Training in progress, epoch 6, 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 sha256:4ef2964c596680496bac1a5fde881df5501c7c42822b39cd64932847d5d20b51
|
| 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 sha256:12f7764af7f92a2663cb676fefbb2e8350dab83243e3739b4d7d76ba820aa83c
|
| 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 sha256:8e9e9b1b8a737a0e6724d8363ae32af08a7ae44ac84fc74cf26efc38d72c2e99
|
| 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 sha256:4dbd5ff4bdf3d44747ad00fa29200a8d92013019282f4c83378b09ca4fd6fe51
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.29741692543029785,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-1610",
|
| 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,
|
|
@@ -68,6 +68,14 @@
|
|
| 68 |
"eval_samples_per_second": 19.612,
|
| 69 |
"eval_steps_per_second": 4.903,
|
| 70 |
"step": 1610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|
| 72 |
],
|
| 73 |
"logging_steps": 500,
|
|
@@ -87,7 +95,7 @@
|
|
| 87 |
"attributes": {}
|
| 88 |
}
|
| 89 |
},
|
| 90 |
-
"total_flos":
|
| 91 |
"train_batch_size": 10,
|
| 92 |
"trial_name": null,
|
| 93 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.29741692543029785,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-1610",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1932,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 68 |
"eval_samples_per_second": 19.612,
|
| 69 |
"eval_steps_per_second": 4.903,
|
| 70 |
"step": 1610
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.0,
|
| 74 |
+
"eval_loss": 0.29865920543670654,
|
| 75 |
+
"eval_runtime": 145.5148,
|
| 76 |
+
"eval_samples_per_second": 19.627,
|
| 77 |
+
"eval_steps_per_second": 4.907,
|
| 78 |
+
"step": 1932
|
| 79 |
}
|
| 80 |
],
|
| 81 |
"logging_steps": 500,
|
|
|
|
| 95 |
"attributes": {}
|
| 96 |
}
|
| 97 |
},
|
| 98 |
+
"total_flos": 8.056678514688e+16,
|
| 99 |
"train_batch_size": 10,
|
| 100 |
"trial_name": null,
|
| 101 |
"trial_params": null
|