Upload 10 files
Browse files- hf_bert_pro_20_epochs/config.json +25 -0
- hf_bert_pro_20_epochs/model.safetensors +3 -0
- hf_bert_pro_20_epochs/optimizer.pt +3 -0
- hf_bert_pro_20_epochs/rng_state.pth +3 -0
- hf_bert_pro_20_epochs/scheduler.pt +3 -0
- hf_bert_pro_20_epochs/special_tokens_map.json +7 -0
- hf_bert_pro_20_epochs/tokenizer_config.json +58 -0
- hf_bert_pro_20_epochs/trainer_state.json +575 -0
- hf_bert_pro_20_epochs/training_args.bin +3 -0
- hf_bert_pro_20_epochs/vocab.txt +0 -0
hf_bert_pro_20_epochs/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.50.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
hf_bert_pro_20_epochs/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75dcaa4c0a8882aeff6076d9c9c831468dd5cf4705344abd39081a07d309e1d
|
| 3 |
+
size 438080896
|
hf_bert_pro_20_epochs/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a36a06c9bf3dce81b1985ab339b90923af77dbd4698852ef6da9fadaae6e97
|
| 3 |
+
size 876283258
|
hf_bert_pro_20_epochs/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684f71dc1df0e694759ed6bbef1ad2a0a5bae49b4730ac5c9f3ae44cd2457a6a
|
| 3 |
+
size 14244
|
hf_bert_pro_20_epochs/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4170c39a78ba24967ff6c2afbeb63788a3da9095ea34b1afdb0875d95d31831c
|
| 3 |
+
size 1064
|
hf_bert_pro_20_epochs/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
hf_bert_pro_20_epochs/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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
hf_bert_pro_20_epochs/trainer_state.json
ADDED
|
@@ -0,0 +1,575 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 26250,
|
| 3 |
+
"best_metric": 1.6726031303405762,
|
| 4 |
+
"best_model_checkpoint": "output/checkpoint-26250",
|
| 5 |
+
"epoch": 21.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 26250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.4,
|
| 14 |
+
"grad_norm": 3.792271852493286,
|
| 15 |
+
"learning_rate": 4.9800000000000004e-05,
|
| 16 |
+
"loss": 2.1127,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.8,
|
| 21 |
+
"grad_norm": 3.493194341659546,
|
| 22 |
+
"learning_rate": 4.96e-05,
|
| 23 |
+
"loss": 2.0322,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0,
|
| 28 |
+
"eval_loss": 1.8727474212646484,
|
| 29 |
+
"eval_runtime": 79.5418,
|
| 30 |
+
"eval_samples_per_second": 125.72,
|
| 31 |
+
"eval_steps_per_second": 3.935,
|
| 32 |
+
"step": 1250
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.2,
|
| 36 |
+
"grad_norm": 3.216500759124756,
|
| 37 |
+
"learning_rate": 4.94e-05,
|
| 38 |
+
"loss": 1.9934,
|
| 39 |
+
"step": 1500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.6,
|
| 43 |
+
"grad_norm": 3.296123743057251,
|
| 44 |
+
"learning_rate": 4.92e-05,
|
| 45 |
+
"loss": 1.9576,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0,
|
| 50 |
+
"grad_norm": 3.778991460800171,
|
| 51 |
+
"learning_rate": 4.9e-05,
|
| 52 |
+
"loss": 1.9395,
|
| 53 |
+
"step": 2500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.0,
|
| 57 |
+
"eval_loss": 1.8361996412277222,
|
| 58 |
+
"eval_runtime": 79.8291,
|
| 59 |
+
"eval_samples_per_second": 125.268,
|
| 60 |
+
"eval_steps_per_second": 3.921,
|
| 61 |
+
"step": 2500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.4,
|
| 65 |
+
"grad_norm": 3.35451340675354,
|
| 66 |
+
"learning_rate": 4.88e-05,
|
| 67 |
+
"loss": 1.9039,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.8,
|
| 72 |
+
"grad_norm": 3.2007856369018555,
|
| 73 |
+
"learning_rate": 4.86e-05,
|
| 74 |
+
"loss": 1.899,
|
| 75 |
+
"step": 3500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.0,
|
| 79 |
+
"eval_loss": 1.8026707172393799,
|
| 80 |
+
"eval_runtime": 79.3622,
|
| 81 |
+
"eval_samples_per_second": 126.005,
|
| 82 |
+
"eval_steps_per_second": 3.944,
|
| 83 |
+
"step": 3750
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.2,
|
| 87 |
+
"grad_norm": 3.4291458129882812,
|
| 88 |
+
"learning_rate": 4.8400000000000004e-05,
|
| 89 |
+
"loss": 1.8836,
|
| 90 |
+
"step": 4000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.6,
|
| 94 |
+
"grad_norm": 3.329169988632202,
|
| 95 |
+
"learning_rate": 4.82e-05,
|
| 96 |
+
"loss": 1.8707,
|
| 97 |
+
"step": 4500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.0,
|
| 101 |
+
"grad_norm": 3.29327392578125,
|
| 102 |
+
"learning_rate": 4.8e-05,
|
| 103 |
+
"loss": 1.8571,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.0,
|
| 108 |
+
"eval_loss": 1.793080449104309,
|
| 109 |
+
"eval_runtime": 79.2565,
|
| 110 |
+
"eval_samples_per_second": 126.173,
|
| 111 |
+
"eval_steps_per_second": 3.949,
|
| 112 |
+
"step": 5000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.4,
|
| 116 |
+
"grad_norm": 3.511061429977417,
|
| 117 |
+
"learning_rate": 4.78e-05,
|
| 118 |
+
"loss": 1.8375,
|
| 119 |
+
"step": 5500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.8,
|
| 123 |
+
"grad_norm": 2.9841179847717285,
|
| 124 |
+
"learning_rate": 4.76e-05,
|
| 125 |
+
"loss": 1.8261,
|
| 126 |
+
"step": 6000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.0,
|
| 130 |
+
"eval_loss": 1.7694125175476074,
|
| 131 |
+
"eval_runtime": 79.3477,
|
| 132 |
+
"eval_samples_per_second": 126.028,
|
| 133 |
+
"eval_steps_per_second": 3.945,
|
| 134 |
+
"step": 6250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.2,
|
| 138 |
+
"grad_norm": 3.2486345767974854,
|
| 139 |
+
"learning_rate": 4.74e-05,
|
| 140 |
+
"loss": 1.8106,
|
| 141 |
+
"step": 6500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.6,
|
| 145 |
+
"grad_norm": 3.1133296489715576,
|
| 146 |
+
"learning_rate": 4.72e-05,
|
| 147 |
+
"loss": 1.797,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 6.0,
|
| 152 |
+
"grad_norm": 3.72696852684021,
|
| 153 |
+
"learning_rate": 4.7e-05,
|
| 154 |
+
"loss": 1.7989,
|
| 155 |
+
"step": 7500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 6.0,
|
| 159 |
+
"eval_loss": 1.752471685409546,
|
| 160 |
+
"eval_runtime": 79.6162,
|
| 161 |
+
"eval_samples_per_second": 125.603,
|
| 162 |
+
"eval_steps_per_second": 3.931,
|
| 163 |
+
"step": 7500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 6.4,
|
| 167 |
+
"grad_norm": 3.4890694618225098,
|
| 168 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 169 |
+
"loss": 1.7788,
|
| 170 |
+
"step": 8000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.8,
|
| 174 |
+
"grad_norm": 3.2990198135375977,
|
| 175 |
+
"learning_rate": 4.660000000000001e-05,
|
| 176 |
+
"loss": 1.7786,
|
| 177 |
+
"step": 8500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.0,
|
| 181 |
+
"eval_loss": 1.743485927581787,
|
| 182 |
+
"eval_runtime": 79.3229,
|
| 183 |
+
"eval_samples_per_second": 126.067,
|
| 184 |
+
"eval_steps_per_second": 3.946,
|
| 185 |
+
"step": 8750
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.2,
|
| 189 |
+
"grad_norm": 3.170145034790039,
|
| 190 |
+
"learning_rate": 4.64e-05,
|
| 191 |
+
"loss": 1.7718,
|
| 192 |
+
"step": 9000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 7.6,
|
| 196 |
+
"grad_norm": 3.1817779541015625,
|
| 197 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 198 |
+
"loss": 1.7558,
|
| 199 |
+
"step": 9500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 8.0,
|
| 203 |
+
"grad_norm": 3.174926519393921,
|
| 204 |
+
"learning_rate": 4.600000000000001e-05,
|
| 205 |
+
"loss": 1.756,
|
| 206 |
+
"step": 10000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.0,
|
| 210 |
+
"eval_loss": 1.7325628995895386,
|
| 211 |
+
"eval_runtime": 79.3253,
|
| 212 |
+
"eval_samples_per_second": 126.063,
|
| 213 |
+
"eval_steps_per_second": 3.946,
|
| 214 |
+
"step": 10000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 8.4,
|
| 218 |
+
"grad_norm": 3.2396745681762695,
|
| 219 |
+
"learning_rate": 4.58e-05,
|
| 220 |
+
"loss": 1.7342,
|
| 221 |
+
"step": 10500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 8.8,
|
| 225 |
+
"grad_norm": 3.2978265285491943,
|
| 226 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 227 |
+
"loss": 1.7325,
|
| 228 |
+
"step": 11000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 9.0,
|
| 232 |
+
"eval_loss": 1.7237361669540405,
|
| 233 |
+
"eval_runtime": 79.3397,
|
| 234 |
+
"eval_samples_per_second": 126.04,
|
| 235 |
+
"eval_steps_per_second": 3.945,
|
| 236 |
+
"step": 11250
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.2,
|
| 240 |
+
"grad_norm": 3.6129040718078613,
|
| 241 |
+
"learning_rate": 4.5400000000000006e-05,
|
| 242 |
+
"loss": 1.7311,
|
| 243 |
+
"step": 11500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.6,
|
| 247 |
+
"grad_norm": 3.5869312286376953,
|
| 248 |
+
"learning_rate": 4.52e-05,
|
| 249 |
+
"loss": 1.721,
|
| 250 |
+
"step": 12000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 10.0,
|
| 254 |
+
"grad_norm": 3.2217297554016113,
|
| 255 |
+
"learning_rate": 4.5e-05,
|
| 256 |
+
"loss": 1.7256,
|
| 257 |
+
"step": 12500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 10.0,
|
| 261 |
+
"eval_loss": 1.7248116731643677,
|
| 262 |
+
"eval_runtime": 79.9338,
|
| 263 |
+
"eval_samples_per_second": 125.104,
|
| 264 |
+
"eval_steps_per_second": 3.916,
|
| 265 |
+
"step": 12500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 10.4,
|
| 269 |
+
"grad_norm": 3.1793668270111084,
|
| 270 |
+
"learning_rate": 4.4800000000000005e-05,
|
| 271 |
+
"loss": 1.6923,
|
| 272 |
+
"step": 13000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 10.8,
|
| 276 |
+
"grad_norm": 2.925715684890747,
|
| 277 |
+
"learning_rate": 4.46e-05,
|
| 278 |
+
"loss": 1.7066,
|
| 279 |
+
"step": 13500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 11.0,
|
| 283 |
+
"eval_loss": 1.7208353281021118,
|
| 284 |
+
"eval_runtime": 79.1759,
|
| 285 |
+
"eval_samples_per_second": 126.301,
|
| 286 |
+
"eval_steps_per_second": 3.953,
|
| 287 |
+
"step": 13750
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 11.2,
|
| 291 |
+
"grad_norm": 3.0651283264160156,
|
| 292 |
+
"learning_rate": 4.44e-05,
|
| 293 |
+
"loss": 1.6894,
|
| 294 |
+
"step": 14000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 11.6,
|
| 298 |
+
"grad_norm": 2.897967576980591,
|
| 299 |
+
"learning_rate": 4.4200000000000004e-05,
|
| 300 |
+
"loss": 1.6852,
|
| 301 |
+
"step": 14500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 12.0,
|
| 305 |
+
"grad_norm": 3.138188123703003,
|
| 306 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 307 |
+
"loss": 1.6891,
|
| 308 |
+
"step": 15000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 12.0,
|
| 312 |
+
"eval_loss": 1.7089905738830566,
|
| 313 |
+
"eval_runtime": 79.1389,
|
| 314 |
+
"eval_samples_per_second": 126.36,
|
| 315 |
+
"eval_steps_per_second": 3.955,
|
| 316 |
+
"step": 15000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 12.4,
|
| 320 |
+
"grad_norm": 3.3055591583251953,
|
| 321 |
+
"learning_rate": 4.38e-05,
|
| 322 |
+
"loss": 1.6685,
|
| 323 |
+
"step": 15500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 12.8,
|
| 327 |
+
"grad_norm": 3.092822551727295,
|
| 328 |
+
"learning_rate": 4.36e-05,
|
| 329 |
+
"loss": 1.6747,
|
| 330 |
+
"step": 16000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 13.0,
|
| 334 |
+
"eval_loss": 1.7045754194259644,
|
| 335 |
+
"eval_runtime": 79.6544,
|
| 336 |
+
"eval_samples_per_second": 125.542,
|
| 337 |
+
"eval_steps_per_second": 3.929,
|
| 338 |
+
"step": 16250
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 13.2,
|
| 342 |
+
"grad_norm": 3.1481597423553467,
|
| 343 |
+
"learning_rate": 4.3400000000000005e-05,
|
| 344 |
+
"loss": 1.662,
|
| 345 |
+
"step": 16500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 13.6,
|
| 349 |
+
"grad_norm": 3.1880903244018555,
|
| 350 |
+
"learning_rate": 4.32e-05,
|
| 351 |
+
"loss": 1.6573,
|
| 352 |
+
"step": 17000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 14.0,
|
| 356 |
+
"grad_norm": 3.1915714740753174,
|
| 357 |
+
"learning_rate": 4.3e-05,
|
| 358 |
+
"loss": 1.656,
|
| 359 |
+
"step": 17500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 14.0,
|
| 363 |
+
"eval_loss": 1.699405312538147,
|
| 364 |
+
"eval_runtime": 79.9022,
|
| 365 |
+
"eval_samples_per_second": 125.153,
|
| 366 |
+
"eval_steps_per_second": 3.917,
|
| 367 |
+
"step": 17500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 14.4,
|
| 371 |
+
"grad_norm": 3.177797317504883,
|
| 372 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 373 |
+
"loss": 1.6334,
|
| 374 |
+
"step": 18000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 14.8,
|
| 378 |
+
"grad_norm": 3.0355215072631836,
|
| 379 |
+
"learning_rate": 4.26e-05,
|
| 380 |
+
"loss": 1.646,
|
| 381 |
+
"step": 18500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 15.0,
|
| 385 |
+
"eval_loss": 1.6880792379379272,
|
| 386 |
+
"eval_runtime": 79.6882,
|
| 387 |
+
"eval_samples_per_second": 125.489,
|
| 388 |
+
"eval_steps_per_second": 3.928,
|
| 389 |
+
"step": 18750
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 15.2,
|
| 393 |
+
"grad_norm": 3.201802968978882,
|
| 394 |
+
"learning_rate": 4.24e-05,
|
| 395 |
+
"loss": 1.6369,
|
| 396 |
+
"step": 19000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 15.6,
|
| 400 |
+
"grad_norm": 2.9140782356262207,
|
| 401 |
+
"learning_rate": 4.22e-05,
|
| 402 |
+
"loss": 1.6254,
|
| 403 |
+
"step": 19500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 16.0,
|
| 407 |
+
"grad_norm": 2.9663515090942383,
|
| 408 |
+
"learning_rate": 4.2e-05,
|
| 409 |
+
"loss": 1.6272,
|
| 410 |
+
"step": 20000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 16.0,
|
| 414 |
+
"eval_loss": 1.6963340044021606,
|
| 415 |
+
"eval_runtime": 79.4158,
|
| 416 |
+
"eval_samples_per_second": 125.919,
|
| 417 |
+
"eval_steps_per_second": 3.941,
|
| 418 |
+
"step": 20000
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 16.4,
|
| 422 |
+
"grad_norm": 3.0621337890625,
|
| 423 |
+
"learning_rate": 4.18e-05,
|
| 424 |
+
"loss": 1.6149,
|
| 425 |
+
"step": 20500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 16.8,
|
| 429 |
+
"grad_norm": 3.031522750854492,
|
| 430 |
+
"learning_rate": 4.16e-05,
|
| 431 |
+
"loss": 1.6216,
|
| 432 |
+
"step": 21000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 17.0,
|
| 436 |
+
"eval_loss": 1.6839699745178223,
|
| 437 |
+
"eval_runtime": 79.786,
|
| 438 |
+
"eval_samples_per_second": 125.335,
|
| 439 |
+
"eval_steps_per_second": 3.923,
|
| 440 |
+
"step": 21250
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 17.2,
|
| 444 |
+
"grad_norm": 3.0754151344299316,
|
| 445 |
+
"learning_rate": 4.14e-05,
|
| 446 |
+
"loss": 1.6137,
|
| 447 |
+
"step": 21500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 17.6,
|
| 451 |
+
"grad_norm": 3.2484161853790283,
|
| 452 |
+
"learning_rate": 4.12e-05,
|
| 453 |
+
"loss": 1.601,
|
| 454 |
+
"step": 22000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 18.0,
|
| 458 |
+
"grad_norm": 2.982337236404419,
|
| 459 |
+
"learning_rate": 4.1e-05,
|
| 460 |
+
"loss": 1.6163,
|
| 461 |
+
"step": 22500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 18.0,
|
| 465 |
+
"eval_loss": 1.6896445751190186,
|
| 466 |
+
"eval_runtime": 79.3863,
|
| 467 |
+
"eval_samples_per_second": 125.966,
|
| 468 |
+
"eval_steps_per_second": 3.943,
|
| 469 |
+
"step": 22500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 18.4,
|
| 473 |
+
"grad_norm": 3.2979774475097656,
|
| 474 |
+
"learning_rate": 4.08e-05,
|
| 475 |
+
"loss": 1.5941,
|
| 476 |
+
"step": 23000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 18.8,
|
| 480 |
+
"grad_norm": 3.40487003326416,
|
| 481 |
+
"learning_rate": 4.0600000000000004e-05,
|
| 482 |
+
"loss": 1.5928,
|
| 483 |
+
"step": 23500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 19.0,
|
| 487 |
+
"eval_loss": 1.6783804893493652,
|
| 488 |
+
"eval_runtime": 79.4878,
|
| 489 |
+
"eval_samples_per_second": 125.805,
|
| 490 |
+
"eval_steps_per_second": 3.938,
|
| 491 |
+
"step": 23750
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 19.2,
|
| 495 |
+
"grad_norm": 3.0854432582855225,
|
| 496 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 497 |
+
"loss": 1.5911,
|
| 498 |
+
"step": 24000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 19.6,
|
| 502 |
+
"grad_norm": 3.0497543811798096,
|
| 503 |
+
"learning_rate": 4.02e-05,
|
| 504 |
+
"loss": 1.5861,
|
| 505 |
+
"step": 24500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 20.0,
|
| 509 |
+
"grad_norm": 3.2561333179473877,
|
| 510 |
+
"learning_rate": 4e-05,
|
| 511 |
+
"loss": 1.5906,
|
| 512 |
+
"step": 25000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 20.0,
|
| 516 |
+
"eval_loss": 1.686535358428955,
|
| 517 |
+
"eval_runtime": 79.4354,
|
| 518 |
+
"eval_samples_per_second": 125.888,
|
| 519 |
+
"eval_steps_per_second": 3.94,
|
| 520 |
+
"step": 25000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 20.4,
|
| 524 |
+
"grad_norm": 2.977836847305298,
|
| 525 |
+
"learning_rate": 3.9800000000000005e-05,
|
| 526 |
+
"loss": 1.5759,
|
| 527 |
+
"step": 25500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 20.8,
|
| 531 |
+
"grad_norm": 3.172325849533081,
|
| 532 |
+
"learning_rate": 3.960000000000001e-05,
|
| 533 |
+
"loss": 1.5745,
|
| 534 |
+
"step": 26000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 21.0,
|
| 538 |
+
"eval_loss": 1.6726031303405762,
|
| 539 |
+
"eval_runtime": 79.5286,
|
| 540 |
+
"eval_samples_per_second": 125.741,
|
| 541 |
+
"eval_steps_per_second": 3.936,
|
| 542 |
+
"step": 26250
|
| 543 |
+
}
|
| 544 |
+
],
|
| 545 |
+
"logging_steps": 500,
|
| 546 |
+
"max_steps": 125000,
|
| 547 |
+
"num_input_tokens_seen": 0,
|
| 548 |
+
"num_train_epochs": 100,
|
| 549 |
+
"save_steps": 500,
|
| 550 |
+
"stateful_callbacks": {
|
| 551 |
+
"EarlyStoppingCallback": {
|
| 552 |
+
"args": {
|
| 553 |
+
"early_stopping_patience": 2,
|
| 554 |
+
"early_stopping_threshold": 0.0
|
| 555 |
+
},
|
| 556 |
+
"attributes": {
|
| 557 |
+
"early_stopping_patience_counter": 0
|
| 558 |
+
}
|
| 559 |
+
},
|
| 560 |
+
"TrainerControl": {
|
| 561 |
+
"args": {
|
| 562 |
+
"should_epoch_stop": false,
|
| 563 |
+
"should_evaluate": false,
|
| 564 |
+
"should_log": false,
|
| 565 |
+
"should_save": true,
|
| 566 |
+
"should_training_stop": false
|
| 567 |
+
},
|
| 568 |
+
"attributes": {}
|
| 569 |
+
}
|
| 570 |
+
},
|
| 571 |
+
"total_flos": 2.21092042752e+17,
|
| 572 |
+
"train_batch_size": 32,
|
| 573 |
+
"trial_name": null,
|
| 574 |
+
"trial_params": null
|
| 575 |
+
}
|
hf_bert_pro_20_epochs/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a869cfb5e8648cac80034c3c19dd58178378a28654fb923b5a7f7ee5de136ecf
|
| 3 |
+
size 5304
|
hf_bert_pro_20_epochs/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|