Commit
•
b7398da
1
Parent(s):
0f28af8
Training in progress, step 850000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +312 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 885330713
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377aef4dd059b74792c5352ef81f8e44e00ebae2aba8904e27b6d7bddc64b4be
|
| 3 |
size 885330713
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442678571
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:157afe62666c333a6a822593f8ac020489c93154c07c70eed8f687050fb132b0
|
| 3 |
size 442678571
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17563
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eed8b2b295b4b043aa8b2feddb689917b282e526c45b6eb23bd29ebdfbe6d494
|
| 3 |
size 17563
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:065f3ff4df60950ed9b6903fc98546b04d3292228f5f7ea2579fd161acf366b2
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cd1b1b8a91f71cb25cb8a1516a3c8cda9e53c3b6dd58a61caf55df95b8a1c51
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -4950,11 +4950,320 @@
|
|
| 4950 |
"eval_samples_per_second": 415.274,
|
| 4951 |
"eval_steps_per_second": 0.831,
|
| 4952 |
"step": 800000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4953 |
}
|
| 4954 |
],
|
| 4955 |
"max_steps": 1000000,
|
| 4956 |
"num_train_epochs": 9223372036854775807,
|
| 4957 |
-
"total_flos": 5.
|
| 4958 |
"trial_name": null,
|
| 4959 |
"trial_params": null
|
| 4960 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.239467,
|
| 5 |
+
"global_step": 850000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 4950 |
"eval_samples_per_second": 415.274,
|
| 4951 |
"eval_steps_per_second": 0.831,
|
| 4952 |
"step": 800000
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 1.19,
|
| 4956 |
+
"learning_rate": 1.0473407182373813e-05,
|
| 4957 |
+
"loss": 0.9342,
|
| 4958 |
+
"step": 801000
|
| 4959 |
+
},
|
| 4960 |
+
{
|
| 4961 |
+
"epoch": 1.19,
|
| 4962 |
+
"learning_rate": 1.0372361544374464e-05,
|
| 4963 |
+
"loss": 0.8919,
|
| 4964 |
+
"step": 802000
|
| 4965 |
+
},
|
| 4966 |
+
{
|
| 4967 |
+
"epoch": 1.19,
|
| 4968 |
+
"learning_rate": 1.0271849663326171e-05,
|
| 4969 |
+
"loss": 0.8567,
|
| 4970 |
+
"step": 803000
|
| 4971 |
+
},
|
| 4972 |
+
{
|
| 4973 |
+
"epoch": 1.19,
|
| 4974 |
+
"learning_rate": 1.0171671413607247e-05,
|
| 4975 |
+
"loss": 0.9096,
|
| 4976 |
+
"step": 804000
|
| 4977 |
+
},
|
| 4978 |
+
{
|
| 4979 |
+
"epoch": 1.19,
|
| 4980 |
+
"learning_rate": 1.0072028244878407e-05,
|
| 4981 |
+
"loss": 1.0644,
|
| 4982 |
+
"step": 805000
|
| 4983 |
+
},
|
| 4984 |
+
{
|
| 4985 |
+
"epoch": 1.2,
|
| 4986 |
+
"learning_rate": 9.97272176118008e-06,
|
| 4987 |
+
"loss": 1.0327,
|
| 4988 |
+
"step": 806000
|
| 4989 |
+
},
|
| 4990 |
+
{
|
| 4991 |
+
"epoch": 1.2,
|
| 4992 |
+
"learning_rate": 9.873853009383633e-06,
|
| 4993 |
+
"loss": 1.076,
|
| 4994 |
+
"step": 807000
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 1.2,
|
| 4998 |
+
"learning_rate": 9.775423070701888e-06,
|
| 4999 |
+
"loss": 1.0958,
|
| 5000 |
+
"step": 808000
|
| 5001 |
+
},
|
| 5002 |
+
{
|
| 5003 |
+
"epoch": 1.2,
|
| 5004 |
+
"learning_rate": 9.67753079151617e-06,
|
| 5005 |
+
"loss": 1.0053,
|
| 5006 |
+
"step": 809000
|
| 5007 |
+
},
|
| 5008 |
+
{
|
| 5009 |
+
"epoch": 1.2,
|
| 5010 |
+
"learning_rate": 9.57998126200062e-06,
|
| 5011 |
+
"loss": 0.8648,
|
| 5012 |
+
"step": 810000
|
| 5013 |
+
},
|
| 5014 |
+
{
|
| 5015 |
+
"epoch": 1.2,
|
| 5016 |
+
"learning_rate": 9.482970645690526e-06,
|
| 5017 |
+
"loss": 0.8919,
|
| 5018 |
+
"step": 811000
|
| 5019 |
+
},
|
| 5020 |
+
{
|
| 5021 |
+
"epoch": 1.2,
|
| 5022 |
+
"learning_rate": 9.38630578820755e-06,
|
| 5023 |
+
"loss": 0.8439,
|
| 5024 |
+
"step": 812000
|
| 5025 |
+
},
|
| 5026 |
+
{
|
| 5027 |
+
"epoch": 1.2,
|
| 5028 |
+
"learning_rate": 9.290181074089233e-06,
|
| 5029 |
+
"loss": 0.7462,
|
| 5030 |
+
"step": 813000
|
| 5031 |
+
},
|
| 5032 |
+
{
|
| 5033 |
+
"epoch": 1.2,
|
| 5034 |
+
"learning_rate": 9.194405112845483e-06,
|
| 5035 |
+
"loss": 0.8975,
|
| 5036 |
+
"step": 814000
|
| 5037 |
+
},
|
| 5038 |
+
{
|
| 5039 |
+
"epoch": 1.2,
|
| 5040 |
+
"learning_rate": 9.099170501521598e-06,
|
| 5041 |
+
"loss": 0.9167,
|
| 5042 |
+
"step": 815000
|
| 5043 |
+
},
|
| 5044 |
+
{
|
| 5045 |
+
"epoch": 1.21,
|
| 5046 |
+
"learning_rate": 9.00428762187942e-06,
|
| 5047 |
+
"loss": 0.8518,
|
| 5048 |
+
"step": 816000
|
| 5049 |
+
},
|
| 5050 |
+
{
|
| 5051 |
+
"epoch": 1.21,
|
| 5052 |
+
"learning_rate": 8.909947275055568e-06,
|
| 5053 |
+
"loss": 0.8843,
|
| 5054 |
+
"step": 817000
|
| 5055 |
+
},
|
| 5056 |
+
{
|
| 5057 |
+
"epoch": 1.21,
|
| 5058 |
+
"learning_rate": 8.815961623350038e-06,
|
| 5059 |
+
"loss": 0.926,
|
| 5060 |
+
"step": 818000
|
| 5061 |
+
},
|
| 5062 |
+
{
|
| 5063 |
+
"epoch": 1.21,
|
| 5064 |
+
"learning_rate": 8.722519663652901e-06,
|
| 5065 |
+
"loss": 0.9408,
|
| 5066 |
+
"step": 819000
|
| 5067 |
+
},
|
| 5068 |
+
{
|
| 5069 |
+
"epoch": 1.21,
|
| 5070 |
+
"learning_rate": 8.629435347010716e-06,
|
| 5071 |
+
"loss": 0.7628,
|
| 5072 |
+
"step": 820000
|
| 5073 |
+
},
|
| 5074 |
+
{
|
| 5075 |
+
"epoch": 1.21,
|
| 5076 |
+
"learning_rate": 8.536803452235437e-06,
|
| 5077 |
+
"loss": 0.7669,
|
| 5078 |
+
"step": 821000
|
| 5079 |
+
},
|
| 5080 |
+
{
|
| 5081 |
+
"epoch": 1.21,
|
| 5082 |
+
"learning_rate": 8.444624992334588e-06,
|
| 5083 |
+
"loss": 0.7749,
|
| 5084 |
+
"step": 822000
|
| 5085 |
+
},
|
| 5086 |
+
{
|
| 5087 |
+
"epoch": 1.21,
|
| 5088 |
+
"learning_rate": 8.352992472045557e-06,
|
| 5089 |
+
"loss": 0.7575,
|
| 5090 |
+
"step": 823000
|
| 5091 |
+
},
|
| 5092 |
+
{
|
| 5093 |
+
"epoch": 1.21,
|
| 5094 |
+
"learning_rate": 8.26172344512513e-06,
|
| 5095 |
+
"loss": 0.899,
|
| 5096 |
+
"step": 824000
|
| 5097 |
+
},
|
| 5098 |
+
{
|
| 5099 |
+
"epoch": 1.21,
|
| 5100 |
+
"learning_rate": 8.171001445569593e-06,
|
| 5101 |
+
"loss": 0.9519,
|
| 5102 |
+
"step": 825000
|
| 5103 |
+
},
|
| 5104 |
+
{
|
| 5105 |
+
"epoch": 1.22,
|
| 5106 |
+
"learning_rate": 8.080645840041112e-06,
|
| 5107 |
+
"loss": 0.9472,
|
| 5108 |
+
"step": 826000
|
| 5109 |
+
},
|
| 5110 |
+
{
|
| 5111 |
+
"epoch": 1.22,
|
| 5112 |
+
"learning_rate": 7.990838325725758e-06,
|
| 5113 |
+
"loss": 0.9576,
|
| 5114 |
+
"step": 827000
|
| 5115 |
+
},
|
| 5116 |
+
{
|
| 5117 |
+
"epoch": 1.22,
|
| 5118 |
+
"learning_rate": 7.901400090084665e-06,
|
| 5119 |
+
"loss": 0.9493,
|
| 5120 |
+
"step": 828000
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 1.22,
|
| 5124 |
+
"learning_rate": 7.81251098555364e-06,
|
| 5125 |
+
"loss": 0.8743,
|
| 5126 |
+
"step": 829000
|
| 5127 |
+
},
|
| 5128 |
+
{
|
| 5129 |
+
"epoch": 1.22,
|
| 5130 |
+
"learning_rate": 7.723994028206778e-06,
|
| 5131 |
+
"loss": 0.8593,
|
| 5132 |
+
"step": 830000
|
| 5133 |
+
},
|
| 5134 |
+
{
|
| 5135 |
+
"epoch": 1.22,
|
| 5136 |
+
"learning_rate": 7.636027217870157e-06,
|
| 5137 |
+
"loss": 0.8767,
|
| 5138 |
+
"step": 831000
|
| 5139 |
+
},
|
| 5140 |
+
{
|
| 5141 |
+
"epoch": 1.22,
|
| 5142 |
+
"learning_rate": 7.54843540696496e-06,
|
| 5143 |
+
"loss": 0.853,
|
| 5144 |
+
"step": 832000
|
| 5145 |
+
},
|
| 5146 |
+
{
|
| 5147 |
+
"epoch": 1.22,
|
| 5148 |
+
"learning_rate": 7.461394734929022e-06,
|
| 5149 |
+
"loss": 0.8742,
|
| 5150 |
+
"step": 833000
|
| 5151 |
+
},
|
| 5152 |
+
{
|
| 5153 |
+
"epoch": 1.22,
|
| 5154 |
+
"learning_rate": 7.374731898184495e-06,
|
| 5155 |
+
"loss": 1.0273,
|
| 5156 |
+
"step": 834000
|
| 5157 |
+
},
|
| 5158 |
+
{
|
| 5159 |
+
"epoch": 1.22,
|
| 5160 |
+
"learning_rate": 7.2886211680837424e-06,
|
| 5161 |
+
"loss": 1.0271,
|
| 5162 |
+
"step": 835000
|
| 5163 |
+
},
|
| 5164 |
+
{
|
| 5165 |
+
"epoch": 1.23,
|
| 5166 |
+
"learning_rate": 7.202891092623126e-06,
|
| 5167 |
+
"loss": 1.049,
|
| 5168 |
+
"step": 836000
|
| 5169 |
+
},
|
| 5170 |
+
{
|
| 5171 |
+
"epoch": 1.23,
|
| 5172 |
+
"learning_rate": 7.11771406745404e-06,
|
| 5173 |
+
"loss": 1.0773,
|
| 5174 |
+
"step": 837000
|
| 5175 |
+
},
|
| 5176 |
+
{
|
| 5177 |
+
"epoch": 1.23,
|
| 5178 |
+
"learning_rate": 7.032920499639423e-06,
|
| 5179 |
+
"loss": 1.0882,
|
| 5180 |
+
"step": 838000
|
| 5181 |
+
},
|
| 5182 |
+
{
|
| 5183 |
+
"epoch": 1.23,
|
| 5184 |
+
"learning_rate": 6.94868090159605e-06,
|
| 5185 |
+
"loss": 0.9609,
|
| 5186 |
+
"step": 839000
|
| 5187 |
+
},
|
| 5188 |
+
{
|
| 5189 |
+
"epoch": 1.23,
|
| 5190 |
+
"learning_rate": 6.864827546864583e-06,
|
| 5191 |
+
"loss": 0.9468,
|
| 5192 |
+
"step": 840000
|
| 5193 |
+
},
|
| 5194 |
+
{
|
| 5195 |
+
"epoch": 1.23,
|
| 5196 |
+
"learning_rate": 6.781529057175845e-06,
|
| 5197 |
+
"loss": 0.8922,
|
| 5198 |
+
"step": 841000
|
| 5199 |
+
},
|
| 5200 |
+
{
|
| 5201 |
+
"epoch": 1.23,
|
| 5202 |
+
"learning_rate": 6.698619579877818e-06,
|
| 5203 |
+
"loss": 0.7689,
|
| 5204 |
+
"step": 842000
|
| 5205 |
+
},
|
| 5206 |
+
{
|
| 5207 |
+
"epoch": 1.23,
|
| 5208 |
+
"learning_rate": 6.616183639538559e-06,
|
| 5209 |
+
"loss": 0.852,
|
| 5210 |
+
"step": 843000
|
| 5211 |
+
},
|
| 5212 |
+
{
|
| 5213 |
+
"epoch": 1.23,
|
| 5214 |
+
"learning_rate": 6.534385586581854e-06,
|
| 5215 |
+
"loss": 1.0235,
|
| 5216 |
+
"step": 844000
|
| 5217 |
+
},
|
| 5218 |
+
{
|
| 5219 |
+
"epoch": 1.23,
|
| 5220 |
+
"learning_rate": 6.452898467929852e-06,
|
| 5221 |
+
"loss": 0.9675,
|
| 5222 |
+
"step": 845000
|
| 5223 |
+
},
|
| 5224 |
+
{
|
| 5225 |
+
"epoch": 1.24,
|
| 5226 |
+
"learning_rate": 6.371887573403335e-06,
|
| 5227 |
+
"loss": 0.9587,
|
| 5228 |
+
"step": 846000
|
| 5229 |
+
},
|
| 5230 |
+
{
|
| 5231 |
+
"epoch": 1.24,
|
| 5232 |
+
"learning_rate": 6.29135378892447e-06,
|
| 5233 |
+
"loss": 1.0189,
|
| 5234 |
+
"step": 847000
|
| 5235 |
+
},
|
| 5236 |
+
{
|
| 5237 |
+
"epoch": 1.24,
|
| 5238 |
+
"learning_rate": 6.211377811943364e-06,
|
| 5239 |
+
"loss": 0.9343,
|
| 5240 |
+
"step": 848000
|
| 5241 |
+
},
|
| 5242 |
+
{
|
| 5243 |
+
"epoch": 1.24,
|
| 5244 |
+
"learning_rate": 6.131879743067948e-06,
|
| 5245 |
+
"loss": 0.7473,
|
| 5246 |
+
"step": 849000
|
| 5247 |
+
},
|
| 5248 |
+
{
|
| 5249 |
+
"epoch": 1.24,
|
| 5250 |
+
"learning_rate": 6.0528604499385185e-06,
|
| 5251 |
+
"loss": 0.7263,
|
| 5252 |
+
"step": 850000
|
| 5253 |
+
},
|
| 5254 |
+
{
|
| 5255 |
+
"epoch": 1.24,
|
| 5256 |
+
"eval_accuracy": 0.8377542903972233,
|
| 5257 |
+
"eval_loss": 0.7093546986579895,
|
| 5258 |
+
"eval_runtime": 11.2849,
|
| 5259 |
+
"eval_samples_per_second": 443.071,
|
| 5260 |
+
"eval_steps_per_second": 0.886,
|
| 5261 |
+
"step": 850000
|
| 5262 |
}
|
| 5263 |
],
|
| 5264 |
"max_steps": 1000000,
|
| 5265 |
"num_train_epochs": 9223372036854775807,
|
| 5266 |
+
"total_flos": 5.727433420305334e+19,
|
| 5267 |
"trial_name": null,
|
| 5268 |
"trial_params": null
|
| 5269 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e25faf06c9975aea2aa997e353bc16bb59f3eabd76c81f0c49c46d732c973aeb
|
| 3 |
size 3503
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442678571
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:157afe62666c333a6a822593f8ac020489c93154c07c70eed8f687050fb132b0
|
| 3 |
size 442678571
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e25faf06c9975aea2aa997e353bc16bb59f3eabd76c81f0c49c46d732c973aeb
|
| 3 |
size 3503
|