Training in progress, epoch 15, 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 500979600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c788a3231500becd0e9a6adaea3cc99b5c460910f00c856dd75fb13a6c610b
|
| 3 |
size 500979600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1002078330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a24dd36fd82efe9d6d32a045e4511183d5b4a5a8db10e4b322a9b7c2b8e4c7d
|
| 3 |
size 1002078330
|
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 sha256:824f71db9f1256709fc08ef93182ab782a12b918c06c53930c51cb2d50c70df1
|
| 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 sha256:3a7151eaee3e7a4e65d1924a3b0e9e091841f505cff806dfce44af7b59f8fee2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained/checkpoint-
|
| 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,
|
|
@@ -119,6 +119,14 @@
|
|
| 119 |
"eval_samples_per_second": 37.002,
|
| 120 |
"eval_steps_per_second": 9.25,
|
| 121 |
"step": 308
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
}
|
| 123 |
],
|
| 124 |
"logging_steps": 500,
|
|
@@ -138,7 +146,7 @@
|
|
| 138 |
"attributes": {}
|
| 139 |
}
|
| 140 |
},
|
| 141 |
-
"total_flos":
|
| 142 |
"train_batch_size": 16,
|
| 143 |
"trial_name": null,
|
| 144 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.323224663734436,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-330",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 330,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 119 |
"eval_samples_per_second": 37.002,
|
| 120 |
"eval_steps_per_second": 9.25,
|
| 121 |
"step": 308
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 15.0,
|
| 125 |
+
"eval_loss": 1.323224663734436,
|
| 126 |
+
"eval_runtime": 8.1229,
|
| 127 |
+
"eval_samples_per_second": 36.933,
|
| 128 |
+
"eval_steps_per_second": 9.233,
|
| 129 |
+
"step": 330
|
| 130 |
}
|
| 131 |
],
|
| 132 |
"logging_steps": 500,
|
|
|
|
| 146 |
"attributes": {}
|
| 147 |
}
|
| 148 |
},
|
| 149 |
+
"total_flos": 1.064130172416e+16,
|
| 150 |
"train_batch_size": 16,
|
| 151 |
"trial_name": null,
|
| 152 |
"trial_params": null
|