Upload 12 files
Browse files- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +341 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "woolf",
|
| 15 |
+
"1": "fitzgerald",
|
| 16 |
+
"2": "hemingway"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"fitzgerald": 1,
|
| 22 |
+
"hemingway": 2,
|
| 23 |
+
"woolf": 0
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 16,
|
| 29 |
+
"num_hidden_layers": 24,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.38.0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1a43a2c43776180138382dc40a5987df33047730cfabb175900db3e8dd88569
|
| 3 |
+
size 1421499516
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99543c6af1071b52ea1634e9d1a7a6732785ea9dd4b5ba779055961a61d3fabb
|
| 3 |
+
size 2843231469
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceb3f416d587f417a6cc12fc98914bbd1f12442a6fd522ada079ff9284e37534
|
| 3 |
+
size 14180
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b85a293c5c1534416685cc7b27fae42d9a00ae4392060f72e8170e11fa1f9bb1
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9596994535519126,
|
| 3 |
+
"best_model_checkpoint": "train_authorship/train_outputs/05-25-2024_21:30:31/checkpoint-560",
|
| 4 |
+
"epoch": 8.115942028985508,
|
| 5 |
+
"eval_steps": 35,
|
| 6 |
+
"global_step": 560,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.51,
|
| 13 |
+
"grad_norm": 9.12179946899414,
|
| 14 |
+
"learning_rate": 2.5362318840579714e-05,
|
| 15 |
+
"loss": 0.9599,
|
| 16 |
+
"step": 35
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.51,
|
| 20 |
+
"eval_acc_product": 0.522295927646477,
|
| 21 |
+
"eval_fitzgerald_acc": 0.6823770491803278,
|
| 22 |
+
"eval_hemingway_acc": 0.9651639344262295,
|
| 23 |
+
"eval_loss": 0.4738686978816986,
|
| 24 |
+
"eval_overall_acc": 0.8135245901639344,
|
| 25 |
+
"eval_runtime": 13.1203,
|
| 26 |
+
"eval_samples_per_second": 111.583,
|
| 27 |
+
"eval_steps_per_second": 1.753,
|
| 28 |
+
"eval_woolf_acc": 0.7930327868852459,
|
| 29 |
+
"step": 35
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.01,
|
| 33 |
+
"grad_norm": 18.4027099609375,
|
| 34 |
+
"learning_rate": 4.99194847020934e-05,
|
| 35 |
+
"loss": 0.3839,
|
| 36 |
+
"step": 70
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.01,
|
| 40 |
+
"eval_acc_product": 0.7210372836134964,
|
| 41 |
+
"eval_fitzgerald_acc": 0.764344262295082,
|
| 42 |
+
"eval_hemingway_acc": 0.9815573770491803,
|
| 43 |
+
"eval_loss": 0.24899350106716156,
|
| 44 |
+
"eval_overall_acc": 0.9023224043715847,
|
| 45 |
+
"eval_runtime": 13.1386,
|
| 46 |
+
"eval_samples_per_second": 111.428,
|
| 47 |
+
"eval_steps_per_second": 1.751,
|
| 48 |
+
"eval_woolf_acc": 0.9610655737704918,
|
| 49 |
+
"step": 70
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.52,
|
| 53 |
+
"grad_norm": 7.836585998535156,
|
| 54 |
+
"learning_rate": 4.710144927536232e-05,
|
| 55 |
+
"loss": 0.2387,
|
| 56 |
+
"step": 105
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.52,
|
| 60 |
+
"eval_acc_product": 0.8025821475696203,
|
| 61 |
+
"eval_fitzgerald_acc": 0.9631147540983607,
|
| 62 |
+
"eval_hemingway_acc": 0.9221311475409836,
|
| 63 |
+
"eval_loss": 0.20742054283618927,
|
| 64 |
+
"eval_overall_acc": 0.9296448087431693,
|
| 65 |
+
"eval_runtime": 13.1443,
|
| 66 |
+
"eval_samples_per_second": 111.379,
|
| 67 |
+
"eval_steps_per_second": 1.75,
|
| 68 |
+
"eval_woolf_acc": 0.9036885245901639,
|
| 69 |
+
"step": 105
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.03,
|
| 73 |
+
"grad_norm": 10.438405990600586,
|
| 74 |
+
"learning_rate": 4.428341384863124e-05,
|
| 75 |
+
"loss": 0.1938,
|
| 76 |
+
"step": 140
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.03,
|
| 80 |
+
"eval_acc_product": 0.8229529244050163,
|
| 81 |
+
"eval_fitzgerald_acc": 0.9528688524590164,
|
| 82 |
+
"eval_hemingway_acc": 0.9733606557377049,
|
| 83 |
+
"eval_loss": 0.2009282410144806,
|
| 84 |
+
"eval_overall_acc": 0.9378415300546448,
|
| 85 |
+
"eval_runtime": 13.1419,
|
| 86 |
+
"eval_samples_per_second": 111.399,
|
| 87 |
+
"eval_steps_per_second": 1.75,
|
| 88 |
+
"eval_woolf_acc": 0.8872950819672131,
|
| 89 |
+
"step": 140
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.54,
|
| 93 |
+
"grad_norm": 11.882472038269043,
|
| 94 |
+
"learning_rate": 4.146537842190016e-05,
|
| 95 |
+
"loss": 0.1373,
|
| 96 |
+
"step": 175
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.54,
|
| 100 |
+
"eval_acc_product": 0.8087266940845269,
|
| 101 |
+
"eval_fitzgerald_acc": 0.9467213114754098,
|
| 102 |
+
"eval_hemingway_acc": 0.8831967213114754,
|
| 103 |
+
"eval_loss": 0.20678555965423584,
|
| 104 |
+
"eval_overall_acc": 0.9323770491803278,
|
| 105 |
+
"eval_runtime": 13.1478,
|
| 106 |
+
"eval_samples_per_second": 111.35,
|
| 107 |
+
"eval_steps_per_second": 1.749,
|
| 108 |
+
"eval_woolf_acc": 0.9672131147540983,
|
| 109 |
+
"step": 175
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.04,
|
| 113 |
+
"grad_norm": 3.76464581489563,
|
| 114 |
+
"learning_rate": 3.864734299516908e-05,
|
| 115 |
+
"loss": 0.0751,
|
| 116 |
+
"step": 210
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.04,
|
| 120 |
+
"eval_acc_product": 0.8355915183980156,
|
| 121 |
+
"eval_fitzgerald_acc": 0.8913934426229508,
|
| 122 |
+
"eval_hemingway_acc": 0.9774590163934426,
|
| 123 |
+
"eval_loss": 0.21373361349105835,
|
| 124 |
+
"eval_overall_acc": 0.9426229508196722,
|
| 125 |
+
"eval_runtime": 13.1464,
|
| 126 |
+
"eval_samples_per_second": 111.361,
|
| 127 |
+
"eval_steps_per_second": 1.75,
|
| 128 |
+
"eval_woolf_acc": 0.9590163934426229,
|
| 129 |
+
"step": 210
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.55,
|
| 133 |
+
"grad_norm": 7.145068168640137,
|
| 134 |
+
"learning_rate": 3.5829307568438e-05,
|
| 135 |
+
"loss": 0.0799,
|
| 136 |
+
"step": 245
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.55,
|
| 140 |
+
"eval_acc_product": 0.8595802071539027,
|
| 141 |
+
"eval_fitzgerald_acc": 0.9467213114754098,
|
| 142 |
+
"eval_hemingway_acc": 0.9508196721311475,
|
| 143 |
+
"eval_loss": 0.19885893166065216,
|
| 144 |
+
"eval_overall_acc": 0.9508196721311475,
|
| 145 |
+
"eval_runtime": 13.143,
|
| 146 |
+
"eval_samples_per_second": 111.39,
|
| 147 |
+
"eval_steps_per_second": 1.75,
|
| 148 |
+
"eval_woolf_acc": 0.9549180327868853,
|
| 149 |
+
"step": 245
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.06,
|
| 153 |
+
"grad_norm": 19.213457107543945,
|
| 154 |
+
"learning_rate": 3.301127214170693e-05,
|
| 155 |
+
"loss": 0.0689,
|
| 156 |
+
"step": 280
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.06,
|
| 160 |
+
"eval_acc_product": 0.720976809113428,
|
| 161 |
+
"eval_fitzgerald_acc": 0.985655737704918,
|
| 162 |
+
"eval_hemingway_acc": 0.9036885245901639,
|
| 163 |
+
"eval_loss": 0.44272100925445557,
|
| 164 |
+
"eval_overall_acc": 0.8995901639344263,
|
| 165 |
+
"eval_runtime": 13.1467,
|
| 166 |
+
"eval_samples_per_second": 111.359,
|
| 167 |
+
"eval_steps_per_second": 1.749,
|
| 168 |
+
"eval_woolf_acc": 0.8094262295081968,
|
| 169 |
+
"step": 280
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.57,
|
| 173 |
+
"grad_norm": 18.969886779785156,
|
| 174 |
+
"learning_rate": 3.0193236714975848e-05,
|
| 175 |
+
"loss": 0.0514,
|
| 176 |
+
"step": 315
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.57,
|
| 180 |
+
"eval_acc_product": 0.8326357712760099,
|
| 181 |
+
"eval_fitzgerald_acc": 0.9139344262295082,
|
| 182 |
+
"eval_hemingway_acc": 0.9836065573770492,
|
| 183 |
+
"eval_loss": 0.3214350938796997,
|
| 184 |
+
"eval_overall_acc": 0.9412568306010929,
|
| 185 |
+
"eval_runtime": 13.1454,
|
| 186 |
+
"eval_samples_per_second": 111.37,
|
| 187 |
+
"eval_steps_per_second": 1.75,
|
| 188 |
+
"eval_woolf_acc": 0.9262295081967213,
|
| 189 |
+
"step": 315
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.07,
|
| 193 |
+
"grad_norm": 3.789048433303833,
|
| 194 |
+
"learning_rate": 2.7375201288244768e-05,
|
| 195 |
+
"loss": 0.0247,
|
| 196 |
+
"step": 350
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 5.07,
|
| 200 |
+
"eval_acc_product": 0.8625536629442553,
|
| 201 |
+
"eval_fitzgerald_acc": 0.9200819672131147,
|
| 202 |
+
"eval_hemingway_acc": 0.9651639344262295,
|
| 203 |
+
"eval_loss": 0.282697856426239,
|
| 204 |
+
"eval_overall_acc": 0.9521857923497268,
|
| 205 |
+
"eval_runtime": 13.1482,
|
| 206 |
+
"eval_samples_per_second": 111.346,
|
| 207 |
+
"eval_steps_per_second": 1.749,
|
| 208 |
+
"eval_woolf_acc": 0.9713114754098361,
|
| 209 |
+
"step": 350
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.58,
|
| 213 |
+
"grad_norm": 0.13263003528118134,
|
| 214 |
+
"learning_rate": 2.455716586151369e-05,
|
| 215 |
+
"loss": 0.0061,
|
| 216 |
+
"step": 385
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.58,
|
| 220 |
+
"eval_acc_product": 0.870603844594922,
|
| 221 |
+
"eval_fitzgerald_acc": 0.9508196721311475,
|
| 222 |
+
"eval_hemingway_acc": 0.9692622950819673,
|
| 223 |
+
"eval_loss": 0.28144514560699463,
|
| 224 |
+
"eval_overall_acc": 0.9549180327868853,
|
| 225 |
+
"eval_runtime": 13.1424,
|
| 226 |
+
"eval_samples_per_second": 111.395,
|
| 227 |
+
"eval_steps_per_second": 1.75,
|
| 228 |
+
"eval_woolf_acc": 0.944672131147541,
|
| 229 |
+
"step": 385
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 6.09,
|
| 233 |
+
"grad_norm": 0.01614902913570404,
|
| 234 |
+
"learning_rate": 2.173913043478261e-05,
|
| 235 |
+
"loss": 0.017,
|
| 236 |
+
"step": 420
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.09,
|
| 240 |
+
"eval_acc_product": 0.8501492828694912,
|
| 241 |
+
"eval_fitzgerald_acc": 0.9528688524590164,
|
| 242 |
+
"eval_hemingway_acc": 0.930327868852459,
|
| 243 |
+
"eval_loss": 0.34684956073760986,
|
| 244 |
+
"eval_overall_acc": 0.9474043715846995,
|
| 245 |
+
"eval_runtime": 13.1477,
|
| 246 |
+
"eval_samples_per_second": 111.35,
|
| 247 |
+
"eval_steps_per_second": 1.749,
|
| 248 |
+
"eval_woolf_acc": 0.9590163934426229,
|
| 249 |
+
"step": 420
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.59,
|
| 253 |
+
"grad_norm": 0.007705519441515207,
|
| 254 |
+
"learning_rate": 1.892109500805153e-05,
|
| 255 |
+
"loss": 0.0108,
|
| 256 |
+
"step": 455
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 6.59,
|
| 260 |
+
"eval_acc_product": 0.8705621113386143,
|
| 261 |
+
"eval_fitzgerald_acc": 0.9385245901639344,
|
| 262 |
+
"eval_hemingway_acc": 0.9651639344262295,
|
| 263 |
+
"eval_loss": 0.26387327909469604,
|
| 264 |
+
"eval_overall_acc": 0.9549180327868853,
|
| 265 |
+
"eval_runtime": 13.1463,
|
| 266 |
+
"eval_samples_per_second": 111.362,
|
| 267 |
+
"eval_steps_per_second": 1.75,
|
| 268 |
+
"eval_woolf_acc": 0.9610655737704918,
|
| 269 |
+
"step": 455
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.1,
|
| 273 |
+
"grad_norm": 0.04329540580511093,
|
| 274 |
+
"learning_rate": 1.610305958132045e-05,
|
| 275 |
+
"loss": 0.0237,
|
| 276 |
+
"step": 490
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 7.1,
|
| 280 |
+
"eval_acc_product": 0.8607751722611143,
|
| 281 |
+
"eval_fitzgerald_acc": 0.9426229508196722,
|
| 282 |
+
"eval_hemingway_acc": 0.9815573770491803,
|
| 283 |
+
"eval_loss": 0.32457903027534485,
|
| 284 |
+
"eval_overall_acc": 0.9515027322404371,
|
| 285 |
+
"eval_runtime": 13.1416,
|
| 286 |
+
"eval_samples_per_second": 111.402,
|
| 287 |
+
"eval_steps_per_second": 1.75,
|
| 288 |
+
"eval_woolf_acc": 0.930327868852459,
|
| 289 |
+
"step": 490
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.61,
|
| 293 |
+
"grad_norm": 18.448688507080078,
|
| 294 |
+
"learning_rate": 1.3285024154589374e-05,
|
| 295 |
+
"loss": 0.0109,
|
| 296 |
+
"step": 525
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.61,
|
| 300 |
+
"eval_acc_product": 0.8574545818262321,
|
| 301 |
+
"eval_fitzgerald_acc": 0.9569672131147541,
|
| 302 |
+
"eval_hemingway_acc": 0.9631147540983607,
|
| 303 |
+
"eval_loss": 0.32199960947036743,
|
| 304 |
+
"eval_overall_acc": 0.950136612021858,
|
| 305 |
+
"eval_runtime": 13.141,
|
| 306 |
+
"eval_samples_per_second": 111.407,
|
| 307 |
+
"eval_steps_per_second": 1.75,
|
| 308 |
+
"eval_woolf_acc": 0.930327868852459,
|
| 309 |
+
"step": 525
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.12,
|
| 313 |
+
"grad_norm": 0.07037464529275894,
|
| 314 |
+
"learning_rate": 1.0466988727858294e-05,
|
| 315 |
+
"loss": 0.0108,
|
| 316 |
+
"step": 560
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 8.12,
|
| 320 |
+
"eval_acc_product": 0.8835792216639279,
|
| 321 |
+
"eval_fitzgerald_acc": 0.9385245901639344,
|
| 322 |
+
"eval_hemingway_acc": 0.9692622950819673,
|
| 323 |
+
"eval_loss": 0.27515432238578796,
|
| 324 |
+
"eval_overall_acc": 0.9596994535519126,
|
| 325 |
+
"eval_runtime": 13.1404,
|
| 326 |
+
"eval_samples_per_second": 111.412,
|
| 327 |
+
"eval_steps_per_second": 1.75,
|
| 328 |
+
"eval_woolf_acc": 0.9713114754098361,
|
| 329 |
+
"step": 560
|
| 330 |
+
}
|
| 331 |
+
],
|
| 332 |
+
"logging_steps": 35,
|
| 333 |
+
"max_steps": 690,
|
| 334 |
+
"num_input_tokens_seen": 0,
|
| 335 |
+
"num_train_epochs": 10,
|
| 336 |
+
"save_steps": 35,
|
| 337 |
+
"total_flos": 1.4725988675974908e+16,
|
| 338 |
+
"train_batch_size": 64,
|
| 339 |
+
"trial_name": null,
|
| 340 |
+
"trial_params": null
|
| 341 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d86e96cbec3daedc9199b2a1b651d035cddc1ade59af4fe22a503be2d76b86f7
|
| 3 |
+
size 4920
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|