Panzy18
commited on
Commit
·
b852d47
1
Parent(s):
c3c26f9
add model
Browse files- added_tokens.json +3 -0
- config.json +45 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer_config.json +58 -0
- trainer_state.json +508 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4096,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0,
|
| 19 |
+
"LABEL_1": 1,
|
| 20 |
+
"LABEL_2": 2
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-07,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"max_relative_positions": -1,
|
| 25 |
+
"model_type": "deberta-v2",
|
| 26 |
+
"norm_rel_ebd": "layer_norm",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_dropout": 0,
|
| 31 |
+
"pooler_hidden_act": "gelu",
|
| 32 |
+
"pooler_hidden_size": 1024,
|
| 33 |
+
"pos_att_type": [
|
| 34 |
+
"p2c",
|
| 35 |
+
"c2p"
|
| 36 |
+
],
|
| 37 |
+
"position_biased_input": false,
|
| 38 |
+
"position_buckets": 256,
|
| 39 |
+
"relative_attention": true,
|
| 40 |
+
"share_att_key": true,
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.40.1",
|
| 43 |
+
"type_vocab_size": 0,
|
| 44 |
+
"vocab_size": 128100
|
| 45 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a07bf4649b53441eb837f1e3ae8d38bf4689d180dee3c78f5c78aac3975693f9
|
| 3 |
+
size 1740308548
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7803cedf7bc7807b866becaee1d7635d37591322f30eec782bb39b63b91da2ef
|
| 3 |
+
size 3480848432
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afb349f3bbfcbbd518d2508729c7b8fa98e74cebfdb97dad1afea6f567780777
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e017e7b1fc0d86725217f81b87cf073c408c6dfdd02236437dc30e0227ffaf31
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 29073,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05159426271798576,
|
| 13 |
+
"grad_norm": 7.558670997619629,
|
| 14 |
+
"learning_rate": 2.5736389684813753e-06,
|
| 15 |
+
"loss": 0.7519,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10318852543597153,
|
| 20 |
+
"grad_norm": 6.3421125411987305,
|
| 21 |
+
"learning_rate": 5.15243553008596e-06,
|
| 22 |
+
"loss": 0.3291,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15478278815395727,
|
| 27 |
+
"grad_norm": 7.725200176239014,
|
| 28 |
+
"learning_rate": 7.720916905444127e-06,
|
| 29 |
+
"loss": 0.2716,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20637705087194305,
|
| 34 |
+
"grad_norm": 6.253057479858398,
|
| 35 |
+
"learning_rate": 8.917008196721311e-06,
|
| 36 |
+
"loss": 0.2444,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2579713135899288,
|
| 41 |
+
"grad_norm": 8.090571403503418,
|
| 42 |
+
"learning_rate": 8.752341920374708e-06,
|
| 43 |
+
"loss": 0.2057,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.30956557630791454,
|
| 48 |
+
"grad_norm": 5.437821865081787,
|
| 49 |
+
"learning_rate": 8.587675644028104e-06,
|
| 50 |
+
"loss": 0.1938,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3611598390259003,
|
| 55 |
+
"grad_norm": 3.594510316848755,
|
| 56 |
+
"learning_rate": 8.423009367681498e-06,
|
| 57 |
+
"loss": 0.1888,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4127541017438861,
|
| 62 |
+
"grad_norm": 1.5619558095932007,
|
| 63 |
+
"learning_rate": 8.258343091334895e-06,
|
| 64 |
+
"loss": 0.1681,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.46434836446187183,
|
| 69 |
+
"grad_norm": 5.857831001281738,
|
| 70 |
+
"learning_rate": 8.093676814988291e-06,
|
| 71 |
+
"loss": 0.1581,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5159426271798576,
|
| 76 |
+
"grad_norm": 2.4653804302215576,
|
| 77 |
+
"learning_rate": 7.929010538641687e-06,
|
| 78 |
+
"loss": 0.1469,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5675368898978433,
|
| 83 |
+
"grad_norm": 8.388437271118164,
|
| 84 |
+
"learning_rate": 7.764673594847776e-06,
|
| 85 |
+
"loss": 0.1416,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6191311526158291,
|
| 90 |
+
"grad_norm": 0.739997386932373,
|
| 91 |
+
"learning_rate": 7.600007318501171e-06,
|
| 92 |
+
"loss": 0.143,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6707254153338149,
|
| 97 |
+
"grad_norm": 4.071037292480469,
|
| 98 |
+
"learning_rate": 7.435341042154568e-06,
|
| 99 |
+
"loss": 0.1309,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7223196780518006,
|
| 104 |
+
"grad_norm": 1.3754676580429077,
|
| 105 |
+
"learning_rate": 7.270674765807963e-06,
|
| 106 |
+
"loss": 0.1311,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7739139407697864,
|
| 111 |
+
"grad_norm": 7.085391998291016,
|
| 112 |
+
"learning_rate": 7.1060084894613585e-06,
|
| 113 |
+
"loss": 0.1194,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8255082034877722,
|
| 118 |
+
"grad_norm": 3.828031539916992,
|
| 119 |
+
"learning_rate": 6.941342213114754e-06,
|
| 120 |
+
"loss": 0.1128,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8771024662057579,
|
| 125 |
+
"grad_norm": 6.162450790405273,
|
| 126 |
+
"learning_rate": 6.77667593676815e-06,
|
| 127 |
+
"loss": 0.115,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9286967289237437,
|
| 132 |
+
"grad_norm": 3.1122217178344727,
|
| 133 |
+
"learning_rate": 6.612009660421546e-06,
|
| 134 |
+
"loss": 0.1105,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9802909916417294,
|
| 139 |
+
"grad_norm": 9.108379364013672,
|
| 140 |
+
"learning_rate": 6.447343384074942e-06,
|
| 141 |
+
"loss": 0.1054,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"eval_dev_accuracy": 0.9035151515151515,
|
| 147 |
+
"eval_dev_loss": 0.38524121046066284,
|
| 148 |
+
"eval_dev_runtime": 24.3219,
|
| 149 |
+
"eval_dev_samples_per_second": 678.401,
|
| 150 |
+
"eval_dev_steps_per_second": 42.431,
|
| 151 |
+
"step": 9691
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.0,
|
| 155 |
+
"eval_test_accuracy": 0.9203636363636364,
|
| 156 |
+
"eval_test_loss": 0.31113502383232117,
|
| 157 |
+
"eval_test_runtime": 24.5354,
|
| 158 |
+
"eval_test_samples_per_second": 672.497,
|
| 159 |
+
"eval_test_steps_per_second": 42.062,
|
| 160 |
+
"step": 9691
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.0,
|
| 164 |
+
"eval_verified_test_accuracy": 0.963639301874596,
|
| 165 |
+
"eval_verified_test_loss": 0.13967397809028625,
|
| 166 |
+
"eval_verified_test_runtime": 18.4171,
|
| 167 |
+
"eval_verified_test_samples_per_second": 671.986,
|
| 168 |
+
"eval_verified_test_steps_per_second": 42.026,
|
| 169 |
+
"step": 9691
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.0318852543597152,
|
| 173 |
+
"grad_norm": 0.7660722136497498,
|
| 174 |
+
"learning_rate": 6.2826771077283374e-06,
|
| 175 |
+
"loss": 0.095,
|
| 176 |
+
"step": 10000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.083479517077701,
|
| 180 |
+
"grad_norm": 4.1145124435424805,
|
| 181 |
+
"learning_rate": 6.118010831381733e-06,
|
| 182 |
+
"loss": 0.0881,
|
| 183 |
+
"step": 10500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.1350737797956867,
|
| 187 |
+
"grad_norm": 0.3238352835178375,
|
| 188 |
+
"learning_rate": 5.953344555035129e-06,
|
| 189 |
+
"loss": 0.0771,
|
| 190 |
+
"step": 11000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.1866680425136724,
|
| 194 |
+
"grad_norm": 5.4124908447265625,
|
| 195 |
+
"learning_rate": 5.788678278688525e-06,
|
| 196 |
+
"loss": 0.0841,
|
| 197 |
+
"step": 11500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.2382623052316581,
|
| 201 |
+
"grad_norm": 13.157797813415527,
|
| 202 |
+
"learning_rate": 5.624012002341921e-06,
|
| 203 |
+
"loss": 0.0861,
|
| 204 |
+
"step": 12000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.289856567949644,
|
| 208 |
+
"grad_norm": 1.3548617362976074,
|
| 209 |
+
"learning_rate": 5.4593457259953155e-06,
|
| 210 |
+
"loss": 0.0852,
|
| 211 |
+
"step": 12500
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.3414508306676298,
|
| 215 |
+
"grad_norm": 2.0701634883880615,
|
| 216 |
+
"learning_rate": 5.294679449648712e-06,
|
| 217 |
+
"loss": 0.088,
|
| 218 |
+
"step": 13000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.3930450933856156,
|
| 222 |
+
"grad_norm": 0.24185556173324585,
|
| 223 |
+
"learning_rate": 5.1303425058548e-06,
|
| 224 |
+
"loss": 0.076,
|
| 225 |
+
"step": 13500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.4446393561036013,
|
| 229 |
+
"grad_norm": 1.3316065073013306,
|
| 230 |
+
"learning_rate": 4.965676229508197e-06,
|
| 231 |
+
"loss": 0.0769,
|
| 232 |
+
"step": 14000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.496233618821587,
|
| 236 |
+
"grad_norm": 2.571403741836548,
|
| 237 |
+
"learning_rate": 4.801339285714286e-06,
|
| 238 |
+
"loss": 0.0775,
|
| 239 |
+
"step": 14500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.5478278815395727,
|
| 243 |
+
"grad_norm": 2.0419647693634033,
|
| 244 |
+
"learning_rate": 4.636673009367682e-06,
|
| 245 |
+
"loss": 0.0757,
|
| 246 |
+
"step": 15000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.5994221442575585,
|
| 250 |
+
"grad_norm": 4.6739912033081055,
|
| 251 |
+
"learning_rate": 4.472006733021077e-06,
|
| 252 |
+
"loss": 0.0775,
|
| 253 |
+
"step": 15500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.6510164069755442,
|
| 257 |
+
"grad_norm": 7.1135053634643555,
|
| 258 |
+
"learning_rate": 4.307340456674473e-06,
|
| 259 |
+
"loss": 0.0728,
|
| 260 |
+
"step": 16000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.70261066969353,
|
| 264 |
+
"grad_norm": 4.576988220214844,
|
| 265 |
+
"learning_rate": 4.142674180327869e-06,
|
| 266 |
+
"loss": 0.0774,
|
| 267 |
+
"step": 16500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.7542049324115159,
|
| 271 |
+
"grad_norm": 0.0673130601644516,
|
| 272 |
+
"learning_rate": 3.978337236533958e-06,
|
| 273 |
+
"loss": 0.0636,
|
| 274 |
+
"step": 17000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.8057991951295016,
|
| 278 |
+
"grad_norm": 8.489474296569824,
|
| 279 |
+
"learning_rate": 3.8136709601873536e-06,
|
| 280 |
+
"loss": 0.0692,
|
| 281 |
+
"step": 17500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.8573934578474873,
|
| 285 |
+
"grad_norm": 13.07606315612793,
|
| 286 |
+
"learning_rate": 3.6490046838407495e-06,
|
| 287 |
+
"loss": 0.0689,
|
| 288 |
+
"step": 18000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.9089877205654733,
|
| 292 |
+
"grad_norm": 0.5132156610488892,
|
| 293 |
+
"learning_rate": 3.4843384074941454e-06,
|
| 294 |
+
"loss": 0.0668,
|
| 295 |
+
"step": 18500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.960581983283459,
|
| 299 |
+
"grad_norm": 6.281818389892578,
|
| 300 |
+
"learning_rate": 3.3196721311475413e-06,
|
| 301 |
+
"loss": 0.0705,
|
| 302 |
+
"step": 19000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_dev_accuracy": 0.8983636363636364,
|
| 307 |
+
"eval_dev_loss": 0.5292544364929199,
|
| 308 |
+
"eval_dev_runtime": 24.2247,
|
| 309 |
+
"eval_dev_samples_per_second": 681.122,
|
| 310 |
+
"eval_dev_steps_per_second": 42.601,
|
| 311 |
+
"step": 19382
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.0,
|
| 315 |
+
"eval_test_accuracy": 0.9152727272727272,
|
| 316 |
+
"eval_test_loss": 0.4211724102497101,
|
| 317 |
+
"eval_test_runtime": 24.492,
|
| 318 |
+
"eval_test_samples_per_second": 673.688,
|
| 319 |
+
"eval_test_steps_per_second": 42.136,
|
| 320 |
+
"step": 19382
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.0,
|
| 324 |
+
"eval_verified_test_accuracy": 0.9569327731092437,
|
| 325 |
+
"eval_verified_test_loss": 0.1964138001203537,
|
| 326 |
+
"eval_verified_test_runtime": 18.3946,
|
| 327 |
+
"eval_verified_test_samples_per_second": 672.807,
|
| 328 |
+
"eval_verified_test_steps_per_second": 42.078,
|
| 329 |
+
"step": 19382
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.0121762460014447,
|
| 333 |
+
"grad_norm": 0.1685587465763092,
|
| 334 |
+
"learning_rate": 3.15533518735363e-06,
|
| 335 |
+
"loss": 0.0604,
|
| 336 |
+
"step": 19500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.0637705087194305,
|
| 340 |
+
"grad_norm": 3.583531141281128,
|
| 341 |
+
"learning_rate": 2.990668911007026e-06,
|
| 342 |
+
"loss": 0.0486,
|
| 343 |
+
"step": 20000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.115364771437416,
|
| 347 |
+
"grad_norm": 2.067493200302124,
|
| 348 |
+
"learning_rate": 2.8260026346604216e-06,
|
| 349 |
+
"loss": 0.0446,
|
| 350 |
+
"step": 20500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.166959034155402,
|
| 354 |
+
"grad_norm": 0.8109681010246277,
|
| 355 |
+
"learning_rate": 2.6616656908665106e-06,
|
| 356 |
+
"loss": 0.043,
|
| 357 |
+
"step": 21000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.2185532968733876,
|
| 361 |
+
"grad_norm": 1.798444151878357,
|
| 362 |
+
"learning_rate": 2.4969994145199065e-06,
|
| 363 |
+
"loss": 0.051,
|
| 364 |
+
"step": 21500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.2701475595913734,
|
| 368 |
+
"grad_norm": 0.02468039281666279,
|
| 369 |
+
"learning_rate": 2.332333138173302e-06,
|
| 370 |
+
"loss": 0.0475,
|
| 371 |
+
"step": 22000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.321741822309359,
|
| 375 |
+
"grad_norm": 6.017990589141846,
|
| 376 |
+
"learning_rate": 2.167666861826698e-06,
|
| 377 |
+
"loss": 0.0473,
|
| 378 |
+
"step": 22500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.373336085027345,
|
| 382 |
+
"grad_norm": 0.12943503260612488,
|
| 383 |
+
"learning_rate": 2.0030005854800936e-06,
|
| 384 |
+
"loss": 0.0469,
|
| 385 |
+
"step": 23000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.4249303477453306,
|
| 389 |
+
"grad_norm": 0.710267961025238,
|
| 390 |
+
"learning_rate": 1.8386636416861827e-06,
|
| 391 |
+
"loss": 0.0482,
|
| 392 |
+
"step": 23500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.4765246104633163,
|
| 396 |
+
"grad_norm": 4.638703346252441,
|
| 397 |
+
"learning_rate": 1.6739973653395785e-06,
|
| 398 |
+
"loss": 0.0554,
|
| 399 |
+
"step": 24000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.5281188731813025,
|
| 403 |
+
"grad_norm": 1.667284607887268,
|
| 404 |
+
"learning_rate": 1.5096604215456673e-06,
|
| 405 |
+
"loss": 0.042,
|
| 406 |
+
"step": 24500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.579713135899288,
|
| 410 |
+
"grad_norm": 2.6058883666992188,
|
| 411 |
+
"learning_rate": 1.3449941451990634e-06,
|
| 412 |
+
"loss": 0.0487,
|
| 413 |
+
"step": 25000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.631307398617274,
|
| 417 |
+
"grad_norm": 1.2941348552703857,
|
| 418 |
+
"learning_rate": 1.180327868852459e-06,
|
| 419 |
+
"loss": 0.0482,
|
| 420 |
+
"step": 25500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.6829016613352596,
|
| 424 |
+
"grad_norm": 0.13713909685611725,
|
| 425 |
+
"learning_rate": 1.0156615925058547e-06,
|
| 426 |
+
"loss": 0.047,
|
| 427 |
+
"step": 26000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.7344959240532454,
|
| 431 |
+
"grad_norm": 6.215357303619385,
|
| 432 |
+
"learning_rate": 8.509953161592506e-07,
|
| 433 |
+
"loss": 0.0408,
|
| 434 |
+
"step": 26500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.786090186771231,
|
| 438 |
+
"grad_norm": 0.08112023025751114,
|
| 439 |
+
"learning_rate": 6.863290398126464e-07,
|
| 440 |
+
"loss": 0.0419,
|
| 441 |
+
"step": 27000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.837684449489217,
|
| 445 |
+
"grad_norm": 1.3868869543075562,
|
| 446 |
+
"learning_rate": 5.216627634660422e-07,
|
| 447 |
+
"loss": 0.0449,
|
| 448 |
+
"step": 27500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.8892787122072026,
|
| 452 |
+
"grad_norm": 0.07935940474271774,
|
| 453 |
+
"learning_rate": 3.56996487119438e-07,
|
| 454 |
+
"loss": 0.048,
|
| 455 |
+
"step": 28000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.9408729749251883,
|
| 459 |
+
"grad_norm": 0.05485483631491661,
|
| 460 |
+
"learning_rate": 1.9233021077283373e-07,
|
| 461 |
+
"loss": 0.0393,
|
| 462 |
+
"step": 28500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.992467237643174,
|
| 466 |
+
"grad_norm": 4.398229598999023,
|
| 467 |
+
"learning_rate": 2.7663934426229508e-08,
|
| 468 |
+
"loss": 0.0446,
|
| 469 |
+
"step": 29000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 3.0,
|
| 473 |
+
"eval_dev_accuracy": 0.8943030303030303,
|
| 474 |
+
"eval_dev_loss": 0.6738013625144958,
|
| 475 |
+
"eval_dev_runtime": 24.3063,
|
| 476 |
+
"eval_dev_samples_per_second": 678.836,
|
| 477 |
+
"eval_dev_steps_per_second": 42.458,
|
| 478 |
+
"step": 29073
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.0,
|
| 482 |
+
"eval_test_accuracy": 0.9123030303030303,
|
| 483 |
+
"eval_test_loss": 0.5465541481971741,
|
| 484 |
+
"eval_test_runtime": 24.5738,
|
| 485 |
+
"eval_test_samples_per_second": 671.448,
|
| 486 |
+
"eval_test_steps_per_second": 41.996,
|
| 487 |
+
"step": 29073
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 3.0,
|
| 491 |
+
"eval_verified_test_accuracy": 0.9536199095022625,
|
| 492 |
+
"eval_verified_test_loss": 0.27511948347091675,
|
| 493 |
+
"eval_verified_test_runtime": 18.4409,
|
| 494 |
+
"eval_verified_test_samples_per_second": 671.117,
|
| 495 |
+
"eval_verified_test_steps_per_second": 41.972,
|
| 496 |
+
"step": 29073
|
| 497 |
+
}
|
| 498 |
+
],
|
| 499 |
+
"logging_steps": 500,
|
| 500 |
+
"max_steps": 29073,
|
| 501 |
+
"num_input_tokens_seen": 0,
|
| 502 |
+
"num_train_epochs": 3,
|
| 503 |
+
"save_steps": 500,
|
| 504 |
+
"total_flos": 5.067736824879187e+16,
|
| 505 |
+
"train_batch_size": 8,
|
| 506 |
+
"trial_name": null,
|
| 507 |
+
"trial_params": null
|
| 508 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c88a760b3d67bd130291b0f2977f142285e096b9d190e620ad4933273032a900
|
| 3 |
+
size 4920
|