Training in progress, step 43000, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-43000/config.json +35 -0
- checkpoint-43000/model.safetensors +3 -0
- checkpoint-43000/optimizer.pt +3 -0
- checkpoint-43000/rng_state.pth +3 -0
- checkpoint-43000/scheduler.pt +3 -0
- checkpoint-43000/sentencepiece.bpe.model +3 -0
- checkpoint-43000/special_tokens_map.json +51 -0
- checkpoint-43000/tokenizer.json +3 -0
- checkpoint-43000/tokenizer_config.json +59 -0
- checkpoint-43000/trainer_state.json +1152 -0
- checkpoint-43000/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -76,3 +76,4 @@ checkpoint-39000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 76 |
checkpoint-40000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
checkpoint-41000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 78 |
checkpoint-42000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 76 |
checkpoint-40000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
checkpoint-41000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 78 |
checkpoint-42000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
checkpoint-43000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-43000/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B",
|
| 15 |
+
"1": "I"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"B": 0,
|
| 21 |
+
"I": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "xlm-roberta",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.57.1",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
+
}
|
checkpoint-43000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972d5d3691d1d1511c52b4e9feab6232b6ee004e7d6fcae5734cd20ac821e766
|
| 3 |
+
size 1109842416
|
checkpoint-43000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4019050cf90dc622b3bf138dacd127329d64bbf5372af8a2dbc76d521ea177d5
|
| 3 |
+
size 2219806475
|
checkpoint-43000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d28f0ef2581794711a7181a80ff1661134625a58b5cbb616e16197514a048d4
|
| 3 |
+
size 14645
|
checkpoint-43000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06c26cf8a0cf3ad5fc6b581699278ba621c2102241730b514424ab4724861bfc
|
| 3 |
+
size 1465
|
checkpoint-43000/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-43000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 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": "</s>",
|
| 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 |
+
}
|
checkpoint-43000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
| 3 |
+
size 17082832
|
checkpoint-43000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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>",
|
| 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 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"stride": 0,
|
| 55 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 56 |
+
"truncation_side": "right",
|
| 57 |
+
"truncation_strategy": "longest_first",
|
| 58 |
+
"unk_token": "<unk>"
|
| 59 |
+
}
|
checkpoint-43000/trainer_state.json
ADDED
|
@@ -0,0 +1,1152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 38000,
|
| 3 |
+
"best_metric": 0.10237538069486618,
|
| 4 |
+
"best_model_checkpoint": "myanmar_text_segmentation_model/checkpoint-38000",
|
| 5 |
+
"epoch": 3.9511164201047504,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 43000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04594321418726454,
|
| 14 |
+
"grad_norm": 0.577109158039093,
|
| 15 |
+
"learning_rate": 1.9816594688964442e-05,
|
| 16 |
+
"loss": 0.1144,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09188642837452908,
|
| 21 |
+
"grad_norm": 0.8819814324378967,
|
| 22 |
+
"learning_rate": 1.9632821832215383e-05,
|
| 23 |
+
"loss": 0.1133,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09188642837452908,
|
| 28 |
+
"eval_accuracy": 0.9564004775738034,
|
| 29 |
+
"eval_f1": 0.7581789101913106,
|
| 30 |
+
"eval_loss": 0.11448723077774048,
|
| 31 |
+
"eval_precision": 0.7703745996379334,
|
| 32 |
+
"eval_recall": 0.7463633395484631,
|
| 33 |
+
"eval_runtime": 465.4607,
|
| 34 |
+
"eval_samples_per_second": 61.528,
|
| 35 |
+
"eval_steps_per_second": 1.231,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.1378296425617936,
|
| 40 |
+
"grad_norm": 0.5137984156608582,
|
| 41 |
+
"learning_rate": 1.9449048975466325e-05,
|
| 42 |
+
"loss": 0.1119,
|
| 43 |
+
"step": 1500
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.18377285674905816,
|
| 47 |
+
"grad_norm": 0.6753482222557068,
|
| 48 |
+
"learning_rate": 1.9265276118717266e-05,
|
| 49 |
+
"loss": 0.1115,
|
| 50 |
+
"step": 2000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.18377285674905816,
|
| 54 |
+
"eval_accuracy": 0.9565513036953667,
|
| 55 |
+
"eval_f1": 0.7631813253052621,
|
| 56 |
+
"eval_loss": 0.11509840190410614,
|
| 57 |
+
"eval_precision": 0.7619568901058112,
|
| 58 |
+
"eval_recall": 0.7644097020785157,
|
| 59 |
+
"eval_runtime": 471.4797,
|
| 60 |
+
"eval_samples_per_second": 60.743,
|
| 61 |
+
"eval_steps_per_second": 1.215,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2297160709363227,
|
| 66 |
+
"grad_norm": 0.46862444281578064,
|
| 67 |
+
"learning_rate": 1.9081503261968207e-05,
|
| 68 |
+
"loss": 0.1083,
|
| 69 |
+
"step": 2500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.2756592851235872,
|
| 73 |
+
"grad_norm": 0.6514066457748413,
|
| 74 |
+
"learning_rate": 1.889773040521915e-05,
|
| 75 |
+
"loss": 0.1085,
|
| 76 |
+
"step": 3000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.2756592851235872,
|
| 80 |
+
"eval_accuracy": 0.955793370748351,
|
| 81 |
+
"eval_f1": 0.7617613129080717,
|
| 82 |
+
"eval_loss": 0.11627302318811417,
|
| 83 |
+
"eval_precision": 0.7514122514122514,
|
| 84 |
+
"eval_recall": 0.7723994268768838,
|
| 85 |
+
"eval_runtime": 464.541,
|
| 86 |
+
"eval_samples_per_second": 61.65,
|
| 87 |
+
"eval_steps_per_second": 1.233,
|
| 88 |
+
"step": 3000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3216024993108518,
|
| 92 |
+
"grad_norm": 0.5837205052375793,
|
| 93 |
+
"learning_rate": 1.8713957548470093e-05,
|
| 94 |
+
"loss": 0.1068,
|
| 95 |
+
"step": 3500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.3675457134981163,
|
| 99 |
+
"grad_norm": 0.590044379234314,
|
| 100 |
+
"learning_rate": 1.8530184691721034e-05,
|
| 101 |
+
"loss": 0.1076,
|
| 102 |
+
"step": 4000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.3675457134981163,
|
| 106 |
+
"eval_accuracy": 0.9567566300121167,
|
| 107 |
+
"eval_f1": 0.7569129075628852,
|
| 108 |
+
"eval_loss": 0.11681018769741058,
|
| 109 |
+
"eval_precision": 0.7790560842692136,
|
| 110 |
+
"eval_recall": 0.7359936967250493,
|
| 111 |
+
"eval_runtime": 464.1614,
|
| 112 |
+
"eval_samples_per_second": 61.701,
|
| 113 |
+
"eval_steps_per_second": 1.234,
|
| 114 |
+
"step": 4000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.41348892768538087,
|
| 118 |
+
"grad_norm": 0.43107616901397705,
|
| 119 |
+
"learning_rate": 1.8346411834971975e-05,
|
| 120 |
+
"loss": 0.1071,
|
| 121 |
+
"step": 4500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4594321418726454,
|
| 125 |
+
"grad_norm": 0.6132990121841431,
|
| 126 |
+
"learning_rate": 1.8162638978222916e-05,
|
| 127 |
+
"loss": 0.1056,
|
| 128 |
+
"step": 5000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4594321418726454,
|
| 132 |
+
"eval_accuracy": 0.9576032842071108,
|
| 133 |
+
"eval_f1": 0.7661190672004459,
|
| 134 |
+
"eval_loss": 0.11183962970972061,
|
| 135 |
+
"eval_precision": 0.7719609680194174,
|
| 136 |
+
"eval_recall": 0.7603649207638403,
|
| 137 |
+
"eval_runtime": 473.1438,
|
| 138 |
+
"eval_samples_per_second": 60.529,
|
| 139 |
+
"eval_steps_per_second": 1.211,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.5053753560599099,
|
| 144 |
+
"grad_norm": 0.4892466962337494,
|
| 145 |
+
"learning_rate": 1.7978866121473858e-05,
|
| 146 |
+
"loss": 0.1154,
|
| 147 |
+
"step": 5500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.5513185702471745,
|
| 151 |
+
"grad_norm": 0.8282744884490967,
|
| 152 |
+
"learning_rate": 1.7795093264724802e-05,
|
| 153 |
+
"loss": 0.1141,
|
| 154 |
+
"step": 6000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.5513185702471745,
|
| 158 |
+
"eval_accuracy": 0.9580804777765948,
|
| 159 |
+
"eval_f1": 0.7681685393564336,
|
| 160 |
+
"eval_loss": 0.11200755834579468,
|
| 161 |
+
"eval_precision": 0.7751412801894542,
|
| 162 |
+
"eval_recall": 0.7613201259575663,
|
| 163 |
+
"eval_runtime": 463.6002,
|
| 164 |
+
"eval_samples_per_second": 61.775,
|
| 165 |
+
"eval_steps_per_second": 1.236,
|
| 166 |
+
"step": 6000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.597261784434439,
|
| 170 |
+
"grad_norm": 0.44782352447509766,
|
| 171 |
+
"learning_rate": 1.7611320407975743e-05,
|
| 172 |
+
"loss": 0.1135,
|
| 173 |
+
"step": 6500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.6432049986217035,
|
| 177 |
+
"grad_norm": 0.5544679760932922,
|
| 178 |
+
"learning_rate": 1.7427547551226684e-05,
|
| 179 |
+
"loss": 0.1154,
|
| 180 |
+
"step": 7000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.6432049986217035,
|
| 184 |
+
"eval_accuracy": 0.9576146912247081,
|
| 185 |
+
"eval_f1": 0.7686338805157804,
|
| 186 |
+
"eval_loss": 0.11075501888990402,
|
| 187 |
+
"eval_precision": 0.7656366294168357,
|
| 188 |
+
"eval_recall": 0.7716546906241484,
|
| 189 |
+
"eval_runtime": 472.6577,
|
| 190 |
+
"eval_samples_per_second": 60.591,
|
| 191 |
+
"eval_steps_per_second": 1.212,
|
| 192 |
+
"step": 7000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6891482128089681,
|
| 196 |
+
"grad_norm": 0.4101652503013611,
|
| 197 |
+
"learning_rate": 1.7243774694477626e-05,
|
| 198 |
+
"loss": 0.1123,
|
| 199 |
+
"step": 7500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7350914269962326,
|
| 203 |
+
"grad_norm": 0.5032928586006165,
|
| 204 |
+
"learning_rate": 1.7060001837728567e-05,
|
| 205 |
+
"loss": 0.1128,
|
| 206 |
+
"step": 8000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7350914269962326,
|
| 210 |
+
"eval_accuracy": 0.9583707230021242,
|
| 211 |
+
"eval_f1": 0.7702898098589065,
|
| 212 |
+
"eval_loss": 0.10922538489103317,
|
| 213 |
+
"eval_precision": 0.7744496660220761,
|
| 214 |
+
"eval_recall": 0.7661744031991279,
|
| 215 |
+
"eval_runtime": 465.4833,
|
| 216 |
+
"eval_samples_per_second": 61.525,
|
| 217 |
+
"eval_steps_per_second": 1.231,
|
| 218 |
+
"step": 8000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.7810346411834972,
|
| 222 |
+
"grad_norm": 0.5559138059616089,
|
| 223 |
+
"learning_rate": 1.687622898097951e-05,
|
| 224 |
+
"loss": 0.112,
|
| 225 |
+
"step": 8500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8269778553707617,
|
| 229 |
+
"grad_norm": 0.7113578915596008,
|
| 230 |
+
"learning_rate": 1.6692456124230453e-05,
|
| 231 |
+
"loss": 0.1082,
|
| 232 |
+
"step": 9000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8269778553707617,
|
| 236 |
+
"eval_accuracy": 0.9588998818739956,
|
| 237 |
+
"eval_f1": 0.7713698035177239,
|
| 238 |
+
"eval_loss": 0.10946337133646011,
|
| 239 |
+
"eval_precision": 0.78099547261026,
|
| 240 |
+
"eval_recall": 0.7619785159781004,
|
| 241 |
+
"eval_runtime": 477.2564,
|
| 242 |
+
"eval_samples_per_second": 60.008,
|
| 243 |
+
"eval_steps_per_second": 1.201,
|
| 244 |
+
"step": 9000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8729210695580263,
|
| 248 |
+
"grad_norm": 0.4333978593349457,
|
| 249 |
+
"learning_rate": 1.6508683267481394e-05,
|
| 250 |
+
"loss": 0.1116,
|
| 251 |
+
"step": 9500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.9188642837452908,
|
| 255 |
+
"grad_norm": 0.3579271137714386,
|
| 256 |
+
"learning_rate": 1.6324910410732335e-05,
|
| 257 |
+
"loss": 0.1101,
|
| 258 |
+
"step": 10000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.9188642837452908,
|
| 262 |
+
"eval_accuracy": 0.9590893651107495,
|
| 263 |
+
"eval_f1": 0.7721416651417115,
|
| 264 |
+
"eval_loss": 0.10736154764890671,
|
| 265 |
+
"eval_precision": 0.7816850586599052,
|
| 266 |
+
"eval_recall": 0.7628284867013311,
|
| 267 |
+
"eval_runtime": 478.6898,
|
| 268 |
+
"eval_samples_per_second": 59.828,
|
| 269 |
+
"eval_steps_per_second": 1.197,
|
| 270 |
+
"step": 10000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.9648074979325554,
|
| 274 |
+
"grad_norm": 0.4602518677711487,
|
| 275 |
+
"learning_rate": 1.6141137553983276e-05,
|
| 276 |
+
"loss": 0.1101,
|
| 277 |
+
"step": 10500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.0107507121198198,
|
| 281 |
+
"grad_norm": 0.5322664976119995,
|
| 282 |
+
"learning_rate": 1.5957364697234217e-05,
|
| 283 |
+
"loss": 0.1101,
|
| 284 |
+
"step": 11000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.0107507121198198,
|
| 288 |
+
"eval_accuracy": 0.9591349931811384,
|
| 289 |
+
"eval_f1": 0.7744744313952638,
|
| 290 |
+
"eval_loss": 0.10792569071054459,
|
| 291 |
+
"eval_precision": 0.7768799906601179,
|
| 292 |
+
"eval_recall": 0.7720837234653981,
|
| 293 |
+
"eval_runtime": 477.7344,
|
| 294 |
+
"eval_samples_per_second": 59.948,
|
| 295 |
+
"eval_steps_per_second": 1.199,
|
| 296 |
+
"step": 11000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.0566939263070845,
|
| 300 |
+
"grad_norm": 0.5673955678939819,
|
| 301 |
+
"learning_rate": 1.5773591840485162e-05,
|
| 302 |
+
"loss": 0.1071,
|
| 303 |
+
"step": 11500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.102637140494349,
|
| 307 |
+
"grad_norm": 0.42657607793807983,
|
| 308 |
+
"learning_rate": 1.5589818983736103e-05,
|
| 309 |
+
"loss": 0.1058,
|
| 310 |
+
"step": 12000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.102637140494349,
|
| 314 |
+
"eval_accuracy": 0.9584847931780965,
|
| 315 |
+
"eval_f1": 0.7735292150015388,
|
| 316 |
+
"eval_loss": 0.10933595150709152,
|
| 317 |
+
"eval_precision": 0.7671773857517072,
|
| 318 |
+
"eval_recall": 0.779987102031565,
|
| 319 |
+
"eval_runtime": 475.9965,
|
| 320 |
+
"eval_samples_per_second": 60.166,
|
| 321 |
+
"eval_steps_per_second": 1.204,
|
| 322 |
+
"step": 12000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.1485803546816136,
|
| 326 |
+
"grad_norm": 0.4599572718143463,
|
| 327 |
+
"learning_rate": 1.5406046126987044e-05,
|
| 328 |
+
"loss": 0.107,
|
| 329 |
+
"step": 12500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.194523568868878,
|
| 333 |
+
"grad_norm": 0.4379059970378876,
|
| 334 |
+
"learning_rate": 1.5222273270237986e-05,
|
| 335 |
+
"loss": 0.107,
|
| 336 |
+
"step": 13000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.194523568868878,
|
| 340 |
+
"eval_accuracy": 0.959601413456225,
|
| 341 |
+
"eval_f1": 0.7737560775183182,
|
| 342 |
+
"eval_loss": 0.1075456365942955,
|
| 343 |
+
"eval_precision": 0.7856481314090709,
|
| 344 |
+
"eval_recall": 0.76221866643641,
|
| 345 |
+
"eval_runtime": 478.1835,
|
| 346 |
+
"eval_samples_per_second": 59.891,
|
| 347 |
+
"eval_steps_per_second": 1.198,
|
| 348 |
+
"step": 13000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.2404667830561427,
|
| 352 |
+
"grad_norm": 0.43774718046188354,
|
| 353 |
+
"learning_rate": 1.5038500413488928e-05,
|
| 354 |
+
"loss": 0.1055,
|
| 355 |
+
"step": 13500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.286409997243407,
|
| 359 |
+
"grad_norm": 0.4196317195892334,
|
| 360 |
+
"learning_rate": 1.485472755673987e-05,
|
| 361 |
+
"loss": 0.1055,
|
| 362 |
+
"step": 14000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.286409997243407,
|
| 366 |
+
"eval_accuracy": 0.959860606244962,
|
| 367 |
+
"eval_f1": 0.7768597287158228,
|
| 368 |
+
"eval_loss": 0.10658087581396103,
|
| 369 |
+
"eval_precision": 0.7824100936011823,
|
| 370 |
+
"eval_recall": 0.7713875569682759,
|
| 371 |
+
"eval_runtime": 464.4067,
|
| 372 |
+
"eval_samples_per_second": 61.668,
|
| 373 |
+
"eval_steps_per_second": 1.234,
|
| 374 |
+
"step": 14000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3323532114306718,
|
| 378 |
+
"grad_norm": 0.36208856105804443,
|
| 379 |
+
"learning_rate": 1.467095469999081e-05,
|
| 380 |
+
"loss": 0.1035,
|
| 381 |
+
"step": 14500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3782964256179362,
|
| 385 |
+
"grad_norm": 0.5692697763442993,
|
| 386 |
+
"learning_rate": 1.4487181843241755e-05,
|
| 387 |
+
"loss": 0.1054,
|
| 388 |
+
"step": 15000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3782964256179362,
|
| 392 |
+
"eval_accuracy": 0.9593396857746885,
|
| 393 |
+
"eval_f1": 0.7750922296908528,
|
| 394 |
+
"eval_loss": 0.10651089251041412,
|
| 395 |
+
"eval_precision": 0.7777847213920075,
|
| 396 |
+
"eval_recall": 0.7724183151151778,
|
| 397 |
+
"eval_runtime": 484.7629,
|
| 398 |
+
"eval_samples_per_second": 59.078,
|
| 399 |
+
"eval_steps_per_second": 1.182,
|
| 400 |
+
"step": 15000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.4242396398052009,
|
| 404 |
+
"grad_norm": 0.4805659055709839,
|
| 405 |
+
"learning_rate": 1.4303408986492697e-05,
|
| 406 |
+
"loss": 0.1043,
|
| 407 |
+
"step": 15500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.4701828539924653,
|
| 411 |
+
"grad_norm": 0.5373257994651794,
|
| 412 |
+
"learning_rate": 1.411963612974364e-05,
|
| 413 |
+
"loss": 0.1038,
|
| 414 |
+
"step": 16000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.4701828539924653,
|
| 418 |
+
"eval_accuracy": 0.9594822734946539,
|
| 419 |
+
"eval_f1": 0.77620383584155,
|
| 420 |
+
"eval_loss": 0.10620830953121185,
|
| 421 |
+
"eval_precision": 0.7775004264051742,
|
| 422 |
+
"eval_recall": 0.7749115625699877,
|
| 423 |
+
"eval_runtime": 484.6548,
|
| 424 |
+
"eval_samples_per_second": 59.092,
|
| 425 |
+
"eval_steps_per_second": 1.182,
|
| 426 |
+
"step": 16000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.5161260681797297,
|
| 430 |
+
"grad_norm": 0.5227932929992676,
|
| 431 |
+
"learning_rate": 1.393586327299458e-05,
|
| 432 |
+
"loss": 0.1057,
|
| 433 |
+
"step": 16500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.5620692823669944,
|
| 437 |
+
"grad_norm": 0.2855619192123413,
|
| 438 |
+
"learning_rate": 1.3752090416245523e-05,
|
| 439 |
+
"loss": 0.1052,
|
| 440 |
+
"step": 17000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.5620692823669944,
|
| 444 |
+
"eval_accuracy": 0.9600310777857204,
|
| 445 |
+
"eval_f1": 0.7757748564065305,
|
| 446 |
+
"eval_loss": 0.10526877641677856,
|
| 447 |
+
"eval_precision": 0.7884331924355441,
|
| 448 |
+
"eval_recall": 0.7635165582391844,
|
| 449 |
+
"eval_runtime": 483.926,
|
| 450 |
+
"eval_samples_per_second": 59.181,
|
| 451 |
+
"eval_steps_per_second": 1.184,
|
| 452 |
+
"step": 17000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.608012496554259,
|
| 456 |
+
"grad_norm": 0.36337897181510925,
|
| 457 |
+
"learning_rate": 1.3568317559496465e-05,
|
| 458 |
+
"loss": 0.1058,
|
| 459 |
+
"step": 17500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.6539557107415235,
|
| 463 |
+
"grad_norm": 0.7537007927894592,
|
| 464 |
+
"learning_rate": 1.3384544702747406e-05,
|
| 465 |
+
"loss": 0.1061,
|
| 466 |
+
"step": 18000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.6539557107415235,
|
| 470 |
+
"eval_accuracy": 0.9598663097537605,
|
| 471 |
+
"eval_f1": 0.7781213928303998,
|
| 472 |
+
"eval_loss": 0.1061909943819046,
|
| 473 |
+
"eval_precision": 0.7795501631707945,
|
| 474 |
+
"eval_recall": 0.7766978502486501,
|
| 475 |
+
"eval_runtime": 483.1917,
|
| 476 |
+
"eval_samples_per_second": 59.27,
|
| 477 |
+
"eval_steps_per_second": 1.186,
|
| 478 |
+
"step": 18000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.699898924928788,
|
| 482 |
+
"grad_norm": 0.7511648535728455,
|
| 483 |
+
"learning_rate": 1.3200771845998349e-05,
|
| 484 |
+
"loss": 0.1035,
|
| 485 |
+
"step": 18500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.7458421391160526,
|
| 489 |
+
"grad_norm": 0.5765513181686401,
|
| 490 |
+
"learning_rate": 1.301699898924929e-05,
|
| 491 |
+
"loss": 0.1038,
|
| 492 |
+
"step": 19000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.7458421391160526,
|
| 496 |
+
"eval_accuracy": 0.9596578148210112,
|
| 497 |
+
"eval_f1": 0.7782083489589002,
|
| 498 |
+
"eval_loss": 0.10631386935710907,
|
| 499 |
+
"eval_precision": 0.7753205917958497,
|
| 500 |
+
"eval_recall": 0.7811176980094495,
|
| 501 |
+
"eval_runtime": 481.5937,
|
| 502 |
+
"eval_samples_per_second": 59.467,
|
| 503 |
+
"eval_steps_per_second": 1.19,
|
| 504 |
+
"step": 19000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.7917853533033172,
|
| 508 |
+
"grad_norm": 1.3671506643295288,
|
| 509 |
+
"learning_rate": 1.2833226132500231e-05,
|
| 510 |
+
"loss": 0.1037,
|
| 511 |
+
"step": 19500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.8377285674905817,
|
| 515 |
+
"grad_norm": 0.6475801467895508,
|
| 516 |
+
"learning_rate": 1.2649453275751174e-05,
|
| 517 |
+
"loss": 0.1017,
|
| 518 |
+
"step": 20000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.8377285674905817,
|
| 522 |
+
"eval_accuracy": 0.9603023113152545,
|
| 523 |
+
"eval_f1": 0.7790918283030356,
|
| 524 |
+
"eval_loss": 0.10478387773036957,
|
| 525 |
+
"eval_precision": 0.784845306908137,
|
| 526 |
+
"eval_recall": 0.7734220900645168,
|
| 527 |
+
"eval_runtime": 483.6282,
|
| 528 |
+
"eval_samples_per_second": 59.217,
|
| 529 |
+
"eval_steps_per_second": 1.185,
|
| 530 |
+
"step": 20000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.883671781677846,
|
| 534 |
+
"grad_norm": 0.898071825504303,
|
| 535 |
+
"learning_rate": 1.2465680419002115e-05,
|
| 536 |
+
"loss": 0.1027,
|
| 537 |
+
"step": 20500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.9296149958651108,
|
| 541 |
+
"grad_norm": 0.6122450232505798,
|
| 542 |
+
"learning_rate": 1.2281907562253056e-05,
|
| 543 |
+
"loss": 0.1029,
|
| 544 |
+
"step": 21000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.9296149958651108,
|
| 548 |
+
"eval_accuracy": 0.96032068928805,
|
| 549 |
+
"eval_f1": 0.7800494094554808,
|
| 550 |
+
"eval_loss": 0.10455518215894699,
|
| 551 |
+
"eval_precision": 0.7826737729678044,
|
| 552 |
+
"eval_recall": 0.7774425865013855,
|
| 553 |
+
"eval_runtime": 483.8492,
|
| 554 |
+
"eval_samples_per_second": 59.19,
|
| 555 |
+
"eval_steps_per_second": 1.184,
|
| 556 |
+
"step": 21000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.9755582100523754,
|
| 560 |
+
"grad_norm": 0.6479480266571045,
|
| 561 |
+
"learning_rate": 1.2098134705504e-05,
|
| 562 |
+
"loss": 0.1032,
|
| 563 |
+
"step": 21500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.0215014242396396,
|
| 567 |
+
"grad_norm": 0.9193481206893921,
|
| 568 |
+
"learning_rate": 1.191436184875494e-05,
|
| 569 |
+
"loss": 0.1018,
|
| 570 |
+
"step": 22000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0215014242396396,
|
| 574 |
+
"eval_accuracy": 0.9604075093664289,
|
| 575 |
+
"eval_f1": 0.7798349386244161,
|
| 576 |
+
"eval_loss": 0.10434387624263763,
|
| 577 |
+
"eval_precision": 0.7843734048157843,
|
| 578 |
+
"eval_recall": 0.7753486903705062,
|
| 579 |
+
"eval_runtime": 482.4895,
|
| 580 |
+
"eval_samples_per_second": 59.357,
|
| 581 |
+
"eval_steps_per_second": 1.188,
|
| 582 |
+
"step": 22000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.0674446384269043,
|
| 586 |
+
"grad_norm": 0.41459354758262634,
|
| 587 |
+
"learning_rate": 1.1730588992005882e-05,
|
| 588 |
+
"loss": 0.1015,
|
| 589 |
+
"step": 22500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.113387852614169,
|
| 593 |
+
"grad_norm": 0.5848496556282043,
|
| 594 |
+
"learning_rate": 1.1546816135256825e-05,
|
| 595 |
+
"loss": 0.1007,
|
| 596 |
+
"step": 23000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.113387852614169,
|
| 600 |
+
"eval_accuracy": 0.960530451667199,
|
| 601 |
+
"eval_f1": 0.7787409881226326,
|
| 602 |
+
"eval_loss": 0.10433882474899292,
|
| 603 |
+
"eval_precision": 0.7888630191217876,
|
| 604 |
+
"eval_recall": 0.7688754212751719,
|
| 605 |
+
"eval_runtime": 481.4982,
|
| 606 |
+
"eval_samples_per_second": 59.479,
|
| 607 |
+
"eval_steps_per_second": 1.19,
|
| 608 |
+
"step": 23000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.1593310668014336,
|
| 612 |
+
"grad_norm": 0.5300314426422119,
|
| 613 |
+
"learning_rate": 1.1363043278507766e-05,
|
| 614 |
+
"loss": 0.1008,
|
| 615 |
+
"step": 23500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.205274280988698,
|
| 619 |
+
"grad_norm": 0.34308552742004395,
|
| 620 |
+
"learning_rate": 1.1179270421758709e-05,
|
| 621 |
+
"loss": 0.1008,
|
| 622 |
+
"step": 24000
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.205274280988698,
|
| 626 |
+
"eval_accuracy": 0.9605203120960014,
|
| 627 |
+
"eval_f1": 0.7802636835797044,
|
| 628 |
+
"eval_loss": 0.10480789840221405,
|
| 629 |
+
"eval_precision": 0.7859456144721461,
|
| 630 |
+
"eval_recall": 0.7746633171524092,
|
| 631 |
+
"eval_runtime": 482.2132,
|
| 632 |
+
"eval_samples_per_second": 59.391,
|
| 633 |
+
"eval_steps_per_second": 1.188,
|
| 634 |
+
"step": 24000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.2512174951759625,
|
| 638 |
+
"grad_norm": 0.668408215045929,
|
| 639 |
+
"learning_rate": 1.099549756500965e-05,
|
| 640 |
+
"loss": 0.101,
|
| 641 |
+
"step": 24500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.297160709363227,
|
| 645 |
+
"grad_norm": 0.6432192921638489,
|
| 646 |
+
"learning_rate": 1.0811724708260591e-05,
|
| 647 |
+
"loss": 0.1015,
|
| 648 |
+
"step": 25000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.297160709363227,
|
| 652 |
+
"eval_accuracy": 0.9606768417263634,
|
| 653 |
+
"eval_f1": 0.7810441317665336,
|
| 654 |
+
"eval_loss": 0.10385506600141525,
|
| 655 |
+
"eval_precision": 0.78621070532204,
|
| 656 |
+
"eval_recall": 0.7759450190366459,
|
| 657 |
+
"eval_runtime": 480.9669,
|
| 658 |
+
"eval_samples_per_second": 59.545,
|
| 659 |
+
"eval_steps_per_second": 1.191,
|
| 660 |
+
"step": 25000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.3431039235504914,
|
| 664 |
+
"grad_norm": 0.6759513020515442,
|
| 665 |
+
"learning_rate": 1.0627951851511534e-05,
|
| 666 |
+
"loss": 0.1007,
|
| 667 |
+
"step": 25500
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.389047137737756,
|
| 671 |
+
"grad_norm": 0.9079370498657227,
|
| 672 |
+
"learning_rate": 1.0444178994762475e-05,
|
| 673 |
+
"loss": 0.1008,
|
| 674 |
+
"step": 26000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.389047137737756,
|
| 678 |
+
"eval_accuracy": 0.960218026129675,
|
| 679 |
+
"eval_f1": 0.7791951377937008,
|
| 680 |
+
"eval_loss": 0.10625031590461731,
|
| 681 |
+
"eval_precision": 0.7831873122488701,
|
| 682 |
+
"eval_recall": 0.7752434559000111,
|
| 683 |
+
"eval_runtime": 480.1994,
|
| 684 |
+
"eval_samples_per_second": 59.64,
|
| 685 |
+
"eval_steps_per_second": 1.193,
|
| 686 |
+
"step": 26000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.4349903519250207,
|
| 690 |
+
"grad_norm": 0.5865328907966614,
|
| 691 |
+
"learning_rate": 1.0260406138013416e-05,
|
| 692 |
+
"loss": 0.1009,
|
| 693 |
+
"step": 26500
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.4809335661122853,
|
| 697 |
+
"grad_norm": 0.4314309060573578,
|
| 698 |
+
"learning_rate": 1.0076633281264359e-05,
|
| 699 |
+
"loss": 0.1003,
|
| 700 |
+
"step": 27000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.4809335661122853,
|
| 704 |
+
"eval_accuracy": 0.9607592257423434,
|
| 705 |
+
"eval_f1": 0.7807987830560178,
|
| 706 |
+
"eval_loss": 0.10385860502719879,
|
| 707 |
+
"eval_precision": 0.7889295945350374,
|
| 708 |
+
"eval_recall": 0.7728338563576461,
|
| 709 |
+
"eval_runtime": 480.1646,
|
| 710 |
+
"eval_samples_per_second": 59.644,
|
| 711 |
+
"eval_steps_per_second": 1.193,
|
| 712 |
+
"step": 27000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.52687678029955,
|
| 716 |
+
"grad_norm": 0.5162900686264038,
|
| 717 |
+
"learning_rate": 9.8928604245153e-06,
|
| 718 |
+
"loss": 0.102,
|
| 719 |
+
"step": 27500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.572819994486814,
|
| 723 |
+
"grad_norm": 0.8881911039352417,
|
| 724 |
+
"learning_rate": 9.709087567766241e-06,
|
| 725 |
+
"loss": 0.0998,
|
| 726 |
+
"step": 28000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.572819994486814,
|
| 730 |
+
"eval_accuracy": 0.9608099235983311,
|
| 731 |
+
"eval_f1": 0.7834099891185191,
|
| 732 |
+
"eval_loss": 0.10304800420999527,
|
| 733 |
+
"eval_precision": 0.7829613019033707,
|
| 734 |
+
"eval_recall": 0.7838591908818379,
|
| 735 |
+
"eval_runtime": 481.0354,
|
| 736 |
+
"eval_samples_per_second": 59.536,
|
| 737 |
+
"eval_steps_per_second": 1.191,
|
| 738 |
+
"step": 28000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.618763208674079,
|
| 742 |
+
"grad_norm": 0.36895298957824707,
|
| 743 |
+
"learning_rate": 9.525314711017184e-06,
|
| 744 |
+
"loss": 0.0989,
|
| 745 |
+
"step": 28500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.6647064228613435,
|
| 749 |
+
"grad_norm": 0.4097418785095215,
|
| 750 |
+
"learning_rate": 9.341541854268126e-06,
|
| 751 |
+
"loss": 0.0991,
|
| 752 |
+
"step": 29000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.6647064228613435,
|
| 756 |
+
"eval_accuracy": 0.9608473132671219,
|
| 757 |
+
"eval_f1": 0.7830652507074841,
|
| 758 |
+
"eval_loss": 0.10377328097820282,
|
| 759 |
+
"eval_precision": 0.7843967022702352,
|
| 760 |
+
"eval_recall": 0.7817383115533957,
|
| 761 |
+
"eval_runtime": 494.1609,
|
| 762 |
+
"eval_samples_per_second": 57.955,
|
| 763 |
+
"eval_steps_per_second": 1.16,
|
| 764 |
+
"step": 29000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.7106496370486077,
|
| 768 |
+
"grad_norm": 0.4404696524143219,
|
| 769 |
+
"learning_rate": 9.157768997519067e-06,
|
| 770 |
+
"loss": 0.0977,
|
| 771 |
+
"step": 29500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.7565928512358724,
|
| 775 |
+
"grad_norm": 0.45993557572364807,
|
| 776 |
+
"learning_rate": 8.97399614077001e-06,
|
| 777 |
+
"loss": 0.0971,
|
| 778 |
+
"step": 30000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.7565928512358724,
|
| 782 |
+
"eval_accuracy": 0.9610475697982732,
|
| 783 |
+
"eval_f1": 0.7825106312355632,
|
| 784 |
+
"eval_loss": 0.10452987253665924,
|
| 785 |
+
"eval_precision": 0.7890627357701161,
|
| 786 |
+
"eval_recall": 0.7760664434256789,
|
| 787 |
+
"eval_runtime": 494.0836,
|
| 788 |
+
"eval_samples_per_second": 57.964,
|
| 789 |
+
"eval_steps_per_second": 1.16,
|
| 790 |
+
"step": 30000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.802536065423137,
|
| 794 |
+
"grad_norm": 0.506994366645813,
|
| 795 |
+
"learning_rate": 8.79022328402095e-06,
|
| 796 |
+
"loss": 0.0965,
|
| 797 |
+
"step": 30500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.8484792796104017,
|
| 801 |
+
"grad_norm": 0.6458877325057983,
|
| 802 |
+
"learning_rate": 8.606450427271894e-06,
|
| 803 |
+
"loss": 0.0961,
|
| 804 |
+
"step": 31000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.8484792796104017,
|
| 808 |
+
"eval_accuracy": 0.9609030809087084,
|
| 809 |
+
"eval_f1": 0.7821163878725582,
|
| 810 |
+
"eval_loss": 0.10469945520162582,
|
| 811 |
+
"eval_precision": 0.788239130911403,
|
| 812 |
+
"eval_recall": 0.7760880299837292,
|
| 813 |
+
"eval_runtime": 493.3004,
|
| 814 |
+
"eval_samples_per_second": 58.056,
|
| 815 |
+
"eval_steps_per_second": 1.162,
|
| 816 |
+
"step": 31000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.894422493797666,
|
| 820 |
+
"grad_norm": 0.5674518942832947,
|
| 821 |
+
"learning_rate": 8.422677570522835e-06,
|
| 822 |
+
"loss": 0.0968,
|
| 823 |
+
"step": 31500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.9403657079849306,
|
| 827 |
+
"grad_norm": 0.6595680117607117,
|
| 828 |
+
"learning_rate": 8.238904713773776e-06,
|
| 829 |
+
"loss": 0.0958,
|
| 830 |
+
"step": 32000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.9403657079849306,
|
| 834 |
+
"eval_accuracy": 0.9610779885118659,
|
| 835 |
+
"eval_f1": 0.7836532860065301,
|
| 836 |
+
"eval_loss": 0.10300234705209732,
|
| 837 |
+
"eval_precision": 0.7869283784408849,
|
| 838 |
+
"eval_recall": 0.7804053415937895,
|
| 839 |
+
"eval_runtime": 493.1751,
|
| 840 |
+
"eval_samples_per_second": 58.071,
|
| 841 |
+
"eval_steps_per_second": 1.162,
|
| 842 |
+
"step": 32000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.9863089221721952,
|
| 846 |
+
"grad_norm": 0.5502172112464905,
|
| 847 |
+
"learning_rate": 8.055131857024719e-06,
|
| 848 |
+
"loss": 0.0971,
|
| 849 |
+
"step": 32500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.03225213635946,
|
| 853 |
+
"grad_norm": 0.5948086380958557,
|
| 854 |
+
"learning_rate": 7.87135900027566e-06,
|
| 855 |
+
"loss": 0.0963,
|
| 856 |
+
"step": 33000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.03225213635946,
|
| 860 |
+
"eval_accuracy": 0.9608828017663134,
|
| 861 |
+
"eval_f1": 0.7828877352895777,
|
| 862 |
+
"eval_loss": 0.10367628186941147,
|
| 863 |
+
"eval_precision": 0.7857005030479105,
|
| 864 |
+
"eval_recall": 0.7800950348218164,
|
| 865 |
+
"eval_runtime": 492.9957,
|
| 866 |
+
"eval_samples_per_second": 58.092,
|
| 867 |
+
"eval_steps_per_second": 1.162,
|
| 868 |
+
"step": 33000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 3.078195350546724,
|
| 872 |
+
"grad_norm": 0.5747931599617004,
|
| 873 |
+
"learning_rate": 7.687586143526601e-06,
|
| 874 |
+
"loss": 0.0961,
|
| 875 |
+
"step": 33500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 3.1241385647339888,
|
| 879 |
+
"grad_norm": 0.5392933487892151,
|
| 880 |
+
"learning_rate": 7.503813286777543e-06,
|
| 881 |
+
"loss": 0.0972,
|
| 882 |
+
"step": 34000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.1241385647339888,
|
| 886 |
+
"eval_accuracy": 0.9612465588830248,
|
| 887 |
+
"eval_f1": 0.7833850043316463,
|
| 888 |
+
"eval_loss": 0.10355565696954727,
|
| 889 |
+
"eval_precision": 0.7910026930303056,
|
| 890 |
+
"eval_recall": 0.7759126391995704,
|
| 891 |
+
"eval_runtime": 493.4779,
|
| 892 |
+
"eval_samples_per_second": 58.035,
|
| 893 |
+
"eval_steps_per_second": 1.161,
|
| 894 |
+
"step": 34000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.1700817789212534,
|
| 898 |
+
"grad_norm": 0.47470977902412415,
|
| 899 |
+
"learning_rate": 7.3200404300284854e-06,
|
| 900 |
+
"loss": 0.0963,
|
| 901 |
+
"step": 34500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.216024993108518,
|
| 905 |
+
"grad_norm": 0.4675300121307373,
|
| 906 |
+
"learning_rate": 7.1362675732794275e-06,
|
| 907 |
+
"loss": 0.0966,
|
| 908 |
+
"step": 35000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.216024993108518,
|
| 912 |
+
"eval_accuracy": 0.9612091692142339,
|
| 913 |
+
"eval_f1": 0.7841735299101847,
|
| 914 |
+
"eval_loss": 0.1029718816280365,
|
| 915 |
+
"eval_precision": 0.7879947905314094,
|
| 916 |
+
"eval_recall": 0.7803891516752518,
|
| 917 |
+
"eval_runtime": 493.9167,
|
| 918 |
+
"eval_samples_per_second": 57.983,
|
| 919 |
+
"eval_steps_per_second": 1.16,
|
| 920 |
+
"step": 35000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.2619682072957823,
|
| 924 |
+
"grad_norm": 0.65328049659729,
|
| 925 |
+
"learning_rate": 6.9524947165303695e-06,
|
| 926 |
+
"loss": 0.0981,
|
| 927 |
+
"step": 35500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.307911421483047,
|
| 931 |
+
"grad_norm": 0.8536853194236755,
|
| 932 |
+
"learning_rate": 6.768721859781311e-06,
|
| 933 |
+
"loss": 0.0972,
|
| 934 |
+
"step": 36000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.307911421483047,
|
| 938 |
+
"eval_accuracy": 0.9613213382206066,
|
| 939 |
+
"eval_f1": 0.7841876799047575,
|
| 940 |
+
"eval_loss": 0.10238692909479141,
|
| 941 |
+
"eval_precision": 0.7899809695924207,
|
| 942 |
+
"eval_recall": 0.7784787412878,
|
| 943 |
+
"eval_runtime": 493.9879,
|
| 944 |
+
"eval_samples_per_second": 57.975,
|
| 945 |
+
"eval_steps_per_second": 1.16,
|
| 946 |
+
"step": 36000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.3538546356703116,
|
| 950 |
+
"grad_norm": 0.4792385995388031,
|
| 951 |
+
"learning_rate": 6.584949003032253e-06,
|
| 952 |
+
"loss": 0.0961,
|
| 953 |
+
"step": 36500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.399797849857576,
|
| 957 |
+
"grad_norm": 0.5664140582084656,
|
| 958 |
+
"learning_rate": 6.401176146283195e-06,
|
| 959 |
+
"loss": 0.0961,
|
| 960 |
+
"step": 37000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.399797849857576,
|
| 964 |
+
"eval_accuracy": 0.9612731752574184,
|
| 965 |
+
"eval_f1": 0.7838260321119623,
|
| 966 |
+
"eval_loss": 0.10364777594804764,
|
| 967 |
+
"eval_precision": 0.7897582688488667,
|
| 968 |
+
"eval_recall": 0.7779822504526431,
|
| 969 |
+
"eval_runtime": 487.6212,
|
| 970 |
+
"eval_samples_per_second": 58.732,
|
| 971 |
+
"eval_steps_per_second": 1.175,
|
| 972 |
+
"step": 37000
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 3.4457410640448405,
|
| 976 |
+
"grad_norm": 0.4458509087562561,
|
| 977 |
+
"learning_rate": 6.217403289534136e-06,
|
| 978 |
+
"loss": 0.0956,
|
| 979 |
+
"step": 37500
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 3.491684278232105,
|
| 983 |
+
"grad_norm": 1.0309734344482422,
|
| 984 |
+
"learning_rate": 6.033630432785078e-06,
|
| 985 |
+
"loss": 0.0968,
|
| 986 |
+
"step": 38000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.491684278232105,
|
| 990 |
+
"eval_accuracy": 0.9613644313981962,
|
| 991 |
+
"eval_f1": 0.7849622795571747,
|
| 992 |
+
"eval_loss": 0.10237538069486618,
|
| 993 |
+
"eval_precision": 0.7891754053427515,
|
| 994 |
+
"eval_recall": 0.7807938996386949,
|
| 995 |
+
"eval_runtime": 489.0957,
|
| 996 |
+
"eval_samples_per_second": 58.555,
|
| 997 |
+
"eval_steps_per_second": 1.172,
|
| 998 |
+
"step": 38000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.53762749241937,
|
| 1002 |
+
"grad_norm": 0.6991232633590698,
|
| 1003 |
+
"learning_rate": 5.84985757603602e-06,
|
| 1004 |
+
"loss": 0.0964,
|
| 1005 |
+
"step": 38500
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.5835707066066345,
|
| 1009 |
+
"grad_norm": 0.6872137784957886,
|
| 1010 |
+
"learning_rate": 5.666084719286962e-06,
|
| 1011 |
+
"loss": 0.0956,
|
| 1012 |
+
"step": 39000
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 3.5835707066066345,
|
| 1016 |
+
"eval_accuracy": 0.9613866117101908,
|
| 1017 |
+
"eval_f1": 0.7850481992416146,
|
| 1018 |
+
"eval_loss": 0.1031898632645607,
|
| 1019 |
+
"eval_precision": 0.789164428569481,
|
| 1020 |
+
"eval_recall": 0.7809746870623663,
|
| 1021 |
+
"eval_runtime": 488.2001,
|
| 1022 |
+
"eval_samples_per_second": 58.662,
|
| 1023 |
+
"eval_steps_per_second": 1.174,
|
| 1024 |
+
"step": 39000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.6295139207938987,
|
| 1028 |
+
"grad_norm": 0.5371155738830566,
|
| 1029 |
+
"learning_rate": 5.482311862537903e-06,
|
| 1030 |
+
"loss": 0.0947,
|
| 1031 |
+
"step": 39500
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.6754571349811633,
|
| 1035 |
+
"grad_norm": 0.5987829566001892,
|
| 1036 |
+
"learning_rate": 5.298539005788845e-06,
|
| 1037 |
+
"loss": 0.0946,
|
| 1038 |
+
"step": 40000
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.6754571349811633,
|
| 1042 |
+
"eval_accuracy": 0.9612731752574184,
|
| 1043 |
+
"eval_f1": 0.7850010409935133,
|
| 1044 |
+
"eval_loss": 0.10323267430067062,
|
| 1045 |
+
"eval_precision": 0.7866217618545723,
|
| 1046 |
+
"eval_recall": 0.7833869849244876,
|
| 1047 |
+
"eval_runtime": 488.7815,
|
| 1048 |
+
"eval_samples_per_second": 58.593,
|
| 1049 |
+
"eval_steps_per_second": 1.172,
|
| 1050 |
+
"step": 40000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.7214003491684275,
|
| 1054 |
+
"grad_norm": 0.4283543825149536,
|
| 1055 |
+
"learning_rate": 5.114766149039787e-06,
|
| 1056 |
+
"loss": 0.0931,
|
| 1057 |
+
"step": 40500
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 3.767343563355692,
|
| 1061 |
+
"grad_norm": 1.0369564294815063,
|
| 1062 |
+
"learning_rate": 4.9309932922907285e-06,
|
| 1063 |
+
"loss": 0.0933,
|
| 1064 |
+
"step": 41000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.767343563355692,
|
| 1068 |
+
"eval_accuracy": 0.9615013156093629,
|
| 1069 |
+
"eval_f1": 0.7854287067997648,
|
| 1070 |
+
"eval_loss": 0.10276814550161362,
|
| 1071 |
+
"eval_precision": 0.7903677069273602,
|
| 1072 |
+
"eval_recall": 0.780551050860629,
|
| 1073 |
+
"eval_runtime": 488.7183,
|
| 1074 |
+
"eval_samples_per_second": 58.6,
|
| 1075 |
+
"eval_steps_per_second": 1.172,
|
| 1076 |
+
"step": 41000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.813286777542957,
|
| 1080 |
+
"grad_norm": 0.5058717131614685,
|
| 1081 |
+
"learning_rate": 4.7472204355416705e-06,
|
| 1082 |
+
"loss": 0.0914,
|
| 1083 |
+
"step": 41500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.8592299917302215,
|
| 1087 |
+
"grad_norm": 0.5976991057395935,
|
| 1088 |
+
"learning_rate": 4.5634475787926126e-06,
|
| 1089 |
+
"loss": 0.0928,
|
| 1090 |
+
"step": 42000
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.8592299917302215,
|
| 1094 |
+
"eval_accuracy": 0.9614994144397634,
|
| 1095 |
+
"eval_f1": 0.784492448549999,
|
| 1096 |
+
"eval_loss": 0.1031479462981224,
|
| 1097 |
+
"eval_precision": 0.7923046862099713,
|
| 1098 |
+
"eval_recall": 0.7768327662364646,
|
| 1099 |
+
"eval_runtime": 489.9123,
|
| 1100 |
+
"eval_samples_per_second": 58.457,
|
| 1101 |
+
"eval_steps_per_second": 1.17,
|
| 1102 |
+
"step": 42000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.905173205917486,
|
| 1106 |
+
"grad_norm": 0.45505064725875854,
|
| 1107 |
+
"learning_rate": 4.379674722043555e-06,
|
| 1108 |
+
"loss": 0.0922,
|
| 1109 |
+
"step": 42500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.9511164201047504,
|
| 1113 |
+
"grad_norm": 0.5285763740539551,
|
| 1114 |
+
"learning_rate": 4.195901865294497e-06,
|
| 1115 |
+
"loss": 0.0924,
|
| 1116 |
+
"step": 43000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 3.9511164201047504,
|
| 1120 |
+
"eval_accuracy": 0.961282681105416,
|
| 1121 |
+
"eval_f1": 0.7860457849952998,
|
| 1122 |
+
"eval_loss": 0.10335655510425568,
|
| 1123 |
+
"eval_precision": 0.7846593154850732,
|
| 1124 |
+
"eval_recall": 0.7874371628786755,
|
| 1125 |
+
"eval_runtime": 488.6406,
|
| 1126 |
+
"eval_samples_per_second": 58.61,
|
| 1127 |
+
"eval_steps_per_second": 1.173,
|
| 1128 |
+
"step": 43000
|
| 1129 |
+
}
|
| 1130 |
+
],
|
| 1131 |
+
"logging_steps": 500,
|
| 1132 |
+
"max_steps": 54415,
|
| 1133 |
+
"num_input_tokens_seen": 0,
|
| 1134 |
+
"num_train_epochs": 5,
|
| 1135 |
+
"save_steps": 1000,
|
| 1136 |
+
"stateful_callbacks": {
|
| 1137 |
+
"TrainerControl": {
|
| 1138 |
+
"args": {
|
| 1139 |
+
"should_epoch_stop": false,
|
| 1140 |
+
"should_evaluate": false,
|
| 1141 |
+
"should_log": false,
|
| 1142 |
+
"should_save": true,
|
| 1143 |
+
"should_training_stop": false
|
| 1144 |
+
},
|
| 1145 |
+
"attributes": {}
|
| 1146 |
+
}
|
| 1147 |
+
},
|
| 1148 |
+
"total_flos": 4.998882777541608e+17,
|
| 1149 |
+
"train_batch_size": 50,
|
| 1150 |
+
"trial_name": null,
|
| 1151 |
+
"trial_params": null
|
| 1152 |
+
}
|
checkpoint-43000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac4077e59dc9a8933d46bf3eed4a423b32cc4558c1708705565ee8cbfbce624c
|
| 3 |
+
size 5841
|