Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/added_tokens.json +4 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +58 -0
- last-checkpoint/tokenizer_config.json +213 -0
- last-checkpoint/trainer_state.json +564 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
last-checkpoint/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 49152,
|
| 3 |
+
"<pad>": 49153
|
| 4 |
+
}
|
last-checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee43cc787e4bbdf3b74113157c9557cc3d4eb0246845be2bc07fb9cb991c0e49
|
| 3 |
+
size 1450506728
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08bd408cd0095fb58cfc3775ff2ec9590d9677439cedc7321f7510f80768e38
|
| 3 |
+
size 2901193658
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5daace352b191b76e3c99c762305288cdf737ab918956dd1b4d849f72bed01cc
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56f1d9ce5cbe4f6e6e248b69695a1b0c3f76ed7a81860142c34e6f660cddfc4f
|
| 3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"mask_token": {
|
| 38 |
+
"content": "<mask>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"pad_token": {
|
| 45 |
+
"content": "<pad>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
},
|
| 51 |
+
"unk_token": {
|
| 52 |
+
"content": "<|endoftext|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false
|
| 57 |
+
}
|
| 58 |
+
}
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<fim_prefix>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "<fim_middle>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"3": {
|
| 31 |
+
"content": "<fim_suffix>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"4": {
|
| 39 |
+
"content": "<fim_pad>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"5": {
|
| 47 |
+
"content": "<filename>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"6": {
|
| 55 |
+
"content": "<gh_stars>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"7": {
|
| 63 |
+
"content": "<issue_start>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"8": {
|
| 71 |
+
"content": "<issue_comment>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"9": {
|
| 79 |
+
"content": "<issue_closed>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"10": {
|
| 87 |
+
"content": "<jupyter_start>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"11": {
|
| 95 |
+
"content": "<jupyter_text>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"12": {
|
| 103 |
+
"content": "<jupyter_code>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"13": {
|
| 111 |
+
"content": "<jupyter_output>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"14": {
|
| 119 |
+
"content": "<empty_output>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"15": {
|
| 127 |
+
"content": "<commit_before>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"16": {
|
| 135 |
+
"content": "<commit_msg>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"17": {
|
| 143 |
+
"content": "<commit_after>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"18": {
|
| 151 |
+
"content": "<reponame>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"49152": {
|
| 159 |
+
"content": "<mask>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"49153": {
|
| 167 |
+
"content": "<pad>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
}
|
| 174 |
+
},
|
| 175 |
+
"additional_special_tokens": [
|
| 176 |
+
"<|endoftext|>",
|
| 177 |
+
"<fim_prefix>",
|
| 178 |
+
"<fim_middle>",
|
| 179 |
+
"<fim_suffix>",
|
| 180 |
+
"<fim_pad>",
|
| 181 |
+
"<filename>",
|
| 182 |
+
"<gh_stars>",
|
| 183 |
+
"<issue_start>",
|
| 184 |
+
"<issue_comment>",
|
| 185 |
+
"<issue_closed>",
|
| 186 |
+
"<jupyter_start>",
|
| 187 |
+
"<jupyter_text>",
|
| 188 |
+
"<jupyter_code>",
|
| 189 |
+
"<jupyter_output>",
|
| 190 |
+
"<empty_output>",
|
| 191 |
+
"<commit_before>",
|
| 192 |
+
"<commit_msg>",
|
| 193 |
+
"<commit_after>",
|
| 194 |
+
"<reponame>"
|
| 195 |
+
],
|
| 196 |
+
"auto_map": {
|
| 197 |
+
"AutoTokenizer": [
|
| 198 |
+
"codesage/codesage-base-v2--tokenization_codesage.CodeSageTokenizer",
|
| 199 |
+
null
|
| 200 |
+
]
|
| 201 |
+
},
|
| 202 |
+
"bos_token": "<|endoftext|>",
|
| 203 |
+
"clean_up_tokenization_spaces": false,
|
| 204 |
+
"eos_token": "<|endoftext|>",
|
| 205 |
+
"errors": "replace",
|
| 206 |
+
"extra_special_tokens": {},
|
| 207 |
+
"mask_token": "<mask>",
|
| 208 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 209 |
+
"pad_token": "<pad>",
|
| 210 |
+
"tokenizer_class": "CodeSageTokenizer",
|
| 211 |
+
"unk_token": "<|endoftext|>",
|
| 212 |
+
"vocab_size": 49152
|
| 213 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,564 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 370,
|
| 3 |
+
"best_metric": 0.3884802460670471,
|
| 4 |
+
"best_model_checkpoint": "./VulnSentry/checkpoint-370",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 370,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013544018058690745,
|
| 14 |
+
"grad_norm": 61.920562744140625,
|
| 15 |
+
"learning_rate": 4.210526315789474e-06,
|
| 16 |
+
"loss": 0.7503,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02708803611738149,
|
| 21 |
+
"grad_norm": 53.86005783081055,
|
| 22 |
+
"learning_rate": 9.473684210526315e-06,
|
| 23 |
+
"loss": 0.5629,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.040632054176072234,
|
| 28 |
+
"grad_norm": 52.824466705322266,
|
| 29 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 30 |
+
"loss": 0.5162,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05417607223476298,
|
| 35 |
+
"grad_norm": 49.85675048828125,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 0.2927,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06772009029345373,
|
| 42 |
+
"grad_norm": 40.95595169067383,
|
| 43 |
+
"learning_rate": 1.9999629996754254e-05,
|
| 44 |
+
"loss": 0.4022,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08126410835214447,
|
| 49 |
+
"grad_norm": 40.73978042602539,
|
| 50 |
+
"learning_rate": 1.9998520014397486e-05,
|
| 51 |
+
"loss": 0.495,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09480812641083522,
|
| 56 |
+
"grad_norm": 25.020273208618164,
|
| 57 |
+
"learning_rate": 1.9996670135069123e-05,
|
| 58 |
+
"loss": 0.4785,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10835214446952596,
|
| 63 |
+
"grad_norm": 26.943941116333008,
|
| 64 |
+
"learning_rate": 1.999408049566142e-05,
|
| 65 |
+
"loss": 0.432,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12189616252821671,
|
| 70 |
+
"grad_norm": 22.082460403442383,
|
| 71 |
+
"learning_rate": 1.9990751287809393e-05,
|
| 72 |
+
"loss": 0.3905,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13544018058690746,
|
| 77 |
+
"grad_norm": 26.54736328125,
|
| 78 |
+
"learning_rate": 1.9986682757876574e-05,
|
| 79 |
+
"loss": 0.4153,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1489841986455982,
|
| 84 |
+
"grad_norm": 17.708812713623047,
|
| 85 |
+
"learning_rate": 1.9981875206936818e-05,
|
| 86 |
+
"loss": 0.4651,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16252821670428894,
|
| 91 |
+
"grad_norm": 21.073911666870117,
|
| 92 |
+
"learning_rate": 1.9976328990752013e-05,
|
| 93 |
+
"loss": 0.4979,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17607223476297967,
|
| 98 |
+
"grad_norm": 17.107423782348633,
|
| 99 |
+
"learning_rate": 1.997004451974577e-05,
|
| 100 |
+
"loss": 0.3886,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.18961625282167044,
|
| 105 |
+
"grad_norm": 18.816625595092773,
|
| 106 |
+
"learning_rate": 1.9963022258973007e-05,
|
| 107 |
+
"loss": 0.5016,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.20316027088036118,
|
| 112 |
+
"grad_norm": 18.011642456054688,
|
| 113 |
+
"learning_rate": 1.9955262728085592e-05,
|
| 114 |
+
"loss": 0.4861,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.21670428893905191,
|
| 119 |
+
"grad_norm": 21.518707275390625,
|
| 120 |
+
"learning_rate": 1.9946766501293838e-05,
|
| 121 |
+
"loss": 0.4783,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.23024830699774265,
|
| 126 |
+
"grad_norm": 14.0570650100708,
|
| 127 |
+
"learning_rate": 1.9937534207324053e-05,
|
| 128 |
+
"loss": 0.4393,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24379232505643342,
|
| 133 |
+
"grad_norm": 11.293530464172363,
|
| 134 |
+
"learning_rate": 1.992756652937198e-05,
|
| 135 |
+
"loss": 0.4614,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.25733634311512416,
|
| 140 |
+
"grad_norm": 10.388118743896484,
|
| 141 |
+
"learning_rate": 1.991686420505225e-05,
|
| 142 |
+
"loss": 0.515,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2708803611738149,
|
| 147 |
+
"grad_norm": 9.720160484313965,
|
| 148 |
+
"learning_rate": 1.990542802634382e-05,
|
| 149 |
+
"loss": 0.4896,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.28442437923250563,
|
| 154 |
+
"grad_norm": 8.744847297668457,
|
| 155 |
+
"learning_rate": 1.9893258839531335e-05,
|
| 156 |
+
"loss": 0.4879,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2979683972911964,
|
| 161 |
+
"grad_norm": 11.211833953857422,
|
| 162 |
+
"learning_rate": 1.988035754514252e-05,
|
| 163 |
+
"loss": 0.4154,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3115124153498871,
|
| 168 |
+
"grad_norm": 9.039229393005371,
|
| 169 |
+
"learning_rate": 1.986672509788153e-05,
|
| 170 |
+
"loss": 0.3759,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.32505643340857787,
|
| 175 |
+
"grad_norm": 11.156192779541016,
|
| 176 |
+
"learning_rate": 1.985236250655832e-05,
|
| 177 |
+
"loss": 0.4234,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.33860045146726864,
|
| 182 |
+
"grad_norm": 9.05034065246582,
|
| 183 |
+
"learning_rate": 1.983727083401396e-05,
|
| 184 |
+
"loss": 0.4786,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.35214446952595935,
|
| 189 |
+
"grad_norm": 15.79513931274414,
|
| 190 |
+
"learning_rate": 1.9821451197042028e-05,
|
| 191 |
+
"loss": 0.5549,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3656884875846501,
|
| 196 |
+
"grad_norm": 10.228875160217285,
|
| 197 |
+
"learning_rate": 1.980490476630592e-05,
|
| 198 |
+
"loss": 0.5006,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3792325056433409,
|
| 203 |
+
"grad_norm": 5.66217041015625,
|
| 204 |
+
"learning_rate": 1.9787632766252256e-05,
|
| 205 |
+
"loss": 0.4001,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3927765237020316,
|
| 210 |
+
"grad_norm": 6.6009521484375,
|
| 211 |
+
"learning_rate": 1.976963647502025e-05,
|
| 212 |
+
"loss": 0.6198,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.40632054176072235,
|
| 217 |
+
"grad_norm": 6.579983234405518,
|
| 218 |
+
"learning_rate": 1.9750917224347136e-05,
|
| 219 |
+
"loss": 0.3937,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.4198645598194131,
|
| 224 |
+
"grad_norm": 9.299453735351562,
|
| 225 |
+
"learning_rate": 1.9731476399469615e-05,
|
| 226 |
+
"loss": 0.4485,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.43340857787810383,
|
| 231 |
+
"grad_norm": 8.393924713134766,
|
| 232 |
+
"learning_rate": 1.9711315439021347e-05,
|
| 233 |
+
"loss": 0.4297,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.4469525959367946,
|
| 238 |
+
"grad_norm": 6.152463912963867,
|
| 239 |
+
"learning_rate": 1.9690435834926495e-05,
|
| 240 |
+
"loss": 0.3706,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4604966139954853,
|
| 245 |
+
"grad_norm": 9.310385704040527,
|
| 246 |
+
"learning_rate": 1.9668839132289315e-05,
|
| 247 |
+
"loss": 0.4448,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.47404063205417607,
|
| 252 |
+
"grad_norm": 8.190108299255371,
|
| 253 |
+
"learning_rate": 1.964652692927982e-05,
|
| 254 |
+
"loss": 0.371,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.48758465011286684,
|
| 259 |
+
"grad_norm": 6.591668605804443,
|
| 260 |
+
"learning_rate": 1.962350087701552e-05,
|
| 261 |
+
"loss": 0.3555,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5011286681715575,
|
| 266 |
+
"grad_norm": 8.31998062133789,
|
| 267 |
+
"learning_rate": 1.959976267943923e-05,
|
| 268 |
+
"loss": 0.4765,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5146726862302483,
|
| 273 |
+
"grad_norm": 15.614466667175293,
|
| 274 |
+
"learning_rate": 1.9575314093192978e-05,
|
| 275 |
+
"loss": 0.3886,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5282167042889391,
|
| 280 |
+
"grad_norm": 10.621317863464355,
|
| 281 |
+
"learning_rate": 1.9550156927488017e-05,
|
| 282 |
+
"loss": 0.4668,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5417607223476298,
|
| 287 |
+
"grad_norm": 9.298853874206543,
|
| 288 |
+
"learning_rate": 1.9524293043970937e-05,
|
| 289 |
+
"loss": 0.4527,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5553047404063205,
|
| 294 |
+
"grad_norm": 5.578908920288086,
|
| 295 |
+
"learning_rate": 1.9497724356585913e-05,
|
| 296 |
+
"loss": 0.3918,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5688487584650113,
|
| 301 |
+
"grad_norm": 6.8293256759643555,
|
| 302 |
+
"learning_rate": 1.947045283143306e-05,
|
| 303 |
+
"loss": 0.4018,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.582392776523702,
|
| 308 |
+
"grad_norm": 7.2509894371032715,
|
| 309 |
+
"learning_rate": 1.9442480486622933e-05,
|
| 310 |
+
"loss": 0.3758,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5959367945823928,
|
| 315 |
+
"grad_norm": 7.862231254577637,
|
| 316 |
+
"learning_rate": 1.941380939212722e-05,
|
| 317 |
+
"loss": 0.4305,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6094808126410836,
|
| 322 |
+
"grad_norm": 6.373060703277588,
|
| 323 |
+
"learning_rate": 1.9384441669625514e-05,
|
| 324 |
+
"loss": 0.3768,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6230248306997742,
|
| 329 |
+
"grad_norm": 10.84733772277832,
|
| 330 |
+
"learning_rate": 1.9354379492348348e-05,
|
| 331 |
+
"loss": 0.5301,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.636568848758465,
|
| 336 |
+
"grad_norm": 8.134037971496582,
|
| 337 |
+
"learning_rate": 1.9323625084916358e-05,
|
| 338 |
+
"loss": 0.4017,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6501128668171557,
|
| 343 |
+
"grad_norm": 7.003602504730225,
|
| 344 |
+
"learning_rate": 1.9292180723175656e-05,
|
| 345 |
+
"loss": 0.4416,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6636568848758465,
|
| 350 |
+
"grad_norm": 9.637020111083984,
|
| 351 |
+
"learning_rate": 1.926004873402942e-05,
|
| 352 |
+
"loss": 0.4691,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6772009029345373,
|
| 357 |
+
"grad_norm": 9.159772872924805,
|
| 358 |
+
"learning_rate": 1.9227231495265707e-05,
|
| 359 |
+
"loss": 0.4566,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.690744920993228,
|
| 364 |
+
"grad_norm": 8.606935501098633,
|
| 365 |
+
"learning_rate": 1.919373143538149e-05,
|
| 366 |
+
"loss": 0.389,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.7042889390519187,
|
| 371 |
+
"grad_norm": 6.0342607498168945,
|
| 372 |
+
"learning_rate": 1.9159551033402952e-05,
|
| 373 |
+
"loss": 0.3691,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7178329571106095,
|
| 378 |
+
"grad_norm": 12.473052978515625,
|
| 379 |
+
"learning_rate": 1.912469281870202e-05,
|
| 380 |
+
"loss": 0.4589,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7313769751693002,
|
| 385 |
+
"grad_norm": 11.965147018432617,
|
| 386 |
+
"learning_rate": 1.9089159370809213e-05,
|
| 387 |
+
"loss": 0.4183,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.744920993227991,
|
| 392 |
+
"grad_norm": 7.451316833496094,
|
| 393 |
+
"learning_rate": 1.9052953319222737e-05,
|
| 394 |
+
"loss": 0.3731,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7584650112866818,
|
| 399 |
+
"grad_norm": 7.067313194274902,
|
| 400 |
+
"learning_rate": 1.901607734321392e-05,
|
| 401 |
+
"loss": 0.4241,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7720090293453724,
|
| 406 |
+
"grad_norm": 8.900699615478516,
|
| 407 |
+
"learning_rate": 1.897853417162892e-05,
|
| 408 |
+
"loss": 0.4662,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7855530474040632,
|
| 413 |
+
"grad_norm": 8.984304428100586,
|
| 414 |
+
"learning_rate": 1.894032658268681e-05,
|
| 415 |
+
"loss": 0.4368,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7990970654627539,
|
| 420 |
+
"grad_norm": 17.687589645385742,
|
| 421 |
+
"learning_rate": 1.890145740377397e-05,
|
| 422 |
+
"loss": 0.4358,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8126410835214447,
|
| 427 |
+
"grad_norm": 10.592819213867188,
|
| 428 |
+
"learning_rate": 1.886192951123487e-05,
|
| 429 |
+
"loss": 0.4406,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8261851015801355,
|
| 434 |
+
"grad_norm": 7.463470458984375,
|
| 435 |
+
"learning_rate": 1.882174583015922e-05,
|
| 436 |
+
"loss": 0.5127,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8397291196388262,
|
| 441 |
+
"grad_norm": 9.488760948181152,
|
| 442 |
+
"learning_rate": 1.8780909334165505e-05,
|
| 443 |
+
"loss": 0.4632,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8532731376975169,
|
| 448 |
+
"grad_norm": 7.275017738342285,
|
| 449 |
+
"learning_rate": 1.8739423045180936e-05,
|
| 450 |
+
"loss": 0.3711,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8668171557562077,
|
| 455 |
+
"grad_norm": 10.391792297363281,
|
| 456 |
+
"learning_rate": 1.8697290033217834e-05,
|
| 457 |
+
"loss": 0.3747,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8803611738148984,
|
| 462 |
+
"grad_norm": 10.058419227600098,
|
| 463 |
+
"learning_rate": 1.8654513416146428e-05,
|
| 464 |
+
"loss": 0.4147,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8939051918735892,
|
| 469 |
+
"grad_norm": 15.269502639770508,
|
| 470 |
+
"learning_rate": 1.861109635946415e-05,
|
| 471 |
+
"loss": 0.425,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.90744920993228,
|
| 476 |
+
"grad_norm": 5.774105548858643,
|
| 477 |
+
"learning_rate": 1.8567042076061382e-05,
|
| 478 |
+
"loss": 0.4217,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9209932279909706,
|
| 483 |
+
"grad_norm": 12.779688835144043,
|
| 484 |
+
"learning_rate": 1.8522353825983696e-05,
|
| 485 |
+
"loss": 0.3445,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9345372460496614,
|
| 490 |
+
"grad_norm": 18.34588050842285,
|
| 491 |
+
"learning_rate": 1.8477034916190605e-05,
|
| 492 |
+
"loss": 0.4231,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9480812641083521,
|
| 497 |
+
"grad_norm": 6.060946941375732,
|
| 498 |
+
"learning_rate": 1.8431088700310846e-05,
|
| 499 |
+
"loss": 0.3402,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9616252821670429,
|
| 504 |
+
"grad_norm": 8.50345230102539,
|
| 505 |
+
"learning_rate": 1.8384518578394228e-05,
|
| 506 |
+
"loss": 0.4596,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.9751693002257337,
|
| 511 |
+
"grad_norm": 4.315084934234619,
|
| 512 |
+
"learning_rate": 1.833732799666e-05,
|
| 513 |
+
"loss": 0.346,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9887133182844243,
|
| 518 |
+
"grad_norm": 12.581374168395996,
|
| 519 |
+
"learning_rate": 1.8289520447241846e-05,
|
| 520 |
+
"loss": 0.4715,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0,
|
| 525 |
+
"grad_norm": 2.780374765396118,
|
| 526 |
+
"learning_rate": 1.8241099467929455e-05,
|
| 527 |
+
"loss": 0.3656,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0,
|
| 532 |
+
"eval_accuracy": 0.9081264108352144,
|
| 533 |
+
"eval_f1": 0.0,
|
| 534 |
+
"eval_loss": 0.3884802460670471,
|
| 535 |
+
"eval_precision": 0.0,
|
| 536 |
+
"eval_recall": 0.0,
|
| 537 |
+
"eval_runtime": 241.8618,
|
| 538 |
+
"eval_samples_per_second": 18.316,
|
| 539 |
+
"eval_steps_per_second": 4.581,
|
| 540 |
+
"step": 370
|
| 541 |
+
}
|
| 542 |
+
],
|
| 543 |
+
"logging_steps": 5,
|
| 544 |
+
"max_steps": 1845,
|
| 545 |
+
"num_input_tokens_seen": 0,
|
| 546 |
+
"num_train_epochs": 5,
|
| 547 |
+
"save_steps": 500,
|
| 548 |
+
"stateful_callbacks": {
|
| 549 |
+
"TrainerControl": {
|
| 550 |
+
"args": {
|
| 551 |
+
"should_epoch_stop": false,
|
| 552 |
+
"should_evaluate": false,
|
| 553 |
+
"should_log": false,
|
| 554 |
+
"should_save": true,
|
| 555 |
+
"should_training_stop": false
|
| 556 |
+
},
|
| 557 |
+
"attributes": {}
|
| 558 |
+
}
|
| 559 |
+
},
|
| 560 |
+
"total_flos": 0.0,
|
| 561 |
+
"train_batch_size": 4,
|
| 562 |
+
"trial_name": null,
|
| 563 |
+
"trial_params": null
|
| 564 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37a84c70d6770979b673065161611b4cc8e6918473e736a58dc10be5dba7f4a6
|
| 3 |
+
size 5304
|
last-checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|