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 +421 -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": "obama",
|
| 15 |
+
"1": "bush",
|
| 16 |
+
"2": "trump"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"bush": 1,
|
| 22 |
+
"obama": 0,
|
| 23 |
+
"trump": 2
|
| 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:bc9444187b1d1594f9368df05e82d952358b9eb3164ecedf7c6f084b5c169d92
|
| 3 |
+
size 1421499516
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f043ac91d34064e7820d7ed5385f0213a78c2e374db5726a501834a656c081
|
| 3 |
+
size 2843231469
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:702b914c8ca17d46392652ae297d2c4b50d7d0d380a1f933995c75da1490d558
|
| 3 |
+
size 14180
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cabdd96162ecddbb53d954d7eb1984d5ac789bd18a1ad68743eeb1f283f45df1
|
| 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 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9064748201438849,
|
| 3 |
+
"best_model_checkpoint": "train_authorship/train_outputs/05-26-2024_17:09:07/checkpoint-300",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 15,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5,
|
| 13 |
+
"grad_norm": 5.808341979980469,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.0972,
|
| 16 |
+
"step": 15
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"eval_acc_product": 0.21928799282400072,
|
| 21 |
+
"eval_bush_acc": 0.8201438848920863,
|
| 22 |
+
"eval_loss": 0.9504616856575012,
|
| 23 |
+
"eval_obama_acc": 0.45323741007194246,
|
| 24 |
+
"eval_overall_acc": 0.6211031175059952,
|
| 25 |
+
"eval_runtime": 2.8206,
|
| 26 |
+
"eval_samples_per_second": 147.84,
|
| 27 |
+
"eval_steps_per_second": 2.482,
|
| 28 |
+
"eval_trump_acc": 0.5899280575539568,
|
| 29 |
+
"step": 15
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.0,
|
| 33 |
+
"grad_norm": 48.525230407714844,
|
| 34 |
+
"learning_rate": 5e-05,
|
| 35 |
+
"loss": 0.8423,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.0,
|
| 40 |
+
"eval_acc_product": 0.39412887680642716,
|
| 41 |
+
"eval_bush_acc": 0.5755395683453237,
|
| 42 |
+
"eval_loss": 0.648549497127533,
|
| 43 |
+
"eval_obama_acc": 0.7266187050359713,
|
| 44 |
+
"eval_overall_acc": 0.7482014388489209,
|
| 45 |
+
"eval_runtime": 2.7763,
|
| 46 |
+
"eval_samples_per_second": 150.202,
|
| 47 |
+
"eval_steps_per_second": 2.521,
|
| 48 |
+
"eval_trump_acc": 0.9424460431654677,
|
| 49 |
+
"step": 30
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5,
|
| 53 |
+
"grad_norm": 12.380006790161133,
|
| 54 |
+
"learning_rate": 4.722222222222222e-05,
|
| 55 |
+
"loss": 0.5581,
|
| 56 |
+
"step": 45
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.5,
|
| 60 |
+
"eval_acc_product": 0.43508777678442107,
|
| 61 |
+
"eval_bush_acc": 0.9640287769784173,
|
| 62 |
+
"eval_loss": 0.6018202304840088,
|
| 63 |
+
"eval_obama_acc": 0.5755395683453237,
|
| 64 |
+
"eval_overall_acc": 0.7745803357314148,
|
| 65 |
+
"eval_runtime": 2.7813,
|
| 66 |
+
"eval_samples_per_second": 149.93,
|
| 67 |
+
"eval_steps_per_second": 2.517,
|
| 68 |
+
"eval_trump_acc": 0.7841726618705036,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.0,
|
| 73 |
+
"grad_norm": 3.6562857627868652,
|
| 74 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 75 |
+
"loss": 0.4719,
|
| 76 |
+
"step": 60
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.0,
|
| 80 |
+
"eval_acc_product": 0.5783158370565594,
|
| 81 |
+
"eval_bush_acc": 0.7482014388489209,
|
| 82 |
+
"eval_loss": 0.4394747018814087,
|
| 83 |
+
"eval_obama_acc": 0.8201438848920863,
|
| 84 |
+
"eval_overall_acc": 0.8369304556354916,
|
| 85 |
+
"eval_runtime": 2.7839,
|
| 86 |
+
"eval_samples_per_second": 149.787,
|
| 87 |
+
"eval_steps_per_second": 2.514,
|
| 88 |
+
"eval_trump_acc": 0.9424460431654677,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.5,
|
| 93 |
+
"grad_norm": 14.938467025756836,
|
| 94 |
+
"learning_rate": 4.166666666666667e-05,
|
| 95 |
+
"loss": 0.265,
|
| 96 |
+
"step": 75
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.5,
|
| 100 |
+
"eval_acc_product": 0.5558941905013333,
|
| 101 |
+
"eval_bush_acc": 0.7913669064748201,
|
| 102 |
+
"eval_loss": 0.4741947650909424,
|
| 103 |
+
"eval_obama_acc": 0.8345323741007195,
|
| 104 |
+
"eval_overall_acc": 0.8225419664268585,
|
| 105 |
+
"eval_runtime": 2.7828,
|
| 106 |
+
"eval_samples_per_second": 149.851,
|
| 107 |
+
"eval_steps_per_second": 2.515,
|
| 108 |
+
"eval_trump_acc": 0.841726618705036,
|
| 109 |
+
"step": 75
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"grad_norm": 0.4905509948730469,
|
| 114 |
+
"learning_rate": 3.888888888888889e-05,
|
| 115 |
+
"loss": 0.1729,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_acc_product": 0.25067517023077357,
|
| 121 |
+
"eval_bush_acc": 0.302158273381295,
|
| 122 |
+
"eval_loss": 1.0451148748397827,
|
| 123 |
+
"eval_obama_acc": 0.841726618705036,
|
| 124 |
+
"eval_overall_acc": 0.709832134292566,
|
| 125 |
+
"eval_runtime": 2.7825,
|
| 126 |
+
"eval_samples_per_second": 149.863,
|
| 127 |
+
"eval_steps_per_second": 2.516,
|
| 128 |
+
"eval_trump_acc": 0.9856115107913669,
|
| 129 |
+
"step": 90
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.5,
|
| 133 |
+
"grad_norm": 32.64374542236328,
|
| 134 |
+
"learning_rate": 3.611111111111111e-05,
|
| 135 |
+
"loss": 0.2945,
|
| 136 |
+
"step": 105
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.5,
|
| 140 |
+
"eval_acc_product": 0.5622189893652079,
|
| 141 |
+
"eval_bush_acc": 0.7338129496402878,
|
| 142 |
+
"eval_loss": 0.5390242338180542,
|
| 143 |
+
"eval_obama_acc": 0.8129496402877698,
|
| 144 |
+
"eval_overall_acc": 0.829736211031175,
|
| 145 |
+
"eval_runtime": 2.7882,
|
| 146 |
+
"eval_samples_per_second": 149.56,
|
| 147 |
+
"eval_steps_per_second": 2.511,
|
| 148 |
+
"eval_trump_acc": 0.9424460431654677,
|
| 149 |
+
"step": 105
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"grad_norm": 0.29498815536499023,
|
| 154 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 155 |
+
"loss": 0.1925,
|
| 156 |
+
"step": 120
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.0,
|
| 160 |
+
"eval_acc_product": 0.6885265557028006,
|
| 161 |
+
"eval_bush_acc": 0.935251798561151,
|
| 162 |
+
"eval_loss": 0.42252907156944275,
|
| 163 |
+
"eval_obama_acc": 0.8057553956834532,
|
| 164 |
+
"eval_overall_acc": 0.8848920863309353,
|
| 165 |
+
"eval_runtime": 2.7847,
|
| 166 |
+
"eval_samples_per_second": 149.745,
|
| 167 |
+
"eval_steps_per_second": 2.514,
|
| 168 |
+
"eval_trump_acc": 0.9136690647482014,
|
| 169 |
+
"step": 120
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.5,
|
| 173 |
+
"grad_norm": 5.147099018096924,
|
| 174 |
+
"learning_rate": 3.055555555555556e-05,
|
| 175 |
+
"loss": 0.0396,
|
| 176 |
+
"step": 135
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.5,
|
| 180 |
+
"eval_acc_product": 0.628604429742268,
|
| 181 |
+
"eval_bush_acc": 0.920863309352518,
|
| 182 |
+
"eval_loss": 0.6601312160491943,
|
| 183 |
+
"eval_obama_acc": 0.8705035971223022,
|
| 184 |
+
"eval_overall_acc": 0.8585131894484412,
|
| 185 |
+
"eval_runtime": 2.7927,
|
| 186 |
+
"eval_samples_per_second": 149.316,
|
| 187 |
+
"eval_steps_per_second": 2.507,
|
| 188 |
+
"eval_trump_acc": 0.7841726618705036,
|
| 189 |
+
"step": 135
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.0,
|
| 193 |
+
"grad_norm": 0.057328637689352036,
|
| 194 |
+
"learning_rate": 2.777777777777778e-05,
|
| 195 |
+
"loss": 0.0438,
|
| 196 |
+
"step": 150
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 5.0,
|
| 200 |
+
"eval_acc_product": 0.6582616521554249,
|
| 201 |
+
"eval_bush_acc": 0.8633093525179856,
|
| 202 |
+
"eval_loss": 0.6852461695671082,
|
| 203 |
+
"eval_obama_acc": 0.9136690647482014,
|
| 204 |
+
"eval_overall_acc": 0.8705035971223022,
|
| 205 |
+
"eval_runtime": 2.7951,
|
| 206 |
+
"eval_samples_per_second": 149.19,
|
| 207 |
+
"eval_steps_per_second": 2.504,
|
| 208 |
+
"eval_trump_acc": 0.8345323741007195,
|
| 209 |
+
"step": 150
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.5,
|
| 213 |
+
"grad_norm": 1.9609147310256958,
|
| 214 |
+
"learning_rate": 2.5e-05,
|
| 215 |
+
"loss": 0.0264,
|
| 216 |
+
"step": 165
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.5,
|
| 220 |
+
"eval_acc_product": 0.6410678506519354,
|
| 221 |
+
"eval_bush_acc": 0.9064748201438849,
|
| 222 |
+
"eval_loss": 0.7376511096954346,
|
| 223 |
+
"eval_obama_acc": 0.8057553956834532,
|
| 224 |
+
"eval_overall_acc": 0.8633093525179856,
|
| 225 |
+
"eval_runtime": 2.7923,
|
| 226 |
+
"eval_samples_per_second": 149.337,
|
| 227 |
+
"eval_steps_per_second": 2.507,
|
| 228 |
+
"eval_trump_acc": 0.8776978417266187,
|
| 229 |
+
"step": 165
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 6.0,
|
| 233 |
+
"grad_norm": 0.07944349199533463,
|
| 234 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 235 |
+
"loss": 0.0444,
|
| 236 |
+
"step": 180
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.0,
|
| 240 |
+
"eval_acc_product": 0.6344280406118664,
|
| 241 |
+
"eval_bush_acc": 0.9280575539568345,
|
| 242 |
+
"eval_loss": 0.775315523147583,
|
| 243 |
+
"eval_obama_acc": 0.7482014388489209,
|
| 244 |
+
"eval_overall_acc": 0.8633093525179856,
|
| 245 |
+
"eval_runtime": 2.7918,
|
| 246 |
+
"eval_samples_per_second": 149.364,
|
| 247 |
+
"eval_steps_per_second": 2.507,
|
| 248 |
+
"eval_trump_acc": 0.9136690647482014,
|
| 249 |
+
"step": 180
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.5,
|
| 253 |
+
"grad_norm": 17.292938232421875,
|
| 254 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 255 |
+
"loss": 0.0344,
|
| 256 |
+
"step": 195
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 6.5,
|
| 260 |
+
"eval_acc_product": 0.6043388879807597,
|
| 261 |
+
"eval_bush_acc": 0.9784172661870504,
|
| 262 |
+
"eval_loss": 0.862628698348999,
|
| 263 |
+
"eval_obama_acc": 0.7338129496402878,
|
| 264 |
+
"eval_overall_acc": 0.8513189448441247,
|
| 265 |
+
"eval_runtime": 2.7928,
|
| 266 |
+
"eval_samples_per_second": 149.314,
|
| 267 |
+
"eval_steps_per_second": 2.506,
|
| 268 |
+
"eval_trump_acc": 0.841726618705036,
|
| 269 |
+
"step": 195
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.0,
|
| 273 |
+
"grad_norm": 0.018421683460474014,
|
| 274 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 275 |
+
"loss": 0.0185,
|
| 276 |
+
"step": 210
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 7.0,
|
| 280 |
+
"eval_acc_product": 0.698349244624796,
|
| 281 |
+
"eval_bush_acc": 0.8992805755395683,
|
| 282 |
+
"eval_loss": 0.6285017132759094,
|
| 283 |
+
"eval_obama_acc": 0.8920863309352518,
|
| 284 |
+
"eval_overall_acc": 0.8872901678657075,
|
| 285 |
+
"eval_runtime": 2.7927,
|
| 286 |
+
"eval_samples_per_second": 149.321,
|
| 287 |
+
"eval_steps_per_second": 2.507,
|
| 288 |
+
"eval_trump_acc": 0.8705035971223022,
|
| 289 |
+
"step": 210
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.5,
|
| 293 |
+
"grad_norm": 0.12802745401859283,
|
| 294 |
+
"learning_rate": 1.388888888888889e-05,
|
| 295 |
+
"loss": 0.0114,
|
| 296 |
+
"step": 225
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.5,
|
| 300 |
+
"eval_acc_product": 0.6621914724314953,
|
| 301 |
+
"eval_bush_acc": 0.8129496402877698,
|
| 302 |
+
"eval_loss": 0.7886965870857239,
|
| 303 |
+
"eval_obama_acc": 0.9280575539568345,
|
| 304 |
+
"eval_overall_acc": 0.8729016786570744,
|
| 305 |
+
"eval_runtime": 2.7919,
|
| 306 |
+
"eval_samples_per_second": 149.361,
|
| 307 |
+
"eval_steps_per_second": 2.507,
|
| 308 |
+
"eval_trump_acc": 0.8776978417266187,
|
| 309 |
+
"step": 225
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.0,
|
| 313 |
+
"grad_norm": 0.008947780355811119,
|
| 314 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 315 |
+
"loss": 0.0025,
|
| 316 |
+
"step": 240
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 8.0,
|
| 320 |
+
"eval_acc_product": 0.7039360385817944,
|
| 321 |
+
"eval_bush_acc": 0.9064748201438849,
|
| 322 |
+
"eval_loss": 0.6208213567733765,
|
| 323 |
+
"eval_obama_acc": 0.8920863309352518,
|
| 324 |
+
"eval_overall_acc": 0.8896882494004796,
|
| 325 |
+
"eval_runtime": 2.7916,
|
| 326 |
+
"eval_samples_per_second": 149.375,
|
| 327 |
+
"eval_steps_per_second": 2.508,
|
| 328 |
+
"eval_trump_acc": 0.8705035971223022,
|
| 329 |
+
"step": 240
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 8.5,
|
| 333 |
+
"grad_norm": 0.06868788599967957,
|
| 334 |
+
"learning_rate": 8.333333333333334e-06,
|
| 335 |
+
"loss": 0.0069,
|
| 336 |
+
"step": 255
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 8.5,
|
| 340 |
+
"eval_acc_product": 0.7387000911149348,
|
| 341 |
+
"eval_bush_acc": 0.9136690647482014,
|
| 342 |
+
"eval_loss": 0.6432462334632874,
|
| 343 |
+
"eval_obama_acc": 0.9136690647482014,
|
| 344 |
+
"eval_overall_acc": 0.9040767386091128,
|
| 345 |
+
"eval_runtime": 2.796,
|
| 346 |
+
"eval_samples_per_second": 149.139,
|
| 347 |
+
"eval_steps_per_second": 2.504,
|
| 348 |
+
"eval_trump_acc": 0.8848920863309353,
|
| 349 |
+
"step": 255
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 9.0,
|
| 353 |
+
"grad_norm": 0.00421088607981801,
|
| 354 |
+
"learning_rate": 5.555555555555556e-06,
|
| 355 |
+
"loss": 0.0019,
|
| 356 |
+
"step": 270
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 9.0,
|
| 360 |
+
"eval_acc_product": 0.7271128183111604,
|
| 361 |
+
"eval_bush_acc": 0.8848920863309353,
|
| 362 |
+
"eval_loss": 0.6422414779663086,
|
| 363 |
+
"eval_obama_acc": 0.9064748201438849,
|
| 364 |
+
"eval_overall_acc": 0.8992805755395683,
|
| 365 |
+
"eval_runtime": 2.794,
|
| 366 |
+
"eval_samples_per_second": 149.248,
|
| 367 |
+
"eval_steps_per_second": 2.505,
|
| 368 |
+
"eval_trump_acc": 0.9064748201438849,
|
| 369 |
+
"step": 270
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.5,
|
| 373 |
+
"grad_norm": 0.2265014946460724,
|
| 374 |
+
"learning_rate": 2.777777777777778e-06,
|
| 375 |
+
"loss": 0.0009,
|
| 376 |
+
"step": 285
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 9.5,
|
| 380 |
+
"eval_acc_product": 0.7271128183111604,
|
| 381 |
+
"eval_bush_acc": 0.8848920863309353,
|
| 382 |
+
"eval_loss": 0.6394339799880981,
|
| 383 |
+
"eval_obama_acc": 0.9064748201438849,
|
| 384 |
+
"eval_overall_acc": 0.8992805755395683,
|
| 385 |
+
"eval_runtime": 2.7933,
|
| 386 |
+
"eval_samples_per_second": 149.288,
|
| 387 |
+
"eval_steps_per_second": 2.506,
|
| 388 |
+
"eval_trump_acc": 0.9064748201438849,
|
| 389 |
+
"step": 285
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 10.0,
|
| 393 |
+
"grad_norm": 0.013048585504293442,
|
| 394 |
+
"learning_rate": 0.0,
|
| 395 |
+
"loss": 0.0021,
|
| 396 |
+
"step": 300
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 10.0,
|
| 400 |
+
"eval_acc_product": 0.7448472772943594,
|
| 401 |
+
"eval_bush_acc": 0.9064748201438849,
|
| 402 |
+
"eval_loss": 0.6265907287597656,
|
| 403 |
+
"eval_obama_acc": 0.9064748201438849,
|
| 404 |
+
"eval_overall_acc": 0.9064748201438849,
|
| 405 |
+
"eval_runtime": 2.7927,
|
| 406 |
+
"eval_samples_per_second": 149.318,
|
| 407 |
+
"eval_steps_per_second": 2.507,
|
| 408 |
+
"eval_trump_acc": 0.9064748201438849,
|
| 409 |
+
"step": 300
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 15,
|
| 413 |
+
"max_steps": 300,
|
| 414 |
+
"num_input_tokens_seen": 0,
|
| 415 |
+
"num_train_epochs": 10,
|
| 416 |
+
"save_steps": 15,
|
| 417 |
+
"total_flos": 5170662082636590.0,
|
| 418 |
+
"train_batch_size": 64,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d43a8fe91990bcc0b74c2f83df7904d636e2b789d8e66744a7c15756771d0d
|
| 3 |
+
size 4920
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|