Training in progress, step 2000
Browse files- model.safetensors +1 -1
- run-2/checkpoint-2000/config.json +48 -0
- run-2/checkpoint-2000/model.safetensors +3 -0
- run-2/checkpoint-2000/optimizer.pt +3 -0
- run-2/checkpoint-2000/rng_state.pth +3 -0
- run-2/checkpoint-2000/scheduler.pt +3 -0
- run-2/checkpoint-2000/special_tokens_map.json +51 -0
- run-2/checkpoint-2000/tokenizer.json +0 -0
- run-2/checkpoint-2000/tokenizer_config.json +59 -0
- run-2/checkpoint-2000/trainer_state.json +626 -0
- run-2/checkpoint-2000/training_args.bin +3 -0
- run-2/checkpoint-2000/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 sha256:113eba0e6b90e0bb677bbfb986fe78ee95b5c8cce1532311561842da585bec67
|
| 3 |
size 442518124
|
run-2/checkpoint-2000/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-2/checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:113eba0e6b90e0bb677bbfb986fe78ee95b5c8cce1532311561842da585bec67
|
| 3 |
+
size 442518124
|
run-2/checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a93cdfeb3effdb1f9a43592171cf1f9caf173b6b5e4e93bcfd08ae190e796788
|
| 3 |
+
size 885156090
|
run-2/checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939fd5510f65cc3ec5dbc64b6ae59d4b5f524535e6a0ab42fe9fe15128491743
|
| 3 |
+
size 14244
|
run-2/checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faf23bb8ac89c48a2f5b1700cb5896db1f9e5805884a76028d78c32811314841
|
| 3 |
+
size 1064
|
run-2/checkpoint-2000/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-2/checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-2/checkpoint-2000/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-2/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,626 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8493072488776222,
|
| 3 |
+
"best_model_checkpoint": "test-klue/ynat/run-2/checkpoint-2000",
|
| 4 |
+
"epoch": 3.502626970227671,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2000,
|
| 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": 9.520888692829572e-06,
|
| 14 |
+
"loss": 1.9542,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"eval_f1": 0.04583937972534243,
|
| 20 |
+
"eval_loss": 1.94540536403656,
|
| 21 |
+
"eval_runtime": 12.7715,
|
| 22 |
+
"eval_samples_per_second": 713.073,
|
| 23 |
+
"eval_steps_per_second": 1.409,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18,
|
| 28 |
+
"learning_rate": 9.307798077502143e-06,
|
| 29 |
+
"loss": 1.6697,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18,
|
| 34 |
+
"eval_f1": 0.5702339339536844,
|
| 35 |
+
"eval_loss": 1.5132834911346436,
|
| 36 |
+
"eval_runtime": 13.3022,
|
| 37 |
+
"eval_samples_per_second": 684.621,
|
| 38 |
+
"eval_steps_per_second": 1.353,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 9.094707462174712e-06,
|
| 44 |
+
"loss": 0.8971,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"eval_f1": 0.7432151839966054,
|
| 50 |
+
"eval_loss": 0.97530198097229,
|
| 51 |
+
"eval_runtime": 12.9877,
|
| 52 |
+
"eval_samples_per_second": 701.204,
|
| 53 |
+
"eval_steps_per_second": 1.386,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.35,
|
| 58 |
+
"learning_rate": 8.881616846847283e-06,
|
| 59 |
+
"loss": 0.6418,
|
| 60 |
+
"step": 200
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.35,
|
| 64 |
+
"eval_f1": 0.7297934771119111,
|
| 65 |
+
"eval_loss": 0.8931246995925903,
|
| 66 |
+
"eval_runtime": 12.7184,
|
| 67 |
+
"eval_samples_per_second": 716.049,
|
| 68 |
+
"eval_steps_per_second": 1.415,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.44,
|
| 73 |
+
"learning_rate": 8.668526231519852e-06,
|
| 74 |
+
"loss": 0.6438,
|
| 75 |
+
"step": 250
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.44,
|
| 79 |
+
"eval_f1": 0.7761230585561165,
|
| 80 |
+
"eval_loss": 0.7596781849861145,
|
| 81 |
+
"eval_runtime": 12.6711,
|
| 82 |
+
"eval_samples_per_second": 718.722,
|
| 83 |
+
"eval_steps_per_second": 1.421,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.53,
|
| 88 |
+
"learning_rate": 8.455435616192421e-06,
|
| 89 |
+
"loss": 0.5509,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.53,
|
| 94 |
+
"eval_f1": 0.8095769257080263,
|
| 95 |
+
"eval_loss": 0.6825068593025208,
|
| 96 |
+
"eval_runtime": 12.713,
|
| 97 |
+
"eval_samples_per_second": 716.351,
|
| 98 |
+
"eval_steps_per_second": 1.416,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.61,
|
| 103 |
+
"learning_rate": 8.242345000864992e-06,
|
| 104 |
+
"loss": 0.45,
|
| 105 |
+
"step": 350
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.61,
|
| 109 |
+
"eval_f1": 0.820467350641947,
|
| 110 |
+
"eval_loss": 0.6184367537498474,
|
| 111 |
+
"eval_runtime": 12.8329,
|
| 112 |
+
"eval_samples_per_second": 709.662,
|
| 113 |
+
"eval_steps_per_second": 1.403,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7,
|
| 118 |
+
"learning_rate": 8.029254385537563e-06,
|
| 119 |
+
"loss": 0.4877,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7,
|
| 124 |
+
"eval_f1": 0.8192647088110643,
|
| 125 |
+
"eval_loss": 0.5932053327560425,
|
| 126 |
+
"eval_runtime": 12.9021,
|
| 127 |
+
"eval_samples_per_second": 705.857,
|
| 128 |
+
"eval_steps_per_second": 1.395,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.79,
|
| 133 |
+
"learning_rate": 7.816163770210132e-06,
|
| 134 |
+
"loss": 0.5672,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.79,
|
| 139 |
+
"eval_f1": 0.8008517524970246,
|
| 140 |
+
"eval_loss": 0.6429001092910767,
|
| 141 |
+
"eval_runtime": 12.7777,
|
| 142 |
+
"eval_samples_per_second": 712.728,
|
| 143 |
+
"eval_steps_per_second": 1.409,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.88,
|
| 148 |
+
"learning_rate": 7.603073154882702e-06,
|
| 149 |
+
"loss": 0.5631,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.88,
|
| 154 |
+
"eval_f1": 0.8381595689513368,
|
| 155 |
+
"eval_loss": 0.5315341353416443,
|
| 156 |
+
"eval_runtime": 12.733,
|
| 157 |
+
"eval_samples_per_second": 715.231,
|
| 158 |
+
"eval_steps_per_second": 1.414,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.96,
|
| 163 |
+
"learning_rate": 7.3899825395552714e-06,
|
| 164 |
+
"loss": 0.5015,
|
| 165 |
+
"step": 550
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.96,
|
| 169 |
+
"eval_f1": 0.8180551239783007,
|
| 170 |
+
"eval_loss": 0.6169003844261169,
|
| 171 |
+
"eval_runtime": 12.9102,
|
| 172 |
+
"eval_samples_per_second": 705.412,
|
| 173 |
+
"eval_steps_per_second": 1.394,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.05,
|
| 178 |
+
"learning_rate": 7.176891924227842e-06,
|
| 179 |
+
"loss": 0.4257,
|
| 180 |
+
"step": 600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.05,
|
| 184 |
+
"eval_f1": 0.817923619273461,
|
| 185 |
+
"eval_loss": 0.6071110963821411,
|
| 186 |
+
"eval_runtime": 13.735,
|
| 187 |
+
"eval_samples_per_second": 663.053,
|
| 188 |
+
"eval_steps_per_second": 1.311,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.14,
|
| 193 |
+
"learning_rate": 6.963801308900412e-06,
|
| 194 |
+
"loss": 0.3327,
|
| 195 |
+
"step": 650
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.14,
|
| 199 |
+
"eval_f1": 0.826695023066157,
|
| 200 |
+
"eval_loss": 0.5854237675666809,
|
| 201 |
+
"eval_runtime": 13.1401,
|
| 202 |
+
"eval_samples_per_second": 693.07,
|
| 203 |
+
"eval_steps_per_second": 1.37,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.23,
|
| 208 |
+
"learning_rate": 6.7507106935729815e-06,
|
| 209 |
+
"loss": 0.403,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.23,
|
| 214 |
+
"eval_f1": 0.8378257942819006,
|
| 215 |
+
"eval_loss": 0.5514610409736633,
|
| 216 |
+
"eval_runtime": 12.6701,
|
| 217 |
+
"eval_samples_per_second": 718.777,
|
| 218 |
+
"eval_steps_per_second": 1.421,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.31,
|
| 223 |
+
"learning_rate": 6.537620078245552e-06,
|
| 224 |
+
"loss": 0.3681,
|
| 225 |
+
"step": 750
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.31,
|
| 229 |
+
"eval_f1": 0.8209323144303958,
|
| 230 |
+
"eval_loss": 0.6371071338653564,
|
| 231 |
+
"eval_runtime": 13.0054,
|
| 232 |
+
"eval_samples_per_second": 700.248,
|
| 233 |
+
"eval_steps_per_second": 1.384,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.4,
|
| 238 |
+
"learning_rate": 6.324529462918122e-06,
|
| 239 |
+
"loss": 0.3236,
|
| 240 |
+
"step": 800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.4,
|
| 244 |
+
"eval_f1": 0.8376510055572749,
|
| 245 |
+
"eval_loss": 0.5530755519866943,
|
| 246 |
+
"eval_runtime": 12.7123,
|
| 247 |
+
"eval_samples_per_second": 716.393,
|
| 248 |
+
"eval_steps_per_second": 1.416,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.49,
|
| 253 |
+
"learning_rate": 6.111438847590692e-06,
|
| 254 |
+
"loss": 0.4138,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.49,
|
| 259 |
+
"eval_f1": 0.8451899128476951,
|
| 260 |
+
"eval_loss": 0.5386557579040527,
|
| 261 |
+
"eval_runtime": 12.9136,
|
| 262 |
+
"eval_samples_per_second": 705.227,
|
| 263 |
+
"eval_steps_per_second": 1.394,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.58,
|
| 268 |
+
"learning_rate": 5.8983482322632625e-06,
|
| 269 |
+
"loss": 0.3877,
|
| 270 |
+
"step": 900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.58,
|
| 274 |
+
"eval_f1": 0.8396443482352846,
|
| 275 |
+
"eval_loss": 0.5918898582458496,
|
| 276 |
+
"eval_runtime": 12.97,
|
| 277 |
+
"eval_samples_per_second": 702.16,
|
| 278 |
+
"eval_steps_per_second": 1.388,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.66,
|
| 283 |
+
"learning_rate": 5.6852576169358325e-06,
|
| 284 |
+
"loss": 0.4276,
|
| 285 |
+
"step": 950
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.66,
|
| 289 |
+
"eval_f1": 0.8384743295885987,
|
| 290 |
+
"eval_loss": 0.5536447763442993,
|
| 291 |
+
"eval_runtime": 12.8415,
|
| 292 |
+
"eval_samples_per_second": 709.185,
|
| 293 |
+
"eval_steps_per_second": 1.402,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.75,
|
| 298 |
+
"learning_rate": 5.472167001608402e-06,
|
| 299 |
+
"loss": 0.3926,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.75,
|
| 304 |
+
"eval_f1": 0.8172426280935748,
|
| 305 |
+
"eval_loss": 0.6521010398864746,
|
| 306 |
+
"eval_runtime": 12.7489,
|
| 307 |
+
"eval_samples_per_second": 714.335,
|
| 308 |
+
"eval_steps_per_second": 1.412,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.84,
|
| 313 |
+
"learning_rate": 5.2590763862809725e-06,
|
| 314 |
+
"loss": 0.4432,
|
| 315 |
+
"step": 1050
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.84,
|
| 319 |
+
"eval_f1": 0.8475488904826799,
|
| 320 |
+
"eval_loss": 0.49612656235694885,
|
| 321 |
+
"eval_runtime": 12.9412,
|
| 322 |
+
"eval_samples_per_second": 703.724,
|
| 323 |
+
"eval_steps_per_second": 1.391,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.93,
|
| 328 |
+
"learning_rate": 5.0459857709535426e-06,
|
| 329 |
+
"loss": 0.4031,
|
| 330 |
+
"step": 1100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.93,
|
| 334 |
+
"eval_f1": 0.8534964001754608,
|
| 335 |
+
"eval_loss": 0.5003403425216675,
|
| 336 |
+
"eval_runtime": 13.459,
|
| 337 |
+
"eval_samples_per_second": 676.648,
|
| 338 |
+
"eval_steps_per_second": 1.337,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.01,
|
| 343 |
+
"learning_rate": 4.832895155626112e-06,
|
| 344 |
+
"loss": 0.403,
|
| 345 |
+
"step": 1150
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.01,
|
| 349 |
+
"eval_f1": 0.850177595861797,
|
| 350 |
+
"eval_loss": 0.48595184087753296,
|
| 351 |
+
"eval_runtime": 13.0479,
|
| 352 |
+
"eval_samples_per_second": 697.967,
|
| 353 |
+
"eval_steps_per_second": 1.38,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.1,
|
| 358 |
+
"learning_rate": 4.619804540298683e-06,
|
| 359 |
+
"loss": 0.2496,
|
| 360 |
+
"step": 1200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.1,
|
| 364 |
+
"eval_f1": 0.8431021077169384,
|
| 365 |
+
"eval_loss": 0.5751626491546631,
|
| 366 |
+
"eval_runtime": 12.7058,
|
| 367 |
+
"eval_samples_per_second": 716.759,
|
| 368 |
+
"eval_steps_per_second": 1.417,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.19,
|
| 373 |
+
"learning_rate": 4.406713924971253e-06,
|
| 374 |
+
"loss": 0.257,
|
| 375 |
+
"step": 1250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.19,
|
| 379 |
+
"eval_f1": 0.8475870877960617,
|
| 380 |
+
"eval_loss": 0.5579206347465515,
|
| 381 |
+
"eval_runtime": 12.6855,
|
| 382 |
+
"eval_samples_per_second": 717.908,
|
| 383 |
+
"eval_steps_per_second": 1.419,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.28,
|
| 388 |
+
"learning_rate": 4.193623309643822e-06,
|
| 389 |
+
"loss": 0.3404,
|
| 390 |
+
"step": 1300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.28,
|
| 394 |
+
"eval_f1": 0.8376321081317408,
|
| 395 |
+
"eval_loss": 0.6273791790008545,
|
| 396 |
+
"eval_runtime": 12.7187,
|
| 397 |
+
"eval_samples_per_second": 716.034,
|
| 398 |
+
"eval_steps_per_second": 1.415,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.36,
|
| 403 |
+
"learning_rate": 3.980532694316393e-06,
|
| 404 |
+
"loss": 0.2248,
|
| 405 |
+
"step": 1350
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.36,
|
| 409 |
+
"eval_f1": 0.8374320586864977,
|
| 410 |
+
"eval_loss": 0.6183853149414062,
|
| 411 |
+
"eval_runtime": 12.8619,
|
| 412 |
+
"eval_samples_per_second": 708.058,
|
| 413 |
+
"eval_steps_per_second": 1.399,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.45,
|
| 418 |
+
"learning_rate": 3.7674420789889623e-06,
|
| 419 |
+
"loss": 0.335,
|
| 420 |
+
"step": 1400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.45,
|
| 424 |
+
"eval_f1": 0.8499224527475217,
|
| 425 |
+
"eval_loss": 0.5527887940406799,
|
| 426 |
+
"eval_runtime": 12.9423,
|
| 427 |
+
"eval_samples_per_second": 703.662,
|
| 428 |
+
"eval_steps_per_second": 1.391,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.54,
|
| 433 |
+
"learning_rate": 3.5543514636615323e-06,
|
| 434 |
+
"loss": 0.3058,
|
| 435 |
+
"step": 1450
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.54,
|
| 439 |
+
"eval_f1": 0.8389360164023282,
|
| 440 |
+
"eval_loss": 0.6216479539871216,
|
| 441 |
+
"eval_runtime": 12.7941,
|
| 442 |
+
"eval_samples_per_second": 711.813,
|
| 443 |
+
"eval_steps_per_second": 1.407,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.63,
|
| 448 |
+
"learning_rate": 3.341260848334102e-06,
|
| 449 |
+
"loss": 0.2675,
|
| 450 |
+
"step": 1500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.63,
|
| 454 |
+
"eval_f1": 0.8420632349860007,
|
| 455 |
+
"eval_loss": 0.6038542985916138,
|
| 456 |
+
"eval_runtime": 12.7939,
|
| 457 |
+
"eval_samples_per_second": 711.826,
|
| 458 |
+
"eval_steps_per_second": 1.407,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.71,
|
| 463 |
+
"learning_rate": 3.1281702330066724e-06,
|
| 464 |
+
"loss": 0.2097,
|
| 465 |
+
"step": 1550
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.71,
|
| 469 |
+
"eval_f1": 0.8351176102968624,
|
| 470 |
+
"eval_loss": 0.6655907034873962,
|
| 471 |
+
"eval_runtime": 13.3086,
|
| 472 |
+
"eval_samples_per_second": 684.295,
|
| 473 |
+
"eval_steps_per_second": 1.353,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.8,
|
| 478 |
+
"learning_rate": 2.9150796176792424e-06,
|
| 479 |
+
"loss": 0.2868,
|
| 480 |
+
"step": 1600
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.8,
|
| 484 |
+
"eval_f1": 0.8457462458632461,
|
| 485 |
+
"eval_loss": 0.5934119820594788,
|
| 486 |
+
"eval_runtime": 13.4832,
|
| 487 |
+
"eval_samples_per_second": 675.433,
|
| 488 |
+
"eval_steps_per_second": 1.335,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.89,
|
| 493 |
+
"learning_rate": 2.701989002351812e-06,
|
| 494 |
+
"loss": 0.3255,
|
| 495 |
+
"step": 1650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.89,
|
| 499 |
+
"eval_f1": 0.843285508336316,
|
| 500 |
+
"eval_loss": 0.6201077103614807,
|
| 501 |
+
"eval_runtime": 13.4442,
|
| 502 |
+
"eval_samples_per_second": 677.394,
|
| 503 |
+
"eval_steps_per_second": 1.339,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.98,
|
| 508 |
+
"learning_rate": 2.4888983870243825e-06,
|
| 509 |
+
"loss": 0.3317,
|
| 510 |
+
"step": 1700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.98,
|
| 514 |
+
"eval_f1": 0.8462407461032612,
|
| 515 |
+
"eval_loss": 0.599490761756897,
|
| 516 |
+
"eval_runtime": 13.006,
|
| 517 |
+
"eval_samples_per_second": 700.216,
|
| 518 |
+
"eval_steps_per_second": 1.384,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.06,
|
| 523 |
+
"learning_rate": 2.2758077716969525e-06,
|
| 524 |
+
"loss": 0.3481,
|
| 525 |
+
"step": 1750
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.06,
|
| 529 |
+
"eval_f1": 0.8533197825326935,
|
| 530 |
+
"eval_loss": 0.565264105796814,
|
| 531 |
+
"eval_runtime": 12.6526,
|
| 532 |
+
"eval_samples_per_second": 719.772,
|
| 533 |
+
"eval_steps_per_second": 1.423,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.15,
|
| 538 |
+
"learning_rate": 2.062717156369522e-06,
|
| 539 |
+
"loss": 0.1945,
|
| 540 |
+
"step": 1800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.15,
|
| 544 |
+
"eval_f1": 0.8491469838704785,
|
| 545 |
+
"eval_loss": 0.6022334098815918,
|
| 546 |
+
"eval_runtime": 12.8004,
|
| 547 |
+
"eval_samples_per_second": 711.465,
|
| 548 |
+
"eval_steps_per_second": 1.406,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.24,
|
| 553 |
+
"learning_rate": 1.8496265410420923e-06,
|
| 554 |
+
"loss": 0.2752,
|
| 555 |
+
"step": 1850
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.24,
|
| 559 |
+
"eval_f1": 0.8365374998533712,
|
| 560 |
+
"eval_loss": 0.6872730851173401,
|
| 561 |
+
"eval_runtime": 12.9696,
|
| 562 |
+
"eval_samples_per_second": 702.183,
|
| 563 |
+
"eval_steps_per_second": 1.388,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.33,
|
| 568 |
+
"learning_rate": 1.6365359257146626e-06,
|
| 569 |
+
"loss": 0.1996,
|
| 570 |
+
"step": 1900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.33,
|
| 574 |
+
"eval_f1": 0.8451033394376192,
|
| 575 |
+
"eval_loss": 0.6422092318534851,
|
| 576 |
+
"eval_runtime": 12.8718,
|
| 577 |
+
"eval_samples_per_second": 707.513,
|
| 578 |
+
"eval_steps_per_second": 1.398,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.42,
|
| 583 |
+
"learning_rate": 1.4234453103872324e-06,
|
| 584 |
+
"loss": 0.2491,
|
| 585 |
+
"step": 1950
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.42,
|
| 589 |
+
"eval_f1": 0.8470154791947956,
|
| 590 |
+
"eval_loss": 0.6257719397544861,
|
| 591 |
+
"eval_runtime": 12.7843,
|
| 592 |
+
"eval_samples_per_second": 712.356,
|
| 593 |
+
"eval_steps_per_second": 1.408,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.5,
|
| 598 |
+
"learning_rate": 1.2103546950598024e-06,
|
| 599 |
+
"loss": 0.2368,
|
| 600 |
+
"step": 2000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.5,
|
| 604 |
+
"eval_f1": 0.8493072488776222,
|
| 605 |
+
"eval_loss": 0.6073781251907349,
|
| 606 |
+
"eval_runtime": 12.7011,
|
| 607 |
+
"eval_samples_per_second": 717.024,
|
| 608 |
+
"eval_steps_per_second": 1.417,
|
| 609 |
+
"step": 2000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 50,
|
| 613 |
+
"max_steps": 2284,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 4,
|
| 616 |
+
"save_steps": 500,
|
| 617 |
+
"total_flos": 162782606311200.0,
|
| 618 |
+
"train_batch_size": 8,
|
| 619 |
+
"trial_name": null,
|
| 620 |
+
"trial_params": {
|
| 621 |
+
"learning_rate": 9.520888692829572e-06,
|
| 622 |
+
"num_train_epochs": 4,
|
| 623 |
+
"per_device_train_batch_size": 8,
|
| 624 |
+
"seed": 4
|
| 625 |
+
}
|
| 626 |
+
}
|
run-2/checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffebf7e3158659f9acfc5251a7413b79224a3042a0cc4d9f259be5d9dbc266cd
|
| 3 |
+
size 4728
|
run-2/checkpoint-2000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|