
| 220 |
+
"eval_precision": 0.9791449919606545,
|
| 221 |
+
"eval_recall": 0.9759144042232277,
|
| 222 |
+
"eval_runtime": 217.6653,
|
| 223 |
+
"eval_samples_per_second": 67.801,
|
| 224 |
+
"eval_steps_per_second": 2.123,
|
| 225 |
+
"step": 6000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.4722222222222223,
|
| 229 |
+
"grad_norm": 0.01724930852651596,
|
| 230 |
+
"learning_rate": 4.751984126984127e-05,
|
| 231 |
+
"loss": 0.0009,
|
| 232 |
+
"step": 6500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.4722222222222223,
|
| 236 |
+
"eval_f1": 0.9748389220712035,
|
| 237 |
+
"eval_loss": 0.0014127923641353846,
|
| 238 |
+
"eval_precision": 0.9726888784608165,
|
| 239 |
+
"eval_recall": 0.976998491704374,
|
| 240 |
+
"eval_runtime": 120.5351,
|
| 241 |
+
"eval_samples_per_second": 122.437,
|
| 242 |
+
"eval_steps_per_second": 3.833,
|
| 243 |
+
"step": 6500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.7393162393162394,
|
| 247 |
+
"grad_norm": 0.0373033843934536,
|
| 248 |
+
"learning_rate": 4.732905982905983e-05,
|
| 249 |
+
"loss": 0.0008,
|
| 250 |
+
"step": 7000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.7393162393162394,
|
| 254 |
+
"eval_f1": 0.9767944381811348,
|
| 255 |
+
"eval_loss": 0.001502642291598022,
|
| 256 |
+
"eval_precision": 0.973501872659176,
|
| 257 |
+
"eval_recall": 0.9801093514328808,
|
| 258 |
+
"eval_runtime": 119.8163,
|
| 259 |
+
"eval_samples_per_second": 123.172,
|
| 260 |
+
"eval_steps_per_second": 3.856,
|
| 261 |
+
"step": 7000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.006410256410256,
|
| 265 |
+
"grad_norm": 0.004327626433223486,
|
| 266 |
+
"learning_rate": 4.713827838827839e-05,
|
| 267 |
+
"loss": 0.0007,
|
| 268 |
+
"step": 7500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 4.006410256410256,
|
| 272 |
+
"eval_f1": 0.9779735682819383,
|
| 273 |
+
"eval_loss": 0.001390722580254078,
|
| 274 |
+
"eval_precision": 0.9724137931034482,
|
| 275 |
+
"eval_recall": 0.9835972850678733,
|
| 276 |
+
"eval_runtime": 119.5661,
|
| 277 |
+
"eval_samples_per_second": 123.43,
|
| 278 |
+
"eval_steps_per_second": 3.864,
|
| 279 |
+
"step": 7500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.273504273504273,
|
| 283 |
+
"grad_norm": 0.0008369502611458302,
|
| 284 |
+
"learning_rate": 4.694749694749695e-05,
|
| 285 |
+
"loss": 0.0006,
|
| 286 |
+
"step": 8000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.273504273504273,
|
| 290 |
+
"eval_f1": 0.9788639365918097,
|
| 291 |
+
"eval_loss": 0.0014948239549994469,
|
| 292 |
+
"eval_precision": 0.9797884397431054,
|
| 293 |
+
"eval_recall": 0.9779411764705882,
|
| 294 |
+
"eval_runtime": 121.1034,
|
| 295 |
+
"eval_samples_per_second": 121.863,
|
| 296 |
+
"eval_steps_per_second": 3.815,
|
| 297 |
+
"step": 8000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.5405982905982905,
|
| 301 |
+
"grad_norm": 0.034645263105630875,
|
| 302 |
+
"learning_rate": 4.675671550671551e-05,
|
| 303 |
+
"loss": 0.0005,
|
| 304 |
+
"step": 8500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.5405982905982905,
|
| 308 |
+
"eval_f1": 0.9742678851052889,
|
| 309 |
+
"eval_loss": 0.0017295886063948274,
|
| 310 |
+
"eval_precision": 0.9662509851189096,
|
| 311 |
+
"eval_recall": 0.9824189291101055,
|
| 312 |
+
"eval_runtime": 214.7422,
|
| 313 |
+
"eval_samples_per_second": 68.724,
|
| 314 |
+
"eval_steps_per_second": 2.151,
|
| 315 |
+
"step": 8500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.8076923076923075,
|
| 319 |
+
"grad_norm": 0.010439756326377392,
|
| 320 |
+
"learning_rate": 4.656593406593407e-05,
|
| 321 |
+
"loss": 0.0006,
|
| 322 |
+
"step": 9000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.8076923076923075,
|
| 326 |
+
"eval_f1": 0.9778079816277271,
|
| 327 |
+
"eval_loss": 0.0013649952597916126,
|
| 328 |
+
"eval_precision": 0.9723167264762083,
|
| 329 |
+
"eval_recall": 0.9833616138763197,
|
| 330 |
+
"eval_runtime": 215.7325,
|
| 331 |
+
"eval_samples_per_second": 68.409,
|
| 332 |
+
"eval_steps_per_second": 2.142,
|
| 333 |
+
"step": 9000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 5.0747863247863245,
|
| 337 |
+
"grad_norm": 0.022446786984801292,
|
| 338 |
+
"learning_rate": 4.637515262515263e-05,
|
| 339 |
+
"loss": 0.0005,
|
| 340 |
+
"step": 9500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 5.0747863247863245,
|
| 344 |
+
"eval_f1": 0.9819268602626252,
|
| 345 |
+
"eval_loss": 0.0013456182787194848,
|
| 346 |
+
"eval_precision": 0.9804962872450418,
|
| 347 |
+
"eval_recall": 0.9833616138763197,
|
| 348 |
+
"eval_runtime": 145.9782,
|
| 349 |
+
"eval_samples_per_second": 101.097,
|
| 350 |
+
"eval_steps_per_second": 3.165,
|
| 351 |
+
"step": 9500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.3418803418803416,
|
| 355 |
+
"grad_norm": 0.0010687178000807762,
|
| 356 |
+
"learning_rate": 4.618437118437119e-05,
|
| 357 |
+
"loss": 0.0004,
|
| 358 |
+
"step": 10000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.3418803418803416,
|
| 362 |
+
"eval_f1": 0.9747765825886088,
|
| 363 |
+
"eval_loss": 0.0019718140829354525,
|
| 364 |
+
"eval_precision": 0.9652049350769373,
|
| 365 |
+
"eval_recall": 0.9845399698340875,
|
| 366 |
+
"eval_runtime": 218.776,
|
| 367 |
+
"eval_samples_per_second": 67.457,
|
| 368 |
+
"eval_steps_per_second": 2.112,
|
| 369 |
+
"step": 10000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.608974358974359,
|
| 373 |
+
"grad_norm": 0.010968877002596855,
|
| 374 |
+
"learning_rate": 4.599358974358974e-05,
|
| 375 |
+
"loss": 0.0005,
|
| 376 |
+
"step": 10500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 5.608974358974359,
|
| 380 |
+
"eval_f1": 0.9817333301906805,
|
| 381 |
+
"eval_loss": 0.0013046471867710352,
|
| 382 |
+
"eval_precision": 0.9818490405921456,
|
| 383 |
+
"eval_recall": 0.9816176470588235,
|
| 384 |
+
"eval_runtime": 205.7951,
|
| 385 |
+
"eval_samples_per_second": 71.712,
|
| 386 |
+
"eval_steps_per_second": 2.245,
|
| 387 |
+
"step": 10500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.8760683760683765,
|
| 391 |
+
"grad_norm": 0.0015924246981739998,
|
| 392 |
+
"learning_rate": 4.5802808302808305e-05,
|
| 393 |
+
"loss": 0.0004,
|
| 394 |
+
"step": 11000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.8760683760683765,
|
| 398 |
+
"eval_f1": 0.9823409981585532,
|
| 399 |
+
"eval_loss": 0.0014677270082756877,
|
| 400 |
+
"eval_precision": 0.9840601646012677,
|
| 401 |
+
"eval_recall": 0.9806278280542986,
|
| 402 |
+
"eval_runtime": 203.592,
|
| 403 |
+
"eval_samples_per_second": 72.488,
|
| 404 |
+
"eval_steps_per_second": 2.269,
|
| 405 |
+
"step": 11000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 6.1431623931623935,
|
| 409 |
+
"grad_norm": 0.004735188093036413,
|
| 410 |
+
"learning_rate": 4.561202686202686e-05,
|
| 411 |
+
"loss": 0.0004,
|
| 412 |
+
"step": 11500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 6.1431623931623935,
|
| 416 |
+
"eval_f1": 0.9827679432023886,
|
| 417 |
+
"eval_loss": 0.0012729066656902432,
|
| 418 |
+
"eval_precision": 0.9803480136954177,
|
| 419 |
+
"eval_recall": 0.9851998491704375,
|
| 420 |
+
"eval_runtime": 119.9744,
|
| 421 |
+
"eval_samples_per_second": 123.01,
|
| 422 |
+
"eval_steps_per_second": 3.851,
|
| 423 |
+
"step": 11500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 6.410256410256411,
|
| 427 |
+
"grad_norm": 0.008303467184305191,
|
| 428 |
+
"learning_rate": 4.5421245421245424e-05,
|
| 429 |
+
"loss": 0.0003,
|
| 430 |
+
"step": 12000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 6.410256410256411,
|
| 434 |
+
"eval_f1": 0.9750854909623841,
|
| 435 |
+
"eval_loss": 0.0016973286401480436,
|
| 436 |
+
"eval_precision": 0.9626567452115199,
|
| 437 |
+
"eval_recall": 0.9878393665158371,
|
| 438 |
+
"eval_runtime": 219.3026,
|
| 439 |
+
"eval_samples_per_second": 67.295,
|
| 440 |
+
"eval_steps_per_second": 2.107,
|
| 441 |
+
"step": 12000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.677350427350428,
|
| 445 |
+
"grad_norm": 0.007308937143534422,
|
| 446 |
+
"learning_rate": 4.5230463980463986e-05,
|
| 447 |
+
"loss": 0.0003,
|
| 448 |
+
"step": 12500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.677350427350428,
|
| 452 |
+
"eval_f1": 0.9813210991994756,
|
| 453 |
+
"eval_loss": 0.0012571236584335566,
|
| 454 |
+
"eval_precision": 0.9747047335627267,
|
| 455 |
+
"eval_recall": 0.98802790346908,
|
| 456 |
+
"eval_runtime": 219.2644,
|
| 457 |
+
"eval_samples_per_second": 67.307,
|
| 458 |
+
"eval_steps_per_second": 2.107,
|
| 459 |
+
"step": 12500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.944444444444445,
|
| 463 |
+
"grad_norm": 0.05341866984963417,
|
| 464 |
+
"learning_rate": 4.503968253968254e-05,
|
| 465 |
+
"loss": 0.0004,
|
| 466 |
+
"step": 13000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 6.944444444444445,
|
| 470 |
+
"eval_f1": 0.9821235357764502,
|
| 471 |
+
"eval_loss": 0.0013370579108595848,
|
| 472 |
+
"eval_precision": 0.9802328857169688,
|
| 473 |
+
"eval_recall": 0.9840214932126696,
|
| 474 |
+
"eval_runtime": 219.0265,
|
| 475 |
+
"eval_samples_per_second": 67.38,
|
| 476 |
+
"eval_steps_per_second": 2.109,
|
| 477 |
+
"step": 13000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 7.211538461538462,
|
| 481 |
+
"grad_norm": 0.0043980698101222515,
|
| 482 |
+
"learning_rate": 4.4848901098901105e-05,
|
| 483 |
+
"loss": 0.0003,
|
| 484 |
+
"step": 13500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 7.211538461538462,
|
| 488 |
+
"eval_f1": 0.9812013269651554,
|
| 489 |
+
"eval_loss": 0.00139136821962893,
|
| 490 |
+
"eval_precision": 0.9795649927185607,
|
| 491 |
+
"eval_recall": 0.9828431372549019,
|
| 492 |
+
"eval_runtime": 205.0799,
|
| 493 |
+
"eval_samples_per_second": 71.962,
|
| 494 |
+
"eval_steps_per_second": 2.253,
|
| 495 |
+
"step": 13500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 7.478632478632479,
|
| 499 |
+
"grad_norm": 0.012946384958922863,
|
| 500 |
+
"learning_rate": 4.465811965811966e-05,
|
| 501 |
+
"loss": 0.0003,
|
| 502 |
+
"step": 14000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 7.478632478632479,
|
| 506 |
+
"eval_f1": 0.9811170275151885,
|
| 507 |
+
"eval_loss": 0.0012917759595438838,
|
| 508 |
+
"eval_precision": 0.9765584870417932,
|
| 509 |
+
"eval_recall": 0.9857183257918553,
|
| 510 |
+
"eval_runtime": 205.9645,
|
| 511 |
+
"eval_samples_per_second": 71.653,
|
| 512 |
+
"eval_steps_per_second": 2.243,
|
| 513 |
+
"step": 14000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.745726495726496,
|
| 517 |
+
"grad_norm": 0.0030930449720472097,
|
| 518 |
+
"learning_rate": 4.4467338217338216e-05,
|
| 519 |
+
"loss": 0.0003,
|
| 520 |
+
"step": 14500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.745726495726496,
|
| 524 |
+
"eval_f1": 0.9808375067597752,
|
| 525 |
+
"eval_loss": 0.0013525269459933043,
|
| 526 |
+
"eval_precision": 0.9785596997419658,
|
| 527 |
+
"eval_recall": 0.9831259426847662,
|
| 528 |
+
"eval_runtime": 122.7721,
|
| 529 |
+
"eval_samples_per_second": 120.206,
|
| 530 |
+
"eval_steps_per_second": 3.763,
|
| 531 |
+
"step": 14500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 8.012820512820513,
|
| 535 |
+
"grad_norm": 0.00297636934556067,
|
| 536 |
+
"learning_rate": 4.427655677655678e-05,
|
| 537 |
+
"loss": 0.0002,
|
| 538 |
+
"step": 15000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 8.012820512820513,
|
| 542 |
+
"eval_f1": 0.9820384687912502,
|
| 543 |
+
"eval_loss": 0.0015595377190038562,
|
| 544 |
+
"eval_precision": 0.9822236891738967,
|
| 545 |
+
"eval_recall": 0.981853318250377,
|
| 546 |
+
"eval_runtime": 208.3474,
|
| 547 |
+
"eval_samples_per_second": 70.834,
|
| 548 |
+
"eval_steps_per_second": 2.217,
|
| 549 |
+
"step": 15000
|
| 550 |
+
}
|
| 551 |
+
],
|
| 552 |
+
"logging_steps": 500,
|
| 553 |
+
"max_steps": 131040,
|
| 554 |
+
"num_input_tokens_seen": 0,
|
| 555 |
+
"num_train_epochs": 70,
|
| 556 |
+
"save_steps": 100,
|
| 557 |
+
"stateful_callbacks": {
|
| 558 |
+
"TrainerControl": {
|
| 559 |
+
"args": {
|
| 560 |
+
"should_epoch_stop": false,
|
| 561 |
+
"should_evaluate": false,
|
| 562 |
+
"should_log": false,
|
| 563 |
+
"should_save": true,
|
| 564 |
+
"should_training_stop": false
|
| 565 |
+
},
|
| 566 |
+
"attributes": {}
|
| 567 |
+
}
|
| 568 |
+
},
|
| 569 |
+
"total_flos": 1.2536694351387706e+17,
|
| 570 |
+
"train_batch_size": 32,
|
| 571 |
+
"trial_name": null,
|
| 572 |
+
"trial_params": null
|
| 573 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a8c58f72524065143ac20fabf03255178e489fc0486c1568faf3b263e9ae66d
|
| 3 |
+
size 5240
|