Training in progress, epoch 5, 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 sha256:083b04407fd15fb51b765fd0582cd56fd518d7f8ff8b0233f2e4f0ac48fc9ebb
|
| 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 sha256:2510e2fa7fa1d955397b34cbb7c26285c975a1bcbc0b125f763ec572fa45e545
|
| 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 sha256:3777b3c6a0fa94be51a89ad5a8c3cb7b6b136acc79e9c81f0ff9a820338ceb26
|
| 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:b854623af9d18b24ea9409e13bcaf50b1828dd5c83def071277f73f4a36ca466
|
| 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,
|
|
@@ -39,6 +39,14 @@
|
|
| 39 |
"eval_samples_per_second": 37.2,
|
| 40 |
"eval_steps_per_second": 9.3,
|
| 41 |
"step": 88
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
],
|
| 44 |
"logging_steps": 500,
|
|
@@ -58,7 +66,7 @@
|
|
| 58 |
"attributes": {}
|
| 59 |
}
|
| 60 |
},
|
| 61 |
-
"total_flos":
|
| 62 |
"train_batch_size": 16,
|
| 63 |
"trial_name": null,
|
| 64 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.354698896408081,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-110",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 110,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 39 |
"eval_samples_per_second": 37.2,
|
| 40 |
"eval_steps_per_second": 9.3,
|
| 41 |
"step": 88
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 5.0,
|
| 45 |
+
"eval_loss": 1.354698896408081,
|
| 46 |
+
"eval_runtime": 8.0581,
|
| 47 |
+
"eval_samples_per_second": 37.23,
|
| 48 |
+
"eval_steps_per_second": 9.307,
|
| 49 |
+
"step": 110
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 500,
|
|
|
|
| 66 |
"attributes": {}
|
| 67 |
}
|
| 68 |
},
|
| 69 |
+
"total_flos": 3547100574720000.0,
|
| 70 |
"train_batch_size": 16,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|