train more dataset
Browse files- checkpoint-20/config.json +0 -43
- checkpoint-20/special_tokens_map.json +0 -51
- checkpoint-20/tokenizer.json +0 -3
- checkpoint-20/tokenizer_config.json +0 -59
- checkpoint-20/trainer_state.json +0 -48
- checkpoint-20/training_args.bin +0 -3
- checkpoint-25/config.json +0 -43
- checkpoint-25/special_tokens_map.json +0 -51
- checkpoint-25/tokenizer.json +0 -3
- checkpoint-25/tokenizer_config.json +0 -59
- checkpoint-25/trainer_state.json +0 -48
- checkpoint-25/training_args.bin +0 -3
- pytorch_model.bin +1 -1
checkpoint-20/config.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 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 |
-
"id2label": {
|
| 10 |
-
"0": "\u0e40\u0e1b\u0e47\u0e19\u0e07\u0e32\u0e19",
|
| 11 |
-
"1": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19"
|
| 12 |
-
},
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 3072,
|
| 15 |
-
"label2id": {
|
| 16 |
-
"entailment": 0,
|
| 17 |
-
"not_entailment": 1
|
| 18 |
-
},
|
| 19 |
-
"layer_norm_eps": 1e-07,
|
| 20 |
-
"legacy": true,
|
| 21 |
-
"max_position_embeddings": 512,
|
| 22 |
-
"max_relative_positions": -1,
|
| 23 |
-
"model_type": "deberta-v2",
|
| 24 |
-
"norm_rel_ebd": "layer_norm",
|
| 25 |
-
"num_attention_heads": 12,
|
| 26 |
-
"num_hidden_layers": 12,
|
| 27 |
-
"pad_token_id": 0,
|
| 28 |
-
"pooler_dropout": 0,
|
| 29 |
-
"pooler_hidden_act": "gelu",
|
| 30 |
-
"pooler_hidden_size": 768,
|
| 31 |
-
"pos_att_type": [
|
| 32 |
-
"p2c",
|
| 33 |
-
"c2p"
|
| 34 |
-
],
|
| 35 |
-
"position_biased_input": false,
|
| 36 |
-
"position_buckets": 256,
|
| 37 |
-
"relative_attention": true,
|
| 38 |
-
"share_att_key": true,
|
| 39 |
-
"torch_dtype": "float32",
|
| 40 |
-
"transformers_version": "4.52.4",
|
| 41 |
-
"type_vocab_size": 0,
|
| 42 |
-
"vocab_size": 251000
|
| 43 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-20/special_tokens_map.json
DELETED
|
@@ -1,51 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-20/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
|
| 3 |
-
size 16316224
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-20/tokenizer_config.json
DELETED
|
@@ -1,59 +0,0 @@
|
|
| 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 |
-
"250101": {
|
| 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 |
-
"extra_special_tokens": {},
|
| 50 |
-
"mask_token": "[MASK]",
|
| 51 |
-
"model_max_length": 512,
|
| 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-20/trainer_state.json
DELETED
|
@@ -1,48 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 4.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 20,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 2.0,
|
| 14 |
-
"grad_norm": 6.662973403930664,
|
| 15 |
-
"learning_rate": 1.2800000000000001e-05,
|
| 16 |
-
"loss": 0.6505,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 4.0,
|
| 21 |
-
"grad_norm": 6.020062446594238,
|
| 22 |
-
"learning_rate": 4.800000000000001e-06,
|
| 23 |
-
"loss": 0.4503,
|
| 24 |
-
"step": 20
|
| 25 |
-
}
|
| 26 |
-
],
|
| 27 |
-
"logging_steps": 10,
|
| 28 |
-
"max_steps": 25,
|
| 29 |
-
"num_input_tokens_seen": 0,
|
| 30 |
-
"num_train_epochs": 5,
|
| 31 |
-
"save_steps": 500,
|
| 32 |
-
"stateful_callbacks": {
|
| 33 |
-
"TrainerControl": {
|
| 34 |
-
"args": {
|
| 35 |
-
"should_epoch_stop": false,
|
| 36 |
-
"should_evaluate": false,
|
| 37 |
-
"should_log": false,
|
| 38 |
-
"should_save": true,
|
| 39 |
-
"should_training_stop": false
|
| 40 |
-
},
|
| 41 |
-
"attributes": {}
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"total_flos": 1385468997216.0,
|
| 45 |
-
"train_batch_size": 8,
|
| 46 |
-
"trial_name": null,
|
| 47 |
-
"trial_params": null
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-20/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cc8f550d6d3617db1b6992d1d5c428d1c2201c6e42324b75997f5dd20f4df04e
|
| 3 |
-
size 5649
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-25/config.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 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 |
-
"id2label": {
|
| 10 |
-
"0": "\u0e40\u0e1b\u0e47\u0e19\u0e07\u0e32\u0e19",
|
| 11 |
-
"1": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19"
|
| 12 |
-
},
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 3072,
|
| 15 |
-
"label2id": {
|
| 16 |
-
"entailment": 0,
|
| 17 |
-
"not_entailment": 1
|
| 18 |
-
},
|
| 19 |
-
"layer_norm_eps": 1e-07,
|
| 20 |
-
"legacy": true,
|
| 21 |
-
"max_position_embeddings": 512,
|
| 22 |
-
"max_relative_positions": -1,
|
| 23 |
-
"model_type": "deberta-v2",
|
| 24 |
-
"norm_rel_ebd": "layer_norm",
|
| 25 |
-
"num_attention_heads": 12,
|
| 26 |
-
"num_hidden_layers": 12,
|
| 27 |
-
"pad_token_id": 0,
|
| 28 |
-
"pooler_dropout": 0,
|
| 29 |
-
"pooler_hidden_act": "gelu",
|
| 30 |
-
"pooler_hidden_size": 768,
|
| 31 |
-
"pos_att_type": [
|
| 32 |
-
"p2c",
|
| 33 |
-
"c2p"
|
| 34 |
-
],
|
| 35 |
-
"position_biased_input": false,
|
| 36 |
-
"position_buckets": 256,
|
| 37 |
-
"relative_attention": true,
|
| 38 |
-
"share_att_key": true,
|
| 39 |
-
"torch_dtype": "float32",
|
| 40 |
-
"transformers_version": "4.52.4",
|
| 41 |
-
"type_vocab_size": 0,
|
| 42 |
-
"vocab_size": 251000
|
| 43 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-25/special_tokens_map.json
DELETED
|
@@ -1,51 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-25/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
|
| 3 |
-
size 16316224
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-25/tokenizer_config.json
DELETED
|
@@ -1,59 +0,0 @@
|
|
| 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 |
-
"250101": {
|
| 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 |
-
"extra_special_tokens": {},
|
| 50 |
-
"mask_token": "[MASK]",
|
| 51 |
-
"model_max_length": 512,
|
| 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-25/trainer_state.json
DELETED
|
@@ -1,48 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 5.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 25,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 2.0,
|
| 14 |
-
"grad_norm": 6.662973403930664,
|
| 15 |
-
"learning_rate": 1.2800000000000001e-05,
|
| 16 |
-
"loss": 0.6505,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 4.0,
|
| 21 |
-
"grad_norm": 6.020062446594238,
|
| 22 |
-
"learning_rate": 4.800000000000001e-06,
|
| 23 |
-
"loss": 0.4503,
|
| 24 |
-
"step": 20
|
| 25 |
-
}
|
| 26 |
-
],
|
| 27 |
-
"logging_steps": 10,
|
| 28 |
-
"max_steps": 25,
|
| 29 |
-
"num_input_tokens_seen": 0,
|
| 30 |
-
"num_train_epochs": 5,
|
| 31 |
-
"save_steps": 500,
|
| 32 |
-
"stateful_callbacks": {
|
| 33 |
-
"TrainerControl": {
|
| 34 |
-
"args": {
|
| 35 |
-
"should_epoch_stop": false,
|
| 36 |
-
"should_evaluate": false,
|
| 37 |
-
"should_log": false,
|
| 38 |
-
"should_save": true,
|
| 39 |
-
"should_training_stop": true
|
| 40 |
-
},
|
| 41 |
-
"attributes": {}
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"total_flos": 1734919634496.0,
|
| 45 |
-
"train_batch_size": 8,
|
| 46 |
-
"trial_name": null,
|
| 47 |
-
"trial_params": null
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-25/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cc8f550d6d3617db1b6992d1d5c428d1c2201c6e42324b75997f5dd20f4df04e
|
| 3 |
-
size 5649
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1115313995
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82b17584630bf4cde1aa07b851eb0c32944b7be6763a5614659456561a1e7ff
|
| 3 |
size 1115313995
|