prune intermediate checkpoint-200 (keeping only final checkpoint)
Browse files- checkpoint-200/config.json +0 -36
- checkpoint-200/generation_config.json +0 -12
- checkpoint-200/model.safetensors +0 -3
- checkpoint-200/optimizer.pt +0 -3
- checkpoint-200/rng_state.pth +0 -3
- checkpoint-200/scheduler.pt +0 -3
- checkpoint-200/tokenizer.json +0 -3
- checkpoint-200/tokenizer_config.json +0 -15
- checkpoint-200/trainer_state.json +0 -661
- checkpoint-200/training_args.bin +0 -3
checkpoint-200/config.json
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"LlamaForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 128000,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 128001,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 4096,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 14336,
|
| 15 |
-
"max_position_embeddings": 131072,
|
| 16 |
-
"mlp_bias": false,
|
| 17 |
-
"model_type": "llama",
|
| 18 |
-
"num_attention_heads": 32,
|
| 19 |
-
"num_hidden_layers": 32,
|
| 20 |
-
"num_key_value_heads": 8,
|
| 21 |
-
"pad_token_id": 128001,
|
| 22 |
-
"pretraining_tp": 1,
|
| 23 |
-
"rms_norm_eps": 1e-05,
|
| 24 |
-
"rope_parameters": {
|
| 25 |
-
"factor": 8.0,
|
| 26 |
-
"high_freq_factor": 4.0,
|
| 27 |
-
"low_freq_factor": 1.0,
|
| 28 |
-
"original_max_position_embeddings": 8192,
|
| 29 |
-
"rope_theta": 500000.0,
|
| 30 |
-
"rope_type": "llama3"
|
| 31 |
-
},
|
| 32 |
-
"tie_word_embeddings": false,
|
| 33 |
-
"transformers_version": "5.6.0",
|
| 34 |
-
"use_cache": false,
|
| 35 |
-
"vocab_size": 128256
|
| 36 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 128000,
|
| 4 |
-
"do_sample": true,
|
| 5 |
-
"eos_token_id": [
|
| 6 |
-
128001
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 128001,
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_p": 0.9,
|
| 11 |
-
"transformers_version": "5.6.0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6e07e5b561ec0fde5a2ea146fd143d76eb8e9d222941d37d51150074159c21e9
|
| 3 |
-
size 16060556616
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ce4a1c70427daa6eb23ce55c4b25a94a7aa6674844d916890e6ccff2ce738e36
|
| 3 |
-
size 9080995015
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:91317c5e4abc67d24eaa48e06aae01d8e24c1621d2d7b287b5317f05ead1b119
|
| 3 |
-
size 14645
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6064554228f0a8789adc25287f0e1251cf8bf5c5613edc79a0122720bfc71c3e
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
-
size 17209920
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/tokenizer_config.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"backend": "tokenizers",
|
| 3 |
-
"bos_token": "<|begin_of_text|>",
|
| 4 |
-
"clean_up_tokenization_spaces": true,
|
| 5 |
-
"eos_token": "<|end_of_text|>",
|
| 6 |
-
"is_local": false,
|
| 7 |
-
"local_files_only": false,
|
| 8 |
-
"model_input_names": [
|
| 9 |
-
"input_ids",
|
| 10 |
-
"attention_mask"
|
| 11 |
-
],
|
| 12 |
-
"model_max_length": 131072,
|
| 13 |
-
"pad_token": "<|end_of_text|>",
|
| 14 |
-
"tokenizer_class": "TokenizersBackend"
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/trainer_state.json
DELETED
|
@@ -1,661 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.7511737089201878,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 200,
|
| 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,
|
| 14 |
-
"forget_loss": 0.00946044921875,
|
| 15 |
-
"retain_loss": 0.0,
|
| 16 |
-
"step": 0
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0,
|
| 20 |
-
"forget_loss": 0.00994873046875,
|
| 21 |
-
"retain_loss": 0.0,
|
| 22 |
-
"step": 0
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0,
|
| 26 |
-
"forget_loss": 0.00958251953125,
|
| 27 |
-
"retain_loss": 0.0,
|
| 28 |
-
"step": 0
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"epoch": 0,
|
| 32 |
-
"forget_loss": 0.009521484375,
|
| 33 |
-
"retain_loss": 0.0,
|
| 34 |
-
"step": 0
|
| 35 |
-
},
|
| 36 |
-
{
|
| 37 |
-
"epoch": 0.003755868544600939,
|
| 38 |
-
"grad_norm": 0.11474609375,
|
| 39 |
-
"learning_rate": 0.0,
|
| 40 |
-
"loss": 0.0096282958984375,
|
| 41 |
-
"step": 1
|
| 42 |
-
},
|
| 43 |
-
{
|
| 44 |
-
"epoch": 0.03755868544600939,
|
| 45 |
-
"grad_norm": 0.09814453125,
|
| 46 |
-
"learning_rate": 4.5e-06,
|
| 47 |
-
"loss": 0.009236653645833334,
|
| 48 |
-
"step": 10
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.03755868544600939,
|
| 52 |
-
"forget_loss": 0.00799560546875,
|
| 53 |
-
"retain_loss": 1.919269561767578e-05,
|
| 54 |
-
"step": 10
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 0.03755868544600939,
|
| 58 |
-
"forget_loss": 0.008056640625,
|
| 59 |
-
"retain_loss": 1.6570091247558594e-05,
|
| 60 |
-
"step": 10
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 0.03755868544600939,
|
| 64 |
-
"forget_loss": 0.0081787109375,
|
| 65 |
-
"retain_loss": 2.2649765014648438e-05,
|
| 66 |
-
"step": 10
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.03755868544600939,
|
| 70 |
-
"forget_loss": 0.00823974609375,
|
| 71 |
-
"retain_loss": 2.1457672119140625e-05,
|
| 72 |
-
"step": 10
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.07511737089201878,
|
| 76 |
-
"grad_norm": 0.047607421875,
|
| 77 |
-
"learning_rate": 9.5e-06,
|
| 78 |
-
"loss": 0.00635223388671875,
|
| 79 |
-
"step": 20
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.07511737089201878,
|
| 83 |
-
"forget_loss": 0.003662109375,
|
| 84 |
-
"retain_loss": 0.00022602081298828125,
|
| 85 |
-
"step": 20
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 0.07511737089201878,
|
| 89 |
-
"forget_loss": 0.004425048828125,
|
| 90 |
-
"retain_loss": 0.0002880096435546875,
|
| 91 |
-
"step": 20
|
| 92 |
-
},
|
| 93 |
-
{
|
| 94 |
-
"epoch": 0.07511737089201878,
|
| 95 |
-
"forget_loss": 0.0037078857421875,
|
| 96 |
-
"retain_loss": 0.00020885467529296875,
|
| 97 |
-
"step": 20
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 0.07511737089201878,
|
| 101 |
-
"forget_loss": 0.00421142578125,
|
| 102 |
-
"retain_loss": 0.00021457672119140625,
|
| 103 |
-
"step": 20
|
| 104 |
-
},
|
| 105 |
-
{
|
| 106 |
-
"epoch": 0.11267605633802817,
|
| 107 |
-
"grad_norm": 0.123046875,
|
| 108 |
-
"learning_rate": 9.82490272373541e-06,
|
| 109 |
-
"loss": 0.00320587158203125,
|
| 110 |
-
"step": 30
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.11267605633802817,
|
| 114 |
-
"forget_loss": 0.0018310546875,
|
| 115 |
-
"retain_loss": 0.00054168701171875,
|
| 116 |
-
"step": 30
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.11267605633802817,
|
| 120 |
-
"forget_loss": 0.00177001953125,
|
| 121 |
-
"retain_loss": 0.0004177093505859375,
|
| 122 |
-
"step": 30
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.11267605633802817,
|
| 126 |
-
"forget_loss": 0.00177001953125,
|
| 127 |
-
"retain_loss": 0.0002956390380859375,
|
| 128 |
-
"step": 30
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.11267605633802817,
|
| 132 |
-
"forget_loss": 0.0016937255859375,
|
| 133 |
-
"retain_loss": 0.000331878662109375,
|
| 134 |
-
"step": 30
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 0.15023474178403756,
|
| 138 |
-
"grad_norm": 0.05517578125,
|
| 139 |
-
"learning_rate": 9.63035019455253e-06,
|
| 140 |
-
"loss": 0.0016145706176757812,
|
| 141 |
-
"step": 40
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.15023474178403756,
|
| 145 |
-
"forget_loss": 0.0007781982421875,
|
| 146 |
-
"retain_loss": 0.00021648406982421875,
|
| 147 |
-
"step": 40
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 0.15023474178403756,
|
| 151 |
-
"forget_loss": 0.000762939453125,
|
| 152 |
-
"retain_loss": 0.0004100799560546875,
|
| 153 |
-
"step": 40
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.15023474178403756,
|
| 157 |
-
"forget_loss": 0.000766754150390625,
|
| 158 |
-
"retain_loss": 0.000331878662109375,
|
| 159 |
-
"step": 40
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.15023474178403756,
|
| 163 |
-
"forget_loss": 0.0007781982421875,
|
| 164 |
-
"retain_loss": 0.00038909912109375,
|
| 165 |
-
"step": 40
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.18779342723004694,
|
| 169 |
-
"grad_norm": 0.1416015625,
|
| 170 |
-
"learning_rate": 9.435797665369651e-06,
|
| 171 |
-
"loss": 0.000954437255859375,
|
| 172 |
-
"step": 50
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.18779342723004694,
|
| 176 |
-
"forget_loss": 0.0003452301025390625,
|
| 177 |
-
"retain_loss": 0.00020599365234375,
|
| 178 |
-
"step": 50
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.18779342723004694,
|
| 182 |
-
"forget_loss": 0.0003814697265625,
|
| 183 |
-
"retain_loss": 0.00020694732666015625,
|
| 184 |
-
"step": 50
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.18779342723004694,
|
| 188 |
-
"forget_loss": 0.000415802001953125,
|
| 189 |
-
"retain_loss": 0.0003604888916015625,
|
| 190 |
-
"step": 50
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 0.18779342723004694,
|
| 194 |
-
"forget_loss": 0.0003719329833984375,
|
| 195 |
-
"retain_loss": 0.0001964569091796875,
|
| 196 |
-
"step": 50
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 0.22535211267605634,
|
| 200 |
-
"grad_norm": 0.06396484375,
|
| 201 |
-
"learning_rate": 9.241245136186772e-06,
|
| 202 |
-
"loss": 0.0008329868316650391,
|
| 203 |
-
"step": 60
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 0.22535211267605634,
|
| 207 |
-
"forget_loss": 0.0002574920654296875,
|
| 208 |
-
"retain_loss": 0.0002727508544921875,
|
| 209 |
-
"step": 60
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 0.22535211267605634,
|
| 213 |
-
"forget_loss": 0.00019931793212890625,
|
| 214 |
-
"retain_loss": 0.00010919570922851562,
|
| 215 |
-
"step": 60
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 0.22535211267605634,
|
| 219 |
-
"forget_loss": 0.0001983642578125,
|
| 220 |
-
"retain_loss": 0.000202178955078125,
|
| 221 |
-
"step": 60
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.22535211267605634,
|
| 225 |
-
"forget_loss": 0.00023365020751953125,
|
| 226 |
-
"retain_loss": 0.0002002716064453125,
|
| 227 |
-
"step": 60
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.26291079812206575,
|
| 231 |
-
"grad_norm": 0.28515625,
|
| 232 |
-
"learning_rate": 9.046692607003892e-06,
|
| 233 |
-
"loss": 0.0006081581115722657,
|
| 234 |
-
"step": 70
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.26291079812206575,
|
| 238 |
-
"forget_loss": 0.00018405914306640625,
|
| 239 |
-
"retain_loss": 0.0002689361572265625,
|
| 240 |
-
"step": 70
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 0.26291079812206575,
|
| 244 |
-
"forget_loss": 0.0001811981201171875,
|
| 245 |
-
"retain_loss": 8.535385131835938e-05,
|
| 246 |
-
"step": 70
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 0.26291079812206575,
|
| 250 |
-
"forget_loss": 0.00022792816162109375,
|
| 251 |
-
"retain_loss": 0.00010728836059570312,
|
| 252 |
-
"step": 70
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 0.26291079812206575,
|
| 256 |
-
"forget_loss": 0.0003643035888671875,
|
| 257 |
-
"retain_loss": 0.00011777877807617188,
|
| 258 |
-
"step": 70
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 0.3004694835680751,
|
| 262 |
-
"grad_norm": 0.07177734375,
|
| 263 |
-
"learning_rate": 8.852140077821012e-06,
|
| 264 |
-
"loss": 0.0004550933837890625,
|
| 265 |
-
"step": 80
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 0.3004694835680751,
|
| 269 |
-
"forget_loss": 0.0002155303955078125,
|
| 270 |
-
"retain_loss": 0.000110626220703125,
|
| 271 |
-
"step": 80
|
| 272 |
-
},
|
| 273 |
-
{
|
| 274 |
-
"epoch": 0.3004694835680751,
|
| 275 |
-
"forget_loss": 0.00014019012451171875,
|
| 276 |
-
"retain_loss": 6.723403930664062e-05,
|
| 277 |
-
"step": 80
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.3004694835680751,
|
| 281 |
-
"forget_loss": 0.0001773834228515625,
|
| 282 |
-
"retain_loss": 0.000331878662109375,
|
| 283 |
-
"step": 80
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 0.3004694835680751,
|
| 287 |
-
"forget_loss": 0.00016498565673828125,
|
| 288 |
-
"retain_loss": 9.489059448242188e-05,
|
| 289 |
-
"step": 80
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 0.3380281690140845,
|
| 293 |
-
"grad_norm": 0.0810546875,
|
| 294 |
-
"learning_rate": 8.657587548638134e-06,
|
| 295 |
-
"loss": 0.0003980875015258789,
|
| 296 |
-
"step": 90
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.3380281690140845,
|
| 300 |
-
"forget_loss": 0.00015735626220703125,
|
| 301 |
-
"retain_loss": 0.0001544952392578125,
|
| 302 |
-
"step": 90
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.3380281690140845,
|
| 306 |
-
"forget_loss": 0.000133514404296875,
|
| 307 |
-
"retain_loss": 0.00080108642578125,
|
| 308 |
-
"step": 90
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.3380281690140845,
|
| 312 |
-
"forget_loss": 0.00014781951904296875,
|
| 313 |
-
"retain_loss": 0.000431060791015625,
|
| 314 |
-
"step": 90
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.3380281690140845,
|
| 318 |
-
"forget_loss": 0.00014400482177734375,
|
| 319 |
-
"retain_loss": 0.00031280517578125,
|
| 320 |
-
"step": 90
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.3755868544600939,
|
| 324 |
-
"grad_norm": 0.025146484375,
|
| 325 |
-
"learning_rate": 8.463035019455253e-06,
|
| 326 |
-
"loss": 0.00032124519348144533,
|
| 327 |
-
"step": 100
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.3755868544600939,
|
| 331 |
-
"forget_loss": 0.00015163421630859375,
|
| 332 |
-
"retain_loss": 0.00015926361083984375,
|
| 333 |
-
"step": 100
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.3755868544600939,
|
| 337 |
-
"forget_loss": 0.0001506805419921875,
|
| 338 |
-
"retain_loss": 0.00011587142944335938,
|
| 339 |
-
"step": 100
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.3755868544600939,
|
| 343 |
-
"forget_loss": 0.00013065338134765625,
|
| 344 |
-
"retain_loss": 0.000125885009765625,
|
| 345 |
-
"step": 100
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.3755868544600939,
|
| 349 |
-
"forget_loss": 0.0001239776611328125,
|
| 350 |
-
"retain_loss": 0.0001277923583984375,
|
| 351 |
-
"step": 100
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 0.4131455399061033,
|
| 355 |
-
"grad_norm": 0.06884765625,
|
| 356 |
-
"learning_rate": 8.268482490272373e-06,
|
| 357 |
-
"loss": 0.00034072399139404295,
|
| 358 |
-
"step": 110
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 0.4131455399061033,
|
| 362 |
-
"forget_loss": 0.0001544952392578125,
|
| 363 |
-
"retain_loss": 7.2479248046875e-05,
|
| 364 |
-
"step": 110
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 0.4131455399061033,
|
| 368 |
-
"forget_loss": 0.0001373291015625,
|
| 369 |
-
"retain_loss": 0.000270843505859375,
|
| 370 |
-
"step": 110
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 0.4131455399061033,
|
| 374 |
-
"forget_loss": 0.0001125335693359375,
|
| 375 |
-
"retain_loss": 9.965896606445312e-05,
|
| 376 |
-
"step": 110
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.4131455399061033,
|
| 380 |
-
"forget_loss": 0.00011205673217773438,
|
| 381 |
-
"retain_loss": 6.866455078125e-05,
|
| 382 |
-
"step": 110
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 0.4507042253521127,
|
| 386 |
-
"grad_norm": 0.08544921875,
|
| 387 |
-
"learning_rate": 8.073929961089495e-06,
|
| 388 |
-
"loss": 0.0002372264862060547,
|
| 389 |
-
"step": 120
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.4507042253521127,
|
| 393 |
-
"forget_loss": 0.000179290771484375,
|
| 394 |
-
"retain_loss": 7.05718994140625e-05,
|
| 395 |
-
"step": 120
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.4507042253521127,
|
| 399 |
-
"forget_loss": 0.0001277923583984375,
|
| 400 |
-
"retain_loss": 9.250640869140625e-05,
|
| 401 |
-
"step": 120
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.4507042253521127,
|
| 405 |
-
"forget_loss": 0.00013446807861328125,
|
| 406 |
-
"retain_loss": 8.630752563476562e-05,
|
| 407 |
-
"step": 120
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 0.4507042253521127,
|
| 411 |
-
"forget_loss": 0.0001735687255859375,
|
| 412 |
-
"retain_loss": 8.106231689453125e-05,
|
| 413 |
-
"step": 120
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 0.48826291079812206,
|
| 417 |
-
"grad_norm": 0.0361328125,
|
| 418 |
-
"learning_rate": 7.879377431906614e-06,
|
| 419 |
-
"loss": 0.0002105236053466797,
|
| 420 |
-
"step": 130
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 0.48826291079812206,
|
| 424 |
-
"forget_loss": 0.00010776519775390625,
|
| 425 |
-
"retain_loss": 5.221366882324219e-05,
|
| 426 |
-
"step": 130
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 0.48826291079812206,
|
| 430 |
-
"forget_loss": 0.00010728836059570312,
|
| 431 |
-
"retain_loss": 5.1021575927734375e-05,
|
| 432 |
-
"step": 130
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 0.48826291079812206,
|
| 436 |
-
"forget_loss": 0.00010204315185546875,
|
| 437 |
-
"retain_loss": 0.00011110305786132812,
|
| 438 |
-
"step": 130
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 0.48826291079812206,
|
| 442 |
-
"forget_loss": 0.000156402587890625,
|
| 443 |
-
"retain_loss": 7.05718994140625e-05,
|
| 444 |
-
"step": 130
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 0.5258215962441315,
|
| 448 |
-
"grad_norm": 0.035400390625,
|
| 449 |
-
"learning_rate": 7.684824902723736e-06,
|
| 450 |
-
"loss": 0.000272369384765625,
|
| 451 |
-
"step": 140
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 0.5258215962441315,
|
| 455 |
-
"forget_loss": 0.0001087188720703125,
|
| 456 |
-
"retain_loss": 7.009506225585938e-05,
|
| 457 |
-
"step": 140
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 0.5258215962441315,
|
| 461 |
-
"forget_loss": 0.0001239776611328125,
|
| 462 |
-
"retain_loss": 7.963180541992188e-05,
|
| 463 |
-
"step": 140
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 0.5258215962441315,
|
| 467 |
-
"forget_loss": 0.00017070770263671875,
|
| 468 |
-
"retain_loss": 6.29425048828125e-05,
|
| 469 |
-
"step": 140
|
| 470 |
-
},
|
| 471 |
-
{
|
| 472 |
-
"epoch": 0.5258215962441315,
|
| 473 |
-
"forget_loss": 0.00013446807861328125,
|
| 474 |
-
"retain_loss": 5.5789947509765625e-05,
|
| 475 |
-
"step": 140
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 0.5633802816901409,
|
| 479 |
-
"grad_norm": 0.0177001953125,
|
| 480 |
-
"learning_rate": 7.4902723735408565e-06,
|
| 481 |
-
"loss": 0.00019230842590332032,
|
| 482 |
-
"step": 150
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.5633802816901409,
|
| 486 |
-
"forget_loss": 0.00010585784912109375,
|
| 487 |
-
"retain_loss": 5.793571472167969e-05,
|
| 488 |
-
"step": 150
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 0.5633802816901409,
|
| 492 |
-
"forget_loss": 0.00011157989501953125,
|
| 493 |
-
"retain_loss": 0.00015163421630859375,
|
| 494 |
-
"step": 150
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.5633802816901409,
|
| 498 |
-
"forget_loss": 8.821487426757812e-05,
|
| 499 |
-
"retain_loss": 6.866455078125e-05,
|
| 500 |
-
"step": 150
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.5633802816901409,
|
| 504 |
-
"forget_loss": 9.059906005859375e-05,
|
| 505 |
-
"retain_loss": 0.00010251998901367188,
|
| 506 |
-
"step": 150
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.6009389671361502,
|
| 510 |
-
"grad_norm": 0.06591796875,
|
| 511 |
-
"learning_rate": 7.295719844357977e-06,
|
| 512 |
-
"loss": 0.00020923614501953126,
|
| 513 |
-
"step": 160
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.6009389671361502,
|
| 517 |
-
"forget_loss": 0.00010156631469726562,
|
| 518 |
-
"retain_loss": 8.535385131835938e-05,
|
| 519 |
-
"step": 160
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 0.6009389671361502,
|
| 523 |
-
"forget_loss": 9.441375732421875e-05,
|
| 524 |
-
"retain_loss": 7.05718994140625e-05,
|
| 525 |
-
"step": 160
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 0.6009389671361502,
|
| 529 |
-
"forget_loss": 9.489059448242188e-05,
|
| 530 |
-
"retain_loss": 6.151199340820312e-05,
|
| 531 |
-
"step": 160
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.6009389671361502,
|
| 535 |
-
"forget_loss": 9.679794311523438e-05,
|
| 536 |
-
"retain_loss": 5.984306335449219e-05,
|
| 537 |
-
"step": 160
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.6384976525821596,
|
| 541 |
-
"grad_norm": 0.0152587890625,
|
| 542 |
-
"learning_rate": 7.101167315175098e-06,
|
| 543 |
-
"loss": 0.0001931428909301758,
|
| 544 |
-
"step": 170
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 0.6384976525821596,
|
| 548 |
-
"forget_loss": 9.489059448242188e-05,
|
| 549 |
-
"retain_loss": 6.079673767089844e-05,
|
| 550 |
-
"step": 170
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 0.6384976525821596,
|
| 554 |
-
"forget_loss": 0.000110626220703125,
|
| 555 |
-
"retain_loss": 7.104873657226562e-05,
|
| 556 |
-
"step": 170
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 0.6384976525821596,
|
| 560 |
-
"forget_loss": 0.00010776519775390625,
|
| 561 |
-
"retain_loss": 0.00011539459228515625,
|
| 562 |
-
"step": 170
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 0.6384976525821596,
|
| 566 |
-
"forget_loss": 9.441375732421875e-05,
|
| 567 |
-
"retain_loss": 0.00011682510375976562,
|
| 568 |
-
"step": 170
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 0.676056338028169,
|
| 572 |
-
"grad_norm": 0.0306396484375,
|
| 573 |
-
"learning_rate": 6.9066147859922184e-06,
|
| 574 |
-
"loss": 0.00021104812622070314,
|
| 575 |
-
"step": 180
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 0.676056338028169,
|
| 579 |
-
"forget_loss": 0.000125885009765625,
|
| 580 |
-
"retain_loss": 0.0001239776611328125,
|
| 581 |
-
"step": 180
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 0.676056338028169,
|
| 585 |
-
"forget_loss": 0.00010395050048828125,
|
| 586 |
-
"retain_loss": 8.96453857421875e-05,
|
| 587 |
-
"step": 180
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 0.676056338028169,
|
| 591 |
-
"forget_loss": 8.869171142578125e-05,
|
| 592 |
-
"retain_loss": 8.20159912109375e-05,
|
| 593 |
-
"step": 180
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 0.676056338028169,
|
| 597 |
-
"forget_loss": 9.107589721679688e-05,
|
| 598 |
-
"retain_loss": 5.316734313964844e-05,
|
| 599 |
-
"step": 180
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 0.7136150234741784,
|
| 603 |
-
"grad_norm": 0.0230712890625,
|
| 604 |
-
"learning_rate": 6.712062256809338e-06,
|
| 605 |
-
"loss": 0.0001739978790283203,
|
| 606 |
-
"step": 190
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 0.7136150234741784,
|
| 610 |
-
"forget_loss": 9.059906005859375e-05,
|
| 611 |
-
"retain_loss": 5.793571472167969e-05,
|
| 612 |
-
"step": 190
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 0.7136150234741784,
|
| 616 |
-
"forget_loss": 9.5367431640625e-05,
|
| 617 |
-
"retain_loss": 5.0067901611328125e-05,
|
| 618 |
-
"step": 190
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 0.7136150234741784,
|
| 622 |
-
"forget_loss": 8.869171142578125e-05,
|
| 623 |
-
"retain_loss": 5.7220458984375e-05,
|
| 624 |
-
"step": 190
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 0.7136150234741784,
|
| 628 |
-
"forget_loss": 0.00010919570922851562,
|
| 629 |
-
"retain_loss": 4.9591064453125e-05,
|
| 630 |
-
"step": 190
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 0.7511737089201878,
|
| 634 |
-
"grad_norm": 0.01068115234375,
|
| 635 |
-
"learning_rate": 6.51750972762646e-06,
|
| 636 |
-
"loss": 0.00019364356994628907,
|
| 637 |
-
"step": 200
|
| 638 |
-
}
|
| 639 |
-
],
|
| 640 |
-
"logging_steps": 10,
|
| 641 |
-
"max_steps": 534,
|
| 642 |
-
"num_input_tokens_seen": 0,
|
| 643 |
-
"num_train_epochs": 2,
|
| 644 |
-
"save_steps": 200,
|
| 645 |
-
"stateful_callbacks": {
|
| 646 |
-
"TrainerControl": {
|
| 647 |
-
"args": {
|
| 648 |
-
"should_epoch_stop": false,
|
| 649 |
-
"should_evaluate": false,
|
| 650 |
-
"should_log": false,
|
| 651 |
-
"should_save": true,
|
| 652 |
-
"should_training_stop": false
|
| 653 |
-
},
|
| 654 |
-
"attributes": {}
|
| 655 |
-
}
|
| 656 |
-
},
|
| 657 |
-
"total_flos": 0.0,
|
| 658 |
-
"train_batch_size": 8,
|
| 659 |
-
"trial_name": null,
|
| 660 |
-
"trial_params": null
|
| 661 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cde3986b5d2902c3143ac3a5311b9443a600348ae4fbcaab8a20b0760c034ff1
|
| 3 |
-
size 5265
|
|
|
|
|
|
|
|
|
|
|
|