Training in progress, step 2500
Browse files- model.safetensors +1 -1
- run-3/checkpoint-2500/config.json +48 -0
- run-3/checkpoint-2500/model.safetensors +3 -0
- run-3/checkpoint-2500/optimizer.pt +3 -0
- run-3/checkpoint-2500/rng_state.pth +3 -0
- run-3/checkpoint-2500/scheduler.pt +3 -0
- run-3/checkpoint-2500/special_tokens_map.json +51 -0
- run-3/checkpoint-2500/tokenizer.json +0 -0
- run-3/checkpoint-2500/tokenizer_config.json +59 -0
- run-3/checkpoint-2500/trainer_state.json +776 -0
- run-3/checkpoint-2500/training_args.bin +3 -0
- run-3/checkpoint-2500/vocab.txt +0 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442518124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351a240d5b4317e9574dc531860ae48c255f31e37a6716890e282251f8722a2a
|
| 3 |
size 442518124
|
run-3/checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"max_position_embeddings": 514,
|
| 36 |
+
"model_type": "roberta",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"tokenizer_class": "BertTokenizer",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.37.0",
|
| 45 |
+
"type_vocab_size": 1,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 32000
|
| 48 |
+
}
|
run-3/checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351a240d5b4317e9574dc531860ae48c255f31e37a6716890e282251f8722a2a
|
| 3 |
+
size 442518124
|
run-3/checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5411f48963a9c274e6713eb8c6c327d166add2302fbbd42ad2163e750bf7911
|
| 3 |
+
size 885156090
|
run-3/checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9599c3daf58ffa5ad5e8781b41011279c2f4a579fc06d2098950467209f8af9
|
| 3 |
+
size 14244
|
run-3/checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20e349b84f68f4c780ed0c0f1247324c3c9cd49e891d79f62463fd3da49151d8
|
| 3 |
+
size 1064
|
run-3/checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
run-3/checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-3/checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 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": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 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 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
run-3/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,776 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8421845881825929,
|
| 3 |
+
"best_model_checkpoint": "test-klue/ynat/run-3/checkpoint-2500",
|
| 4 |
+
"epoch": 4.378283712784588,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"learning_rate": 3.851823303957499e-06,
|
| 14 |
+
"loss": 1.934,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"eval_f1": 0.01705140497086806,
|
| 20 |
+
"eval_loss": 2.002474546432495,
|
| 21 |
+
"eval_runtime": 12.8723,
|
| 22 |
+
"eval_samples_per_second": 707.486,
|
| 23 |
+
"eval_steps_per_second": 1.398,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18,
|
| 28 |
+
"learning_rate": 3.783163352015298e-06,
|
| 29 |
+
"loss": 1.9174,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18,
|
| 34 |
+
"eval_f1": 0.16773144497786774,
|
| 35 |
+
"eval_loss": 1.9946870803833008,
|
| 36 |
+
"eval_runtime": 13.4529,
|
| 37 |
+
"eval_samples_per_second": 676.953,
|
| 38 |
+
"eval_steps_per_second": 1.338,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 3.7145034000730966e-06,
|
| 44 |
+
"loss": 1.6984,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"eval_f1": 0.579749057690188,
|
| 50 |
+
"eval_loss": 1.6373496055603027,
|
| 51 |
+
"eval_runtime": 13.0114,
|
| 52 |
+
"eval_samples_per_second": 699.924,
|
| 53 |
+
"eval_steps_per_second": 1.383,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.35,
|
| 58 |
+
"learning_rate": 3.645843448130895e-06,
|
| 59 |
+
"loss": 1.2585,
|
| 60 |
+
"step": 200
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.35,
|
| 64 |
+
"eval_f1": 0.6734776928120875,
|
| 65 |
+
"eval_loss": 1.2733124494552612,
|
| 66 |
+
"eval_runtime": 12.6224,
|
| 67 |
+
"eval_samples_per_second": 721.493,
|
| 68 |
+
"eval_steps_per_second": 1.426,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.44,
|
| 73 |
+
"learning_rate": 3.5771834961886936e-06,
|
| 74 |
+
"loss": 0.9487,
|
| 75 |
+
"step": 250
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.44,
|
| 79 |
+
"eval_f1": 0.6814953813845488,
|
| 80 |
+
"eval_loss": 1.1104496717453003,
|
| 81 |
+
"eval_runtime": 12.492,
|
| 82 |
+
"eval_samples_per_second": 729.025,
|
| 83 |
+
"eval_steps_per_second": 1.441,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.53,
|
| 88 |
+
"learning_rate": 3.5085235442464923e-06,
|
| 89 |
+
"loss": 0.8072,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.53,
|
| 94 |
+
"eval_f1": 0.6717305786202503,
|
| 95 |
+
"eval_loss": 1.0609983205795288,
|
| 96 |
+
"eval_runtime": 12.6873,
|
| 97 |
+
"eval_samples_per_second": 717.806,
|
| 98 |
+
"eval_steps_per_second": 1.419,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.61,
|
| 103 |
+
"learning_rate": 3.439863592304291e-06,
|
| 104 |
+
"loss": 0.7549,
|
| 105 |
+
"step": 350
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.61,
|
| 109 |
+
"eval_f1": 0.7228793656517608,
|
| 110 |
+
"eval_loss": 0.9494264721870422,
|
| 111 |
+
"eval_runtime": 12.8373,
|
| 112 |
+
"eval_samples_per_second": 709.416,
|
| 113 |
+
"eval_steps_per_second": 1.402,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7,
|
| 118 |
+
"learning_rate": 3.3712036403620893e-06,
|
| 119 |
+
"loss": 0.6644,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7,
|
| 124 |
+
"eval_f1": 0.7719549711033966,
|
| 125 |
+
"eval_loss": 0.8139678239822388,
|
| 126 |
+
"eval_runtime": 12.9124,
|
| 127 |
+
"eval_samples_per_second": 705.29,
|
| 128 |
+
"eval_steps_per_second": 1.394,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.79,
|
| 133 |
+
"learning_rate": 3.302543688419888e-06,
|
| 134 |
+
"loss": 0.6306,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.79,
|
| 139 |
+
"eval_f1": 0.7738311952589042,
|
| 140 |
+
"eval_loss": 0.7844408750534058,
|
| 141 |
+
"eval_runtime": 12.8236,
|
| 142 |
+
"eval_samples_per_second": 710.174,
|
| 143 |
+
"eval_steps_per_second": 1.404,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.88,
|
| 148 |
+
"learning_rate": 3.2338837364776867e-06,
|
| 149 |
+
"loss": 0.6093,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.88,
|
| 154 |
+
"eval_f1": 0.7850534531405503,
|
| 155 |
+
"eval_loss": 0.7450836300849915,
|
| 156 |
+
"eval_runtime": 12.7168,
|
| 157 |
+
"eval_samples_per_second": 716.14,
|
| 158 |
+
"eval_steps_per_second": 1.415,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.96,
|
| 163 |
+
"learning_rate": 3.1652237845354854e-06,
|
| 164 |
+
"loss": 0.599,
|
| 165 |
+
"step": 550
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.96,
|
| 169 |
+
"eval_f1": 0.7932118091019561,
|
| 170 |
+
"eval_loss": 0.7213732004165649,
|
| 171 |
+
"eval_runtime": 12.9294,
|
| 172 |
+
"eval_samples_per_second": 704.366,
|
| 173 |
+
"eval_steps_per_second": 1.392,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.05,
|
| 178 |
+
"learning_rate": 3.0965638325932837e-06,
|
| 179 |
+
"loss": 0.5234,
|
| 180 |
+
"step": 600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.05,
|
| 184 |
+
"eval_f1": 0.8216123467232329,
|
| 185 |
+
"eval_loss": 0.6262369751930237,
|
| 186 |
+
"eval_runtime": 13.578,
|
| 187 |
+
"eval_samples_per_second": 670.72,
|
| 188 |
+
"eval_steps_per_second": 1.326,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.14,
|
| 193 |
+
"learning_rate": 3.0279038806510824e-06,
|
| 194 |
+
"loss": 0.4465,
|
| 195 |
+
"step": 650
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.14,
|
| 199 |
+
"eval_f1": 0.7867065499958213,
|
| 200 |
+
"eval_loss": 0.7198110818862915,
|
| 201 |
+
"eval_runtime": 13.2261,
|
| 202 |
+
"eval_samples_per_second": 688.561,
|
| 203 |
+
"eval_steps_per_second": 1.361,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.23,
|
| 208 |
+
"learning_rate": 2.959243928708881e-06,
|
| 209 |
+
"loss": 0.4521,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.23,
|
| 214 |
+
"eval_f1": 0.8063113996725187,
|
| 215 |
+
"eval_loss": 0.6468276381492615,
|
| 216 |
+
"eval_runtime": 12.8551,
|
| 217 |
+
"eval_samples_per_second": 708.435,
|
| 218 |
+
"eval_steps_per_second": 1.4,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.31,
|
| 223 |
+
"learning_rate": 2.89058397676668e-06,
|
| 224 |
+
"loss": 0.4339,
|
| 225 |
+
"step": 750
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.31,
|
| 229 |
+
"eval_f1": 0.8166775515876931,
|
| 230 |
+
"eval_loss": 0.6203234195709229,
|
| 231 |
+
"eval_runtime": 12.669,
|
| 232 |
+
"eval_samples_per_second": 718.842,
|
| 233 |
+
"eval_steps_per_second": 1.421,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.4,
|
| 238 |
+
"learning_rate": 2.821924024824478e-06,
|
| 239 |
+
"loss": 0.4757,
|
| 240 |
+
"step": 800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.4,
|
| 244 |
+
"eval_f1": 0.8161608316711845,
|
| 245 |
+
"eval_loss": 0.6249090433120728,
|
| 246 |
+
"eval_runtime": 12.9976,
|
| 247 |
+
"eval_samples_per_second": 700.668,
|
| 248 |
+
"eval_steps_per_second": 1.385,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.49,
|
| 253 |
+
"learning_rate": 2.753264072882277e-06,
|
| 254 |
+
"loss": 0.4594,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.49,
|
| 259 |
+
"eval_f1": 0.8290833266193817,
|
| 260 |
+
"eval_loss": 0.5703582167625427,
|
| 261 |
+
"eval_runtime": 12.8799,
|
| 262 |
+
"eval_samples_per_second": 707.072,
|
| 263 |
+
"eval_steps_per_second": 1.398,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.58,
|
| 268 |
+
"learning_rate": 2.6846041209400755e-06,
|
| 269 |
+
"loss": 0.4032,
|
| 270 |
+
"step": 900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.58,
|
| 274 |
+
"eval_f1": 0.8215012797906703,
|
| 275 |
+
"eval_loss": 0.5891036987304688,
|
| 276 |
+
"eval_runtime": 12.8777,
|
| 277 |
+
"eval_samples_per_second": 707.193,
|
| 278 |
+
"eval_steps_per_second": 1.398,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.66,
|
| 283 |
+
"learning_rate": 2.615944168997874e-06,
|
| 284 |
+
"loss": 0.4204,
|
| 285 |
+
"step": 950
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.66,
|
| 289 |
+
"eval_f1": 0.8327085312817779,
|
| 290 |
+
"eval_loss": 0.5532290935516357,
|
| 291 |
+
"eval_runtime": 12.7986,
|
| 292 |
+
"eval_samples_per_second": 711.563,
|
| 293 |
+
"eval_steps_per_second": 1.406,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.75,
|
| 298 |
+
"learning_rate": 2.5472842170556725e-06,
|
| 299 |
+
"loss": 0.4386,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.75,
|
| 304 |
+
"eval_f1": 0.8286389311967884,
|
| 305 |
+
"eval_loss": 0.5586702227592468,
|
| 306 |
+
"eval_runtime": 12.7254,
|
| 307 |
+
"eval_samples_per_second": 715.653,
|
| 308 |
+
"eval_steps_per_second": 1.414,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.84,
|
| 313 |
+
"learning_rate": 2.478624265113471e-06,
|
| 314 |
+
"loss": 0.4258,
|
| 315 |
+
"step": 1050
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.84,
|
| 319 |
+
"eval_f1": 0.8194650098039734,
|
| 320 |
+
"eval_loss": 0.5945160388946533,
|
| 321 |
+
"eval_runtime": 12.8508,
|
| 322 |
+
"eval_samples_per_second": 708.674,
|
| 323 |
+
"eval_steps_per_second": 1.401,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.93,
|
| 328 |
+
"learning_rate": 2.4099643131712695e-06,
|
| 329 |
+
"loss": 0.4544,
|
| 330 |
+
"step": 1100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.93,
|
| 334 |
+
"eval_f1": 0.8274559023611527,
|
| 335 |
+
"eval_loss": 0.5760587453842163,
|
| 336 |
+
"eval_runtime": 13.4335,
|
| 337 |
+
"eval_samples_per_second": 677.933,
|
| 338 |
+
"eval_steps_per_second": 1.34,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.01,
|
| 343 |
+
"learning_rate": 2.341304361229068e-06,
|
| 344 |
+
"loss": 0.418,
|
| 345 |
+
"step": 1150
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.01,
|
| 349 |
+
"eval_f1": 0.8304623515332191,
|
| 350 |
+
"eval_loss": 0.5600340962409973,
|
| 351 |
+
"eval_runtime": 13.2414,
|
| 352 |
+
"eval_samples_per_second": 687.766,
|
| 353 |
+
"eval_steps_per_second": 1.359,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.1,
|
| 358 |
+
"learning_rate": 2.2726444092868665e-06,
|
| 359 |
+
"loss": 0.3918,
|
| 360 |
+
"step": 1200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.1,
|
| 364 |
+
"eval_f1": 0.8230072950822092,
|
| 365 |
+
"eval_loss": 0.5960156321525574,
|
| 366 |
+
"eval_runtime": 12.9264,
|
| 367 |
+
"eval_samples_per_second": 704.529,
|
| 368 |
+
"eval_steps_per_second": 1.393,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.19,
|
| 373 |
+
"learning_rate": 2.203984457344665e-06,
|
| 374 |
+
"loss": 0.4001,
|
| 375 |
+
"step": 1250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.19,
|
| 379 |
+
"eval_f1": 0.8370136201480073,
|
| 380 |
+
"eval_loss": 0.5412853360176086,
|
| 381 |
+
"eval_runtime": 12.8464,
|
| 382 |
+
"eval_samples_per_second": 708.917,
|
| 383 |
+
"eval_steps_per_second": 1.401,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.28,
|
| 388 |
+
"learning_rate": 2.135324505402464e-06,
|
| 389 |
+
"loss": 0.3369,
|
| 390 |
+
"step": 1300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.28,
|
| 394 |
+
"eval_f1": 0.8144549401231569,
|
| 395 |
+
"eval_loss": 0.6154327392578125,
|
| 396 |
+
"eval_runtime": 12.8518,
|
| 397 |
+
"eval_samples_per_second": 708.616,
|
| 398 |
+
"eval_steps_per_second": 1.401,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.36,
|
| 403 |
+
"learning_rate": 2.0666645534602626e-06,
|
| 404 |
+
"loss": 0.3639,
|
| 405 |
+
"step": 1350
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.36,
|
| 409 |
+
"eval_f1": 0.8218463781690494,
|
| 410 |
+
"eval_loss": 0.6043773889541626,
|
| 411 |
+
"eval_runtime": 12.8354,
|
| 412 |
+
"eval_samples_per_second": 709.522,
|
| 413 |
+
"eval_steps_per_second": 1.402,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.45,
|
| 418 |
+
"learning_rate": 1.998004601518061e-06,
|
| 419 |
+
"loss": 0.305,
|
| 420 |
+
"step": 1400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.45,
|
| 424 |
+
"eval_f1": 0.8330006702059005,
|
| 425 |
+
"eval_loss": 0.5544472336769104,
|
| 426 |
+
"eval_runtime": 12.869,
|
| 427 |
+
"eval_samples_per_second": 707.672,
|
| 428 |
+
"eval_steps_per_second": 1.399,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.54,
|
| 433 |
+
"learning_rate": 1.9293446495758596e-06,
|
| 434 |
+
"loss": 0.4444,
|
| 435 |
+
"step": 1450
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.54,
|
| 439 |
+
"eval_f1": 0.8346019595913722,
|
| 440 |
+
"eval_loss": 0.559039294719696,
|
| 441 |
+
"eval_runtime": 12.8371,
|
| 442 |
+
"eval_samples_per_second": 709.431,
|
| 443 |
+
"eval_steps_per_second": 1.402,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.63,
|
| 448 |
+
"learning_rate": 1.8606846976336585e-06,
|
| 449 |
+
"loss": 0.3428,
|
| 450 |
+
"step": 1500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.63,
|
| 454 |
+
"eval_f1": 0.8346071667451987,
|
| 455 |
+
"eval_loss": 0.5472803115844727,
|
| 456 |
+
"eval_runtime": 12.6738,
|
| 457 |
+
"eval_samples_per_second": 718.567,
|
| 458 |
+
"eval_steps_per_second": 1.42,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.71,
|
| 463 |
+
"learning_rate": 1.792024745691457e-06,
|
| 464 |
+
"loss": 0.473,
|
| 465 |
+
"step": 1550
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.71,
|
| 469 |
+
"eval_f1": 0.8339861521101763,
|
| 470 |
+
"eval_loss": 0.5484662055969238,
|
| 471 |
+
"eval_runtime": 12.9188,
|
| 472 |
+
"eval_samples_per_second": 704.942,
|
| 473 |
+
"eval_steps_per_second": 1.393,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.8,
|
| 478 |
+
"learning_rate": 1.7233647937492555e-06,
|
| 479 |
+
"loss": 0.3423,
|
| 480 |
+
"step": 1600
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.8,
|
| 484 |
+
"eval_f1": 0.834766650650793,
|
| 485 |
+
"eval_loss": 0.5558911561965942,
|
| 486 |
+
"eval_runtime": 13.6223,
|
| 487 |
+
"eval_samples_per_second": 668.535,
|
| 488 |
+
"eval_steps_per_second": 1.321,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.89,
|
| 493 |
+
"learning_rate": 1.654704841807054e-06,
|
| 494 |
+
"loss": 0.3275,
|
| 495 |
+
"step": 1650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.89,
|
| 499 |
+
"eval_f1": 0.8462797776414777,
|
| 500 |
+
"eval_loss": 0.5118501782417297,
|
| 501 |
+
"eval_runtime": 13.6479,
|
| 502 |
+
"eval_samples_per_second": 667.283,
|
| 503 |
+
"eval_steps_per_second": 1.319,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.98,
|
| 508 |
+
"learning_rate": 1.5860448898648526e-06,
|
| 509 |
+
"loss": 0.3701,
|
| 510 |
+
"step": 1700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.98,
|
| 514 |
+
"eval_f1": 0.8425787867333626,
|
| 515 |
+
"eval_loss": 0.5238479375839233,
|
| 516 |
+
"eval_runtime": 12.8261,
|
| 517 |
+
"eval_samples_per_second": 710.034,
|
| 518 |
+
"eval_steps_per_second": 1.403,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.06,
|
| 523 |
+
"learning_rate": 1.5173849379226511e-06,
|
| 524 |
+
"loss": 0.3139,
|
| 525 |
+
"step": 1750
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.06,
|
| 529 |
+
"eval_f1": 0.8416221241169144,
|
| 530 |
+
"eval_loss": 0.5329692959785461,
|
| 531 |
+
"eval_runtime": 12.7867,
|
| 532 |
+
"eval_samples_per_second": 712.223,
|
| 533 |
+
"eval_steps_per_second": 1.408,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.15,
|
| 538 |
+
"learning_rate": 1.4487249859804498e-06,
|
| 539 |
+
"loss": 0.2975,
|
| 540 |
+
"step": 1800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.15,
|
| 544 |
+
"eval_f1": 0.8343340529328881,
|
| 545 |
+
"eval_loss": 0.5499953627586365,
|
| 546 |
+
"eval_runtime": 12.7893,
|
| 547 |
+
"eval_samples_per_second": 712.078,
|
| 548 |
+
"eval_steps_per_second": 1.407,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.24,
|
| 553 |
+
"learning_rate": 1.3800650340382483e-06,
|
| 554 |
+
"loss": 0.2981,
|
| 555 |
+
"step": 1850
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.24,
|
| 559 |
+
"eval_f1": 0.8350192040740547,
|
| 560 |
+
"eval_loss": 0.5687865018844604,
|
| 561 |
+
"eval_runtime": 12.92,
|
| 562 |
+
"eval_samples_per_second": 704.877,
|
| 563 |
+
"eval_steps_per_second": 1.393,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.33,
|
| 568 |
+
"learning_rate": 1.311405082096047e-06,
|
| 569 |
+
"loss": 0.2378,
|
| 570 |
+
"step": 1900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.33,
|
| 574 |
+
"eval_f1": 0.8413969129271989,
|
| 575 |
+
"eval_loss": 0.5414060354232788,
|
| 576 |
+
"eval_runtime": 12.8936,
|
| 577 |
+
"eval_samples_per_second": 706.32,
|
| 578 |
+
"eval_steps_per_second": 1.396,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.42,
|
| 583 |
+
"learning_rate": 1.2427451301538455e-06,
|
| 584 |
+
"loss": 0.3733,
|
| 585 |
+
"step": 1950
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.42,
|
| 589 |
+
"eval_f1": 0.8405393522238971,
|
| 590 |
+
"eval_loss": 0.5475384593009949,
|
| 591 |
+
"eval_runtime": 12.7243,
|
| 592 |
+
"eval_samples_per_second": 715.714,
|
| 593 |
+
"eval_steps_per_second": 1.415,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.5,
|
| 598 |
+
"learning_rate": 1.1740851782116442e-06,
|
| 599 |
+
"loss": 0.3825,
|
| 600 |
+
"step": 2000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.5,
|
| 604 |
+
"eval_f1": 0.8412270942316189,
|
| 605 |
+
"eval_loss": 0.5363861322402954,
|
| 606 |
+
"eval_runtime": 12.7385,
|
| 607 |
+
"eval_samples_per_second": 714.922,
|
| 608 |
+
"eval_steps_per_second": 1.413,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.59,
|
| 613 |
+
"learning_rate": 1.1054252262694427e-06,
|
| 614 |
+
"loss": 0.354,
|
| 615 |
+
"step": 2050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.59,
|
| 619 |
+
"eval_f1": 0.8435130537584258,
|
| 620 |
+
"eval_loss": 0.5469411015510559,
|
| 621 |
+
"eval_runtime": 13.1572,
|
| 622 |
+
"eval_samples_per_second": 692.17,
|
| 623 |
+
"eval_steps_per_second": 1.368,
|
| 624 |
+
"step": 2050
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.68,
|
| 628 |
+
"learning_rate": 1.0367652743272414e-06,
|
| 629 |
+
"loss": 0.2521,
|
| 630 |
+
"step": 2100
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 3.68,
|
| 634 |
+
"eval_f1": 0.8351566925627497,
|
| 635 |
+
"eval_loss": 0.5897064208984375,
|
| 636 |
+
"eval_runtime": 13.5969,
|
| 637 |
+
"eval_samples_per_second": 669.785,
|
| 638 |
+
"eval_steps_per_second": 1.324,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.77,
|
| 643 |
+
"learning_rate": 9.6810532238504e-07,
|
| 644 |
+
"loss": 0.3446,
|
| 645 |
+
"step": 2150
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.77,
|
| 649 |
+
"eval_f1": 0.8367972150621695,
|
| 650 |
+
"eval_loss": 0.588862955570221,
|
| 651 |
+
"eval_runtime": 13.2396,
|
| 652 |
+
"eval_samples_per_second": 687.863,
|
| 653 |
+
"eval_steps_per_second": 1.36,
|
| 654 |
+
"step": 2150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.85,
|
| 658 |
+
"learning_rate": 8.994453704428385e-07,
|
| 659 |
+
"loss": 0.3163,
|
| 660 |
+
"step": 2200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.85,
|
| 664 |
+
"eval_f1": 0.8391334175384315,
|
| 665 |
+
"eval_loss": 0.5625515580177307,
|
| 666 |
+
"eval_runtime": 12.8463,
|
| 667 |
+
"eval_samples_per_second": 708.921,
|
| 668 |
+
"eval_steps_per_second": 1.401,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.94,
|
| 673 |
+
"learning_rate": 8.307854185006371e-07,
|
| 674 |
+
"loss": 0.2567,
|
| 675 |
+
"step": 2250
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.94,
|
| 679 |
+
"eval_f1": 0.8368910454697663,
|
| 680 |
+
"eval_loss": 0.5832029581069946,
|
| 681 |
+
"eval_runtime": 12.768,
|
| 682 |
+
"eval_samples_per_second": 713.27,
|
| 683 |
+
"eval_steps_per_second": 1.41,
|
| 684 |
+
"step": 2250
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.03,
|
| 688 |
+
"learning_rate": 7.621254665584357e-07,
|
| 689 |
+
"loss": 0.3499,
|
| 690 |
+
"step": 2300
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 4.03,
|
| 694 |
+
"eval_f1": 0.8444657615396232,
|
| 695 |
+
"eval_loss": 0.5441297292709351,
|
| 696 |
+
"eval_runtime": 12.9731,
|
| 697 |
+
"eval_samples_per_second": 701.993,
|
| 698 |
+
"eval_steps_per_second": 1.387,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 4.12,
|
| 703 |
+
"learning_rate": 6.934655146162342e-07,
|
| 704 |
+
"loss": 0.2326,
|
| 705 |
+
"step": 2350
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.12,
|
| 709 |
+
"eval_f1": 0.8450447921852559,
|
| 710 |
+
"eval_loss": 0.55018550157547,
|
| 711 |
+
"eval_runtime": 13.7914,
|
| 712 |
+
"eval_samples_per_second": 660.338,
|
| 713 |
+
"eval_steps_per_second": 1.305,
|
| 714 |
+
"step": 2350
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.2,
|
| 718 |
+
"learning_rate": 6.248055626740328e-07,
|
| 719 |
+
"loss": 0.2876,
|
| 720 |
+
"step": 2400
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 4.2,
|
| 724 |
+
"eval_f1": 0.8431017293241522,
|
| 725 |
+
"eval_loss": 0.5501366257667542,
|
| 726 |
+
"eval_runtime": 13.0119,
|
| 727 |
+
"eval_samples_per_second": 699.898,
|
| 728 |
+
"eval_steps_per_second": 1.383,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.29,
|
| 733 |
+
"learning_rate": 5.561456107318314e-07,
|
| 734 |
+
"loss": 0.2774,
|
| 735 |
+
"step": 2450
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.29,
|
| 739 |
+
"eval_f1": 0.837914574132576,
|
| 740 |
+
"eval_loss": 0.5795889496803284,
|
| 741 |
+
"eval_runtime": 13.1344,
|
| 742 |
+
"eval_samples_per_second": 693.37,
|
| 743 |
+
"eval_steps_per_second": 1.37,
|
| 744 |
+
"step": 2450
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.38,
|
| 748 |
+
"learning_rate": 4.8748565878963e-07,
|
| 749 |
+
"loss": 0.3329,
|
| 750 |
+
"step": 2500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.38,
|
| 754 |
+
"eval_f1": 0.8421845881825929,
|
| 755 |
+
"eval_loss": 0.5610998272895813,
|
| 756 |
+
"eval_runtime": 12.7868,
|
| 757 |
+
"eval_samples_per_second": 712.221,
|
| 758 |
+
"eval_steps_per_second": 1.408,
|
| 759 |
+
"step": 2500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 50,
|
| 763 |
+
"max_steps": 2855,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 5,
|
| 766 |
+
"save_steps": 500,
|
| 767 |
+
"total_flos": 203702323455600.0,
|
| 768 |
+
"train_batch_size": 8,
|
| 769 |
+
"trial_name": null,
|
| 770 |
+
"trial_params": {
|
| 771 |
+
"learning_rate": 3.851823303957499e-06,
|
| 772 |
+
"num_train_epochs": 5,
|
| 773 |
+
"per_device_train_batch_size": 8,
|
| 774 |
+
"seed": 30
|
| 775 |
+
}
|
| 776 |
+
}
|
run-3/checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9a16d730bb2e3e7b3ca811a9c52609a11c500a75019c1d976993f937b24f628
|
| 3 |
+
size 4728
|
run-3/checkpoint-2500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|