Upload folder using huggingface_hub
Browse files- adapter_config.json +1 -1
- adapter_model.bin +2 -2
- optimizer.pt +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +22 -4
- tokenizer.json +0 -0
- tokenizer_config.json +15 -190
- trainer_state.json +133 -253
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
adapter_model.bin
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:a004a2c039a1412699956d44cedddedfe28d479f3c9a71fc7bd84a8320af76e0
|
| 3 |
+
size 160069389
|
optimizer.pt
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:fd9ce8f210d12d3d5c469cb1f55f6b32936760d91932420bee2b411f3cbd6ebf
|
| 3 |
+
size 320193565
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58fdbed67c3829622dfa48a2bbf084356503a2a890373c8bf0c98c2412e580c5
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094fe83ba6b00779a606e1c315d5190ccde76611e3c53c464d9f758dd4968766
|
| 3 |
size 627
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,24 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,212 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
-
"content": "<
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
"1": {
|
| 13 |
-
"content": "<
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"50254": {
|
| 21 |
-
"content": " ",
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": true,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
-
"special":
|
| 27 |
-
},
|
| 28 |
-
"50255": {
|
| 29 |
-
"content": " ",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": true,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": false
|
| 35 |
-
},
|
| 36 |
-
"50256": {
|
| 37 |
-
"content": " ",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": true,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": false
|
| 43 |
-
},
|
| 44 |
-
"50257": {
|
| 45 |
-
"content": " ",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": true,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": false
|
| 51 |
-
},
|
| 52 |
-
"50258": {
|
| 53 |
-
"content": " ",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": true,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": false
|
| 59 |
-
},
|
| 60 |
-
"50259": {
|
| 61 |
-
"content": " ",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": true,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": false
|
| 67 |
-
},
|
| 68 |
-
"50260": {
|
| 69 |
-
"content": " ",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": true,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": false
|
| 75 |
-
},
|
| 76 |
-
"50261": {
|
| 77 |
-
"content": " ",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": true,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": false
|
| 83 |
-
},
|
| 84 |
-
"50262": {
|
| 85 |
-
"content": " ",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": true,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": false
|
| 91 |
-
},
|
| 92 |
-
"50263": {
|
| 93 |
-
"content": " ",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": true,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": false
|
| 99 |
-
},
|
| 100 |
-
"50264": {
|
| 101 |
-
"content": " ",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": true,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": false
|
| 107 |
-
},
|
| 108 |
-
"50265": {
|
| 109 |
-
"content": " ",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": true,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": false
|
| 115 |
-
},
|
| 116 |
-
"50266": {
|
| 117 |
-
"content": " ",
|
| 118 |
-
"lstrip": false,
|
| 119 |
-
"normalized": true,
|
| 120 |
-
"rstrip": false,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": false
|
| 123 |
-
},
|
| 124 |
-
"50267": {
|
| 125 |
-
"content": " ",
|
| 126 |
-
"lstrip": false,
|
| 127 |
-
"normalized": true,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": false
|
| 131 |
-
},
|
| 132 |
-
"50268": {
|
| 133 |
-
"content": " ",
|
| 134 |
-
"lstrip": false,
|
| 135 |
-
"normalized": true,
|
| 136 |
-
"rstrip": false,
|
| 137 |
-
"single_word": false,
|
| 138 |
-
"special": false
|
| 139 |
-
},
|
| 140 |
-
"50269": {
|
| 141 |
-
"content": " ",
|
| 142 |
-
"lstrip": false,
|
| 143 |
-
"normalized": true,
|
| 144 |
-
"rstrip": false,
|
| 145 |
-
"single_word": false,
|
| 146 |
-
"special": false
|
| 147 |
-
},
|
| 148 |
-
"50270": {
|
| 149 |
-
"content": " ",
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"normalized": true,
|
| 152 |
-
"rstrip": false,
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"special": false
|
| 155 |
-
},
|
| 156 |
-
"50271": {
|
| 157 |
-
"content": " ",
|
| 158 |
-
"lstrip": false,
|
| 159 |
-
"normalized": true,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"single_word": false,
|
| 162 |
-
"special": false
|
| 163 |
-
},
|
| 164 |
-
"50272": {
|
| 165 |
-
"content": " ",
|
| 166 |
-
"lstrip": false,
|
| 167 |
-
"normalized": true,
|
| 168 |
-
"rstrip": false,
|
| 169 |
-
"single_word": false,
|
| 170 |
-
"special": false
|
| 171 |
-
},
|
| 172 |
-
"50273": {
|
| 173 |
-
"content": " ",
|
| 174 |
-
"lstrip": false,
|
| 175 |
-
"normalized": true,
|
| 176 |
-
"rstrip": false,
|
| 177 |
-
"single_word": false,
|
| 178 |
-
"special": false
|
| 179 |
-
},
|
| 180 |
-
"50274": {
|
| 181 |
-
"content": " ",
|
| 182 |
-
"lstrip": false,
|
| 183 |
-
"normalized": true,
|
| 184 |
-
"rstrip": false,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": false
|
| 187 |
-
},
|
| 188 |
-
"50275": {
|
| 189 |
-
"content": " ",
|
| 190 |
-
"lstrip": false,
|
| 191 |
-
"normalized": true,
|
| 192 |
-
"rstrip": false,
|
| 193 |
-
"single_word": false,
|
| 194 |
-
"special": false
|
| 195 |
},
|
| 196 |
-
"
|
| 197 |
-
"content": "
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": true,
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
-
"special":
|
| 203 |
}
|
| 204 |
},
|
| 205 |
-
"bos_token": "<
|
| 206 |
-
"clean_up_tokenization_spaces":
|
| 207 |
-
"eos_token": "<
|
| 208 |
"model_max_length": 1024,
|
| 209 |
-
"pad_token": "<
|
| 210 |
-
"
|
| 211 |
-
"
|
|
|
|
|
|
|
| 212 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
+
"content": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": true,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
+
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": true,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
+
"bos_token": "<s>",
|
| 29 |
+
"clean_up_tokenization_spaces": false,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
"model_max_length": 1024,
|
| 32 |
+
"pad_token": "</s>",
|
| 33 |
+
"sp_model_kwargs": {},
|
| 34 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 35 |
+
"unk_token": "<unk>",
|
| 36 |
+
"use_default_system_prompt": true
|
| 37 |
}
|
trainer_state.json
CHANGED
|
@@ -1,397 +1,277 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss":
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss":
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss":
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss":
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss":
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 1.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss":
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss":
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 1.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss":
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 1.
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 1.
|
| 145 |
-
"learning_rate": 0.
|
| 146 |
-
"loss":
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 1.
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 1.
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 1.
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 1.
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 1.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 1.
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 1.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 1.
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 1.
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 1.
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 1.
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 1.
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 1.
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 1.
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 1.
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 1.
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 1.
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 1.
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
-
"learning_rate": 7.
|
| 260 |
-
"loss": 1.
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 2.
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 1.
|
| 267 |
"step": 86
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 2.09,
|
| 271 |
-
"learning_rate": 6.725663716814161e-05,
|
| 272 |
-
"loss": 1.8455,
|
| 273 |
-
"step": 88
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 2.14,
|
| 277 |
-
"learning_rate": 6.371681415929204e-05,
|
| 278 |
-
"loss": 1.7047,
|
| 279 |
-
"step": 90
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.18,
|
| 283 |
-
"learning_rate": 6.017699115044248e-05,
|
| 284 |
-
"loss": 1.6546,
|
| 285 |
-
"step": 92
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 2.23,
|
| 289 |
-
"learning_rate": 5.663716814159292e-05,
|
| 290 |
-
"loss": 1.7517,
|
| 291 |
-
"step": 94
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 2.28,
|
| 295 |
-
"learning_rate": 5.309734513274337e-05,
|
| 296 |
-
"loss": 1.7851,
|
| 297 |
-
"step": 96
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.33,
|
| 301 |
-
"learning_rate": 4.955752212389381e-05,
|
| 302 |
-
"loss": 1.6925,
|
| 303 |
-
"step": 98
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 2.37,
|
| 307 |
-
"learning_rate": 4.601769911504425e-05,
|
| 308 |
-
"loss": 1.8215,
|
| 309 |
-
"step": 100
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 2.42,
|
| 313 |
-
"learning_rate": 4.247787610619469e-05,
|
| 314 |
-
"loss": 1.7755,
|
| 315 |
-
"step": 102
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 2.47,
|
| 319 |
-
"learning_rate": 3.893805309734514e-05,
|
| 320 |
-
"loss": 1.7762,
|
| 321 |
-
"step": 104
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.52,
|
| 325 |
-
"learning_rate": 3.5398230088495574e-05,
|
| 326 |
-
"loss": 1.7803,
|
| 327 |
-
"step": 106
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 2.56,
|
| 331 |
-
"learning_rate": 3.185840707964602e-05,
|
| 332 |
-
"loss": 1.8136,
|
| 333 |
-
"step": 108
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 2.61,
|
| 337 |
-
"learning_rate": 2.831858407079646e-05,
|
| 338 |
-
"loss": 1.6939,
|
| 339 |
-
"step": 110
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.66,
|
| 343 |
-
"learning_rate": 2.4778761061946905e-05,
|
| 344 |
-
"loss": 1.6688,
|
| 345 |
-
"step": 112
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 2.71,
|
| 349 |
-
"learning_rate": 2.1238938053097346e-05,
|
| 350 |
-
"loss": 1.7594,
|
| 351 |
-
"step": 114
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 2.75,
|
| 355 |
-
"learning_rate": 1.7699115044247787e-05,
|
| 356 |
-
"loss": 1.8506,
|
| 357 |
-
"step": 116
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 2.8,
|
| 361 |
-
"learning_rate": 1.415929203539823e-05,
|
| 362 |
-
"loss": 1.7872,
|
| 363 |
-
"step": 118
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 2.85,
|
| 367 |
-
"learning_rate": 1.0619469026548673e-05,
|
| 368 |
-
"loss": 1.8039,
|
| 369 |
-
"step": 120
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 2.9,
|
| 373 |
-
"learning_rate": 7.079646017699115e-06,
|
| 374 |
-
"loss": 1.7888,
|
| 375 |
-
"step": 122
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 2.94,
|
| 379 |
-
"learning_rate": 3.5398230088495575e-06,
|
| 380 |
-
"loss": 1.8769,
|
| 381 |
-
"step": 124
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 2.99,
|
| 385 |
-
"learning_rate": 0.0,
|
| 386 |
-
"loss": 1.7694,
|
| 387 |
-
"step": 126
|
| 388 |
}
|
| 389 |
],
|
| 390 |
"logging_steps": 2,
|
| 391 |
-
"max_steps":
|
| 392 |
"num_train_epochs": 3,
|
| 393 |
"save_steps": 500,
|
| 394 |
-
"total_flos":
|
| 395 |
"trial_name": null,
|
| 396 |
"trial_params": null
|
| 397 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 87,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 14 |
+
"loss": 1.8555,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 8.888888888888889e-05,
|
| 20 |
+
"loss": 2.0682,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.21,
|
| 25 |
+
"learning_rate": 0.00013333333333333334,
|
| 26 |
+
"loss": 1.856,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.28,
|
| 31 |
+
"learning_rate": 0.00017777777777777779,
|
| 32 |
+
"loss": 1.8259,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.34,
|
| 37 |
+
"learning_rate": 0.00019743589743589744,
|
| 38 |
+
"loss": 1.7161,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.41,
|
| 43 |
+
"learning_rate": 0.00019230769230769233,
|
| 44 |
+
"loss": 1.7221,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.48,
|
| 49 |
+
"learning_rate": 0.0001871794871794872,
|
| 50 |
+
"loss": 1.7174,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.55,
|
| 55 |
+
"learning_rate": 0.00018205128205128207,
|
| 56 |
+
"loss": 1.8246,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.62,
|
| 61 |
+
"learning_rate": 0.00017692307692307693,
|
| 62 |
+
"loss": 1.7917,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.69,
|
| 67 |
+
"learning_rate": 0.0001717948717948718,
|
| 68 |
+
"loss": 1.801,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.76,
|
| 73 |
+
"learning_rate": 0.0001666666666666667,
|
| 74 |
+
"loss": 1.8224,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.83,
|
| 79 |
+
"learning_rate": 0.00016153846153846155,
|
| 80 |
+
"loss": 1.6901,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.9,
|
| 85 |
+
"learning_rate": 0.00015641025641025642,
|
| 86 |
+
"loss": 1.9176,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.97,
|
| 91 |
+
"learning_rate": 0.00015128205128205128,
|
| 92 |
+
"loss": 1.7105,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 1.03,
|
| 97 |
+
"learning_rate": 0.00014615384615384615,
|
| 98 |
+
"loss": 1.7531,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 1.1,
|
| 103 |
+
"learning_rate": 0.00014102564102564104,
|
| 104 |
+
"loss": 1.7971,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 1.17,
|
| 109 |
+
"learning_rate": 0.0001358974358974359,
|
| 110 |
+
"loss": 1.7683,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 1.24,
|
| 115 |
+
"learning_rate": 0.00013076923076923077,
|
| 116 |
+
"loss": 1.6741,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 1.31,
|
| 121 |
+
"learning_rate": 0.00012564102564102564,
|
| 122 |
+
"loss": 1.6559,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.38,
|
| 127 |
+
"learning_rate": 0.00012051282051282052,
|
| 128 |
+
"loss": 1.675,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.45,
|
| 133 |
+
"learning_rate": 0.00011538461538461538,
|
| 134 |
+
"loss": 1.6712,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 1.52,
|
| 139 |
+
"learning_rate": 0.00011025641025641027,
|
| 140 |
+
"loss": 1.6978,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 1.59,
|
| 145 |
+
"learning_rate": 0.00010512820512820514,
|
| 146 |
+
"loss": 1.7027,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 1.66,
|
| 151 |
+
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 1.737,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 1.72,
|
| 157 |
+
"learning_rate": 9.487179487179487e-05,
|
| 158 |
+
"loss": 1.5967,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 1.79,
|
| 163 |
+
"learning_rate": 8.974358974358975e-05,
|
| 164 |
+
"loss": 1.7143,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.86,
|
| 169 |
+
"learning_rate": 8.461538461538461e-05,
|
| 170 |
+
"loss": 1.7453,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 1.93,
|
| 175 |
+
"learning_rate": 7.948717948717948e-05,
|
| 176 |
+
"loss": 1.6414,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 2.0,
|
| 181 |
+
"learning_rate": 7.435897435897436e-05,
|
| 182 |
+
"loss": 1.6197,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 2.07,
|
| 187 |
+
"learning_rate": 6.923076923076924e-05,
|
| 188 |
+
"loss": 1.6796,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 2.14,
|
| 193 |
+
"learning_rate": 6.410256410256412e-05,
|
| 194 |
+
"loss": 1.531,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.21,
|
| 199 |
+
"learning_rate": 5.897435897435898e-05,
|
| 200 |
+
"loss": 1.6981,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 2.28,
|
| 205 |
+
"learning_rate": 5.384615384615385e-05,
|
| 206 |
+
"loss": 1.6986,
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 2.34,
|
| 211 |
+
"learning_rate": 4.871794871794872e-05,
|
| 212 |
+
"loss": 1.6096,
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 2.41,
|
| 217 |
+
"learning_rate": 4.358974358974359e-05,
|
| 218 |
+
"loss": 1.6927,
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 2.48,
|
| 223 |
+
"learning_rate": 3.846153846153846e-05,
|
| 224 |
+
"loss": 1.5048,
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 2.55,
|
| 229 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 230 |
+
"loss": 1.7904,
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 2.62,
|
| 235 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 236 |
+
"loss": 1.5874,
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 2.69,
|
| 241 |
+
"learning_rate": 2.307692307692308e-05,
|
| 242 |
+
"loss": 1.6962,
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 2.76,
|
| 247 |
+
"learning_rate": 1.794871794871795e-05,
|
| 248 |
+
"loss": 1.6124,
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 2.83,
|
| 253 |
+
"learning_rate": 1.282051282051282e-05,
|
| 254 |
+
"loss": 1.5996,
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 2.9,
|
| 259 |
+
"learning_rate": 7.692307692307694e-06,
|
| 260 |
+
"loss": 1.6096,
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 2.97,
|
| 265 |
+
"learning_rate": 2.564102564102564e-06,
|
| 266 |
+
"loss": 1.5895,
|
| 267 |
"step": 86
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 268 |
}
|
| 269 |
],
|
| 270 |
"logging_steps": 2,
|
| 271 |
+
"max_steps": 87,
|
| 272 |
"num_train_epochs": 3,
|
| 273 |
"save_steps": 500,
|
| 274 |
+
"total_flos": 5.685086356557005e+16,
|
| 275 |
"trial_name": null,
|
| 276 |
"trial_params": null
|
| 277 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e1346c8ae0cb36b02e3a5bb8e35fb40730ffa1168ea1f30c339138dc433752
|
| 3 |
size 4027
|