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 sha256:1e455806a65a8cd457de9aa3633ac12ea9ac63a33d03abe081a06d16a7e15279
|
| 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 sha256:28ba346e49cb7072768af3efbad839cff457c7c82964980ad88e972cedf5b94f
|
| 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:cf08d9aba6af994094784f693681fe8e70a1cebc4dd57db2b3c0b7832ef9befc
|
| 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 sha256:67270b189be36e5b1860a3a4562dcdaacfb813ecd7c15717e53cb5f48060b566
|
| 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,
|
|
@@ -31,6 +31,14 @@
|
|
| 31 |
"eval_samples_per_second": 37.271,
|
| 32 |
"eval_steps_per_second": 9.318,
|
| 33 |
"step": 66
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
],
|
| 36 |
"logging_steps": 500,
|
|
@@ -50,7 +58,7 @@
|
|
| 50 |
"attributes": {}
|
| 51 |
}
|
| 52 |
},
|
| 53 |
-
"total_flos":
|
| 54 |
"train_batch_size": 16,
|
| 55 |
"trial_name": null,
|
| 56 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3830264806747437,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-88",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 88,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 31 |
"eval_samples_per_second": 37.271,
|
| 32 |
"eval_steps_per_second": 9.318,
|
| 33 |
"step": 66
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.0,
|
| 37 |
+
"eval_loss": 1.3830264806747437,
|
| 38 |
+
"eval_runtime": 8.0646,
|
| 39 |
+
"eval_samples_per_second": 37.2,
|
| 40 |
+
"eval_steps_per_second": 9.3,
|
| 41 |
+
"step": 88
|
| 42 |
}
|
| 43 |
],
|
| 44 |
"logging_steps": 500,
|
|
|
|
| 58 |
"attributes": {}
|
| 59 |
}
|
| 60 |
},
|
| 61 |
+
"total_flos": 2837680459776000.0,
|
| 62 |
"train_batch_size": 16,
|
| 63 |
"trial_name": null,
|
| 64 |
"trial_params": null
|