End of training
Browse files- mm_projector.bin +1 -1
- trainer_state.json +63 -3
mm_projector.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83920509
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3564ad963e0a52caa824d7ccadfeabf219798c668fb6f7aa45078c1419e6e76e
|
| 3 |
size 83920509
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -79,6 +79,66 @@
|
|
| 79 |
"learning_rate": 9.157348061512727e-05,
|
| 80 |
"loss": 2.0462,
|
| 81 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 1.0,
|
|
@@ -86,7 +146,7 @@
|
|
| 86 |
"num_input_tokens_seen": 0,
|
| 87 |
"num_train_epochs": 1,
|
| 88 |
"save_steps": 10,
|
| 89 |
-
"total_flos":
|
| 90 |
"train_batch_size": 1,
|
| 91 |
"trial_name": null,
|
| 92 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.00011124539216529043,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 22,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 79 |
"learning_rate": 9.157348061512727e-05,
|
| 80 |
"loss": 2.0462,
|
| 81 |
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0,
|
| 85 |
+
"learning_rate": 8.966766701456177e-05,
|
| 86 |
+
"loss": 2.7075,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0,
|
| 91 |
+
"learning_rate": 8.759199037394887e-05,
|
| 92 |
+
"loss": 1.5202,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0,
|
| 97 |
+
"learning_rate": 8.535533905932738e-05,
|
| 98 |
+
"loss": 2.1509,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.0,
|
| 103 |
+
"learning_rate": 8.296729075500344e-05,
|
| 104 |
+
"loss": 2.4468,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.0,
|
| 109 |
+
"learning_rate": 8.043807145043604e-05,
|
| 110 |
+
"loss": 2.0541,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.0,
|
| 115 |
+
"learning_rate": 7.777851165098012e-05,
|
| 116 |
+
"loss": 1.1905,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.0,
|
| 121 |
+
"learning_rate": 7.500000000000001e-05,
|
| 122 |
+
"loss": 1.8179,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.0,
|
| 127 |
+
"learning_rate": 7.211443451095007e-05,
|
| 128 |
+
"loss": 2.0296,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0,
|
| 133 |
+
"learning_rate": 6.91341716182545e-05,
|
| 134 |
+
"loss": 2.0647,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0,
|
| 139 |
+
"learning_rate": 6.607197326515808e-05,
|
| 140 |
+
"loss": 1.3423,
|
| 141 |
+
"step": 22
|
| 142 |
}
|
| 143 |
],
|
| 144 |
"logging_steps": 1.0,
|
|
|
|
| 146 |
"num_input_tokens_seen": 0,
|
| 147 |
"num_train_epochs": 1,
|
| 148 |
"save_steps": 10,
|
| 149 |
+
"total_flos": 177760243906560.0,
|
| 150 |
"train_batch_size": 1,
|
| 151 |
"trial_name": null,
|
| 152 |
"trial_params": null
|