Training in progress, step 6000, 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 267906392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79782b5581a45a76bf9beaa6676def663e9176ff1098e4359cae0192209b0ef5
|
| 3 |
size 267906392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535874874
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaca4cd4edad653caf72115a8324e0606ff1fd4288d900196a37b5ea59d76af4
|
| 3 |
size 535874874
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b42f67e225dd613ea798dba0715bab821e8257fc963218cb0ee7ad1438a755a
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2ece5904c2c0115cd10e487727c768eb0a89eb5baed9b6c9bbd324568530d2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4119344651699066,
|
| 3 |
"best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -117,6 +117,28 @@
|
|
| 117 |
"eval_samples_per_second": 107.017,
|
| 118 |
"eval_steps_per_second": 0.839,
|
| 119 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
}
|
| 121 |
],
|
| 122 |
"logging_steps": 500,
|
|
@@ -136,7 +158,7 @@
|
|
| 136 |
"attributes": {}
|
| 137 |
}
|
| 138 |
},
|
| 139 |
-
"total_flos": 2.
|
| 140 |
"train_batch_size": 32,
|
| 141 |
"trial_name": null,
|
| 142 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4119344651699066,
|
| 3 |
"best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
|
| 4 |
+
"epoch": 0.288711384852276,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 117 |
"eval_samples_per_second": 107.017,
|
| 118 |
"eval_steps_per_second": 0.839,
|
| 119 |
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.264652102781253,
|
| 123 |
+
"grad_norm": 8.764209747314453,
|
| 124 |
+
"learning_rate": 4.234433644500049e-05,
|
| 125 |
+
"loss": 0.429,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.288711384852276,
|
| 130 |
+
"grad_norm": 2.4573419094085693,
|
| 131 |
+
"learning_rate": 4.619382157636416e-05,
|
| 132 |
+
"loss": 0.4191,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.288711384852276,
|
| 137 |
+
"eval_loss": 0.44426167011260986,
|
| 138 |
+
"eval_runtime": 244.015,
|
| 139 |
+
"eval_samples_per_second": 107.17,
|
| 140 |
+
"eval_steps_per_second": 0.84,
|
| 141 |
+
"step": 6000
|
| 142 |
}
|
| 143 |
],
|
| 144 |
"logging_steps": 500,
|
|
|
|
| 158 |
"attributes": {}
|
| 159 |
}
|
| 160 |
},
|
| 161 |
+
"total_flos": 2.5444626333696e+16,
|
| 162 |
"train_batch_size": 32,
|
| 163 |
"trial_name": null,
|
| 164 |
"trial_params": null
|