Upload 12 files
Browse files- deberta-cola/checkpoint-670/config.json +32 -0
- deberta-cola/checkpoint-670/merges.txt +0 -0
- deberta-cola/checkpoint-670/model.safetensors +3 -0
- deberta-cola/checkpoint-670/optimizer.pt +3 -0
- deberta-cola/checkpoint-670/rng_state.pth +3 -0
- deberta-cola/checkpoint-670/scheduler.pt +3 -0
- deberta-cola/checkpoint-670/special_tokens_map.json +51 -0
- deberta-cola/checkpoint-670/tokenizer.json +0 -0
- deberta-cola/checkpoint-670/tokenizer_config.json +59 -0
- deberta-cola/checkpoint-670/trainer_state.json +85 -0
- deberta-cola/checkpoint-670/training_args.bin +3 -0
- deberta-cola/checkpoint-670/vocab.json +0 -0
deberta-cola/checkpoint-670/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/ibex/user/anb/Model_merging/EMR_Merging-main/merge_lm/ckpts/deberta/deberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 768,
|
| 22 |
+
"pos_att_type": [
|
| 23 |
+
"c2p",
|
| 24 |
+
"p2c"
|
| 25 |
+
],
|
| 26 |
+
"position_biased_input": false,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.45.1",
|
| 30 |
+
"type_vocab_size": 0,
|
| 31 |
+
"vocab_size": 50265
|
| 32 |
+
}
|
deberta-cola/checkpoint-670/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
deberta-cola/checkpoint-670/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a339d8cb786008755f5fdf790f54e0fc12027ac4a95d059f88cff52dfefab312
|
| 3 |
+
size 556799560
|
deberta-cola/checkpoint-670/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71c87313c7abf36616f2d85bf0f5213b89332779a4ffc954be9ff45228657dc1
|
| 3 |
+
size 1113718138
|
deberta-cola/checkpoint-670/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aa3740b700797525cf51dba0c1f096b65c15c10a93400e21ce07fb1f7618162
|
| 3 |
+
size 14244
|
deberta-cola/checkpoint-670/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5742a21af3ea0cdb6d973bae995e926398f76d5fed6eae3c4255d6ce460674db
|
| 3 |
+
size 1064
|
deberta-cola/checkpoint-670/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": true,
|
| 26 |
+
"normalized": true,
|
| 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": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
deberta-cola/checkpoint-670/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
deberta-cola/checkpoint-670/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "[PAD]",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "[CLS]",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "[SEP]",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "[UNK]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"50264": {
|
| 38 |
+
"content": "[MASK]",
|
| 39 |
+
"lstrip": true,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
}
|
| 45 |
+
},
|
| 46 |
+
"bos_token": "[CLS]",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"cls_token": "[CLS]",
|
| 49 |
+
"do_lower_case": false,
|
| 50 |
+
"eos_token": "[SEP]",
|
| 51 |
+
"errors": "replace",
|
| 52 |
+
"mask_token": "[MASK]",
|
| 53 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"sep_token": "[SEP]",
|
| 56 |
+
"tokenizer_class": "DebertaTokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "gpt2"
|
| 59 |
+
}
|
deberta-cola/checkpoint-670/trainer_state.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5910166901400468,
|
| 3 |
+
"best_model_checkpoint": "./deberta/deberta-cola/checkpoint-670",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 670,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_loss": 0.4414370656013489,
|
| 14 |
+
"eval_matthews_correlation": 0.5155709926752544,
|
| 15 |
+
"eval_runtime": 0.7237,
|
| 16 |
+
"eval_samples_per_second": 1441.141,
|
| 17 |
+
"eval_steps_per_second": 23.489,
|
| 18 |
+
"step": 134
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_loss": 0.46337422728538513,
|
| 23 |
+
"eval_matthews_correlation": 0.5403330273255521,
|
| 24 |
+
"eval_runtime": 0.7206,
|
| 25 |
+
"eval_samples_per_second": 1447.47,
|
| 26 |
+
"eval_steps_per_second": 23.593,
|
| 27 |
+
"step": 268
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_loss": 0.44762372970581055,
|
| 32 |
+
"eval_matthews_correlation": 0.5701176712316939,
|
| 33 |
+
"eval_runtime": 0.7202,
|
| 34 |
+
"eval_samples_per_second": 1448.139,
|
| 35 |
+
"eval_steps_per_second": 23.603,
|
| 36 |
+
"step": 402
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.7313432835820897,
|
| 40 |
+
"grad_norm": 6.901174545288086,
|
| 41 |
+
"learning_rate": 5.964912280701755e-06,
|
| 42 |
+
"loss": 0.3549,
|
| 43 |
+
"step": 500
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 4.0,
|
| 47 |
+
"eval_loss": 0.56380295753479,
|
| 48 |
+
"eval_matthews_correlation": 0.5870048765235841,
|
| 49 |
+
"eval_runtime": 0.7218,
|
| 50 |
+
"eval_samples_per_second": 1445.075,
|
| 51 |
+
"eval_steps_per_second": 23.553,
|
| 52 |
+
"step": 536
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 5.0,
|
| 56 |
+
"eval_loss": 0.6092517375946045,
|
| 57 |
+
"eval_matthews_correlation": 0.5910166901400468,
|
| 58 |
+
"eval_runtime": 0.719,
|
| 59 |
+
"eval_samples_per_second": 1450.558,
|
| 60 |
+
"eval_steps_per_second": 23.643,
|
| 61 |
+
"step": 670
|
| 62 |
+
}
|
| 63 |
+
],
|
| 64 |
+
"logging_steps": 500,
|
| 65 |
+
"max_steps": 670,
|
| 66 |
+
"num_input_tokens_seen": 0,
|
| 67 |
+
"num_train_epochs": 5,
|
| 68 |
+
"save_steps": 500,
|
| 69 |
+
"stateful_callbacks": {
|
| 70 |
+
"TrainerControl": {
|
| 71 |
+
"args": {
|
| 72 |
+
"should_epoch_stop": false,
|
| 73 |
+
"should_evaluate": false,
|
| 74 |
+
"should_log": false,
|
| 75 |
+
"should_save": true,
|
| 76 |
+
"should_training_stop": true
|
| 77 |
+
},
|
| 78 |
+
"attributes": {}
|
| 79 |
+
}
|
| 80 |
+
},
|
| 81 |
+
"total_flos": 640926711785160.0,
|
| 82 |
+
"train_batch_size": 64,
|
| 83 |
+
"trial_name": null,
|
| 84 |
+
"trial_params": null
|
| 85 |
+
}
|
deberta-cola/checkpoint-670/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26cbd16c08f98bfb311c9a2592dab2ef2e10c12c5cb41eeedc5efd96df7bdae2
|
| 3 |
+
size 5176
|
deberta-cola/checkpoint-670/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|