Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +0 -14
- tokenizer_config.json +0 -2
- trainer_state.json +204 -102
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -19,8 +19,8 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM",
|
| 26 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"c_attn",
|
| 23 |
+
"c_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM",
|
| 26 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 121915776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d54a7cc68cbc78fe614e86830529c32d01e3df1152e2a04825bf0f89ed6970
|
| 3 |
size 121915776
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 243883194
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ca9b673c460d5978f07ae8b6d0269449bf5dd2e240de8e038a208fb76253b6
|
| 3 |
size 243883194
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05a447c020be9ab3e4bdb8a3ced89c940a6577c535317141655409de67ab0884
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
|
| 3 |
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<|endoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
"pad_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"pad_token": {
|
| 3 |
"content": "<|endoftext|>",
|
| 4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -6,9 +6,7 @@
|
|
| 6 |
null
|
| 7 |
]
|
| 8 |
},
|
| 9 |
-
"bos_token": "<|endoftext|>",
|
| 10 |
"clean_up_tokenization_spaces": true,
|
| 11 |
-
"eos_token": "<|endoftext|>",
|
| 12 |
"model_max_length": 8192,
|
| 13 |
"pad_token": "<|endoftext|>",
|
| 14 |
"tokenizer_class": "QWenTokenizer"
|
|
|
|
| 6 |
null
|
| 7 |
]
|
| 8 |
},
|
|
|
|
| 9 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 10 |
"model_max_length": 8192,
|
| 11 |
"pad_token": "<|endoftext|>",
|
| 12 |
"tokenizer_class": "QWenTokenizer"
|
trainer_state.json
CHANGED
|
@@ -1,218 +1,320 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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": 1.3333333333333333e-05,
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 1.
|
| 20 |
-
"loss":
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss":
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss":
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 1.
|
| 38 |
-
"loss":
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
-
"loss":
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 1.
|
| 56 |
-
"loss": 2.
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 1.
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 1.
|
| 68 |
-
"loss":
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 1.
|
| 74 |
-
"loss":
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 1.
|
| 80 |
-
"loss":
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 1.
|
| 86 |
-
"loss":
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 1.
|
| 92 |
-
"loss":
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 1.
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 1.
|
| 104 |
-
"loss": 2.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate": 1.
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss":
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss":
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss":
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss":
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss":
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 2.
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 2.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss":
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss":
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss":
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss":
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0.
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss":
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss":
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 2.
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss":
|
| 207 |
"step": 66
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
}
|
| 209 |
],
|
| 210 |
"logging_steps": 2,
|
| 211 |
-
"max_steps":
|
| 212 |
"num_input_tokens_seen": 0,
|
| 213 |
"num_train_epochs": 1,
|
| 214 |
"save_steps": 500,
|
| 215 |
-
"total_flos":
|
| 216 |
"train_batch_size": 1,
|
| 217 |
"trial_name": null,
|
| 218 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9944064636420137,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
"learning_rate": 1.3333333333333333e-05,
|
| 14 |
+
"loss": 2.4466,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 1.9994755690455154e-05,
|
| 20 |
+
"loss": 2.3396,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 1.995283421166614e-05,
|
| 26 |
+
"loss": 2.3471,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 1.9869167087338908e-05,
|
| 32 |
+
"loss": 2.328,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 1.9744105246469264e-05,
|
| 38 |
+
"loss": 2.4435,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"learning_rate": 1.957817324187987e-05,
|
| 44 |
+
"loss": 2.4121,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.14,
|
| 49 |
+
"learning_rate": 1.937206705006344e-05,
|
| 50 |
+
"loss": 2.3957,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.16,
|
| 55 |
+
"learning_rate": 1.9126651152015404e-05,
|
| 56 |
+
"loss": 2.4533,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.18,
|
| 61 |
+
"learning_rate": 1.8842954907300236e-05,
|
| 62 |
+
"loss": 2.1981,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.2,
|
| 67 |
+
"learning_rate": 1.8522168236559693e-05,
|
| 68 |
+
"loss": 2.0471,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.22,
|
| 73 |
+
"learning_rate": 1.816563663057211e-05,
|
| 74 |
+
"loss": 2.2514,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.24,
|
| 79 |
+
"learning_rate": 1.7774855506796497e-05,
|
| 80 |
+
"loss": 2.1223,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.26,
|
| 85 |
+
"learning_rate": 1.7351463937072008e-05,
|
| 86 |
+
"loss": 2.2617,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.28,
|
| 91 |
+
"learning_rate": 1.6897237772781046e-05,
|
| 92 |
+
"loss": 2.3792,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.3,
|
| 97 |
+
"learning_rate": 1.6414082196311402e-05,
|
| 98 |
+
"loss": 2.2988,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.32,
|
| 103 |
+
"learning_rate": 1.5904023730059227e-05,
|
| 104 |
+
"loss": 2.342,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.34,
|
| 109 |
+
"learning_rate": 1.536920173648984e-05,
|
| 110 |
+
"loss": 2.2828,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.36,
|
| 115 |
+
"learning_rate": 1.4811859444908053e-05,
|
| 116 |
+
"loss": 2.1958,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.38,
|
| 121 |
+
"learning_rate": 1.4234334542574906e-05,
|
| 122 |
+
"loss": 2.3152,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.4,
|
| 127 |
+
"learning_rate": 1.3639049369634878e-05,
|
| 128 |
+
"loss": 2.3084,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.42,
|
| 133 |
+
"learning_rate": 1.3028500758979507e-05,
|
| 134 |
+
"loss": 2.1816,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.44,
|
| 139 |
+
"learning_rate": 1.2405249563662539e-05,
|
| 140 |
+
"loss": 2.2007,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.46,
|
| 145 |
+
"learning_rate": 1.177190991579223e-05,
|
| 146 |
+
"loss": 2.1476,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.48,
|
| 151 |
+
"learning_rate": 1.1131138261952845e-05,
|
| 152 |
+
"loss": 2.2825,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.5,
|
| 157 |
+
"learning_rate": 1.0485622221144485e-05,
|
| 158 |
+
"loss": 2.2515,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.52,
|
| 163 |
+
"learning_rate": 9.838069311974986e-06,
|
| 164 |
+
"loss": 2.2294,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.54,
|
| 169 |
+
"learning_rate": 9.19119559638596e-06,
|
| 170 |
+
"loss": 2.1711,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.56,
|
| 175 |
+
"learning_rate": 8.5477142875451e-06,
|
| 176 |
+
"loss": 2.3261,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.58,
|
| 181 |
+
"learning_rate": 7.91032436968725e-06,
|
| 182 |
+
"loss": 2.1599,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.6,
|
| 187 |
+
"learning_rate": 7.2816992776365714e-06,
|
| 188 |
+
"loss": 2.1393,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.62,
|
| 193 |
+
"learning_rate": 6.664475683491797e-06,
|
| 194 |
+
"loss": 2.2888,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.64,
|
| 199 |
+
"learning_rate": 6.061242437507131e-06,
|
| 200 |
+
"loss": 2.1542,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.66,
|
| 205 |
+
"learning_rate": 5.4745297095546125e-06,
|
| 206 |
+
"loss": 2.1669,
|
| 207 |
"step": 66
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.68,
|
| 211 |
+
"learning_rate": 4.9067983767123736e-06,
|
| 212 |
+
"loss": 2.2456,
|
| 213 |
+
"step": 68
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7,
|
| 217 |
+
"learning_rate": 4.360429701490935e-06,
|
| 218 |
+
"loss": 2.2085,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.72,
|
| 223 |
+
"learning_rate": 3.837715343990727e-06,
|
| 224 |
+
"loss": 2.1769,
|
| 225 |
+
"step": 72
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.74,
|
| 229 |
+
"learning_rate": 3.3408477498831917e-06,
|
| 230 |
+
"loss": 2.2241,
|
| 231 |
+
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.76,
|
| 235 |
+
"learning_rate": 2.8719109545317102e-06,
|
| 236 |
+
"loss": 2.1719,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.78,
|
| 241 |
+
"learning_rate": 2.432871841823047e-06,
|
| 242 |
+
"loss": 2.4544,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.8,
|
| 247 |
+
"learning_rate": 2.025571894372794e-06,
|
| 248 |
+
"loss": 2.1069,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.82,
|
| 253 |
+
"learning_rate": 1.6517194697072903e-06,
|
| 254 |
+
"loss": 2.2405,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.84,
|
| 259 |
+
"learning_rate": 1.3128826348184886e-06,
|
| 260 |
+
"loss": 2.2792,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.86,
|
| 265 |
+
"learning_rate": 1.010482589146048e-06,
|
| 266 |
+
"loss": 2.2133,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.88,
|
| 271 |
+
"learning_rate": 7.457877035729588e-07,
|
| 272 |
+
"loss": 2.2783,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.89,
|
| 277 |
+
"learning_rate": 5.199082004372958e-07,
|
| 278 |
+
"loss": 2.2324,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.91,
|
| 283 |
+
"learning_rate": 3.3379149687388866e-07,
|
| 284 |
+
"loss": 2.0102,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.93,
|
| 289 |
+
"learning_rate": 1.8821823101760949e-07,
|
| 290 |
+
"loss": 2.1938,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.95,
|
| 295 |
+
"learning_rate": 8.379898773574924e-08,
|
| 296 |
+
"loss": 2.201,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.97,
|
| 301 |
+
"learning_rate": 2.0971737622883515e-08,
|
| 302 |
+
"loss": 2.2435,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.99,
|
| 307 |
+
"learning_rate": 0.0,
|
| 308 |
+
"loss": 2.0287,
|
| 309 |
+
"step": 100
|
| 310 |
}
|
| 311 |
],
|
| 312 |
"logging_steps": 2,
|
| 313 |
+
"max_steps": 100,
|
| 314 |
"num_input_tokens_seen": 0,
|
| 315 |
"num_train_epochs": 1,
|
| 316 |
"save_steps": 500,
|
| 317 |
+
"total_flos": 1.3943021234847744e+16,
|
| 318 |
"train_batch_size": 1,
|
| 319 |
"trial_name": null,
|
| 320 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a916a23047c8e0e2e2c112de5a6ab3aa6e5a80224aa43e3d438fcc4ba78b27ca
|
| 3 |
size 4728
|