Training in progress, epoch 7, 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 sha256:24e28a52ef229ba6d8ed71fec15bff705f2501a7e9bd14e4bb54029c74045d56
|
| 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 sha256:332a0dba68d3a65274c093ef9fc6ebceede2b5d048c9bfdaa10b0f40c94e497c
|
| 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 sha256:93cb2a9e1c10d9abbebe7c7a138c2f0ba5fcefafc2c50079c366e35cb5be33d1
|
| 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 sha256:30c198d40e01946dd435e0b3025e9ad1b5a21b75875c7b39f672157105ea2ab6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.354698896408081,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-110",
|
| 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,
|
|
@@ -55,6 +55,14 @@
|
|
| 55 |
"eval_samples_per_second": 37.311,
|
| 56 |
"eval_steps_per_second": 9.328,
|
| 57 |
"step": 132
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"logging_steps": 500,
|
|
@@ -74,7 +82,7 @@
|
|
| 74 |
"attributes": {}
|
| 75 |
}
|
| 76 |
},
|
| 77 |
-
"total_flos":
|
| 78 |
"train_batch_size": 16,
|
| 79 |
"trial_name": null,
|
| 80 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.354698896408081,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-110",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 154,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 55 |
"eval_samples_per_second": 37.311,
|
| 56 |
"eval_steps_per_second": 9.328,
|
| 57 |
"step": 132
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.0,
|
| 61 |
+
"eval_loss": 1.367162823677063,
|
| 62 |
+
"eval_runtime": 8.0926,
|
| 63 |
+
"eval_samples_per_second": 37.071,
|
| 64 |
+
"eval_steps_per_second": 9.268,
|
| 65 |
+
"step": 154
|
| 66 |
}
|
| 67 |
],
|
| 68 |
"logging_steps": 500,
|
|
|
|
| 82 |
"attributes": {}
|
| 83 |
}
|
| 84 |
},
|
| 85 |
+
"total_flos": 4965940804608000.0,
|
| 86 |
"train_batch_size": 16,
|
| 87 |
"trial_name": null,
|
| 88 |
"trial_params": null
|