Commit
•
f182806
1
Parent(s):
a8ab348
Training in progress, step 500
Browse files- added_tokens.json +3 -0
- checkpoint-500/added_tokens.json +3 -0
- checkpoint-500/config.json +59 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +9 -0
- checkpoint-500/spm.model +3 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer_config.json +16 -0
- checkpoint-500/trainer_state.json +282 -0
- checkpoint-500/training_args.bin +3 -0
- config.json +59 -0
- pytorch_model.bin +3 -0
- runs/Jul22_21-38-20_108d00b13d16/events.out.tfevents.1690061910.108d00b13d16.1015.0 +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 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": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Society & Culture",
|
| 12 |
+
"1": "Science & Mathematics",
|
| 13 |
+
"2": "Health",
|
| 14 |
+
"3": "Education & Reference",
|
| 15 |
+
"4": "Computers & Internet",
|
| 16 |
+
"5": "Sports",
|
| 17 |
+
"6": "Business & Finance",
|
| 18 |
+
"7": "Entertainment & Music",
|
| 19 |
+
"8": "Family & Relationships",
|
| 20 |
+
"9": "Politics & Government"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"Business & Finance": 6,
|
| 26 |
+
"Computers & Internet": 4,
|
| 27 |
+
"Education & Reference": 3,
|
| 28 |
+
"Entertainment & Music": 7,
|
| 29 |
+
"Family & Relationships": 8,
|
| 30 |
+
"Health": 2,
|
| 31 |
+
"Politics & Government": 9,
|
| 32 |
+
"Science & Mathematics": 1,
|
| 33 |
+
"Society & Culture": 0,
|
| 34 |
+
"Sports": 5
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"max_position_embeddings": 512,
|
| 38 |
+
"max_relative_positions": -1,
|
| 39 |
+
"model_type": "deberta-v2",
|
| 40 |
+
"norm_rel_ebd": "layer_norm",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"pooler_dropout": 0,
|
| 45 |
+
"pooler_hidden_act": "gelu",
|
| 46 |
+
"pooler_hidden_size": 768,
|
| 47 |
+
"pos_att_type": [
|
| 48 |
+
"p2c",
|
| 49 |
+
"c2p"
|
| 50 |
+
],
|
| 51 |
+
"position_biased_input": false,
|
| 52 |
+
"position_buckets": 256,
|
| 53 |
+
"relative_attention": true,
|
| 54 |
+
"share_att_key": true,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.31.0",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa955e324a06471f2342b43104ae414ccb0fb920abcd82514ce4df36451e604
|
| 3 |
+
size 1475557125
|
checkpoint-500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968947a80606ab66a2d6c65ce7b6bf2543300bd498634bfcce0ea6c119def9fc
|
| 3 |
+
size 737788917
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55dd66cea8c9a015ece35d25b772bb3aa778684c591bca679c2fb53497649527
|
| 3 |
+
size 14575
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae06c66322f4c70d9908a9b192f2653f4d0a744743bb3b8eba97385be1ae7fbe
|
| 3 |
+
size 627
|
checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[UNK]"
|
| 9 |
+
}
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9424768686294556,
|
| 3 |
+
"best_model_checkpoint": "diogopaes10/012-microsoft-deberta-v3-base-finetuned-yahoo-8000_2000/checkpoint-500",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1.9984e-05,
|
| 13 |
+
"loss": 2.308,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 19 |
+
"loss": 2.2963,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"eval_accuracy": 0.2015,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 24.807334899902344,
|
| 27 |
+
"eval_f1": 0.12984294240667255,
|
| 28 |
+
"eval_gpu_ram_allocated": 2.0898146629333496,
|
| 29 |
+
"eval_gpu_ram_cached": 25.845703125,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 48,
|
| 32 |
+
"eval_loss": 2.2150378227233887,
|
| 33 |
+
"eval_precision": 0.20897251377917925,
|
| 34 |
+
"eval_recall": 0.2015,
|
| 35 |
+
"eval_runtime": 2.4064,
|
| 36 |
+
"eval_samples_per_second": 831.127,
|
| 37 |
+
"eval_steps_per_second": 26.181,
|
| 38 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 39 |
+
"eval_system_ram_used": 3.9806594848632812,
|
| 40 |
+
"step": 50
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.4,
|
| 44 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 45 |
+
"loss": 1.8843,
|
| 46 |
+
"step": 100
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.4,
|
| 50 |
+
"eval_accuracy": 0.592,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 24.80740737915039,
|
| 53 |
+
"eval_f1": 0.5588381140615875,
|
| 54 |
+
"eval_gpu_ram_allocated": 2.0897889137268066,
|
| 55 |
+
"eval_gpu_ram_cached": 25.84765625,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 49,
|
| 58 |
+
"eval_loss": 1.4590158462524414,
|
| 59 |
+
"eval_precision": 0.6417526665901784,
|
| 60 |
+
"eval_recall": 0.592,
|
| 61 |
+
"eval_runtime": 2.4022,
|
| 62 |
+
"eval_samples_per_second": 832.564,
|
| 63 |
+
"eval_steps_per_second": 26.226,
|
| 64 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 65 |
+
"eval_system_ram_used": 3.9979324340820312,
|
| 66 |
+
"step": 100
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6,
|
| 70 |
+
"learning_rate": 1.7616000000000002e-05,
|
| 71 |
+
"loss": 1.3348,
|
| 72 |
+
"step": 150
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6,
|
| 76 |
+
"eval_accuracy": 0.668,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 24.80740737915039,
|
| 79 |
+
"eval_f1": 0.6613366784391611,
|
| 80 |
+
"eval_gpu_ram_allocated": 2.089787483215332,
|
| 81 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 49,
|
| 84 |
+
"eval_loss": 1.180911660194397,
|
| 85 |
+
"eval_precision": 0.6736430562605106,
|
| 86 |
+
"eval_recall": 0.668,
|
| 87 |
+
"eval_runtime": 2.3835,
|
| 88 |
+
"eval_samples_per_second": 839.093,
|
| 89 |
+
"eval_steps_per_second": 26.431,
|
| 90 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 91 |
+
"eval_system_ram_used": 3.983623504638672,
|
| 92 |
+
"step": 150
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 1.6816e-05,
|
| 97 |
+
"loss": 1.1501,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.8,
|
| 102 |
+
"eval_accuracy": 0.695,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 24.807422637939453,
|
| 105 |
+
"eval_f1": 0.6929220794455174,
|
| 106 |
+
"eval_gpu_ram_allocated": 2.0897974967956543,
|
| 107 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 51,
|
| 110 |
+
"eval_loss": 1.0483959913253784,
|
| 111 |
+
"eval_precision": 0.6981404124535453,
|
| 112 |
+
"eval_recall": 0.695,
|
| 113 |
+
"eval_runtime": 2.3606,
|
| 114 |
+
"eval_samples_per_second": 847.255,
|
| 115 |
+
"eval_steps_per_second": 26.689,
|
| 116 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 117 |
+
"eval_system_ram_used": 3.9695281982421875,
|
| 118 |
+
"step": 200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.0,
|
| 122 |
+
"learning_rate": 1.6016e-05,
|
| 123 |
+
"loss": 1.0842,
|
| 124 |
+
"step": 250
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.0,
|
| 128 |
+
"eval_accuracy": 0.6905,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 24.80750274658203,
|
| 131 |
+
"eval_f1": 0.6825102140466686,
|
| 132 |
+
"eval_gpu_ram_allocated": 2.0897974967956543,
|
| 133 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 50,
|
| 136 |
+
"eval_loss": 1.0264948606491089,
|
| 137 |
+
"eval_precision": 0.6893511728014889,
|
| 138 |
+
"eval_recall": 0.6905,
|
| 139 |
+
"eval_runtime": 2.3931,
|
| 140 |
+
"eval_samples_per_second": 835.746,
|
| 141 |
+
"eval_steps_per_second": 26.326,
|
| 142 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 143 |
+
"eval_system_ram_used": 3.975543975830078,
|
| 144 |
+
"step": 250
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2,
|
| 148 |
+
"learning_rate": 1.5216000000000001e-05,
|
| 149 |
+
"loss": 0.8618,
|
| 150 |
+
"step": 300
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.2,
|
| 154 |
+
"eval_accuracy": 0.704,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 24.807506561279297,
|
| 157 |
+
"eval_f1": 0.70238565521567,
|
| 158 |
+
"eval_gpu_ram_allocated": 2.0897774696350098,
|
| 159 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 50,
|
| 162 |
+
"eval_loss": 0.9903561472892761,
|
| 163 |
+
"eval_precision": 0.7048361105844692,
|
| 164 |
+
"eval_recall": 0.704,
|
| 165 |
+
"eval_runtime": 2.3588,
|
| 166 |
+
"eval_samples_per_second": 847.898,
|
| 167 |
+
"eval_steps_per_second": 26.709,
|
| 168 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 169 |
+
"eval_system_ram_used": 3.97076416015625,
|
| 170 |
+
"step": 300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.4,
|
| 174 |
+
"learning_rate": 1.4416e-05,
|
| 175 |
+
"loss": 0.9329,
|
| 176 |
+
"step": 350
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.4,
|
| 180 |
+
"eval_accuracy": 0.686,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 24.807571411132812,
|
| 183 |
+
"eval_f1": 0.6824952585178898,
|
| 184 |
+
"eval_gpu_ram_allocated": 2.089780330657959,
|
| 185 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 48,
|
| 188 |
+
"eval_loss": 0.9927061796188354,
|
| 189 |
+
"eval_precision": 0.6938911551302326,
|
| 190 |
+
"eval_recall": 0.686,
|
| 191 |
+
"eval_runtime": 2.3815,
|
| 192 |
+
"eval_samples_per_second": 839.799,
|
| 193 |
+
"eval_steps_per_second": 26.454,
|
| 194 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 195 |
+
"eval_system_ram_used": 3.9594879150390625,
|
| 196 |
+
"step": 350
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.6,
|
| 200 |
+
"learning_rate": 1.3616e-05,
|
| 201 |
+
"loss": 0.9053,
|
| 202 |
+
"step": 400
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.6,
|
| 206 |
+
"eval_accuracy": 0.705,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 24.807575225830078,
|
| 209 |
+
"eval_f1": 0.702067821848656,
|
| 210 |
+
"eval_gpu_ram_allocated": 2.089798927307129,
|
| 211 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 48,
|
| 214 |
+
"eval_loss": 0.9795323610305786,
|
| 215 |
+
"eval_precision": 0.7048247100554489,
|
| 216 |
+
"eval_recall": 0.705,
|
| 217 |
+
"eval_runtime": 2.405,
|
| 218 |
+
"eval_samples_per_second": 831.614,
|
| 219 |
+
"eval_steps_per_second": 26.196,
|
| 220 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 221 |
+
"eval_system_ram_used": 3.9837112426757812,
|
| 222 |
+
"step": 400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.8,
|
| 226 |
+
"learning_rate": 1.2816000000000002e-05,
|
| 227 |
+
"loss": 0.9173,
|
| 228 |
+
"step": 450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.8,
|
| 232 |
+
"eval_accuracy": 0.709,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 24.807697296142578,
|
| 235 |
+
"eval_f1": 0.702389340359417,
|
| 236 |
+
"eval_gpu_ram_allocated": 2.089791774749756,
|
| 237 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 48,
|
| 240 |
+
"eval_loss": 0.9748538136482239,
|
| 241 |
+
"eval_precision": 0.7139968646595424,
|
| 242 |
+
"eval_recall": 0.709,
|
| 243 |
+
"eval_runtime": 2.4003,
|
| 244 |
+
"eval_samples_per_second": 833.243,
|
| 245 |
+
"eval_steps_per_second": 26.247,
|
| 246 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 247 |
+
"eval_system_ram_used": 3.9850807189941406,
|
| 248 |
+
"step": 450
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.0,
|
| 252 |
+
"learning_rate": 1.2016000000000002e-05,
|
| 253 |
+
"loss": 0.9189,
|
| 254 |
+
"step": 500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.0,
|
| 258 |
+
"eval_accuracy": 0.718,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 24.807697296142578,
|
| 261 |
+
"eval_f1": 0.7137748110894239,
|
| 262 |
+
"eval_gpu_ram_allocated": 2.0897889137268066,
|
| 263 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 48,
|
| 266 |
+
"eval_loss": 0.9424768686294556,
|
| 267 |
+
"eval_precision": 0.718404095887314,
|
| 268 |
+
"eval_recall": 0.718,
|
| 269 |
+
"eval_runtime": 2.381,
|
| 270 |
+
"eval_samples_per_second": 839.978,
|
| 271 |
+
"eval_steps_per_second": 26.459,
|
| 272 |
+
"eval_system_ram_total": 83.48073959350586,
|
| 273 |
+
"eval_system_ram_used": 3.994873046875,
|
| 274 |
+
"step": 500
|
| 275 |
+
}
|
| 276 |
+
],
|
| 277 |
+
"max_steps": 1250,
|
| 278 |
+
"num_train_epochs": 5,
|
| 279 |
+
"total_flos": 965391777104256.0,
|
| 280 |
+
"trial_name": null,
|
| 281 |
+
"trial_params": null
|
| 282 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:393da1a7d4f3e179ce48988b5ced2108642f2f9aa55e479d0c2a97ebd87f0815
|
| 3 |
+
size 4091
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 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": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Society & Culture",
|
| 12 |
+
"1": "Science & Mathematics",
|
| 13 |
+
"2": "Health",
|
| 14 |
+
"3": "Education & Reference",
|
| 15 |
+
"4": "Computers & Internet",
|
| 16 |
+
"5": "Sports",
|
| 17 |
+
"6": "Business & Finance",
|
| 18 |
+
"7": "Entertainment & Music",
|
| 19 |
+
"8": "Family & Relationships",
|
| 20 |
+
"9": "Politics & Government"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"Business & Finance": 6,
|
| 26 |
+
"Computers & Internet": 4,
|
| 27 |
+
"Education & Reference": 3,
|
| 28 |
+
"Entertainment & Music": 7,
|
| 29 |
+
"Family & Relationships": 8,
|
| 30 |
+
"Health": 2,
|
| 31 |
+
"Politics & Government": 9,
|
| 32 |
+
"Science & Mathematics": 1,
|
| 33 |
+
"Society & Culture": 0,
|
| 34 |
+
"Sports": 5
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"max_position_embeddings": 512,
|
| 38 |
+
"max_relative_positions": -1,
|
| 39 |
+
"model_type": "deberta-v2",
|
| 40 |
+
"norm_rel_ebd": "layer_norm",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"pooler_dropout": 0,
|
| 45 |
+
"pooler_hidden_act": "gelu",
|
| 46 |
+
"pooler_hidden_size": 768,
|
| 47 |
+
"pos_att_type": [
|
| 48 |
+
"p2c",
|
| 49 |
+
"c2p"
|
| 50 |
+
],
|
| 51 |
+
"position_biased_input": false,
|
| 52 |
+
"position_buckets": 256,
|
| 53 |
+
"relative_attention": true,
|
| 54 |
+
"share_att_key": true,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.31.0",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968947a80606ab66a2d6c65ce7b6bf2543300bd498634bfcce0ea6c119def9fc
|
| 3 |
+
size 737788917
|
runs/Jul22_21-38-20_108d00b13d16/events.out.tfevents.1690061910.108d00b13d16.1015.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:186a93f00a6ebc06f0c34cfbe85b46864e0d8a5f9640f91bd6a990f47a904e74
|
| 3 |
+
size 16099
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[UNK]"
|
| 9 |
+
}
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:393da1a7d4f3e179ce48988b5ced2108642f2f9aa55e479d0c2a97ebd87f0815
|
| 3 |
+
size 4091
|