Training in progress, step 30000
Browse files- checkpoint-30000/config.json +27 -0
- checkpoint-30000/merges.txt +0 -0
- checkpoint-30000/optimizer.pt +3 -0
- checkpoint-30000/pytorch_model.bin +3 -0
- checkpoint-30000/rng_state.pth +3 -0
- checkpoint-30000/scheduler.pt +3 -0
- checkpoint-30000/special_tokens_map.json +15 -0
- checkpoint-30000/tokenizer.json +0 -0
- checkpoint-30000/tokenizer_config.json +16 -0
- checkpoint-30000/trainer_state.json +376 -0
- checkpoint-30000/training_args.bin +3 -0
- checkpoint-30000/vocab.json +0 -0
- pytorch_model.bin +1 -1
- runs/Aug04_06-18-14_af18d8dae9aa/events.out.tfevents.1691129928.af18d8dae9aa.608.0 +2 -2
checkpoint-30000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 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": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.31.0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1e87e5dd049d041b407c17a5243e72dc9bff2871a0f6b73e4b0b58dd5b459da
|
| 3 |
+
size 997697925
|
checkpoint-30000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78980383c92226829f95b2d232214b41594493b12c95d996b56211b7b3ef0098
|
| 3 |
+
size 498859189
|
checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64d0b926d7281db0211da4cd2b829fd6a632dce08c1e89a5ed7d1c1e13d1e778
|
| 3 |
+
size 14575
|
checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48d0f7c5a793a5b6a1351f6c6453363160a2c475c3f55b4bf17e077010734f86
|
| 3 |
+
size 627
|
checkpoint-30000/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 |
+
}
|
checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-30000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"max_len": 40,
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
checkpoint-30000/trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.701457451810061,
|
| 5 |
+
"global_step": 30000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.5e-06,
|
| 13 |
+
"loss": 2.1842,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 3e-06,
|
| 19 |
+
"loss": 1.9448,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 4.5e-06,
|
| 25 |
+
"loss": 1.8931,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 6e-06,
|
| 31 |
+
"loss": 1.8272,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 7.5e-06,
|
| 37 |
+
"loss": 1.7958,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 9e-06,
|
| 43 |
+
"loss": 1.7568,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"learning_rate": 1.05e-05,
|
| 49 |
+
"loss": 1.7422,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.63,
|
| 54 |
+
"learning_rate": 1.2e-05,
|
| 55 |
+
"loss": 1.7167,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.71,
|
| 60 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 61 |
+
"loss": 1.6993,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.78,
|
| 66 |
+
"learning_rate": 1.5e-05,
|
| 67 |
+
"loss": 1.68,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 1.65e-05,
|
| 73 |
+
"loss": 1.6686,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.94,
|
| 78 |
+
"learning_rate": 1.8e-05,
|
| 79 |
+
"loss": 1.6805,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.02,
|
| 84 |
+
"learning_rate": 1.95e-05,
|
| 85 |
+
"loss": 1.6662,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.1,
|
| 90 |
+
"learning_rate": 2.1e-05,
|
| 91 |
+
"loss": 1.6479,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.18,
|
| 96 |
+
"learning_rate": 2.25e-05,
|
| 97 |
+
"loss": 1.6301,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 2.4e-05,
|
| 103 |
+
"loss": 1.639,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.33,
|
| 108 |
+
"learning_rate": 2.55e-05,
|
| 109 |
+
"loss": 1.6367,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.41,
|
| 114 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 115 |
+
"loss": 1.6264,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.49,
|
| 120 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 121 |
+
"loss": 1.625,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.57,
|
| 126 |
+
"learning_rate": 3e-05,
|
| 127 |
+
"loss": 1.6288,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.65,
|
| 132 |
+
"learning_rate": 2.9833333333333335e-05,
|
| 133 |
+
"loss": 1.6335,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.72,
|
| 138 |
+
"learning_rate": 2.966666666666667e-05,
|
| 139 |
+
"loss": 1.6283,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.8,
|
| 144 |
+
"learning_rate": 2.95e-05,
|
| 145 |
+
"loss": 1.6066,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.88,
|
| 150 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 151 |
+
"loss": 1.6155,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.96,
|
| 156 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 157 |
+
"loss": 1.598,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.04,
|
| 162 |
+
"learning_rate": 2.9e-05,
|
| 163 |
+
"loss": 1.5993,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.12,
|
| 168 |
+
"learning_rate": 2.8833333333333334e-05,
|
| 169 |
+
"loss": 1.5692,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.19,
|
| 174 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 175 |
+
"loss": 1.5718,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.27,
|
| 180 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 181 |
+
"loss": 1.5731,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.35,
|
| 186 |
+
"learning_rate": 2.8333333333333332e-05,
|
| 187 |
+
"loss": 1.5491,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.43,
|
| 192 |
+
"learning_rate": 2.8166666666666666e-05,
|
| 193 |
+
"loss": 1.5503,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.51,
|
| 198 |
+
"learning_rate": 2.8e-05,
|
| 199 |
+
"loss": 1.5621,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.59,
|
| 204 |
+
"learning_rate": 2.7833333333333337e-05,
|
| 205 |
+
"loss": 1.5501,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.66,
|
| 210 |
+
"learning_rate": 2.766666666666667e-05,
|
| 211 |
+
"loss": 1.5406,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.74,
|
| 216 |
+
"learning_rate": 2.75e-05,
|
| 217 |
+
"loss": 1.5413,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.82,
|
| 222 |
+
"learning_rate": 2.7333333333333335e-05,
|
| 223 |
+
"loss": 1.5442,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.9,
|
| 228 |
+
"learning_rate": 2.716666666666667e-05,
|
| 229 |
+
"loss": 1.5369,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.98,
|
| 234 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 235 |
+
"loss": 1.5209,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.06,
|
| 240 |
+
"learning_rate": 2.6833333333333336e-05,
|
| 241 |
+
"loss": 1.5246,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.13,
|
| 246 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 247 |
+
"loss": 1.5164,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.21,
|
| 252 |
+
"learning_rate": 2.65e-05,
|
| 253 |
+
"loss": 1.5084,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.29,
|
| 258 |
+
"learning_rate": 2.6333333333333334e-05,
|
| 259 |
+
"loss": 1.5111,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.37,
|
| 264 |
+
"learning_rate": 2.6166666666666668e-05,
|
| 265 |
+
"loss": 1.5255,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.45,
|
| 270 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 271 |
+
"loss": 1.5016,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.53,
|
| 276 |
+
"learning_rate": 2.5833333333333336e-05,
|
| 277 |
+
"loss": 1.5036,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.6,
|
| 282 |
+
"learning_rate": 2.5666666666666666e-05,
|
| 283 |
+
"loss": 1.5048,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.68,
|
| 288 |
+
"learning_rate": 2.55e-05,
|
| 289 |
+
"loss": 1.501,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.76,
|
| 294 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 295 |
+
"loss": 1.5157,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.84,
|
| 300 |
+
"learning_rate": 2.5166666666666667e-05,
|
| 301 |
+
"loss": 1.4914,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.92,
|
| 306 |
+
"learning_rate": 2.5e-05,
|
| 307 |
+
"loss": 1.4933,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.0,
|
| 312 |
+
"learning_rate": 2.483333333333333e-05,
|
| 313 |
+
"loss": 1.4989,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.07,
|
| 318 |
+
"learning_rate": 2.4666666666666665e-05,
|
| 319 |
+
"loss": 1.4849,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.15,
|
| 324 |
+
"learning_rate": 2.45e-05,
|
| 325 |
+
"loss": 1.4722,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.23,
|
| 330 |
+
"learning_rate": 2.4333333333333333e-05,
|
| 331 |
+
"loss": 1.4765,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.31,
|
| 336 |
+
"learning_rate": 2.4166666666666667e-05,
|
| 337 |
+
"loss": 1.4743,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.39,
|
| 342 |
+
"learning_rate": 2.4e-05,
|
| 343 |
+
"loss": 1.4799,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.47,
|
| 348 |
+
"learning_rate": 2.383333333333333e-05,
|
| 349 |
+
"loss": 1.4717,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.54,
|
| 354 |
+
"learning_rate": 2.3666666666666665e-05,
|
| 355 |
+
"loss": 1.4763,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.62,
|
| 360 |
+
"learning_rate": 2.3500000000000002e-05,
|
| 361 |
+
"loss": 1.4742,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.7,
|
| 366 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 367 |
+
"loss": 1.4749,
|
| 368 |
+
"step": 30000
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 100000,
|
| 372 |
+
"num_train_epochs": 16,
|
| 373 |
+
"total_flos": 3.948916133074176e+16,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ec63153d445d6ea56094a531eaef84e5a0b599c84e90c4239e1bb4bc6e81267
|
| 3 |
+
size 4027
|
checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498859189
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78980383c92226829f95b2d232214b41594493b12c95d996b56211b7b3ef0098
|
| 3 |
size 498859189
|
runs/Aug04_06-18-14_af18d8dae9aa/events.out.tfevents.1691129928.af18d8dae9aa.608.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4722742975dc7d9ce9848cef3d6617dbd6fcedd1ba0653a462e940fafdecb3
|
| 3 |
+
size 13587
|