Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- checkpoint-1000/added_tokens.json +3 -0
- checkpoint-1000/config.json +51 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/special_tokens_map.json +15 -0
- checkpoint-1000/spm.model +3 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +59 -0
- checkpoint-1000/trainer_state.json +754 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-500/added_tokens.json +3 -0
- checkpoint-500/config.json +51 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/special_tokens_map.json +15 -0
- checkpoint-500/spm.model +3 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer_config.json +59 -0
- checkpoint-500/trainer_state.json +394 -0
- checkpoint-500/training_args.bin +3 -0
- config.json +51 -0
- label_mappings.json +16 -0
- logs/events.out.tfevents.1757320191.3332ba88c8b5.1966.0 +3 -0
- logs/events.out.tfevents.1757321096.3332ba88c8b5.1966.1 +3 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Communications",
|
| 14 |
+
"1": "Meals & Entertainment",
|
| 15 |
+
"2": "Office Expenses",
|
| 16 |
+
"3": "Transportation",
|
| 17 |
+
"4": "Travel"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Communications": 0,
|
| 23 |
+
"Meals & Entertainment": 1,
|
| 24 |
+
"Office Expenses": 2,
|
| 25 |
+
"Transportation": 3,
|
| 26 |
+
"Travel": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-07,
|
| 29 |
+
"legacy": true,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"max_relative_positions": -1,
|
| 32 |
+
"model_type": "deberta-v2",
|
| 33 |
+
"norm_rel_ebd": "layer_norm",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"pooler_dropout": 0,
|
| 38 |
+
"pooler_hidden_act": "gelu",
|
| 39 |
+
"pooler_hidden_size": 1024,
|
| 40 |
+
"pos_att_type": [
|
| 41 |
+
"p2c",
|
| 42 |
+
"c2p"
|
| 43 |
+
],
|
| 44 |
+
"position_biased_input": false,
|
| 45 |
+
"position_buckets": 256,
|
| 46 |
+
"relative_attention": true,
|
| 47 |
+
"share_att_key": true,
|
| 48 |
+
"transformers_version": "4.56.0",
|
| 49 |
+
"type_vocab_size": 0,
|
| 50 |
+
"vocab_size": 128100
|
| 51 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedd9af8427bde3c4f1532e3bbc4e33affed975368fd795fa717d4717a5e84a0
|
| 3 |
+
size 1740316748
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf0d68027f8b33e35216f21923780c5b50a483355844b3daa94f3700ff1fc66c
|
| 3 |
+
size 14645
|
checkpoint-1000/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 |
+
}
|
checkpoint-1000/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/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 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,754 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02,
|
| 14 |
+
"grad_norm": 8.39200210571289,
|
| 15 |
+
"learning_rate": 1.982e-05,
|
| 16 |
+
"loss": 1.5512,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04,
|
| 21 |
+
"grad_norm": 11.324227333068848,
|
| 22 |
+
"learning_rate": 1.9620000000000002e-05,
|
| 23 |
+
"loss": 1.1959,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 6.3719482421875,
|
| 29 |
+
"learning_rate": 1.942e-05,
|
| 30 |
+
"loss": 0.6321,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 8.07636547088623,
|
| 36 |
+
"learning_rate": 1.9220000000000002e-05,
|
| 37 |
+
"loss": 0.6085,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 3.1197566986083984,
|
| 43 |
+
"learning_rate": 1.902e-05,
|
| 44 |
+
"loss": 0.2591,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"grad_norm": 0.4907987117767334,
|
| 50 |
+
"learning_rate": 1.882e-05,
|
| 51 |
+
"loss": 0.0781,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14,
|
| 56 |
+
"grad_norm": 0.16266797482967377,
|
| 57 |
+
"learning_rate": 1.862e-05,
|
| 58 |
+
"loss": 0.0224,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16,
|
| 63 |
+
"grad_norm": 0.15413975715637207,
|
| 64 |
+
"learning_rate": 1.8420000000000003e-05,
|
| 65 |
+
"loss": 0.0102,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.18,
|
| 70 |
+
"grad_norm": 0.1077665239572525,
|
| 71 |
+
"learning_rate": 1.8220000000000002e-05,
|
| 72 |
+
"loss": 0.0048,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2,
|
| 77 |
+
"grad_norm": 0.05375492572784424,
|
| 78 |
+
"learning_rate": 1.802e-05,
|
| 79 |
+
"loss": 0.003,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22,
|
| 84 |
+
"grad_norm": 0.03678549453616142,
|
| 85 |
+
"learning_rate": 1.7820000000000002e-05,
|
| 86 |
+
"loss": 0.0023,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 0.04655584692955017,
|
| 92 |
+
"learning_rate": 1.762e-05,
|
| 93 |
+
"loss": 0.0019,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.26,
|
| 98 |
+
"grad_norm": 0.037836335599422455,
|
| 99 |
+
"learning_rate": 1.7420000000000003e-05,
|
| 100 |
+
"loss": 0.0018,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.28,
|
| 105 |
+
"grad_norm": 0.03111528977751732,
|
| 106 |
+
"learning_rate": 1.722e-05,
|
| 107 |
+
"loss": 0.0016,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3,
|
| 112 |
+
"grad_norm": 0.022478433325886726,
|
| 113 |
+
"learning_rate": 1.702e-05,
|
| 114 |
+
"loss": 0.0014,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"grad_norm": 0.019292104989290237,
|
| 120 |
+
"learning_rate": 1.682e-05,
|
| 121 |
+
"loss": 0.0013,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.34,
|
| 126 |
+
"grad_norm": 0.02150174230337143,
|
| 127 |
+
"learning_rate": 1.662e-05,
|
| 128 |
+
"loss": 0.0012,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.36,
|
| 133 |
+
"grad_norm": 0.016075951978564262,
|
| 134 |
+
"learning_rate": 1.6420000000000002e-05,
|
| 135 |
+
"loss": 0.001,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.38,
|
| 140 |
+
"grad_norm": 0.01365870051085949,
|
| 141 |
+
"learning_rate": 1.6220000000000004e-05,
|
| 142 |
+
"loss": 0.0009,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4,
|
| 147 |
+
"grad_norm": 0.01567169837653637,
|
| 148 |
+
"learning_rate": 1.6020000000000002e-05,
|
| 149 |
+
"loss": 0.0009,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.42,
|
| 154 |
+
"grad_norm": 0.010838769376277924,
|
| 155 |
+
"learning_rate": 1.582e-05,
|
| 156 |
+
"loss": 0.0008,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.44,
|
| 161 |
+
"grad_norm": 0.018331510946154594,
|
| 162 |
+
"learning_rate": 1.5620000000000003e-05,
|
| 163 |
+
"loss": 0.0008,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.46,
|
| 168 |
+
"grad_norm": 0.025574931874871254,
|
| 169 |
+
"learning_rate": 1.542e-05,
|
| 170 |
+
"loss": 0.0007,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.48,
|
| 175 |
+
"grad_norm": 0.023950673639774323,
|
| 176 |
+
"learning_rate": 1.5220000000000002e-05,
|
| 177 |
+
"loss": 0.0008,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5,
|
| 182 |
+
"grad_norm": 0.010618827305734158,
|
| 183 |
+
"learning_rate": 1.5020000000000002e-05,
|
| 184 |
+
"loss": 0.0007,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.52,
|
| 189 |
+
"grad_norm": 0.014874480664730072,
|
| 190 |
+
"learning_rate": 1.482e-05,
|
| 191 |
+
"loss": 0.0006,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.54,
|
| 196 |
+
"grad_norm": 0.011250246316194534,
|
| 197 |
+
"learning_rate": 1.462e-05,
|
| 198 |
+
"loss": 0.0006,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.56,
|
| 203 |
+
"grad_norm": 0.011498576030135155,
|
| 204 |
+
"learning_rate": 1.4420000000000001e-05,
|
| 205 |
+
"loss": 0.0006,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.58,
|
| 210 |
+
"grad_norm": 0.008709218353033066,
|
| 211 |
+
"learning_rate": 1.4220000000000001e-05,
|
| 212 |
+
"loss": 0.0005,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6,
|
| 217 |
+
"grad_norm": 0.010704316198825836,
|
| 218 |
+
"learning_rate": 1.402e-05,
|
| 219 |
+
"loss": 0.0005,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.62,
|
| 224 |
+
"grad_norm": 0.013085413724184036,
|
| 225 |
+
"learning_rate": 1.382e-05,
|
| 226 |
+
"loss": 0.0006,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.64,
|
| 231 |
+
"grad_norm": 0.010020424611866474,
|
| 232 |
+
"learning_rate": 1.3620000000000002e-05,
|
| 233 |
+
"loss": 0.0005,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.66,
|
| 238 |
+
"grad_norm": 0.0069733611308038235,
|
| 239 |
+
"learning_rate": 1.3420000000000002e-05,
|
| 240 |
+
"loss": 0.0005,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.68,
|
| 245 |
+
"grad_norm": 0.009822344407439232,
|
| 246 |
+
"learning_rate": 1.3220000000000002e-05,
|
| 247 |
+
"loss": 0.0005,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7,
|
| 252 |
+
"grad_norm": 0.010420722886919975,
|
| 253 |
+
"learning_rate": 1.302e-05,
|
| 254 |
+
"loss": 0.0004,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.72,
|
| 259 |
+
"grad_norm": 0.008276022970676422,
|
| 260 |
+
"learning_rate": 1.2820000000000001e-05,
|
| 261 |
+
"loss": 0.0004,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.74,
|
| 266 |
+
"grad_norm": 0.007726218551397324,
|
| 267 |
+
"learning_rate": 1.2620000000000001e-05,
|
| 268 |
+
"loss": 0.0004,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.76,
|
| 273 |
+
"grad_norm": 0.009340759366750717,
|
| 274 |
+
"learning_rate": 1.2420000000000001e-05,
|
| 275 |
+
"loss": 0.0004,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.78,
|
| 280 |
+
"grad_norm": 0.00625102873891592,
|
| 281 |
+
"learning_rate": 1.2220000000000002e-05,
|
| 282 |
+
"loss": 0.0004,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8,
|
| 287 |
+
"grad_norm": 0.009452459402382374,
|
| 288 |
+
"learning_rate": 1.202e-05,
|
| 289 |
+
"loss": 0.0003,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.82,
|
| 294 |
+
"grad_norm": 0.006577606778591871,
|
| 295 |
+
"learning_rate": 1.182e-05,
|
| 296 |
+
"loss": 0.0004,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.84,
|
| 301 |
+
"grad_norm": 0.005760726518929005,
|
| 302 |
+
"learning_rate": 1.162e-05,
|
| 303 |
+
"loss": 0.0003,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.86,
|
| 308 |
+
"grad_norm": 0.006589033640921116,
|
| 309 |
+
"learning_rate": 1.142e-05,
|
| 310 |
+
"loss": 0.0003,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.88,
|
| 315 |
+
"grad_norm": 0.007873634807765484,
|
| 316 |
+
"learning_rate": 1.1220000000000003e-05,
|
| 317 |
+
"loss": 0.0003,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9,
|
| 322 |
+
"grad_norm": 0.005279037170112133,
|
| 323 |
+
"learning_rate": 1.1020000000000001e-05,
|
| 324 |
+
"loss": 0.0003,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.92,
|
| 329 |
+
"grad_norm": 0.008107911795377731,
|
| 330 |
+
"learning_rate": 1.0820000000000001e-05,
|
| 331 |
+
"loss": 0.0003,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.94,
|
| 336 |
+
"grad_norm": 0.006266397424042225,
|
| 337 |
+
"learning_rate": 1.0620000000000002e-05,
|
| 338 |
+
"loss": 0.0003,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.96,
|
| 343 |
+
"grad_norm": 0.00688116904348135,
|
| 344 |
+
"learning_rate": 1.0420000000000002e-05,
|
| 345 |
+
"loss": 0.0003,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.98,
|
| 350 |
+
"grad_norm": 0.006354791112244129,
|
| 351 |
+
"learning_rate": 1.022e-05,
|
| 352 |
+
"loss": 0.0003,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.0,
|
| 357 |
+
"grad_norm": 0.02231195569038391,
|
| 358 |
+
"learning_rate": 1.002e-05,
|
| 359 |
+
"loss": 0.0003,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0,
|
| 364 |
+
"eval_accuracy": 1.0,
|
| 365 |
+
"eval_f1": 1.0,
|
| 366 |
+
"eval_loss": 8.804027311271057e-05,
|
| 367 |
+
"eval_runtime": 8.5077,
|
| 368 |
+
"eval_samples_per_second": 117.541,
|
| 369 |
+
"eval_steps_per_second": 14.693,
|
| 370 |
+
"step": 500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.02,
|
| 374 |
+
"grad_norm": 0.005330471321940422,
|
| 375 |
+
"learning_rate": 9.820000000000001e-06,
|
| 376 |
+
"loss": 0.0003,
|
| 377 |
+
"step": 510
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.04,
|
| 381 |
+
"grad_norm": 0.004275065381079912,
|
| 382 |
+
"learning_rate": 9.620000000000001e-06,
|
| 383 |
+
"loss": 0.0003,
|
| 384 |
+
"step": 520
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.06,
|
| 388 |
+
"grad_norm": 0.007796363439410925,
|
| 389 |
+
"learning_rate": 9.42e-06,
|
| 390 |
+
"loss": 0.0003,
|
| 391 |
+
"step": 530
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.08,
|
| 395 |
+
"grad_norm": 0.0044079492799937725,
|
| 396 |
+
"learning_rate": 9.220000000000002e-06,
|
| 397 |
+
"loss": 0.0003,
|
| 398 |
+
"step": 540
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.1,
|
| 402 |
+
"grad_norm": 0.00512820715084672,
|
| 403 |
+
"learning_rate": 9.020000000000002e-06,
|
| 404 |
+
"loss": 0.0003,
|
| 405 |
+
"step": 550
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.12,
|
| 409 |
+
"grad_norm": 0.006818364840000868,
|
| 410 |
+
"learning_rate": 8.82e-06,
|
| 411 |
+
"loss": 0.0052,
|
| 412 |
+
"step": 560
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.1400000000000001,
|
| 416 |
+
"grad_norm": 0.005178887862712145,
|
| 417 |
+
"learning_rate": 8.62e-06,
|
| 418 |
+
"loss": 0.0002,
|
| 419 |
+
"step": 570
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.16,
|
| 423 |
+
"grad_norm": 0.004207164514809847,
|
| 424 |
+
"learning_rate": 8.42e-06,
|
| 425 |
+
"loss": 0.0002,
|
| 426 |
+
"step": 580
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.18,
|
| 430 |
+
"grad_norm": 0.005639292765408754,
|
| 431 |
+
"learning_rate": 8.220000000000001e-06,
|
| 432 |
+
"loss": 0.0002,
|
| 433 |
+
"step": 590
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.2,
|
| 437 |
+
"grad_norm": 0.004071258008480072,
|
| 438 |
+
"learning_rate": 8.020000000000001e-06,
|
| 439 |
+
"loss": 0.0002,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.22,
|
| 444 |
+
"grad_norm": 0.0040369234047830105,
|
| 445 |
+
"learning_rate": 7.820000000000001e-06,
|
| 446 |
+
"loss": 0.0002,
|
| 447 |
+
"step": 610
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.24,
|
| 451 |
+
"grad_norm": 0.0072736297734081745,
|
| 452 |
+
"learning_rate": 7.620000000000001e-06,
|
| 453 |
+
"loss": 0.0002,
|
| 454 |
+
"step": 620
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.26,
|
| 458 |
+
"grad_norm": 0.003986729774624109,
|
| 459 |
+
"learning_rate": 7.420000000000001e-06,
|
| 460 |
+
"loss": 0.0002,
|
| 461 |
+
"step": 630
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.28,
|
| 465 |
+
"grad_norm": 0.008700714446604252,
|
| 466 |
+
"learning_rate": 7.22e-06,
|
| 467 |
+
"loss": 0.0002,
|
| 468 |
+
"step": 640
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.3,
|
| 472 |
+
"grad_norm": 0.004698322154581547,
|
| 473 |
+
"learning_rate": 7.0200000000000006e-06,
|
| 474 |
+
"loss": 0.0002,
|
| 475 |
+
"step": 650
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.32,
|
| 479 |
+
"grad_norm": 0.004479606170207262,
|
| 480 |
+
"learning_rate": 6.820000000000001e-06,
|
| 481 |
+
"loss": 0.0002,
|
| 482 |
+
"step": 660
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.34,
|
| 486 |
+
"grad_norm": 0.006120480131357908,
|
| 487 |
+
"learning_rate": 6.620000000000001e-06,
|
| 488 |
+
"loss": 0.0002,
|
| 489 |
+
"step": 670
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.3599999999999999,
|
| 493 |
+
"grad_norm": 0.0031735417433083057,
|
| 494 |
+
"learning_rate": 6.42e-06,
|
| 495 |
+
"loss": 0.0002,
|
| 496 |
+
"step": 680
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.38,
|
| 500 |
+
"grad_norm": 0.0037536039017140865,
|
| 501 |
+
"learning_rate": 6.220000000000001e-06,
|
| 502 |
+
"loss": 0.0002,
|
| 503 |
+
"step": 690
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.4,
|
| 507 |
+
"grad_norm": 0.0036679180338978767,
|
| 508 |
+
"learning_rate": 6.02e-06,
|
| 509 |
+
"loss": 0.0002,
|
| 510 |
+
"step": 700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.42,
|
| 514 |
+
"grad_norm": 0.005960715003311634,
|
| 515 |
+
"learning_rate": 5.82e-06,
|
| 516 |
+
"loss": 0.0002,
|
| 517 |
+
"step": 710
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.44,
|
| 521 |
+
"grad_norm": 0.006314941216260195,
|
| 522 |
+
"learning_rate": 5.620000000000001e-06,
|
| 523 |
+
"loss": 0.0004,
|
| 524 |
+
"step": 720
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.46,
|
| 528 |
+
"grad_norm": 0.005109549965709448,
|
| 529 |
+
"learning_rate": 5.420000000000001e-06,
|
| 530 |
+
"loss": 0.0002,
|
| 531 |
+
"step": 730
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.48,
|
| 535 |
+
"grad_norm": 0.003590966574847698,
|
| 536 |
+
"learning_rate": 5.220000000000001e-06,
|
| 537 |
+
"loss": 0.0002,
|
| 538 |
+
"step": 740
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.5,
|
| 542 |
+
"grad_norm": 0.004294182639569044,
|
| 543 |
+
"learning_rate": 5.02e-06,
|
| 544 |
+
"loss": 0.0002,
|
| 545 |
+
"step": 750
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.52,
|
| 549 |
+
"grad_norm": 0.004875560291111469,
|
| 550 |
+
"learning_rate": 4.8200000000000004e-06,
|
| 551 |
+
"loss": 0.0002,
|
| 552 |
+
"step": 760
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.54,
|
| 556 |
+
"grad_norm": 0.00659326184540987,
|
| 557 |
+
"learning_rate": 4.620000000000001e-06,
|
| 558 |
+
"loss": 0.0002,
|
| 559 |
+
"step": 770
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.56,
|
| 563 |
+
"grad_norm": 0.003172930097207427,
|
| 564 |
+
"learning_rate": 4.42e-06,
|
| 565 |
+
"loss": 0.0002,
|
| 566 |
+
"step": 780
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.58,
|
| 570 |
+
"grad_norm": 0.004744864068925381,
|
| 571 |
+
"learning_rate": 4.22e-06,
|
| 572 |
+
"loss": 0.0002,
|
| 573 |
+
"step": 790
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.6,
|
| 577 |
+
"grad_norm": 0.0048369443975389,
|
| 578 |
+
"learning_rate": 4.0200000000000005e-06,
|
| 579 |
+
"loss": 0.0002,
|
| 580 |
+
"step": 800
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.62,
|
| 584 |
+
"grad_norm": 0.006995647680014372,
|
| 585 |
+
"learning_rate": 3.820000000000001e-06,
|
| 586 |
+
"loss": 0.0002,
|
| 587 |
+
"step": 810
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.6400000000000001,
|
| 591 |
+
"grad_norm": 0.006043950095772743,
|
| 592 |
+
"learning_rate": 3.62e-06,
|
| 593 |
+
"loss": 0.0002,
|
| 594 |
+
"step": 820
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.6600000000000001,
|
| 598 |
+
"grad_norm": 0.003441416658461094,
|
| 599 |
+
"learning_rate": 3.4200000000000007e-06,
|
| 600 |
+
"loss": 0.0002,
|
| 601 |
+
"step": 830
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.6800000000000002,
|
| 605 |
+
"grad_norm": 0.003332007909193635,
|
| 606 |
+
"learning_rate": 3.2200000000000005e-06,
|
| 607 |
+
"loss": 0.0002,
|
| 608 |
+
"step": 840
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.7,
|
| 612 |
+
"grad_norm": 0.004367617890238762,
|
| 613 |
+
"learning_rate": 3.0200000000000003e-06,
|
| 614 |
+
"loss": 0.0002,
|
| 615 |
+
"step": 850
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.72,
|
| 619 |
+
"grad_norm": 0.003745694411918521,
|
| 620 |
+
"learning_rate": 2.82e-06,
|
| 621 |
+
"loss": 0.0002,
|
| 622 |
+
"step": 860
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.74,
|
| 626 |
+
"grad_norm": 0.0045255571603775024,
|
| 627 |
+
"learning_rate": 2.6200000000000003e-06,
|
| 628 |
+
"loss": 0.0002,
|
| 629 |
+
"step": 870
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.76,
|
| 633 |
+
"grad_norm": 0.007438857574015856,
|
| 634 |
+
"learning_rate": 2.42e-06,
|
| 635 |
+
"loss": 0.0002,
|
| 636 |
+
"step": 880
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.78,
|
| 640 |
+
"grad_norm": 0.003601241623982787,
|
| 641 |
+
"learning_rate": 2.2200000000000003e-06,
|
| 642 |
+
"loss": 0.0002,
|
| 643 |
+
"step": 890
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.8,
|
| 647 |
+
"grad_norm": 0.005754411686211824,
|
| 648 |
+
"learning_rate": 2.02e-06,
|
| 649 |
+
"loss": 0.0002,
|
| 650 |
+
"step": 900
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.8199999999999998,
|
| 654 |
+
"grad_norm": 0.004126591607928276,
|
| 655 |
+
"learning_rate": 1.8200000000000002e-06,
|
| 656 |
+
"loss": 0.0002,
|
| 657 |
+
"step": 910
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.8399999999999999,
|
| 661 |
+
"grad_norm": 0.0029146517626941204,
|
| 662 |
+
"learning_rate": 1.6200000000000002e-06,
|
| 663 |
+
"loss": 0.0002,
|
| 664 |
+
"step": 920
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.8599999999999999,
|
| 668 |
+
"grad_norm": 0.004145388957113028,
|
| 669 |
+
"learning_rate": 1.42e-06,
|
| 670 |
+
"loss": 0.0002,
|
| 671 |
+
"step": 930
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.88,
|
| 675 |
+
"grad_norm": 0.004146781750023365,
|
| 676 |
+
"learning_rate": 1.2200000000000002e-06,
|
| 677 |
+
"loss": 0.0002,
|
| 678 |
+
"step": 940
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.9,
|
| 682 |
+
"grad_norm": 0.0030123749747872353,
|
| 683 |
+
"learning_rate": 1.02e-06,
|
| 684 |
+
"loss": 0.0002,
|
| 685 |
+
"step": 950
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.92,
|
| 689 |
+
"grad_norm": 0.0036781285889446735,
|
| 690 |
+
"learning_rate": 8.200000000000001e-07,
|
| 691 |
+
"loss": 0.0002,
|
| 692 |
+
"step": 960
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.94,
|
| 696 |
+
"grad_norm": 0.003789982059970498,
|
| 697 |
+
"learning_rate": 6.200000000000001e-07,
|
| 698 |
+
"loss": 0.0002,
|
| 699 |
+
"step": 970
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.96,
|
| 703 |
+
"grad_norm": 0.002757430076599121,
|
| 704 |
+
"learning_rate": 4.2000000000000006e-07,
|
| 705 |
+
"loss": 0.0002,
|
| 706 |
+
"step": 980
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.98,
|
| 710 |
+
"grad_norm": 0.003039994277060032,
|
| 711 |
+
"learning_rate": 2.2e-07,
|
| 712 |
+
"loss": 0.0002,
|
| 713 |
+
"step": 990
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.0,
|
| 717 |
+
"grad_norm": 0.004747174214571714,
|
| 718 |
+
"learning_rate": 2e-08,
|
| 719 |
+
"loss": 0.0002,
|
| 720 |
+
"step": 1000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.0,
|
| 724 |
+
"eval_accuracy": 1.0,
|
| 725 |
+
"eval_f1": 1.0,
|
| 726 |
+
"eval_loss": 5.1833787438226864e-05,
|
| 727 |
+
"eval_runtime": 8.5122,
|
| 728 |
+
"eval_samples_per_second": 117.478,
|
| 729 |
+
"eval_steps_per_second": 14.685,
|
| 730 |
+
"step": 1000
|
| 731 |
+
}
|
| 732 |
+
],
|
| 733 |
+
"logging_steps": 10,
|
| 734 |
+
"max_steps": 1000,
|
| 735 |
+
"num_input_tokens_seen": 0,
|
| 736 |
+
"num_train_epochs": 2,
|
| 737 |
+
"save_steps": 500,
|
| 738 |
+
"stateful_callbacks": {
|
| 739 |
+
"TrainerControl": {
|
| 740 |
+
"args": {
|
| 741 |
+
"should_epoch_stop": false,
|
| 742 |
+
"should_evaluate": false,
|
| 743 |
+
"should_log": false,
|
| 744 |
+
"should_save": true,
|
| 745 |
+
"should_training_stop": true
|
| 746 |
+
},
|
| 747 |
+
"attributes": {}
|
| 748 |
+
}
|
| 749 |
+
},
|
| 750 |
+
"total_flos": 143985827132928.0,
|
| 751 |
+
"train_batch_size": 8,
|
| 752 |
+
"trial_name": null,
|
| 753 |
+
"trial_params": null
|
| 754 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d78d577f3b07fa3794988bb395d77dab5ca4a33d3fe6616fceb1e5020ee22a
|
| 3 |
+
size 5841
|
checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Communications",
|
| 14 |
+
"1": "Meals & Entertainment",
|
| 15 |
+
"2": "Office Expenses",
|
| 16 |
+
"3": "Transportation",
|
| 17 |
+
"4": "Travel"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Communications": 0,
|
| 23 |
+
"Meals & Entertainment": 1,
|
| 24 |
+
"Office Expenses": 2,
|
| 25 |
+
"Transportation": 3,
|
| 26 |
+
"Travel": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-07,
|
| 29 |
+
"legacy": true,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"max_relative_positions": -1,
|
| 32 |
+
"model_type": "deberta-v2",
|
| 33 |
+
"norm_rel_ebd": "layer_norm",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"pooler_dropout": 0,
|
| 38 |
+
"pooler_hidden_act": "gelu",
|
| 39 |
+
"pooler_hidden_size": 1024,
|
| 40 |
+
"pos_att_type": [
|
| 41 |
+
"p2c",
|
| 42 |
+
"c2p"
|
| 43 |
+
],
|
| 44 |
+
"position_biased_input": false,
|
| 45 |
+
"position_buckets": 256,
|
| 46 |
+
"relative_attention": true,
|
| 47 |
+
"share_att_key": true,
|
| 48 |
+
"transformers_version": "4.56.0",
|
| 49 |
+
"type_vocab_size": 0,
|
| 50 |
+
"vocab_size": 128100
|
| 51 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2d5664303d440af07d840cdd5ab6b35773ed9536eea7d40393dda16b1adc2a5
|
| 3 |
+
size 1740316748
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cb1246fe89f999b98fe209bb4dd3e98c8f2fdca954af16de5faab62aa7eec00
|
| 3 |
+
size 14645
|
checkpoint-500/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 |
+
}
|
checkpoint-500/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/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 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02,
|
| 14 |
+
"grad_norm": 8.39200210571289,
|
| 15 |
+
"learning_rate": 1.982e-05,
|
| 16 |
+
"loss": 1.5512,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04,
|
| 21 |
+
"grad_norm": 11.324227333068848,
|
| 22 |
+
"learning_rate": 1.9620000000000002e-05,
|
| 23 |
+
"loss": 1.1959,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 6.3719482421875,
|
| 29 |
+
"learning_rate": 1.942e-05,
|
| 30 |
+
"loss": 0.6321,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 8.07636547088623,
|
| 36 |
+
"learning_rate": 1.9220000000000002e-05,
|
| 37 |
+
"loss": 0.6085,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 3.1197566986083984,
|
| 43 |
+
"learning_rate": 1.902e-05,
|
| 44 |
+
"loss": 0.2591,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"grad_norm": 0.4907987117767334,
|
| 50 |
+
"learning_rate": 1.882e-05,
|
| 51 |
+
"loss": 0.0781,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14,
|
| 56 |
+
"grad_norm": 0.16266797482967377,
|
| 57 |
+
"learning_rate": 1.862e-05,
|
| 58 |
+
"loss": 0.0224,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16,
|
| 63 |
+
"grad_norm": 0.15413975715637207,
|
| 64 |
+
"learning_rate": 1.8420000000000003e-05,
|
| 65 |
+
"loss": 0.0102,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.18,
|
| 70 |
+
"grad_norm": 0.1077665239572525,
|
| 71 |
+
"learning_rate": 1.8220000000000002e-05,
|
| 72 |
+
"loss": 0.0048,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2,
|
| 77 |
+
"grad_norm": 0.05375492572784424,
|
| 78 |
+
"learning_rate": 1.802e-05,
|
| 79 |
+
"loss": 0.003,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22,
|
| 84 |
+
"grad_norm": 0.03678549453616142,
|
| 85 |
+
"learning_rate": 1.7820000000000002e-05,
|
| 86 |
+
"loss": 0.0023,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 0.04655584692955017,
|
| 92 |
+
"learning_rate": 1.762e-05,
|
| 93 |
+
"loss": 0.0019,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.26,
|
| 98 |
+
"grad_norm": 0.037836335599422455,
|
| 99 |
+
"learning_rate": 1.7420000000000003e-05,
|
| 100 |
+
"loss": 0.0018,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.28,
|
| 105 |
+
"grad_norm": 0.03111528977751732,
|
| 106 |
+
"learning_rate": 1.722e-05,
|
| 107 |
+
"loss": 0.0016,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3,
|
| 112 |
+
"grad_norm": 0.022478433325886726,
|
| 113 |
+
"learning_rate": 1.702e-05,
|
| 114 |
+
"loss": 0.0014,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"grad_norm": 0.019292104989290237,
|
| 120 |
+
"learning_rate": 1.682e-05,
|
| 121 |
+
"loss": 0.0013,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.34,
|
| 126 |
+
"grad_norm": 0.02150174230337143,
|
| 127 |
+
"learning_rate": 1.662e-05,
|
| 128 |
+
"loss": 0.0012,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.36,
|
| 133 |
+
"grad_norm": 0.016075951978564262,
|
| 134 |
+
"learning_rate": 1.6420000000000002e-05,
|
| 135 |
+
"loss": 0.001,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.38,
|
| 140 |
+
"grad_norm": 0.01365870051085949,
|
| 141 |
+
"learning_rate": 1.6220000000000004e-05,
|
| 142 |
+
"loss": 0.0009,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4,
|
| 147 |
+
"grad_norm": 0.01567169837653637,
|
| 148 |
+
"learning_rate": 1.6020000000000002e-05,
|
| 149 |
+
"loss": 0.0009,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.42,
|
| 154 |
+
"grad_norm": 0.010838769376277924,
|
| 155 |
+
"learning_rate": 1.582e-05,
|
| 156 |
+
"loss": 0.0008,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.44,
|
| 161 |
+
"grad_norm": 0.018331510946154594,
|
| 162 |
+
"learning_rate": 1.5620000000000003e-05,
|
| 163 |
+
"loss": 0.0008,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.46,
|
| 168 |
+
"grad_norm": 0.025574931874871254,
|
| 169 |
+
"learning_rate": 1.542e-05,
|
| 170 |
+
"loss": 0.0007,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.48,
|
| 175 |
+
"grad_norm": 0.023950673639774323,
|
| 176 |
+
"learning_rate": 1.5220000000000002e-05,
|
| 177 |
+
"loss": 0.0008,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5,
|
| 182 |
+
"grad_norm": 0.010618827305734158,
|
| 183 |
+
"learning_rate": 1.5020000000000002e-05,
|
| 184 |
+
"loss": 0.0007,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.52,
|
| 189 |
+
"grad_norm": 0.014874480664730072,
|
| 190 |
+
"learning_rate": 1.482e-05,
|
| 191 |
+
"loss": 0.0006,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.54,
|
| 196 |
+
"grad_norm": 0.011250246316194534,
|
| 197 |
+
"learning_rate": 1.462e-05,
|
| 198 |
+
"loss": 0.0006,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.56,
|
| 203 |
+
"grad_norm": 0.011498576030135155,
|
| 204 |
+
"learning_rate": 1.4420000000000001e-05,
|
| 205 |
+
"loss": 0.0006,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.58,
|
| 210 |
+
"grad_norm": 0.008709218353033066,
|
| 211 |
+
"learning_rate": 1.4220000000000001e-05,
|
| 212 |
+
"loss": 0.0005,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6,
|
| 217 |
+
"grad_norm": 0.010704316198825836,
|
| 218 |
+
"learning_rate": 1.402e-05,
|
| 219 |
+
"loss": 0.0005,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.62,
|
| 224 |
+
"grad_norm": 0.013085413724184036,
|
| 225 |
+
"learning_rate": 1.382e-05,
|
| 226 |
+
"loss": 0.0006,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.64,
|
| 231 |
+
"grad_norm": 0.010020424611866474,
|
| 232 |
+
"learning_rate": 1.3620000000000002e-05,
|
| 233 |
+
"loss": 0.0005,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.66,
|
| 238 |
+
"grad_norm": 0.0069733611308038235,
|
| 239 |
+
"learning_rate": 1.3420000000000002e-05,
|
| 240 |
+
"loss": 0.0005,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.68,
|
| 245 |
+
"grad_norm": 0.009822344407439232,
|
| 246 |
+
"learning_rate": 1.3220000000000002e-05,
|
| 247 |
+
"loss": 0.0005,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7,
|
| 252 |
+
"grad_norm": 0.010420722886919975,
|
| 253 |
+
"learning_rate": 1.302e-05,
|
| 254 |
+
"loss": 0.0004,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.72,
|
| 259 |
+
"grad_norm": 0.008276022970676422,
|
| 260 |
+
"learning_rate": 1.2820000000000001e-05,
|
| 261 |
+
"loss": 0.0004,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.74,
|
| 266 |
+
"grad_norm": 0.007726218551397324,
|
| 267 |
+
"learning_rate": 1.2620000000000001e-05,
|
| 268 |
+
"loss": 0.0004,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.76,
|
| 273 |
+
"grad_norm": 0.009340759366750717,
|
| 274 |
+
"learning_rate": 1.2420000000000001e-05,
|
| 275 |
+
"loss": 0.0004,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.78,
|
| 280 |
+
"grad_norm": 0.00625102873891592,
|
| 281 |
+
"learning_rate": 1.2220000000000002e-05,
|
| 282 |
+
"loss": 0.0004,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8,
|
| 287 |
+
"grad_norm": 0.009452459402382374,
|
| 288 |
+
"learning_rate": 1.202e-05,
|
| 289 |
+
"loss": 0.0003,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.82,
|
| 294 |
+
"grad_norm": 0.006577606778591871,
|
| 295 |
+
"learning_rate": 1.182e-05,
|
| 296 |
+
"loss": 0.0004,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.84,
|
| 301 |
+
"grad_norm": 0.005760726518929005,
|
| 302 |
+
"learning_rate": 1.162e-05,
|
| 303 |
+
"loss": 0.0003,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.86,
|
| 308 |
+
"grad_norm": 0.006589033640921116,
|
| 309 |
+
"learning_rate": 1.142e-05,
|
| 310 |
+
"loss": 0.0003,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.88,
|
| 315 |
+
"grad_norm": 0.007873634807765484,
|
| 316 |
+
"learning_rate": 1.1220000000000003e-05,
|
| 317 |
+
"loss": 0.0003,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9,
|
| 322 |
+
"grad_norm": 0.005279037170112133,
|
| 323 |
+
"learning_rate": 1.1020000000000001e-05,
|
| 324 |
+
"loss": 0.0003,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.92,
|
| 329 |
+
"grad_norm": 0.008107911795377731,
|
| 330 |
+
"learning_rate": 1.0820000000000001e-05,
|
| 331 |
+
"loss": 0.0003,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.94,
|
| 336 |
+
"grad_norm": 0.006266397424042225,
|
| 337 |
+
"learning_rate": 1.0620000000000002e-05,
|
| 338 |
+
"loss": 0.0003,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.96,
|
| 343 |
+
"grad_norm": 0.00688116904348135,
|
| 344 |
+
"learning_rate": 1.0420000000000002e-05,
|
| 345 |
+
"loss": 0.0003,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.98,
|
| 350 |
+
"grad_norm": 0.006354791112244129,
|
| 351 |
+
"learning_rate": 1.022e-05,
|
| 352 |
+
"loss": 0.0003,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.0,
|
| 357 |
+
"grad_norm": 0.02231195569038391,
|
| 358 |
+
"learning_rate": 1.002e-05,
|
| 359 |
+
"loss": 0.0003,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0,
|
| 364 |
+
"eval_accuracy": 1.0,
|
| 365 |
+
"eval_f1": 1.0,
|
| 366 |
+
"eval_loss": 8.804027311271057e-05,
|
| 367 |
+
"eval_runtime": 8.5077,
|
| 368 |
+
"eval_samples_per_second": 117.541,
|
| 369 |
+
"eval_steps_per_second": 14.693,
|
| 370 |
+
"step": 500
|
| 371 |
+
}
|
| 372 |
+
],
|
| 373 |
+
"logging_steps": 10,
|
| 374 |
+
"max_steps": 1000,
|
| 375 |
+
"num_input_tokens_seen": 0,
|
| 376 |
+
"num_train_epochs": 2,
|
| 377 |
+
"save_steps": 500,
|
| 378 |
+
"stateful_callbacks": {
|
| 379 |
+
"TrainerControl": {
|
| 380 |
+
"args": {
|
| 381 |
+
"should_epoch_stop": false,
|
| 382 |
+
"should_evaluate": false,
|
| 383 |
+
"should_log": false,
|
| 384 |
+
"should_save": true,
|
| 385 |
+
"should_training_stop": false
|
| 386 |
+
},
|
| 387 |
+
"attributes": {}
|
| 388 |
+
}
|
| 389 |
+
},
|
| 390 |
+
"total_flos": 71992913566464.0,
|
| 391 |
+
"train_batch_size": 8,
|
| 392 |
+
"trial_name": null,
|
| 393 |
+
"trial_params": null
|
| 394 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d78d577f3b07fa3794988bb395d77dab5ca4a33d3fe6616fceb1e5020ee22a
|
| 3 |
+
size 5841
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Communications",
|
| 14 |
+
"1": "Meals & Entertainment",
|
| 15 |
+
"2": "Office Expenses",
|
| 16 |
+
"3": "Transportation",
|
| 17 |
+
"4": "Travel"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Communications": 0,
|
| 23 |
+
"Meals & Entertainment": 1,
|
| 24 |
+
"Office Expenses": 2,
|
| 25 |
+
"Transportation": 3,
|
| 26 |
+
"Travel": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-07,
|
| 29 |
+
"legacy": true,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"max_relative_positions": -1,
|
| 32 |
+
"model_type": "deberta-v2",
|
| 33 |
+
"norm_rel_ebd": "layer_norm",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"pooler_dropout": 0,
|
| 38 |
+
"pooler_hidden_act": "gelu",
|
| 39 |
+
"pooler_hidden_size": 1024,
|
| 40 |
+
"pos_att_type": [
|
| 41 |
+
"p2c",
|
| 42 |
+
"c2p"
|
| 43 |
+
],
|
| 44 |
+
"position_biased_input": false,
|
| 45 |
+
"position_buckets": 256,
|
| 46 |
+
"relative_attention": true,
|
| 47 |
+
"share_att_key": true,
|
| 48 |
+
"transformers_version": "4.56.0",
|
| 49 |
+
"type_vocab_size": 0,
|
| 50 |
+
"vocab_size": 128100
|
| 51 |
+
}
|
label_mappings.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"label2id": {
|
| 3 |
+
"Communications": 0,
|
| 4 |
+
"Meals & Entertainment": 1,
|
| 5 |
+
"Office Expenses": 2,
|
| 6 |
+
"Transportation": 3,
|
| 7 |
+
"Travel": 4
|
| 8 |
+
},
|
| 9 |
+
"id2label": {
|
| 10 |
+
"0": "Communications",
|
| 11 |
+
"1": "Meals & Entertainment",
|
| 12 |
+
"2": "Office Expenses",
|
| 13 |
+
"3": "Transportation",
|
| 14 |
+
"4": "Travel"
|
| 15 |
+
}
|
| 16 |
+
}
|
logs/events.out.tfevents.1757320191.3332ba88c8b5.1966.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45779654da758faf1f1c9488b1b24a5e3bc55d6c370d9e725d172fe41f9b891d
|
| 3 |
+
size 27684
|
logs/events.out.tfevents.1757321096.3332ba88c8b5.1966.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a65846ed759ee1120488d98c9f446fbcb0e86e720b486c80ebf9024e62b23e2
|
| 3 |
+
size 27684
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedd9af8427bde3c4f1532e3bbc4e33affed975368fd795fa717d4717a5e84a0
|
| 3 |
+
size 1740316748
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e5f215fb2bd1138f0439480064aa98c25675efaaee45a396f92755fb55cfcc1
|
| 3 |
+
size 1740435979
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d78d577f3b07fa3794988bb395d77dab5ca4a33d3fe6616fceb1e5020ee22a
|
| 3 |
+
size 5841
|