Training in progress, step 68000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65c628bc21a488cc995a999f4ebe043aded7453145c4be01688da0234dc825a
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a4b726e70e9f1b2d482d4b906ff82dfb782045da636caaeed5e73095f82fd90
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cab5a61edbb7c8a2083270aa3aceaa772762aaf6c804e164b525561621e196f
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee827426ba5e510531f97228be83448aeb6e47b62607221c379bc9913032527f
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -5000,6 +5000,318 @@
|
|
| 5000 |
"eval_samples_per_second": 77.085,
|
| 5001 |
"eval_steps_per_second": 19.271,
|
| 5002 |
"step": 64000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5003 |
}
|
| 5004 |
],
|
| 5005 |
"logging_steps": 100,
|
|
@@ -5019,7 +5331,7 @@
|
|
| 5019 |
"attributes": {}
|
| 5020 |
}
|
| 5021 |
},
|
| 5022 |
-
"total_flos": 1.
|
| 5023 |
"train_batch_size": 22,
|
| 5024 |
"trial_name": null,
|
| 5025 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2909090909090909,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 68000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5000 |
"eval_samples_per_second": 77.085,
|
| 5001 |
"eval_steps_per_second": 19.271,
|
| 5002 |
"step": 64000
|
| 5003 |
+
},
|
| 5004 |
+
{
|
| 5005 |
+
"epoch": 0.25545454545454543,
|
| 5006 |
+
"grad_norm": 0.15801353752613068,
|
| 5007 |
+
"learning_rate": 0.0003723892610494738,
|
| 5008 |
+
"loss": 2.6523193359375,
|
| 5009 |
+
"step": 64100
|
| 5010 |
+
},
|
| 5011 |
+
{
|
| 5012 |
+
"epoch": 0.25636363636363635,
|
| 5013 |
+
"grad_norm": 0.16160622239112854,
|
| 5014 |
+
"learning_rate": 0.00037100719429656416,
|
| 5015 |
+
"loss": 2.620086669921875,
|
| 5016 |
+
"step": 64200
|
| 5017 |
+
},
|
| 5018 |
+
{
|
| 5019 |
+
"epoch": 0.25727272727272726,
|
| 5020 |
+
"grad_norm": 0.17042121291160583,
|
| 5021 |
+
"learning_rate": 0.00036962618257367153,
|
| 5022 |
+
"loss": 2.634929504394531,
|
| 5023 |
+
"step": 64300
|
| 5024 |
+
},
|
| 5025 |
+
{
|
| 5026 |
+
"epoch": 0.2581818181818182,
|
| 5027 |
+
"grad_norm": 0.16742800176143646,
|
| 5028 |
+
"learning_rate": 0.00036824623717606755,
|
| 5029 |
+
"loss": 2.6305416870117186,
|
| 5030 |
+
"step": 64400
|
| 5031 |
+
},
|
| 5032 |
+
{
|
| 5033 |
+
"epoch": 0.2590909090909091,
|
| 5034 |
+
"grad_norm": 0.15466608107089996,
|
| 5035 |
+
"learning_rate": 0.000366867369390303,
|
| 5036 |
+
"loss": 2.673544921875,
|
| 5037 |
+
"step": 64500
|
| 5038 |
+
},
|
| 5039 |
+
{
|
| 5040 |
+
"epoch": 0.26,
|
| 5041 |
+
"grad_norm": 0.16298887133598328,
|
| 5042 |
+
"learning_rate": 0.00036548959049411447,
|
| 5043 |
+
"loss": 2.629702453613281,
|
| 5044 |
+
"step": 64600
|
| 5045 |
+
},
|
| 5046 |
+
{
|
| 5047 |
+
"epoch": 0.2609090909090909,
|
| 5048 |
+
"grad_norm": 0.1554904580116272,
|
| 5049 |
+
"learning_rate": 0.00036411291175633275,
|
| 5050 |
+
"loss": 2.664700927734375,
|
| 5051 |
+
"step": 64700
|
| 5052 |
+
},
|
| 5053 |
+
{
|
| 5054 |
+
"epoch": 0.26181818181818184,
|
| 5055 |
+
"grad_norm": 0.16158753633499146,
|
| 5056 |
+
"learning_rate": 0.0003627373444367902,
|
| 5057 |
+
"loss": 2.632271423339844,
|
| 5058 |
+
"step": 64800
|
| 5059 |
+
},
|
| 5060 |
+
{
|
| 5061 |
+
"epoch": 0.26272727272727275,
|
| 5062 |
+
"grad_norm": 0.1622844785451889,
|
| 5063 |
+
"learning_rate": 0.00036136289978622925,
|
| 5064 |
+
"loss": 2.626861877441406,
|
| 5065 |
+
"step": 64900
|
| 5066 |
+
},
|
| 5067 |
+
{
|
| 5068 |
+
"epoch": 0.2636363636363636,
|
| 5069 |
+
"grad_norm": 0.16394828259944916,
|
| 5070 |
+
"learning_rate": 0.0003599895890462101,
|
| 5071 |
+
"loss": 2.648804016113281,
|
| 5072 |
+
"step": 65000
|
| 5073 |
+
},
|
| 5074 |
+
{
|
| 5075 |
+
"epoch": 0.2636363636363636,
|
| 5076 |
+
"eval_loss": 3.0462276935577393,
|
| 5077 |
+
"eval_runtime": 7.4377,
|
| 5078 |
+
"eval_samples_per_second": 77.444,
|
| 5079 |
+
"eval_steps_per_second": 19.361,
|
| 5080 |
+
"step": 65000
|
| 5081 |
+
},
|
| 5082 |
+
{
|
| 5083 |
+
"epoch": 0.26454545454545453,
|
| 5084 |
+
"grad_norm": 0.15556195378303528,
|
| 5085 |
+
"learning_rate": 0.000358617423449018,
|
| 5086 |
+
"loss": 2.6247119140625,
|
| 5087 |
+
"step": 65100
|
| 5088 |
+
},
|
| 5089 |
+
{
|
| 5090 |
+
"epoch": 0.26545454545454544,
|
| 5091 |
+
"grad_norm": 0.1603025197982788,
|
| 5092 |
+
"learning_rate": 0.00035724641421757314,
|
| 5093 |
+
"loss": 2.6453323364257812,
|
| 5094 |
+
"step": 65200
|
| 5095 |
+
},
|
| 5096 |
+
{
|
| 5097 |
+
"epoch": 0.26636363636363636,
|
| 5098 |
+
"grad_norm": 0.17644956707954407,
|
| 5099 |
+
"learning_rate": 0.0003558765725653368,
|
| 5100 |
+
"loss": 2.67004638671875,
|
| 5101 |
+
"step": 65300
|
| 5102 |
+
},
|
| 5103 |
+
{
|
| 5104 |
+
"epoch": 0.2672727272727273,
|
| 5105 |
+
"grad_norm": 0.17642109096050262,
|
| 5106 |
+
"learning_rate": 0.0003545079096962215,
|
| 5107 |
+
"loss": 2.6238552856445314,
|
| 5108 |
+
"step": 65400
|
| 5109 |
+
},
|
| 5110 |
+
{
|
| 5111 |
+
"epoch": 0.2681818181818182,
|
| 5112 |
+
"grad_norm": 0.16550812125205994,
|
| 5113 |
+
"learning_rate": 0.00035314043680449773,
|
| 5114 |
+
"loss": 2.635771484375,
|
| 5115 |
+
"step": 65500
|
| 5116 |
+
},
|
| 5117 |
+
{
|
| 5118 |
+
"epoch": 0.2690909090909091,
|
| 5119 |
+
"grad_norm": 0.18358127772808075,
|
| 5120 |
+
"learning_rate": 0.0003517741650747038,
|
| 5121 |
+
"loss": 2.673054504394531,
|
| 5122 |
+
"step": 65600
|
| 5123 |
+
},
|
| 5124 |
+
{
|
| 5125 |
+
"epoch": 0.27,
|
| 5126 |
+
"grad_norm": 0.14490514993667603,
|
| 5127 |
+
"learning_rate": 0.0003504091056815537,
|
| 5128 |
+
"loss": 2.6274179077148436,
|
| 5129 |
+
"step": 65700
|
| 5130 |
+
},
|
| 5131 |
+
{
|
| 5132 |
+
"epoch": 0.27090909090909093,
|
| 5133 |
+
"grad_norm": 0.15338118374347687,
|
| 5134 |
+
"learning_rate": 0.00034904526978984517,
|
| 5135 |
+
"loss": 2.6343759155273436,
|
| 5136 |
+
"step": 65800
|
| 5137 |
+
},
|
| 5138 |
+
{
|
| 5139 |
+
"epoch": 0.2718181818181818,
|
| 5140 |
+
"grad_norm": 0.1604444533586502,
|
| 5141 |
+
"learning_rate": 0.00034768266855436967,
|
| 5142 |
+
"loss": 2.643642578125,
|
| 5143 |
+
"step": 65900
|
| 5144 |
+
},
|
| 5145 |
+
{
|
| 5146 |
+
"epoch": 0.2727272727272727,
|
| 5147 |
+
"grad_norm": 0.16554522514343262,
|
| 5148 |
+
"learning_rate": 0.0003463213131198198,
|
| 5149 |
+
"loss": 2.645709228515625,
|
| 5150 |
+
"step": 66000
|
| 5151 |
+
},
|
| 5152 |
+
{
|
| 5153 |
+
"epoch": 0.2727272727272727,
|
| 5154 |
+
"eval_loss": 3.0441606044769287,
|
| 5155 |
+
"eval_runtime": 7.4053,
|
| 5156 |
+
"eval_samples_per_second": 77.782,
|
| 5157 |
+
"eval_steps_per_second": 19.445,
|
| 5158 |
+
"step": 66000
|
| 5159 |
+
},
|
| 5160 |
+
{
|
| 5161 |
+
"epoch": 0.2736363636363636,
|
| 5162 |
+
"grad_norm": 0.16071894764900208,
|
| 5163 |
+
"learning_rate": 0.00034496121462069916,
|
| 5164 |
+
"loss": 2.6328436279296876,
|
| 5165 |
+
"step": 66100
|
| 5166 |
+
},
|
| 5167 |
+
{
|
| 5168 |
+
"epoch": 0.27454545454545454,
|
| 5169 |
+
"grad_norm": 0.1610708087682724,
|
| 5170 |
+
"learning_rate": 0.000343602384181231,
|
| 5171 |
+
"loss": 2.650054626464844,
|
| 5172 |
+
"step": 66200
|
| 5173 |
+
},
|
| 5174 |
+
{
|
| 5175 |
+
"epoch": 0.27545454545454545,
|
| 5176 |
+
"grad_norm": 0.1581074744462967,
|
| 5177 |
+
"learning_rate": 0.00034224483291526666,
|
| 5178 |
+
"loss": 2.6330722045898436,
|
| 5179 |
+
"step": 66300
|
| 5180 |
+
},
|
| 5181 |
+
{
|
| 5182 |
+
"epoch": 0.27636363636363637,
|
| 5183 |
+
"grad_norm": 0.16902528703212738,
|
| 5184 |
+
"learning_rate": 0.0003408885719261956,
|
| 5185 |
+
"loss": 2.60602783203125,
|
| 5186 |
+
"step": 66400
|
| 5187 |
+
},
|
| 5188 |
+
{
|
| 5189 |
+
"epoch": 0.2772727272727273,
|
| 5190 |
+
"grad_norm": 0.1647139936685562,
|
| 5191 |
+
"learning_rate": 0.0003395336123068537,
|
| 5192 |
+
"loss": 2.6406063842773437,
|
| 5193 |
+
"step": 66500
|
| 5194 |
+
},
|
| 5195 |
+
{
|
| 5196 |
+
"epoch": 0.2781818181818182,
|
| 5197 |
+
"grad_norm": 0.16128414869308472,
|
| 5198 |
+
"learning_rate": 0.0003381799651394335,
|
| 5199 |
+
"loss": 2.6316217041015624,
|
| 5200 |
+
"step": 66600
|
| 5201 |
+
},
|
| 5202 |
+
{
|
| 5203 |
+
"epoch": 0.2790909090909091,
|
| 5204 |
+
"grad_norm": 0.1957395374774933,
|
| 5205 |
+
"learning_rate": 0.0003368276414953922,
|
| 5206 |
+
"loss": 2.6092684936523436,
|
| 5207 |
+
"step": 66700
|
| 5208 |
+
},
|
| 5209 |
+
{
|
| 5210 |
+
"epoch": 0.28,
|
| 5211 |
+
"grad_norm": 0.14507023990154266,
|
| 5212 |
+
"learning_rate": 0.0003354766524353632,
|
| 5213 |
+
"loss": 2.602089538574219,
|
| 5214 |
+
"step": 66800
|
| 5215 |
+
},
|
| 5216 |
+
{
|
| 5217 |
+
"epoch": 0.2809090909090909,
|
| 5218 |
+
"grad_norm": 0.17211727797985077,
|
| 5219 |
+
"learning_rate": 0.0003341270090090631,
|
| 5220 |
+
"loss": 2.65368896484375,
|
| 5221 |
+
"step": 66900
|
| 5222 |
+
},
|
| 5223 |
+
{
|
| 5224 |
+
"epoch": 0.2818181818181818,
|
| 5225 |
+
"grad_norm": 0.15183623135089874,
|
| 5226 |
+
"learning_rate": 0.0003327787222552032,
|
| 5227 |
+
"loss": 2.647850341796875,
|
| 5228 |
+
"step": 67000
|
| 5229 |
+
},
|
| 5230 |
+
{
|
| 5231 |
+
"epoch": 0.2818181818181818,
|
| 5232 |
+
"eval_loss": 3.037811279296875,
|
| 5233 |
+
"eval_runtime": 7.4649,
|
| 5234 |
+
"eval_samples_per_second": 77.161,
|
| 5235 |
+
"eval_steps_per_second": 19.29,
|
| 5236 |
+
"step": 67000
|
| 5237 |
+
},
|
| 5238 |
+
{
|
| 5239 |
+
"epoch": 0.2827272727272727,
|
| 5240 |
+
"grad_norm": 0.147422194480896,
|
| 5241 |
+
"learning_rate": 0.0003314318032013985,
|
| 5242 |
+
"loss": 2.63864501953125,
|
| 5243 |
+
"step": 67100
|
| 5244 |
+
},
|
| 5245 |
+
{
|
| 5246 |
+
"epoch": 0.28363636363636363,
|
| 5247 |
+
"grad_norm": 0.15864703059196472,
|
| 5248 |
+
"learning_rate": 0.00033008626286407756,
|
| 5249 |
+
"loss": 2.6240463256835938,
|
| 5250 |
+
"step": 67200
|
| 5251 |
+
},
|
| 5252 |
+
{
|
| 5253 |
+
"epoch": 0.28454545454545455,
|
| 5254 |
+
"grad_norm": 0.15877065062522888,
|
| 5255 |
+
"learning_rate": 0.0003287421122483924,
|
| 5256 |
+
"loss": 2.640238952636719,
|
| 5257 |
+
"step": 67300
|
| 5258 |
+
},
|
| 5259 |
+
{
|
| 5260 |
+
"epoch": 0.28545454545454546,
|
| 5261 |
+
"grad_norm": 0.15702606737613678,
|
| 5262 |
+
"learning_rate": 0.00032739936234812863,
|
| 5263 |
+
"loss": 2.6432769775390623,
|
| 5264 |
+
"step": 67400
|
| 5265 |
+
},
|
| 5266 |
+
{
|
| 5267 |
+
"epoch": 0.2863636363636364,
|
| 5268 |
+
"grad_norm": 0.17382535338401794,
|
| 5269 |
+
"learning_rate": 0.0003260580241456155,
|
| 5270 |
+
"loss": 2.6252288818359375,
|
| 5271 |
+
"step": 67500
|
| 5272 |
+
},
|
| 5273 |
+
{
|
| 5274 |
+
"epoch": 0.2872727272727273,
|
| 5275 |
+
"grad_norm": 0.15588997304439545,
|
| 5276 |
+
"learning_rate": 0.00032471810861163573,
|
| 5277 |
+
"loss": 2.6104010009765624,
|
| 5278 |
+
"step": 67600
|
| 5279 |
+
},
|
| 5280 |
+
{
|
| 5281 |
+
"epoch": 0.2881818181818182,
|
| 5282 |
+
"grad_norm": 0.17598041892051697,
|
| 5283 |
+
"learning_rate": 0.0003233796267053365,
|
| 5284 |
+
"loss": 2.6319580078125,
|
| 5285 |
+
"step": 67700
|
| 5286 |
+
},
|
| 5287 |
+
{
|
| 5288 |
+
"epoch": 0.28909090909090907,
|
| 5289 |
+
"grad_norm": 0.15314966440200806,
|
| 5290 |
+
"learning_rate": 0.0003220425893741388,
|
| 5291 |
+
"loss": 2.6283184814453127,
|
| 5292 |
+
"step": 67800
|
| 5293 |
+
},
|
| 5294 |
+
{
|
| 5295 |
+
"epoch": 0.29,
|
| 5296 |
+
"grad_norm": 0.17279887199401855,
|
| 5297 |
+
"learning_rate": 0.000320707007553649,
|
| 5298 |
+
"loss": 2.6345831298828126,
|
| 5299 |
+
"step": 67900
|
| 5300 |
+
},
|
| 5301 |
+
{
|
| 5302 |
+
"epoch": 0.2909090909090909,
|
| 5303 |
+
"grad_norm": 0.20019470155239105,
|
| 5304 |
+
"learning_rate": 0.0003193728921675685,
|
| 5305 |
+
"loss": 2.630293273925781,
|
| 5306 |
+
"step": 68000
|
| 5307 |
+
},
|
| 5308 |
+
{
|
| 5309 |
+
"epoch": 0.2909090909090909,
|
| 5310 |
+
"eval_loss": 3.0448532104492188,
|
| 5311 |
+
"eval_runtime": 7.4367,
|
| 5312 |
+
"eval_samples_per_second": 77.454,
|
| 5313 |
+
"eval_steps_per_second": 19.363,
|
| 5314 |
+
"step": 68000
|
| 5315 |
}
|
| 5316 |
],
|
| 5317 |
"logging_steps": 100,
|
|
|
|
| 5331 |
"attributes": {}
|
| 5332 |
}
|
| 5333 |
},
|
| 5334 |
+
"total_flos": 1.694191507734528e+18,
|
| 5335 |
"train_batch_size": 22,
|
| 5336 |
"trial_name": null,
|
| 5337 |
"trial_params": null
|