Training in progress, step 410000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- pytorch_model.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 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23757c0288979d27bb8e7d987ca91414953ed2fb98096163be33a545f5af5ab4
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
|
3 |
size 102501541
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
|
3 |
size 14503
|
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 sha256:498c95fdcab578849c69bf4a10f0532f5bf3ba8048fa37c1b416b3afd0ea5f33
|
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": 10.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -8006,11 +8006,211 @@
|
|
8006 |
"eval_samples_per_second": 742.696,
|
8007 |
"eval_steps_per_second": 11.883,
|
8008 |
"step": 400000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8009 |
}
|
8010 |
],
|
8011 |
"max_steps": 500000,
|
8012 |
"num_train_epochs": 13,
|
8013 |
-
"total_flos": 1.
|
8014 |
"trial_name": null,
|
8015 |
"trial_params": null
|
8016 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.44905448799633,
|
5 |
+
"global_step": 410000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
8006 |
"eval_samples_per_second": 742.696,
|
8007 |
"eval_steps_per_second": 11.883,
|
8008 |
"step": 400000
|
8009 |
+
},
|
8010 |
+
{
|
8011 |
+
"epoch": 10.21,
|
8012 |
+
"learning_rate": 4.0280733510303475e-05,
|
8013 |
+
"loss": 0.2717,
|
8014 |
+
"step": 400500
|
8015 |
+
},
|
8016 |
+
{
|
8017 |
+
"epoch": 10.22,
|
8018 |
+
"learning_rate": 3.9988095434602716e-05,
|
8019 |
+
"loss": 0.2715,
|
8020 |
+
"step": 401000
|
8021 |
+
},
|
8022 |
+
{
|
8023 |
+
"epoch": 10.22,
|
8024 |
+
"eval_loss": 0.8082920908927917,
|
8025 |
+
"eval_runtime": 1.4032,
|
8026 |
+
"eval_samples_per_second": 712.676,
|
8027 |
+
"eval_steps_per_second": 11.403,
|
8028 |
+
"step": 401000
|
8029 |
+
},
|
8030 |
+
{
|
8031 |
+
"epoch": 10.23,
|
8032 |
+
"learning_rate": 3.9696715110663726e-05,
|
8033 |
+
"loss": 0.2715,
|
8034 |
+
"step": 401500
|
8035 |
+
},
|
8036 |
+
{
|
8037 |
+
"epoch": 10.25,
|
8038 |
+
"learning_rate": 3.9406595724975116e-05,
|
8039 |
+
"loss": 0.2717,
|
8040 |
+
"step": 402000
|
8041 |
+
},
|
8042 |
+
{
|
8043 |
+
"epoch": 10.25,
|
8044 |
+
"eval_loss": 0.8099567890167236,
|
8045 |
+
"eval_runtime": 1.3773,
|
8046 |
+
"eval_samples_per_second": 726.038,
|
8047 |
+
"eval_steps_per_second": 11.617,
|
8048 |
+
"step": 402000
|
8049 |
+
},
|
8050 |
+
{
|
8051 |
+
"epoch": 10.26,
|
8052 |
+
"learning_rate": 3.9117740450235914e-05,
|
8053 |
+
"loss": 0.2714,
|
8054 |
+
"step": 402500
|
8055 |
+
},
|
8056 |
+
{
|
8057 |
+
"epoch": 10.27,
|
8058 |
+
"learning_rate": 3.8830152445321163e-05,
|
8059 |
+
"loss": 0.2715,
|
8060 |
+
"step": 403000
|
8061 |
+
},
|
8062 |
+
{
|
8063 |
+
"epoch": 10.27,
|
8064 |
+
"eval_loss": 0.8108043670654297,
|
8065 |
+
"eval_runtime": 1.3727,
|
8066 |
+
"eval_samples_per_second": 728.507,
|
8067 |
+
"eval_steps_per_second": 11.656,
|
8068 |
+
"step": 403000
|
8069 |
+
},
|
8070 |
+
{
|
8071 |
+
"epoch": 10.28,
|
8072 |
+
"learning_rate": 3.854383485524724e-05,
|
8073 |
+
"loss": 0.2714,
|
8074 |
+
"step": 403500
|
8075 |
+
},
|
8076 |
+
{
|
8077 |
+
"epoch": 10.3,
|
8078 |
+
"learning_rate": 3.8258790811137425e-05,
|
8079 |
+
"loss": 0.2715,
|
8080 |
+
"step": 404000
|
8081 |
+
},
|
8082 |
+
{
|
8083 |
+
"epoch": 10.3,
|
8084 |
+
"eval_loss": 0.8089959621429443,
|
8085 |
+
"eval_runtime": 1.3482,
|
8086 |
+
"eval_samples_per_second": 741.756,
|
8087 |
+
"eval_steps_per_second": 11.868,
|
8088 |
+
"step": 404000
|
8089 |
+
},
|
8090 |
+
{
|
8091 |
+
"epoch": 10.31,
|
8092 |
+
"learning_rate": 3.7975023430187676e-05,
|
8093 |
+
"loss": 0.2715,
|
8094 |
+
"step": 404500
|
8095 |
+
},
|
8096 |
+
{
|
8097 |
+
"epoch": 10.32,
|
8098 |
+
"learning_rate": 3.7692535815632624e-05,
|
8099 |
+
"loss": 0.2716,
|
8100 |
+
"step": 405000
|
8101 |
+
},
|
8102 |
+
{
|
8103 |
+
"epoch": 10.32,
|
8104 |
+
"eval_loss": 0.8159785270690918,
|
8105 |
+
"eval_runtime": 1.3646,
|
8106 |
+
"eval_samples_per_second": 732.809,
|
8107 |
+
"eval_steps_per_second": 11.725,
|
8108 |
+
"step": 405000
|
8109 |
+
},
|
8110 |
+
{
|
8111 |
+
"epoch": 10.33,
|
8112 |
+
"learning_rate": 3.741133105671159e-05,
|
8113 |
+
"loss": 0.2713,
|
8114 |
+
"step": 405500
|
8115 |
+
},
|
8116 |
+
{
|
8117 |
+
"epoch": 10.35,
|
8118 |
+
"learning_rate": 3.713141222863474e-05,
|
8119 |
+
"loss": 0.2712,
|
8120 |
+
"step": 406000
|
8121 |
+
},
|
8122 |
+
{
|
8123 |
+
"epoch": 10.35,
|
8124 |
+
"eval_loss": 0.8142402172088623,
|
8125 |
+
"eval_runtime": 1.3812,
|
8126 |
+
"eval_samples_per_second": 724.033,
|
8127 |
+
"eval_steps_per_second": 11.585,
|
8128 |
+
"step": 406000
|
8129 |
+
},
|
8130 |
+
{
|
8131 |
+
"epoch": 10.36,
|
8132 |
+
"learning_rate": 3.6852782392549584e-05,
|
8133 |
+
"loss": 0.2713,
|
8134 |
+
"step": 406500
|
8135 |
+
},
|
8136 |
+
{
|
8137 |
+
"epoch": 10.37,
|
8138 |
+
"learning_rate": 3.657544459550729e-05,
|
8139 |
+
"loss": 0.2712,
|
8140 |
+
"step": 407000
|
8141 |
+
},
|
8142 |
+
{
|
8143 |
+
"epoch": 10.37,
|
8144 |
+
"eval_loss": 0.8070803284645081,
|
8145 |
+
"eval_runtime": 1.5878,
|
8146 |
+
"eval_samples_per_second": 629.794,
|
8147 |
+
"eval_steps_per_second": 10.077,
|
8148 |
+
"step": 407000
|
8149 |
+
},
|
8150 |
+
{
|
8151 |
+
"epoch": 10.39,
|
8152 |
+
"learning_rate": 3.6299401870429606e-05,
|
8153 |
+
"loss": 0.2712,
|
8154 |
+
"step": 407500
|
8155 |
+
},
|
8156 |
+
{
|
8157 |
+
"epoch": 10.4,
|
8158 |
+
"learning_rate": 3.6024657236075546e-05,
|
8159 |
+
"loss": 0.2712,
|
8160 |
+
"step": 408000
|
8161 |
+
},
|
8162 |
+
{
|
8163 |
+
"epoch": 10.4,
|
8164 |
+
"eval_loss": 0.8115477561950684,
|
8165 |
+
"eval_runtime": 1.3152,
|
8166 |
+
"eval_samples_per_second": 760.367,
|
8167 |
+
"eval_steps_per_second": 12.166,
|
8168 |
+
"step": 408000
|
8169 |
+
},
|
8170 |
+
{
|
8171 |
+
"epoch": 10.41,
|
8172 |
+
"learning_rate": 3.575121369700841e-05,
|
8173 |
+
"loss": 0.2714,
|
8174 |
+
"step": 408500
|
8175 |
+
},
|
8176 |
+
{
|
8177 |
+
"epoch": 10.42,
|
8178 |
+
"learning_rate": 3.5479074243562995e-05,
|
8179 |
+
"loss": 0.2709,
|
8180 |
+
"step": 409000
|
8181 |
+
},
|
8182 |
+
{
|
8183 |
+
"epoch": 10.42,
|
8184 |
+
"eval_loss": 0.80928635597229,
|
8185 |
+
"eval_runtime": 1.3461,
|
8186 |
+
"eval_samples_per_second": 742.862,
|
8187 |
+
"eval_steps_per_second": 11.886,
|
8188 |
+
"step": 409000
|
8189 |
+
},
|
8190 |
+
{
|
8191 |
+
"epoch": 10.44,
|
8192 |
+
"learning_rate": 3.5208241851812644e-05,
|
8193 |
+
"loss": 0.2711,
|
8194 |
+
"step": 409500
|
8195 |
+
},
|
8196 |
+
{
|
8197 |
+
"epoch": 10.45,
|
8198 |
+
"learning_rate": 3.493871948353709e-05,
|
8199 |
+
"loss": 0.271,
|
8200 |
+
"step": 410000
|
8201 |
+
},
|
8202 |
+
{
|
8203 |
+
"epoch": 10.45,
|
8204 |
+
"eval_loss": 0.8108725547790527,
|
8205 |
+
"eval_runtime": 1.3475,
|
8206 |
+
"eval_samples_per_second": 742.097,
|
8207 |
+
"eval_steps_per_second": 11.874,
|
8208 |
+
"step": 410000
|
8209 |
}
|
8210 |
],
|
8211 |
"max_steps": 500000,
|
8212 |
"num_train_epochs": 13,
|
8213 |
+
"total_flos": 1.309883790062405e+22,
|
8214 |
"trial_name": null,
|
8215 |
"trial_params": null
|
8216 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
|
3 |
size 102501541
|