Upload 8 files
Browse files- added_tokens.json +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer_config.json +59 -0
- trainer_state.json +1004 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 3072,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"legacy": true,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.52.3",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7801e20a3633eff11b1b742b47313598ba5facd6844606294182734dba0e69a5
|
| 3 |
+
size 737719272
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 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": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 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": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1004 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 876,
|
| 3 |
+
"best_metric": 0.9498842067308986,
|
| 4 |
+
"best_model_checkpoint": "./saved_best/sst2_DeBERTa-V3-20000/full_text/checkpoint-876",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1314,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0228310502283105,
|
| 14 |
+
"grad_norm": 44412.7421875,
|
| 15 |
+
"learning_rate": 1.9863013698630137e-05,
|
| 16 |
+
"loss": 0.7087,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.045662100456621,
|
| 21 |
+
"grad_norm": 93703.3984375,
|
| 22 |
+
"learning_rate": 1.971080669710807e-05,
|
| 23 |
+
"loss": 0.663,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0684931506849315,
|
| 28 |
+
"grad_norm": 285524.21875,
|
| 29 |
+
"learning_rate": 1.9558599695585997e-05,
|
| 30 |
+
"loss": 0.5619,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.091324200913242,
|
| 35 |
+
"grad_norm": 152150.90625,
|
| 36 |
+
"learning_rate": 1.940639269406393e-05,
|
| 37 |
+
"loss": 0.4453,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1141552511415525,
|
| 42 |
+
"grad_norm": 540688.25,
|
| 43 |
+
"learning_rate": 1.9254185692541858e-05,
|
| 44 |
+
"loss": 0.3976,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.136986301369863,
|
| 49 |
+
"grad_norm": 898374.5625,
|
| 50 |
+
"learning_rate": 1.910197869101979e-05,
|
| 51 |
+
"loss": 0.3562,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1598173515981735,
|
| 56 |
+
"grad_norm": 247806.78125,
|
| 57 |
+
"learning_rate": 1.8949771689497718e-05,
|
| 58 |
+
"loss": 0.3759,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.182648401826484,
|
| 63 |
+
"grad_norm": 937358.4375,
|
| 64 |
+
"learning_rate": 1.879756468797565e-05,
|
| 65 |
+
"loss": 0.2397,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2054794520547945,
|
| 70 |
+
"grad_norm": 640270.1875,
|
| 71 |
+
"learning_rate": 1.8645357686453578e-05,
|
| 72 |
+
"loss": 0.2732,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.228310502283105,
|
| 77 |
+
"grad_norm": 852069.125,
|
| 78 |
+
"learning_rate": 1.849315068493151e-05,
|
| 79 |
+
"loss": 0.261,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2511415525114155,
|
| 84 |
+
"grad_norm": 360171.65625,
|
| 85 |
+
"learning_rate": 1.8340943683409438e-05,
|
| 86 |
+
"loss": 0.2899,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.273972602739726,
|
| 91 |
+
"grad_norm": 457001.71875,
|
| 92 |
+
"learning_rate": 1.818873668188737e-05,
|
| 93 |
+
"loss": 0.2301,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2968036529680365,
|
| 98 |
+
"grad_norm": 903636.25,
|
| 99 |
+
"learning_rate": 1.80365296803653e-05,
|
| 100 |
+
"loss": 0.2055,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.319634703196347,
|
| 105 |
+
"grad_norm": 712907.75,
|
| 106 |
+
"learning_rate": 1.788432267884323e-05,
|
| 107 |
+
"loss": 0.1715,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3424657534246575,
|
| 112 |
+
"grad_norm": 196477.375,
|
| 113 |
+
"learning_rate": 1.773211567732116e-05,
|
| 114 |
+
"loss": 0.1927,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.365296803652968,
|
| 119 |
+
"grad_norm": 570202.375,
|
| 120 |
+
"learning_rate": 1.757990867579909e-05,
|
| 121 |
+
"loss": 0.2912,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3881278538812785,
|
| 126 |
+
"grad_norm": 586032.9375,
|
| 127 |
+
"learning_rate": 1.742770167427702e-05,
|
| 128 |
+
"loss": 0.2795,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.410958904109589,
|
| 133 |
+
"grad_norm": 394806.1875,
|
| 134 |
+
"learning_rate": 1.727549467275495e-05,
|
| 135 |
+
"loss": 0.2906,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4337899543378995,
|
| 140 |
+
"grad_norm": 190110.453125,
|
| 141 |
+
"learning_rate": 1.712328767123288e-05,
|
| 142 |
+
"loss": 0.2747,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.45662100456621,
|
| 147 |
+
"grad_norm": 127135.625,
|
| 148 |
+
"learning_rate": 1.6971080669710807e-05,
|
| 149 |
+
"loss": 0.1809,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4794520547945205,
|
| 154 |
+
"grad_norm": 623488.9375,
|
| 155 |
+
"learning_rate": 1.681887366818874e-05,
|
| 156 |
+
"loss": 0.1913,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.502283105022831,
|
| 161 |
+
"grad_norm": 133701.390625,
|
| 162 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 163 |
+
"loss": 0.1946,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5251141552511416,
|
| 168 |
+
"grad_norm": 310701.9375,
|
| 169 |
+
"learning_rate": 1.65144596651446e-05,
|
| 170 |
+
"loss": 0.2091,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.547945205479452,
|
| 175 |
+
"grad_norm": 355620.1875,
|
| 176 |
+
"learning_rate": 1.6362252663622528e-05,
|
| 177 |
+
"loss": 0.2112,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5707762557077626,
|
| 182 |
+
"grad_norm": 421425.53125,
|
| 183 |
+
"learning_rate": 1.6210045662100456e-05,
|
| 184 |
+
"loss": 0.23,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.593607305936073,
|
| 189 |
+
"grad_norm": 138180.75,
|
| 190 |
+
"learning_rate": 1.6057838660578388e-05,
|
| 191 |
+
"loss": 0.1955,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6164383561643836,
|
| 196 |
+
"grad_norm": 261821.984375,
|
| 197 |
+
"learning_rate": 1.5905631659056316e-05,
|
| 198 |
+
"loss": 0.161,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.639269406392694,
|
| 203 |
+
"grad_norm": 298217.375,
|
| 204 |
+
"learning_rate": 1.5753424657534248e-05,
|
| 205 |
+
"loss": 0.1282,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6621004566210046,
|
| 210 |
+
"grad_norm": 235531.46875,
|
| 211 |
+
"learning_rate": 1.5601217656012176e-05,
|
| 212 |
+
"loss": 0.2325,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.684931506849315,
|
| 217 |
+
"grad_norm": 253014.921875,
|
| 218 |
+
"learning_rate": 1.5449010654490108e-05,
|
| 219 |
+
"loss": 0.154,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7077625570776256,
|
| 224 |
+
"grad_norm": 381513.53125,
|
| 225 |
+
"learning_rate": 1.5296803652968037e-05,
|
| 226 |
+
"loss": 0.2651,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.730593607305936,
|
| 231 |
+
"grad_norm": 423401.25,
|
| 232 |
+
"learning_rate": 1.5144596651445968e-05,
|
| 233 |
+
"loss": 0.1557,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7534246575342466,
|
| 238 |
+
"grad_norm": 575528.0625,
|
| 239 |
+
"learning_rate": 1.4992389649923897e-05,
|
| 240 |
+
"loss": 0.1561,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.776255707762557,
|
| 245 |
+
"grad_norm": 232859.34375,
|
| 246 |
+
"learning_rate": 1.4840182648401829e-05,
|
| 247 |
+
"loss": 0.1712,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7990867579908676,
|
| 252 |
+
"grad_norm": 173308.796875,
|
| 253 |
+
"learning_rate": 1.4687975646879757e-05,
|
| 254 |
+
"loss": 0.1656,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.821917808219178,
|
| 259 |
+
"grad_norm": 323457.78125,
|
| 260 |
+
"learning_rate": 1.4535768645357689e-05,
|
| 261 |
+
"loss": 0.247,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8447488584474886,
|
| 266 |
+
"grad_norm": 843081.0625,
|
| 267 |
+
"learning_rate": 1.4383561643835617e-05,
|
| 268 |
+
"loss": 0.1411,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.867579908675799,
|
| 273 |
+
"grad_norm": 308567.3125,
|
| 274 |
+
"learning_rate": 1.4231354642313549e-05,
|
| 275 |
+
"loss": 0.1978,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8904109589041096,
|
| 280 |
+
"grad_norm": 261897.671875,
|
| 281 |
+
"learning_rate": 1.4079147640791477e-05,
|
| 282 |
+
"loss": 0.1605,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.91324200913242,
|
| 287 |
+
"grad_norm": 248572.203125,
|
| 288 |
+
"learning_rate": 1.3926940639269409e-05,
|
| 289 |
+
"loss": 0.1991,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9360730593607306,
|
| 294 |
+
"grad_norm": 449893.96875,
|
| 295 |
+
"learning_rate": 1.3774733637747338e-05,
|
| 296 |
+
"loss": 0.1689,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.958904109589041,
|
| 301 |
+
"grad_norm": 339795.09375,
|
| 302 |
+
"learning_rate": 1.3622526636225268e-05,
|
| 303 |
+
"loss": 0.1599,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9817351598173516,
|
| 308 |
+
"grad_norm": 385646.6875,
|
| 309 |
+
"learning_rate": 1.3470319634703198e-05,
|
| 310 |
+
"loss": 0.1635,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0,
|
| 315 |
+
"eval_accuracy": 0.9455,
|
| 316 |
+
"eval_f1_macro": 0.9449213297203747,
|
| 317 |
+
"eval_f1_weighted": 0.9455084683455556,
|
| 318 |
+
"eval_loss": 0.14821970462799072,
|
| 319 |
+
"eval_runtime": 23.1775,
|
| 320 |
+
"eval_samples_per_second": 258.872,
|
| 321 |
+
"eval_steps_per_second": 8.111,
|
| 322 |
+
"step": 438
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.004566210045662,
|
| 326 |
+
"grad_norm": 153650.484375,
|
| 327 |
+
"learning_rate": 1.3318112633181128e-05,
|
| 328 |
+
"loss": 0.137,
|
| 329 |
+
"step": 440
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.0273972602739727,
|
| 333 |
+
"grad_norm": 213723.8125,
|
| 334 |
+
"learning_rate": 1.3165905631659058e-05,
|
| 335 |
+
"loss": 0.1054,
|
| 336 |
+
"step": 450
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.0502283105022832,
|
| 340 |
+
"grad_norm": 392386.3125,
|
| 341 |
+
"learning_rate": 1.3013698630136988e-05,
|
| 342 |
+
"loss": 0.0989,
|
| 343 |
+
"step": 460
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.0730593607305936,
|
| 347 |
+
"grad_norm": 96632.03125,
|
| 348 |
+
"learning_rate": 1.2861491628614916e-05,
|
| 349 |
+
"loss": 0.1945,
|
| 350 |
+
"step": 470
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.095890410958904,
|
| 354 |
+
"grad_norm": 55911.53125,
|
| 355 |
+
"learning_rate": 1.2709284627092848e-05,
|
| 356 |
+
"loss": 0.1288,
|
| 357 |
+
"step": 480
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.1187214611872145,
|
| 361 |
+
"grad_norm": 90336.921875,
|
| 362 |
+
"learning_rate": 1.2557077625570777e-05,
|
| 363 |
+
"loss": 0.2038,
|
| 364 |
+
"step": 490
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.1415525114155252,
|
| 368 |
+
"grad_norm": 233133.859375,
|
| 369 |
+
"learning_rate": 1.2404870624048708e-05,
|
| 370 |
+
"loss": 0.1572,
|
| 371 |
+
"step": 500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.1643835616438356,
|
| 375 |
+
"grad_norm": 555786.375,
|
| 376 |
+
"learning_rate": 1.2252663622526637e-05,
|
| 377 |
+
"loss": 0.1482,
|
| 378 |
+
"step": 510
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.187214611872146,
|
| 382 |
+
"grad_norm": 293657.71875,
|
| 383 |
+
"learning_rate": 1.2100456621004569e-05,
|
| 384 |
+
"loss": 0.1014,
|
| 385 |
+
"step": 520
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.2100456621004567,
|
| 389 |
+
"grad_norm": 382341.65625,
|
| 390 |
+
"learning_rate": 1.1948249619482497e-05,
|
| 391 |
+
"loss": 0.1039,
|
| 392 |
+
"step": 530
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.2328767123287672,
|
| 396 |
+
"grad_norm": 720489.3125,
|
| 397 |
+
"learning_rate": 1.1796042617960429e-05,
|
| 398 |
+
"loss": 0.1624,
|
| 399 |
+
"step": 540
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.2557077625570776,
|
| 403 |
+
"grad_norm": 328077.1875,
|
| 404 |
+
"learning_rate": 1.1643835616438357e-05,
|
| 405 |
+
"loss": 0.1379,
|
| 406 |
+
"step": 550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.278538812785388,
|
| 410 |
+
"grad_norm": 1656745.75,
|
| 411 |
+
"learning_rate": 1.1491628614916289e-05,
|
| 412 |
+
"loss": 0.1369,
|
| 413 |
+
"step": 560
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.3013698630136985,
|
| 417 |
+
"grad_norm": 206637.953125,
|
| 418 |
+
"learning_rate": 1.1339421613394217e-05,
|
| 419 |
+
"loss": 0.1307,
|
| 420 |
+
"step": 570
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.3242009132420092,
|
| 424 |
+
"grad_norm": 435248.15625,
|
| 425 |
+
"learning_rate": 1.1187214611872147e-05,
|
| 426 |
+
"loss": 0.1016,
|
| 427 |
+
"step": 580
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.3470319634703196,
|
| 431 |
+
"grad_norm": 540247.5,
|
| 432 |
+
"learning_rate": 1.1035007610350078e-05,
|
| 433 |
+
"loss": 0.1208,
|
| 434 |
+
"step": 590
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.36986301369863,
|
| 438 |
+
"grad_norm": 403679.25,
|
| 439 |
+
"learning_rate": 1.0882800608828008e-05,
|
| 440 |
+
"loss": 0.1142,
|
| 441 |
+
"step": 600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.3926940639269407,
|
| 445 |
+
"grad_norm": 223394.5625,
|
| 446 |
+
"learning_rate": 1.0730593607305938e-05,
|
| 447 |
+
"loss": 0.1179,
|
| 448 |
+
"step": 610
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.4155251141552512,
|
| 452 |
+
"grad_norm": 297122.65625,
|
| 453 |
+
"learning_rate": 1.0578386605783868e-05,
|
| 454 |
+
"loss": 0.1756,
|
| 455 |
+
"step": 620
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.4383561643835616,
|
| 459 |
+
"grad_norm": 304201.28125,
|
| 460 |
+
"learning_rate": 1.0426179604261796e-05,
|
| 461 |
+
"loss": 0.1735,
|
| 462 |
+
"step": 630
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.461187214611872,
|
| 466 |
+
"grad_norm": 681574.875,
|
| 467 |
+
"learning_rate": 1.0273972602739728e-05,
|
| 468 |
+
"loss": 0.0963,
|
| 469 |
+
"step": 640
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.4840182648401825,
|
| 473 |
+
"grad_norm": 152161.0,
|
| 474 |
+
"learning_rate": 1.0121765601217656e-05,
|
| 475 |
+
"loss": 0.1774,
|
| 476 |
+
"step": 650
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.5068493150684932,
|
| 480 |
+
"grad_norm": 116020.0078125,
|
| 481 |
+
"learning_rate": 9.969558599695586e-06,
|
| 482 |
+
"loss": 0.1417,
|
| 483 |
+
"step": 660
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.5296803652968036,
|
| 487 |
+
"grad_norm": 404737.28125,
|
| 488 |
+
"learning_rate": 9.817351598173517e-06,
|
| 489 |
+
"loss": 0.0877,
|
| 490 |
+
"step": 670
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.5525114155251143,
|
| 494 |
+
"grad_norm": 456195.40625,
|
| 495 |
+
"learning_rate": 9.665144596651447e-06,
|
| 496 |
+
"loss": 0.1193,
|
| 497 |
+
"step": 680
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.5753424657534247,
|
| 501 |
+
"grad_norm": 303811.40625,
|
| 502 |
+
"learning_rate": 9.512937595129377e-06,
|
| 503 |
+
"loss": 0.1195,
|
| 504 |
+
"step": 690
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.5981735159817352,
|
| 508 |
+
"grad_norm": 339725.40625,
|
| 509 |
+
"learning_rate": 9.360730593607307e-06,
|
| 510 |
+
"loss": 0.1166,
|
| 511 |
+
"step": 700
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.6210045662100456,
|
| 515 |
+
"grad_norm": 707433.0,
|
| 516 |
+
"learning_rate": 9.208523592085237e-06,
|
| 517 |
+
"loss": 0.1495,
|
| 518 |
+
"step": 710
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.643835616438356,
|
| 522 |
+
"grad_norm": 1326117.75,
|
| 523 |
+
"learning_rate": 9.056316590563167e-06,
|
| 524 |
+
"loss": 0.0757,
|
| 525 |
+
"step": 720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.6666666666666665,
|
| 529 |
+
"grad_norm": 167948.21875,
|
| 530 |
+
"learning_rate": 8.904109589041097e-06,
|
| 531 |
+
"loss": 0.0692,
|
| 532 |
+
"step": 730
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.6894977168949772,
|
| 536 |
+
"grad_norm": 129407.0234375,
|
| 537 |
+
"learning_rate": 8.751902587519027e-06,
|
| 538 |
+
"loss": 0.1005,
|
| 539 |
+
"step": 740
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.7123287671232876,
|
| 543 |
+
"grad_norm": 294357.59375,
|
| 544 |
+
"learning_rate": 8.599695585996957e-06,
|
| 545 |
+
"loss": 0.1871,
|
| 546 |
+
"step": 750
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.7351598173515983,
|
| 550 |
+
"grad_norm": 161314.6875,
|
| 551 |
+
"learning_rate": 8.447488584474887e-06,
|
| 552 |
+
"loss": 0.1187,
|
| 553 |
+
"step": 760
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.7579908675799087,
|
| 557 |
+
"grad_norm": 266825.75,
|
| 558 |
+
"learning_rate": 8.295281582952816e-06,
|
| 559 |
+
"loss": 0.099,
|
| 560 |
+
"step": 770
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.7808219178082192,
|
| 564 |
+
"grad_norm": 878077.375,
|
| 565 |
+
"learning_rate": 8.143074581430746e-06,
|
| 566 |
+
"loss": 0.0694,
|
| 567 |
+
"step": 780
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.8036529680365296,
|
| 571 |
+
"grad_norm": 434940.9375,
|
| 572 |
+
"learning_rate": 7.990867579908676e-06,
|
| 573 |
+
"loss": 0.084,
|
| 574 |
+
"step": 790
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.82648401826484,
|
| 578 |
+
"grad_norm": 551468.0625,
|
| 579 |
+
"learning_rate": 7.838660578386606e-06,
|
| 580 |
+
"loss": 0.095,
|
| 581 |
+
"step": 800
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.8493150684931505,
|
| 585 |
+
"grad_norm": 1308205.0,
|
| 586 |
+
"learning_rate": 7.686453576864536e-06,
|
| 587 |
+
"loss": 0.0996,
|
| 588 |
+
"step": 810
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.8721461187214612,
|
| 592 |
+
"grad_norm": 972998.125,
|
| 593 |
+
"learning_rate": 7.534246575342466e-06,
|
| 594 |
+
"loss": 0.1421,
|
| 595 |
+
"step": 820
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.8949771689497716,
|
| 599 |
+
"grad_norm": 89905.71875,
|
| 600 |
+
"learning_rate": 7.382039573820396e-06,
|
| 601 |
+
"loss": 0.1922,
|
| 602 |
+
"step": 830
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.9178082191780823,
|
| 606 |
+
"grad_norm": 928792.5625,
|
| 607 |
+
"learning_rate": 7.2298325722983265e-06,
|
| 608 |
+
"loss": 0.1608,
|
| 609 |
+
"step": 840
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.9406392694063928,
|
| 613 |
+
"grad_norm": 479650.34375,
|
| 614 |
+
"learning_rate": 7.077625570776257e-06,
|
| 615 |
+
"loss": 0.1509,
|
| 616 |
+
"step": 850
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.9634703196347032,
|
| 620 |
+
"grad_norm": 230009.890625,
|
| 621 |
+
"learning_rate": 6.925418569254187e-06,
|
| 622 |
+
"loss": 0.1297,
|
| 623 |
+
"step": 860
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.9863013698630136,
|
| 627 |
+
"grad_norm": 145690.90625,
|
| 628 |
+
"learning_rate": 6.773211567732117e-06,
|
| 629 |
+
"loss": 0.115,
|
| 630 |
+
"step": 870
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.0,
|
| 634 |
+
"eval_accuracy": 0.9503333333333334,
|
| 635 |
+
"eval_f1_macro": 0.9498842067308986,
|
| 636 |
+
"eval_f1_weighted": 0.9503776134208973,
|
| 637 |
+
"eval_loss": 0.1748909056186676,
|
| 638 |
+
"eval_runtime": 23.5667,
|
| 639 |
+
"eval_samples_per_second": 254.596,
|
| 640 |
+
"eval_steps_per_second": 7.977,
|
| 641 |
+
"step": 876
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.009132420091324,
|
| 645 |
+
"grad_norm": 394251.75,
|
| 646 |
+
"learning_rate": 6.621004566210046e-06,
|
| 647 |
+
"loss": 0.1026,
|
| 648 |
+
"step": 880
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.0319634703196345,
|
| 652 |
+
"grad_norm": 614454.5,
|
| 653 |
+
"learning_rate": 6.468797564687976e-06,
|
| 654 |
+
"loss": 0.0729,
|
| 655 |
+
"step": 890
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.0547945205479454,
|
| 659 |
+
"grad_norm": 60974.125,
|
| 660 |
+
"learning_rate": 6.316590563165906e-06,
|
| 661 |
+
"loss": 0.0719,
|
| 662 |
+
"step": 900
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.077625570776256,
|
| 666 |
+
"grad_norm": 20745.419921875,
|
| 667 |
+
"learning_rate": 6.164383561643836e-06,
|
| 668 |
+
"loss": 0.0629,
|
| 669 |
+
"step": 910
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.1004566210045663,
|
| 673 |
+
"grad_norm": 20693.703125,
|
| 674 |
+
"learning_rate": 6.012176560121766e-06,
|
| 675 |
+
"loss": 0.0986,
|
| 676 |
+
"step": 920
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.1232876712328768,
|
| 680 |
+
"grad_norm": 483461.34375,
|
| 681 |
+
"learning_rate": 5.8599695585996965e-06,
|
| 682 |
+
"loss": 0.0439,
|
| 683 |
+
"step": 930
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.146118721461187,
|
| 687 |
+
"grad_norm": 755613.375,
|
| 688 |
+
"learning_rate": 5.7077625570776266e-06,
|
| 689 |
+
"loss": 0.0714,
|
| 690 |
+
"step": 940
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.1689497716894977,
|
| 694 |
+
"grad_norm": 861670.0625,
|
| 695 |
+
"learning_rate": 5.555555555555557e-06,
|
| 696 |
+
"loss": 0.1343,
|
| 697 |
+
"step": 950
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.191780821917808,
|
| 701 |
+
"grad_norm": 357634.3125,
|
| 702 |
+
"learning_rate": 5.403348554033486e-06,
|
| 703 |
+
"loss": 0.0996,
|
| 704 |
+
"step": 960
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.2146118721461185,
|
| 708 |
+
"grad_norm": 32929.3828125,
|
| 709 |
+
"learning_rate": 5.251141552511416e-06,
|
| 710 |
+
"loss": 0.1417,
|
| 711 |
+
"step": 970
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.237442922374429,
|
| 715 |
+
"grad_norm": 1806.34765625,
|
| 716 |
+
"learning_rate": 5.098934550989346e-06,
|
| 717 |
+
"loss": 0.0378,
|
| 718 |
+
"step": 980
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.26027397260274,
|
| 722 |
+
"grad_norm": 15796.4052734375,
|
| 723 |
+
"learning_rate": 4.946727549467275e-06,
|
| 724 |
+
"loss": 0.1035,
|
| 725 |
+
"step": 990
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.2831050228310503,
|
| 729 |
+
"grad_norm": 313449.59375,
|
| 730 |
+
"learning_rate": 4.7945205479452054e-06,
|
| 731 |
+
"loss": 0.1561,
|
| 732 |
+
"step": 1000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.3059360730593608,
|
| 736 |
+
"grad_norm": 1646670.5,
|
| 737 |
+
"learning_rate": 4.6423135464231355e-06,
|
| 738 |
+
"loss": 0.0752,
|
| 739 |
+
"step": 1010
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.328767123287671,
|
| 743 |
+
"grad_norm": 2477.45751953125,
|
| 744 |
+
"learning_rate": 4.490106544901066e-06,
|
| 745 |
+
"loss": 0.0317,
|
| 746 |
+
"step": 1020
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.3515981735159817,
|
| 750 |
+
"grad_norm": 761541.4375,
|
| 751 |
+
"learning_rate": 4.337899543378996e-06,
|
| 752 |
+
"loss": 0.0831,
|
| 753 |
+
"step": 1030
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.374429223744292,
|
| 757 |
+
"grad_norm": 437790.9375,
|
| 758 |
+
"learning_rate": 4.185692541856926e-06,
|
| 759 |
+
"loss": 0.1715,
|
| 760 |
+
"step": 1040
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.3972602739726026,
|
| 764 |
+
"grad_norm": 904.0252075195312,
|
| 765 |
+
"learning_rate": 4.033485540334856e-06,
|
| 766 |
+
"loss": 0.069,
|
| 767 |
+
"step": 1050
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.4200913242009134,
|
| 771 |
+
"grad_norm": 25560.220703125,
|
| 772 |
+
"learning_rate": 3.881278538812785e-06,
|
| 773 |
+
"loss": 0.1431,
|
| 774 |
+
"step": 1060
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.442922374429224,
|
| 778 |
+
"grad_norm": 34890.45703125,
|
| 779 |
+
"learning_rate": 3.7290715372907157e-06,
|
| 780 |
+
"loss": 0.0754,
|
| 781 |
+
"step": 1070
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.4657534246575343,
|
| 785 |
+
"grad_norm": 1365.3736572265625,
|
| 786 |
+
"learning_rate": 3.5768645357686453e-06,
|
| 787 |
+
"loss": 0.1696,
|
| 788 |
+
"step": 1080
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.4885844748858448,
|
| 792 |
+
"grad_norm": 884040.75,
|
| 793 |
+
"learning_rate": 3.4246575342465754e-06,
|
| 794 |
+
"loss": 0.156,
|
| 795 |
+
"step": 1090
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.5114155251141552,
|
| 799 |
+
"grad_norm": 1091.47705078125,
|
| 800 |
+
"learning_rate": 3.2724505327245055e-06,
|
| 801 |
+
"loss": 0.1472,
|
| 802 |
+
"step": 1100
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.5342465753424657,
|
| 806 |
+
"grad_norm": 946496.0625,
|
| 807 |
+
"learning_rate": 3.120243531202435e-06,
|
| 808 |
+
"loss": 0.0868,
|
| 809 |
+
"step": 1110
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.557077625570776,
|
| 813 |
+
"grad_norm": 1407963.75,
|
| 814 |
+
"learning_rate": 2.9680365296803653e-06,
|
| 815 |
+
"loss": 0.103,
|
| 816 |
+
"step": 1120
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.5799086757990866,
|
| 820 |
+
"grad_norm": 158087.015625,
|
| 821 |
+
"learning_rate": 2.8158295281582954e-06,
|
| 822 |
+
"loss": 0.0216,
|
| 823 |
+
"step": 1130
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.602739726027397,
|
| 827 |
+
"grad_norm": 713.4439697265625,
|
| 828 |
+
"learning_rate": 2.6636225266362255e-06,
|
| 829 |
+
"loss": 0.2038,
|
| 830 |
+
"step": 1140
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.625570776255708,
|
| 834 |
+
"grad_norm": 1539.153076171875,
|
| 835 |
+
"learning_rate": 2.511415525114155e-06,
|
| 836 |
+
"loss": 0.1152,
|
| 837 |
+
"step": 1150
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.6484018264840183,
|
| 841 |
+
"grad_norm": 412512.21875,
|
| 842 |
+
"learning_rate": 2.3592085235920852e-06,
|
| 843 |
+
"loss": 0.0729,
|
| 844 |
+
"step": 1160
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.671232876712329,
|
| 848 |
+
"grad_norm": 193931.359375,
|
| 849 |
+
"learning_rate": 2.2070015220700153e-06,
|
| 850 |
+
"loss": 0.1043,
|
| 851 |
+
"step": 1170
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.6940639269406392,
|
| 855 |
+
"grad_norm": 7703.2265625,
|
| 856 |
+
"learning_rate": 2.0547945205479454e-06,
|
| 857 |
+
"loss": 0.0724,
|
| 858 |
+
"step": 1180
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.7168949771689497,
|
| 862 |
+
"grad_norm": 949454.0625,
|
| 863 |
+
"learning_rate": 1.9025875190258753e-06,
|
| 864 |
+
"loss": 0.1268,
|
| 865 |
+
"step": 1190
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.73972602739726,
|
| 869 |
+
"grad_norm": 2108.031982421875,
|
| 870 |
+
"learning_rate": 1.7503805175038052e-06,
|
| 871 |
+
"loss": 0.0483,
|
| 872 |
+
"step": 1200
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.762557077625571,
|
| 876 |
+
"grad_norm": 2277614.5,
|
| 877 |
+
"learning_rate": 1.5981735159817353e-06,
|
| 878 |
+
"loss": 0.1811,
|
| 879 |
+
"step": 1210
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.7853881278538815,
|
| 883 |
+
"grad_norm": 334.9802551269531,
|
| 884 |
+
"learning_rate": 1.4459665144596652e-06,
|
| 885 |
+
"loss": 0.1917,
|
| 886 |
+
"step": 1220
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.808219178082192,
|
| 890 |
+
"grad_norm": 1848023.375,
|
| 891 |
+
"learning_rate": 1.2937595129375953e-06,
|
| 892 |
+
"loss": 0.1201,
|
| 893 |
+
"step": 1230
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.8310502283105023,
|
| 897 |
+
"grad_norm": 229145.328125,
|
| 898 |
+
"learning_rate": 1.1415525114155251e-06,
|
| 899 |
+
"loss": 0.1832,
|
| 900 |
+
"step": 1240
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.853881278538813,
|
| 904 |
+
"grad_norm": 14015.669921875,
|
| 905 |
+
"learning_rate": 9.89345509893455e-07,
|
| 906 |
+
"loss": 0.1927,
|
| 907 |
+
"step": 1250
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.8767123287671232,
|
| 911 |
+
"grad_norm": 6147.142578125,
|
| 912 |
+
"learning_rate": 8.371385083713851e-07,
|
| 913 |
+
"loss": 0.1481,
|
| 914 |
+
"step": 1260
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.8995433789954337,
|
| 918 |
+
"grad_norm": 218.0597686767578,
|
| 919 |
+
"learning_rate": 6.849315068493151e-07,
|
| 920 |
+
"loss": 0.1186,
|
| 921 |
+
"step": 1270
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.922374429223744,
|
| 925 |
+
"grad_norm": 1167973.0,
|
| 926 |
+
"learning_rate": 5.327245053272451e-07,
|
| 927 |
+
"loss": 0.1563,
|
| 928 |
+
"step": 1280
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.9452054794520546,
|
| 932 |
+
"grad_norm": 2013.74072265625,
|
| 933 |
+
"learning_rate": 3.8051750380517503e-07,
|
| 934 |
+
"loss": 0.1224,
|
| 935 |
+
"step": 1290
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.968036529680365,
|
| 939 |
+
"grad_norm": 1919903.375,
|
| 940 |
+
"learning_rate": 2.2831050228310502e-07,
|
| 941 |
+
"loss": 0.1704,
|
| 942 |
+
"step": 1300
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.990867579908676,
|
| 946 |
+
"grad_norm": 1837018.125,
|
| 947 |
+
"learning_rate": 7.6103500761035e-08,
|
| 948 |
+
"loss": 0.1823,
|
| 949 |
+
"step": 1310
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 3.0,
|
| 953 |
+
"eval_accuracy": 0.9498333333333333,
|
| 954 |
+
"eval_f1_macro": 0.9492865735698077,
|
| 955 |
+
"eval_f1_weighted": 0.9498342109573517,
|
| 956 |
+
"eval_loss": 0.3995734751224518,
|
| 957 |
+
"eval_runtime": 23.8601,
|
| 958 |
+
"eval_samples_per_second": 251.466,
|
| 959 |
+
"eval_steps_per_second": 7.879,
|
| 960 |
+
"step": 1314
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.0,
|
| 964 |
+
"step": 1314,
|
| 965 |
+
"total_flos": 1381357813248000.0,
|
| 966 |
+
"train_loss": 0.16522950693806193,
|
| 967 |
+
"train_runtime": 510.5054,
|
| 968 |
+
"train_samples_per_second": 82.271,
|
| 969 |
+
"train_steps_per_second": 2.574
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.0,
|
| 973 |
+
"eval_accuracy": 0.9503333333333334,
|
| 974 |
+
"eval_f1_macro": 0.9498842067308986,
|
| 975 |
+
"eval_f1_weighted": 0.9503776134208973,
|
| 976 |
+
"eval_loss": 0.1748909056186676,
|
| 977 |
+
"eval_runtime": 23.9264,
|
| 978 |
+
"eval_samples_per_second": 250.769,
|
| 979 |
+
"eval_steps_per_second": 7.857,
|
| 980 |
+
"step": 1314
|
| 981 |
+
}
|
| 982 |
+
],
|
| 983 |
+
"logging_steps": 10,
|
| 984 |
+
"max_steps": 1314,
|
| 985 |
+
"num_input_tokens_seen": 0,
|
| 986 |
+
"num_train_epochs": 3,
|
| 987 |
+
"save_steps": 500,
|
| 988 |
+
"stateful_callbacks": {
|
| 989 |
+
"TrainerControl": {
|
| 990 |
+
"args": {
|
| 991 |
+
"should_epoch_stop": false,
|
| 992 |
+
"should_evaluate": false,
|
| 993 |
+
"should_log": false,
|
| 994 |
+
"should_save": true,
|
| 995 |
+
"should_training_stop": true
|
| 996 |
+
},
|
| 997 |
+
"attributes": {}
|
| 998 |
+
}
|
| 999 |
+
},
|
| 1000 |
+
"total_flos": 1381357813248000.0,
|
| 1001 |
+
"train_batch_size": 32,
|
| 1002 |
+
"trial_name": null,
|
| 1003 |
+
"trial_params": null
|
| 1004 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31324a68c8ef0f38c87f5cc95b0cb66c2cd3b341c4421a3b7b539e06a39dc1ee
|
| 3 |
+
size 5713
|