commit files to HF hub
Browse files- config.json +26 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +465 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.42.0.dev0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.42.0.dev0"
|
| 5 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56011abb0bc8a76c667a400fb4675fd8ceeaa79c0313a876cad63a141115a53f
|
| 3 |
+
size 438080896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85eaef3da135ce7630db7a1de6ac3c9a21908c865a504f7252550f8c85928039
|
| 3 |
+
size 876283258
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a00a7764f8ac3474e6269ba42d2b0840eab43bf25501e0cf3de52159396165f
|
| 3 |
+
size 14960
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938c3f1af73e72ac9fc33aebd25cf0d26422879318f26b3ea325199a5969c9ac
|
| 3 |
+
size 14960
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94a73d2ca9c948698762d3c0e989f98d3c7fd2cdb06bab906459f6b01b571ba6
|
| 3 |
+
size 14960
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2649d953591f262036a5fa4f03ce7756b14a2c6e3d1f713e346627276aafc6c
|
| 3 |
+
size 14960
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5414ff590e460874083e827db46f17a7684f04e4d067c617a8db72bc0ea4b41d
|
| 3 |
+
size 1064
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.10353731364011765,
|
| 3 |
+
"best_model_checkpoint": "bert-base-uncased_rxnorm_babbage/checkpoint-2500",
|
| 4 |
+
"epoch": 49.76958525345622,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.8433179723502304,
|
| 13 |
+
"grad_norm": 0.49460217356681824,
|
| 14 |
+
"learning_rate": 4.8166666666666674e-05,
|
| 15 |
+
"loss": 1.0876,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.8433179723502304,
|
| 20 |
+
"eval_accuracy": 0.861022820273691,
|
| 21 |
+
"eval_loss": 0.6498942375183105,
|
| 22 |
+
"eval_runtime": 1.5825,
|
| 23 |
+
"eval_samples_per_second": 921.986,
|
| 24 |
+
"eval_steps_per_second": 7.583,
|
| 25 |
+
"step": 100
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 3.686635944700461,
|
| 29 |
+
"grad_norm": 0.4745028614997864,
|
| 30 |
+
"learning_rate": 4.631481481481481e-05,
|
| 31 |
+
"loss": 0.6229,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.686635944700461,
|
| 36 |
+
"eval_accuracy": 0.8976233828461907,
|
| 37 |
+
"eval_loss": 0.45648184418678284,
|
| 38 |
+
"eval_runtime": 2.1968,
|
| 39 |
+
"eval_samples_per_second": 664.134,
|
| 40 |
+
"eval_steps_per_second": 5.462,
|
| 41 |
+
"step": 200
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 5.529953917050691,
|
| 45 |
+
"grad_norm": 0.4159073233604431,
|
| 46 |
+
"learning_rate": 4.4462962962962966e-05,
|
| 47 |
+
"loss": 0.4851,
|
| 48 |
+
"step": 300
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 5.529953917050691,
|
| 52 |
+
"eval_accuracy": 0.9128444732034104,
|
| 53 |
+
"eval_loss": 0.3751491904258728,
|
| 54 |
+
"eval_runtime": 2.5186,
|
| 55 |
+
"eval_samples_per_second": 579.279,
|
| 56 |
+
"eval_steps_per_second": 4.764,
|
| 57 |
+
"step": 300
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.373271889400922,
|
| 61 |
+
"grad_norm": 0.40352028608322144,
|
| 62 |
+
"learning_rate": 4.261111111111111e-05,
|
| 63 |
+
"loss": 0.4009,
|
| 64 |
+
"step": 400
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 7.373271889400922,
|
| 68 |
+
"eval_accuracy": 0.926327338644278,
|
| 69 |
+
"eval_loss": 0.3037292957305908,
|
| 70 |
+
"eval_runtime": 2.2024,
|
| 71 |
+
"eval_samples_per_second": 662.468,
|
| 72 |
+
"eval_steps_per_second": 5.449,
|
| 73 |
+
"step": 400
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.216589861751151,
|
| 77 |
+
"grad_norm": 0.3955836296081543,
|
| 78 |
+
"learning_rate": 4.0759259259259264e-05,
|
| 79 |
+
"loss": 0.34,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 9.216589861751151,
|
| 84 |
+
"eval_accuracy": 0.9363742622825171,
|
| 85 |
+
"eval_loss": 0.256952166557312,
|
| 86 |
+
"eval_runtime": 2.2081,
|
| 87 |
+
"eval_samples_per_second": 660.734,
|
| 88 |
+
"eval_steps_per_second": 5.434,
|
| 89 |
+
"step": 500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 11.059907834101383,
|
| 93 |
+
"grad_norm": 0.35034212470054626,
|
| 94 |
+
"learning_rate": 3.890740740740741e-05,
|
| 95 |
+
"loss": 0.302,
|
| 96 |
+
"step": 600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 11.059907834101383,
|
| 100 |
+
"eval_accuracy": 0.9409385419824189,
|
| 101 |
+
"eval_loss": 0.23246321082115173,
|
| 102 |
+
"eval_runtime": 2.205,
|
| 103 |
+
"eval_samples_per_second": 661.68,
|
| 104 |
+
"eval_steps_per_second": 5.442,
|
| 105 |
+
"step": 600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 12.903225806451612,
|
| 109 |
+
"grad_norm": 0.3660498261451721,
|
| 110 |
+
"learning_rate": 3.705555555555556e-05,
|
| 111 |
+
"loss": 0.2701,
|
| 112 |
+
"step": 700
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 12.903225806451612,
|
| 116 |
+
"eval_accuracy": 0.9453203622945321,
|
| 117 |
+
"eval_loss": 0.21490083634853363,
|
| 118 |
+
"eval_runtime": 1.8882,
|
| 119 |
+
"eval_samples_per_second": 772.706,
|
| 120 |
+
"eval_steps_per_second": 6.355,
|
| 121 |
+
"step": 700
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.746543778801843,
|
| 125 |
+
"grad_norm": 0.35468629002571106,
|
| 126 |
+
"learning_rate": 3.520370370370371e-05,
|
| 127 |
+
"loss": 0.2488,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 14.746543778801843,
|
| 132 |
+
"eval_accuracy": 0.9499065420560747,
|
| 133 |
+
"eval_loss": 0.19009685516357422,
|
| 134 |
+
"eval_runtime": 2.5126,
|
| 135 |
+
"eval_samples_per_second": 580.675,
|
| 136 |
+
"eval_steps_per_second": 4.776,
|
| 137 |
+
"step": 800
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 16.589861751152075,
|
| 141 |
+
"grad_norm": 0.33421748876571655,
|
| 142 |
+
"learning_rate": 3.3351851851851854e-05,
|
| 143 |
+
"loss": 0.23,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 16.589861751152075,
|
| 148 |
+
"eval_accuracy": 0.9532317494434636,
|
| 149 |
+
"eval_loss": 0.17756867408752441,
|
| 150 |
+
"eval_runtime": 2.5048,
|
| 151 |
+
"eval_samples_per_second": 582.491,
|
| 152 |
+
"eval_steps_per_second": 4.791,
|
| 153 |
+
"step": 900
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 18.433179723502302,
|
| 157 |
+
"grad_norm": 0.33518287539482117,
|
| 158 |
+
"learning_rate": 3.15e-05,
|
| 159 |
+
"loss": 0.2151,
|
| 160 |
+
"step": 1000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 18.433179723502302,
|
| 164 |
+
"eval_accuracy": 0.9545267509401824,
|
| 165 |
+
"eval_loss": 0.16874656081199646,
|
| 166 |
+
"eval_runtime": 2.1981,
|
| 167 |
+
"eval_samples_per_second": 663.764,
|
| 168 |
+
"eval_steps_per_second": 5.459,
|
| 169 |
+
"step": 1000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 20.276497695852534,
|
| 173 |
+
"grad_norm": 0.34771665930747986,
|
| 174 |
+
"learning_rate": 2.9648148148148146e-05,
|
| 175 |
+
"loss": 0.2035,
|
| 176 |
+
"step": 1100
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 20.276497695852534,
|
| 180 |
+
"eval_accuracy": 0.9563604730084985,
|
| 181 |
+
"eval_loss": 0.1599314957857132,
|
| 182 |
+
"eval_runtime": 1.8901,
|
| 183 |
+
"eval_samples_per_second": 771.908,
|
| 184 |
+
"eval_steps_per_second": 6.349,
|
| 185 |
+
"step": 1100
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 22.119815668202765,
|
| 189 |
+
"grad_norm": 0.36460649967193604,
|
| 190 |
+
"learning_rate": 2.77962962962963e-05,
|
| 191 |
+
"loss": 0.1931,
|
| 192 |
+
"step": 1200
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 22.119815668202765,
|
| 196 |
+
"eval_accuracy": 0.9590011289404363,
|
| 197 |
+
"eval_loss": 0.1495586484670639,
|
| 198 |
+
"eval_runtime": 2.1981,
|
| 199 |
+
"eval_samples_per_second": 663.751,
|
| 200 |
+
"eval_steps_per_second": 5.459,
|
| 201 |
+
"step": 1200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 23.963133640552996,
|
| 205 |
+
"grad_norm": 0.31464290618896484,
|
| 206 |
+
"learning_rate": 2.5944444444444444e-05,
|
| 207 |
+
"loss": 0.1848,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 23.963133640552996,
|
| 212 |
+
"eval_accuracy": 0.9585790320110277,
|
| 213 |
+
"eval_loss": 0.1497500240802765,
|
| 214 |
+
"eval_runtime": 2.2017,
|
| 215 |
+
"eval_samples_per_second": 662.667,
|
| 216 |
+
"eval_steps_per_second": 5.45,
|
| 217 |
+
"step": 1300
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 25.806451612903224,
|
| 221 |
+
"grad_norm": 0.36158451437950134,
|
| 222 |
+
"learning_rate": 2.4092592592592593e-05,
|
| 223 |
+
"loss": 0.1766,
|
| 224 |
+
"step": 1400
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 25.806451612903224,
|
| 228 |
+
"eval_accuracy": 0.962577764207473,
|
| 229 |
+
"eval_loss": 0.13511128723621368,
|
| 230 |
+
"eval_runtime": 1.8934,
|
| 231 |
+
"eval_samples_per_second": 770.57,
|
| 232 |
+
"eval_steps_per_second": 6.338,
|
| 233 |
+
"step": 1400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 27.649769585253456,
|
| 237 |
+
"grad_norm": 0.29482343792915344,
|
| 238 |
+
"learning_rate": 2.2240740740740743e-05,
|
| 239 |
+
"loss": 0.1695,
|
| 240 |
+
"step": 1500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 27.649769585253456,
|
| 244 |
+
"eval_accuracy": 0.9624521660736379,
|
| 245 |
+
"eval_loss": 0.13419833779335022,
|
| 246 |
+
"eval_runtime": 2.1989,
|
| 247 |
+
"eval_samples_per_second": 663.518,
|
| 248 |
+
"eval_steps_per_second": 5.457,
|
| 249 |
+
"step": 1500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 29.493087557603687,
|
| 253 |
+
"grad_norm": 0.3058522939682007,
|
| 254 |
+
"learning_rate": 2.0388888888888892e-05,
|
| 255 |
+
"loss": 0.1648,
|
| 256 |
+
"step": 1600
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 29.493087557603687,
|
| 260 |
+
"eval_accuracy": 0.9629643832989789,
|
| 261 |
+
"eval_loss": 0.12756001949310303,
|
| 262 |
+
"eval_runtime": 1.8879,
|
| 263 |
+
"eval_samples_per_second": 772.823,
|
| 264 |
+
"eval_steps_per_second": 6.356,
|
| 265 |
+
"step": 1600
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 31.336405529953918,
|
| 269 |
+
"grad_norm": 0.302731990814209,
|
| 270 |
+
"learning_rate": 1.8537037037037037e-05,
|
| 271 |
+
"loss": 0.1587,
|
| 272 |
+
"step": 1700
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 31.336405529953918,
|
| 276 |
+
"eval_accuracy": 0.9647220525351252,
|
| 277 |
+
"eval_loss": 0.1241796463727951,
|
| 278 |
+
"eval_runtime": 2.1929,
|
| 279 |
+
"eval_samples_per_second": 665.32,
|
| 280 |
+
"eval_steps_per_second": 5.472,
|
| 281 |
+
"step": 1700
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 33.17972350230415,
|
| 285 |
+
"grad_norm": 0.2924918830394745,
|
| 286 |
+
"learning_rate": 1.6685185185185187e-05,
|
| 287 |
+
"loss": 0.1535,
|
| 288 |
+
"step": 1800
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 33.17972350230415,
|
| 292 |
+
"eval_accuracy": 0.9656390433391728,
|
| 293 |
+
"eval_loss": 0.11920326948165894,
|
| 294 |
+
"eval_runtime": 2.5148,
|
| 295 |
+
"eval_samples_per_second": 580.167,
|
| 296 |
+
"eval_steps_per_second": 4.772,
|
| 297 |
+
"step": 1800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 35.02304147465438,
|
| 301 |
+
"grad_norm": 0.28826281428337097,
|
| 302 |
+
"learning_rate": 1.4833333333333336e-05,
|
| 303 |
+
"loss": 0.1513,
|
| 304 |
+
"step": 1900
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 35.02304147465438,
|
| 308 |
+
"eval_accuracy": 0.9667637762291024,
|
| 309 |
+
"eval_loss": 0.11383702605962753,
|
| 310 |
+
"eval_runtime": 2.2026,
|
| 311 |
+
"eval_samples_per_second": 662.398,
|
| 312 |
+
"eval_steps_per_second": 5.448,
|
| 313 |
+
"step": 1900
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 36.866359447004605,
|
| 317 |
+
"grad_norm": 0.3061148226261139,
|
| 318 |
+
"learning_rate": 1.2981481481481483e-05,
|
| 319 |
+
"loss": 0.1475,
|
| 320 |
+
"step": 2000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 36.866359447004605,
|
| 324 |
+
"eval_accuracy": 0.9674900966719034,
|
| 325 |
+
"eval_loss": 0.11254725605249405,
|
| 326 |
+
"eval_runtime": 2.1953,
|
| 327 |
+
"eval_samples_per_second": 664.587,
|
| 328 |
+
"eval_steps_per_second": 5.466,
|
| 329 |
+
"step": 2000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 38.70967741935484,
|
| 333 |
+
"grad_norm": 0.29151493310928345,
|
| 334 |
+
"learning_rate": 1.1129629629629631e-05,
|
| 335 |
+
"loss": 0.1451,
|
| 336 |
+
"step": 2100
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 38.70967741935484,
|
| 340 |
+
"eval_accuracy": 0.9666907144077611,
|
| 341 |
+
"eval_loss": 0.11542753875255585,
|
| 342 |
+
"eval_runtime": 2.1993,
|
| 343 |
+
"eval_samples_per_second": 663.397,
|
| 344 |
+
"eval_steps_per_second": 5.456,
|
| 345 |
+
"step": 2100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 40.55299539170507,
|
| 349 |
+
"grad_norm": 0.2895043194293976,
|
| 350 |
+
"learning_rate": 9.277777777777778e-06,
|
| 351 |
+
"loss": 0.1434,
|
| 352 |
+
"step": 2200
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 40.55299539170507,
|
| 356 |
+
"eval_accuracy": 0.9673665255454876,
|
| 357 |
+
"eval_loss": 0.11377675086259842,
|
| 358 |
+
"eval_runtime": 2.5118,
|
| 359 |
+
"eval_samples_per_second": 580.85,
|
| 360 |
+
"eval_steps_per_second": 4.777,
|
| 361 |
+
"step": 2200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 42.3963133640553,
|
| 365 |
+
"grad_norm": 0.2832992374897003,
|
| 366 |
+
"learning_rate": 7.425925925925927e-06,
|
| 367 |
+
"loss": 0.1413,
|
| 368 |
+
"step": 2300
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 42.3963133640553,
|
| 372 |
+
"eval_accuracy": 0.9687953762491814,
|
| 373 |
+
"eval_loss": 0.10766085237264633,
|
| 374 |
+
"eval_runtime": 2.5152,
|
| 375 |
+
"eval_samples_per_second": 580.081,
|
| 376 |
+
"eval_steps_per_second": 4.771,
|
| 377 |
+
"step": 2300
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 44.23963133640553,
|
| 381 |
+
"grad_norm": 0.2880547046661377,
|
| 382 |
+
"learning_rate": 5.574074074074074e-06,
|
| 383 |
+
"loss": 0.1398,
|
| 384 |
+
"step": 2400
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 44.23963133640553,
|
| 388 |
+
"eval_accuracy": 0.9683431416498955,
|
| 389 |
+
"eval_loss": 0.10695406049489975,
|
| 390 |
+
"eval_runtime": 2.1984,
|
| 391 |
+
"eval_samples_per_second": 663.665,
|
| 392 |
+
"eval_steps_per_second": 5.459,
|
| 393 |
+
"step": 2400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 46.08294930875576,
|
| 397 |
+
"grad_norm": 0.2785598337650299,
|
| 398 |
+
"learning_rate": 3.722222222222222e-06,
|
| 399 |
+
"loss": 0.1373,
|
| 400 |
+
"step": 2500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 46.08294930875576,
|
| 404 |
+
"eval_accuracy": 0.9688496396065625,
|
| 405 |
+
"eval_loss": 0.10353731364011765,
|
| 406 |
+
"eval_runtime": 1.8905,
|
| 407 |
+
"eval_samples_per_second": 771.736,
|
| 408 |
+
"eval_steps_per_second": 6.347,
|
| 409 |
+
"step": 2500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 47.92626728110599,
|
| 413 |
+
"grad_norm": 0.2812165319919586,
|
| 414 |
+
"learning_rate": 1.8703703703703707e-06,
|
| 415 |
+
"loss": 0.1366,
|
| 416 |
+
"step": 2600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 47.92626728110599,
|
| 420 |
+
"eval_accuracy": 0.9693371955635172,
|
| 421 |
+
"eval_loss": 0.10568127781152725,
|
| 422 |
+
"eval_runtime": 1.8904,
|
| 423 |
+
"eval_samples_per_second": 771.79,
|
| 424 |
+
"eval_steps_per_second": 6.348,
|
| 425 |
+
"step": 2600
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 49.76958525345622,
|
| 429 |
+
"grad_norm": 0.2685796022415161,
|
| 430 |
+
"learning_rate": 1.8518518518518518e-08,
|
| 431 |
+
"loss": 0.1368,
|
| 432 |
+
"step": 2700
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 49.76958525345622,
|
| 436 |
+
"eval_accuracy": 0.9689754071024974,
|
| 437 |
+
"eval_loss": 0.10547203570604324,
|
| 438 |
+
"eval_runtime": 1.8901,
|
| 439 |
+
"eval_samples_per_second": 771.907,
|
| 440 |
+
"eval_steps_per_second": 6.349,
|
| 441 |
+
"step": 2700
|
| 442 |
+
}
|
| 443 |
+
],
|
| 444 |
+
"logging_steps": 100,
|
| 445 |
+
"max_steps": 2700,
|
| 446 |
+
"num_input_tokens_seen": 0,
|
| 447 |
+
"num_train_epochs": 50,
|
| 448 |
+
"save_steps": 100,
|
| 449 |
+
"stateful_callbacks": {
|
| 450 |
+
"TrainerControl": {
|
| 451 |
+
"args": {
|
| 452 |
+
"should_epoch_stop": false,
|
| 453 |
+
"should_evaluate": false,
|
| 454 |
+
"should_log": false,
|
| 455 |
+
"should_save": true,
|
| 456 |
+
"should_training_stop": true
|
| 457 |
+
},
|
| 458 |
+
"attributes": {}
|
| 459 |
+
}
|
| 460 |
+
},
|
| 461 |
+
"total_flos": 3.638543188324516e+17,
|
| 462 |
+
"train_batch_size": 32,
|
| 463 |
+
"trial_name": null,
|
| 464 |
+
"trial_params": null
|
| 465 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e34afbf5523ef0466ca55ab68e3b60028bf0db9f96324a23783c919d51bacedb
|
| 3 |
+
size 5048
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|