Commit
•
aa424b3
1
Parent(s):
4138781
Upload 9 files
Browse files- config.json +31 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +350 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/models/Mixtral-8x7B-v0.3-dna",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2688,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_experts_per_tok": 1,
|
| 17 |
+
"num_hidden_layers": 8,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 8,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.02,
|
| 24 |
+
"router_jitter_noise": 0.0,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 4096
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.41.0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e81b991150e497e7ccb3daa16cf40ed0d3e832453c7a5502af70f9cd4e3074e4
|
| 3 |
+
size 843210512
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:661b7f8abbf23ed51f1223bdc244ebc634871b48a0389f1ccccd4ba3257ddd63
|
| 3 |
+
size 1064
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"tokenizer_class": "PreTrainedTokenizerFast", "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 6.85207986831665,
|
| 3 |
+
"best_model_checkpoint": "./results/models/mistral-dna/checkpoint-18333",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 18333,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19091256204658266,
|
| 13 |
+
"grad_norm": 0.0634765625,
|
| 14 |
+
"learning_rate": 0.003984726995036274,
|
| 15 |
+
"loss": 6.9779,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3818251240931653,
|
| 20 |
+
"grad_norm": 0.09716796875,
|
| 21 |
+
"learning_rate": 0.003969453990072547,
|
| 22 |
+
"loss": 6.8377,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.572737686139748,
|
| 27 |
+
"grad_norm": 0.07177734375,
|
| 28 |
+
"learning_rate": 0.003954180985108821,
|
| 29 |
+
"loss": 6.7842,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7636502481863306,
|
| 34 |
+
"grad_norm": 0.1025390625,
|
| 35 |
+
"learning_rate": 0.003938907980145094,
|
| 36 |
+
"loss": 6.8022,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9545628102329133,
|
| 41 |
+
"grad_norm": 1.4921875,
|
| 42 |
+
"learning_rate": 0.003923634975181367,
|
| 43 |
+
"loss": 6.8364,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 6.887508392333984,
|
| 49 |
+
"eval_runtime": 0.7694,
|
| 50 |
+
"eval_samples_per_second": 109.176,
|
| 51 |
+
"eval_steps_per_second": 3.899,
|
| 52 |
+
"step": 2619
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.145475372279496,
|
| 56 |
+
"grad_norm": 1.515625,
|
| 57 |
+
"learning_rate": 0.0039083619702176406,
|
| 58 |
+
"loss": 6.8965,
|
| 59 |
+
"step": 3000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.3363879343260787,
|
| 63 |
+
"grad_norm": 1.859375,
|
| 64 |
+
"learning_rate": 0.003893088965253914,
|
| 65 |
+
"loss": 6.9056,
|
| 66 |
+
"step": 3500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.5273004963726613,
|
| 70 |
+
"grad_norm": 2.28125,
|
| 71 |
+
"learning_rate": 0.003877815960290187,
|
| 72 |
+
"loss": 6.8995,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.718213058419244,
|
| 77 |
+
"grad_norm": 1.8984375,
|
| 78 |
+
"learning_rate": 0.003862542955326461,
|
| 79 |
+
"loss": 6.8937,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.9091256204658267,
|
| 84 |
+
"grad_norm": 3.859375,
|
| 85 |
+
"learning_rate": 0.0038472699503627338,
|
| 86 |
+
"loss": 6.8934,
|
| 87 |
+
"step": 5000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"eval_loss": 6.88522481918335,
|
| 92 |
+
"eval_runtime": 0.7793,
|
| 93 |
+
"eval_samples_per_second": 107.783,
|
| 94 |
+
"eval_steps_per_second": 3.849,
|
| 95 |
+
"step": 5238
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.1000381825124093,
|
| 99 |
+
"grad_norm": 2.953125,
|
| 100 |
+
"learning_rate": 0.003831996945399007,
|
| 101 |
+
"loss": 6.8913,
|
| 102 |
+
"step": 5500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.290950744558992,
|
| 106 |
+
"grad_norm": 8.75,
|
| 107 |
+
"learning_rate": 0.003816723940435281,
|
| 108 |
+
"loss": 6.8984,
|
| 109 |
+
"step": 6000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4818633066055744,
|
| 113 |
+
"grad_norm": 5.96875,
|
| 114 |
+
"learning_rate": 0.003801450935471554,
|
| 115 |
+
"loss": 6.8961,
|
| 116 |
+
"step": 6500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.6727758686521574,
|
| 120 |
+
"grad_norm": 4.375,
|
| 121 |
+
"learning_rate": 0.003786177930507828,
|
| 122 |
+
"loss": 6.8904,
|
| 123 |
+
"step": 7000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.86368843069874,
|
| 127 |
+
"grad_norm": 4.15625,
|
| 128 |
+
"learning_rate": 0.003770904925544101,
|
| 129 |
+
"loss": 6.8954,
|
| 130 |
+
"step": 7500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.0,
|
| 134 |
+
"eval_loss": 6.886116981506348,
|
| 135 |
+
"eval_runtime": 0.7695,
|
| 136 |
+
"eval_samples_per_second": 109.165,
|
| 137 |
+
"eval_steps_per_second": 3.899,
|
| 138 |
+
"step": 7857
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.0546009927453226,
|
| 142 |
+
"grad_norm": 3.296875,
|
| 143 |
+
"learning_rate": 0.0037556319205803742,
|
| 144 |
+
"loss": 6.891,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.245513554791905,
|
| 149 |
+
"grad_norm": 2.9375,
|
| 150 |
+
"learning_rate": 0.0037403589156166477,
|
| 151 |
+
"loss": 6.8839,
|
| 152 |
+
"step": 8500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.436426116838488,
|
| 156 |
+
"grad_norm": 3.0625,
|
| 157 |
+
"learning_rate": 0.003725085910652921,
|
| 158 |
+
"loss": 6.8833,
|
| 159 |
+
"step": 9000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.6273386788850708,
|
| 163 |
+
"grad_norm": 8.5,
|
| 164 |
+
"learning_rate": 0.0037098129056891945,
|
| 165 |
+
"loss": 6.8767,
|
| 166 |
+
"step": 9500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.8182512409316534,
|
| 170 |
+
"grad_norm": 3.484375,
|
| 171 |
+
"learning_rate": 0.003694539900725468,
|
| 172 |
+
"loss": 6.8793,
|
| 173 |
+
"step": 10000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 4.0,
|
| 177 |
+
"eval_loss": 6.874268531799316,
|
| 178 |
+
"eval_runtime": 0.7764,
|
| 179 |
+
"eval_samples_per_second": 108.196,
|
| 180 |
+
"eval_steps_per_second": 3.864,
|
| 181 |
+
"step": 10476
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 4.009163802978236,
|
| 185 |
+
"grad_norm": 8.875,
|
| 186 |
+
"learning_rate": 0.003679266895761741,
|
| 187 |
+
"loss": 6.8786,
|
| 188 |
+
"step": 10500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.2000763650248185,
|
| 192 |
+
"grad_norm": 3.71875,
|
| 193 |
+
"learning_rate": 0.0036639938907980147,
|
| 194 |
+
"loss": 6.874,
|
| 195 |
+
"step": 11000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.390988927071401,
|
| 199 |
+
"grad_norm": 5.5,
|
| 200 |
+
"learning_rate": 0.003648720885834288,
|
| 201 |
+
"loss": 6.8756,
|
| 202 |
+
"step": 11500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.581901489117984,
|
| 206 |
+
"grad_norm": 19.5,
|
| 207 |
+
"learning_rate": 0.0036334478808705615,
|
| 208 |
+
"loss": 6.8751,
|
| 209 |
+
"step": 12000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.772814051164566,
|
| 213 |
+
"grad_norm": 5.84375,
|
| 214 |
+
"learning_rate": 0.003618174875906835,
|
| 215 |
+
"loss": 6.877,
|
| 216 |
+
"step": 12500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.963726613211149,
|
| 220 |
+
"grad_norm": 3.46875,
|
| 221 |
+
"learning_rate": 0.003602901870943108,
|
| 222 |
+
"loss": 6.8734,
|
| 223 |
+
"step": 13000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_loss": 6.8629889488220215,
|
| 228 |
+
"eval_runtime": 0.767,
|
| 229 |
+
"eval_samples_per_second": 109.512,
|
| 230 |
+
"eval_steps_per_second": 3.911,
|
| 231 |
+
"step": 13095
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.154639175257732,
|
| 235 |
+
"grad_norm": 5.40625,
|
| 236 |
+
"learning_rate": 0.0035876288659793818,
|
| 237 |
+
"loss": 6.8751,
|
| 238 |
+
"step": 13500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.345551737304315,
|
| 242 |
+
"grad_norm": 4.78125,
|
| 243 |
+
"learning_rate": 0.0035723558610156548,
|
| 244 |
+
"loss": 6.8771,
|
| 245 |
+
"step": 14000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.5364642993508975,
|
| 249 |
+
"grad_norm": 4.8125,
|
| 250 |
+
"learning_rate": 0.003557082856051928,
|
| 251 |
+
"loss": 6.8746,
|
| 252 |
+
"step": 14500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.72737686139748,
|
| 256 |
+
"grad_norm": 5.875,
|
| 257 |
+
"learning_rate": 0.0035418098510882016,
|
| 258 |
+
"loss": 6.8753,
|
| 259 |
+
"step": 15000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.918289423444063,
|
| 263 |
+
"grad_norm": 5.3125,
|
| 264 |
+
"learning_rate": 0.003526536846124475,
|
| 265 |
+
"loss": 6.8791,
|
| 266 |
+
"step": 15500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_loss": 6.864416122436523,
|
| 271 |
+
"eval_runtime": 0.7754,
|
| 272 |
+
"eval_samples_per_second": 108.328,
|
| 273 |
+
"eval_steps_per_second": 3.869,
|
| 274 |
+
"step": 15714
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 6.109201985490645,
|
| 278 |
+
"grad_norm": 5.6875,
|
| 279 |
+
"learning_rate": 0.0035112638411607484,
|
| 280 |
+
"loss": 6.8699,
|
| 281 |
+
"step": 16000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.300114547537228,
|
| 285 |
+
"grad_norm": 4.375,
|
| 286 |
+
"learning_rate": 0.003495990836197022,
|
| 287 |
+
"loss": 6.8667,
|
| 288 |
+
"step": 16500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.49102710958381,
|
| 292 |
+
"grad_norm": 11.5,
|
| 293 |
+
"learning_rate": 0.0034807178312332952,
|
| 294 |
+
"loss": 6.8655,
|
| 295 |
+
"step": 17000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.681939671630393,
|
| 299 |
+
"grad_norm": 6.125,
|
| 300 |
+
"learning_rate": 0.0034654448262695686,
|
| 301 |
+
"loss": 6.8647,
|
| 302 |
+
"step": 17500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.872852233676976,
|
| 306 |
+
"grad_norm": 5.9375,
|
| 307 |
+
"learning_rate": 0.003450171821305842,
|
| 308 |
+
"loss": 6.8588,
|
| 309 |
+
"step": 18000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.0,
|
| 313 |
+
"eval_loss": 6.85207986831665,
|
| 314 |
+
"eval_runtime": 0.768,
|
| 315 |
+
"eval_samples_per_second": 109.374,
|
| 316 |
+
"eval_steps_per_second": 3.906,
|
| 317 |
+
"step": 18333
|
| 318 |
+
}
|
| 319 |
+
],
|
| 320 |
+
"logging_steps": 500,
|
| 321 |
+
"max_steps": 130950,
|
| 322 |
+
"num_input_tokens_seen": 0,
|
| 323 |
+
"num_train_epochs": 50,
|
| 324 |
+
"save_steps": 500,
|
| 325 |
+
"stateful_callbacks": {
|
| 326 |
+
"EarlyStoppingCallback": {
|
| 327 |
+
"args": {
|
| 328 |
+
"early_stopping_patience": 3,
|
| 329 |
+
"early_stopping_threshold": 0.0
|
| 330 |
+
},
|
| 331 |
+
"attributes": {
|
| 332 |
+
"early_stopping_patience_counter": 0
|
| 333 |
+
}
|
| 334 |
+
},
|
| 335 |
+
"TrainerControl": {
|
| 336 |
+
"args": {
|
| 337 |
+
"should_epoch_stop": false,
|
| 338 |
+
"should_evaluate": false,
|
| 339 |
+
"should_log": false,
|
| 340 |
+
"should_save": true,
|
| 341 |
+
"should_training_stop": false
|
| 342 |
+
},
|
| 343 |
+
"attributes": {}
|
| 344 |
+
}
|
| 345 |
+
},
|
| 346 |
+
"total_flos": 3.6896228473744097e+18,
|
| 347 |
+
"train_batch_size": 32,
|
| 348 |
+
"trial_name": null,
|
| 349 |
+
"trial_params": null
|
| 350 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aa6f71bbb4599f1d1c3708f58b2b0090b8dfadcb7d659356feaf26509823c60
|
| 3 |
+
size 5048
|