Training in progress, epoch 4, 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 sha256:80e5ebbffbdf2b2b0f373bf3c3ac5fd9b510ca7cfae15dd1959091965542be95
|
| 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 sha256:13a58a920b26ab294974ce24ca31a5f48242d44c9efa09c510a9b13690844009
|
| 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 sha256:0f772128fc6a6bf97a7f6d60182a0d96033d8ba15722d63443d2398fe2eb3b92
|
| 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 sha256:54f205adddbfad9c7a0aedb486db2e44512ccc97c43bb3f3ea372ee55b6a066e
|
| 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,
|
|
@@ -38,6 +38,14 @@
|
|
| 38 |
"eval_samples_per_second": 37.025,
|
| 39 |
"eval_steps_per_second": 9.256,
|
| 40 |
"step": 603
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"logging_steps": 500,
|
|
@@ -57,7 +65,7 @@
|
|
| 57 |
"attributes": {}
|
| 58 |
}
|
| 59 |
},
|
| 60 |
-
"total_flos": 2.
|
| 61 |
"train_batch_size": 16,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0058513879776,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-804",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 804,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 38 |
"eval_samples_per_second": 37.025,
|
| 39 |
"eval_steps_per_second": 9.256,
|
| 40 |
"step": 603
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 4.0,
|
| 44 |
+
"eval_loss": 1.0058513879776,
|
| 45 |
+
"eval_runtime": 76.7488,
|
| 46 |
+
"eval_samples_per_second": 37.212,
|
| 47 |
+
"eval_steps_per_second": 9.303,
|
| 48 |
+
"step": 804
|
| 49 |
}
|
| 50 |
],
|
| 51 |
"logging_steps": 500,
|
|
|
|
| 65 |
"attributes": {}
|
| 66 |
}
|
| 67 |
},
|
| 68 |
+
"total_flos": 2.706540438528e+16,
|
| 69 |
"train_batch_size": 16,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|