Training in progress, epoch 8, 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:c0a30ebbd6657e1cab4ec2b03e03655f4cb11cc943457a8a4467091f0030d5d6
|
| 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 sha256:5599f756b658d54d746a9242579f1e01ebe343bfce18681a57bbe6c9ed1e081f
|
| 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 sha256:52ee4971414a0520b88b927c694c19903060200592189a0a539c94170dd4f40b
|
| 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:b747a0dae9cc690ae54725ad77f1bc3e848725dcbbaa4ba117f697b1bc16ee0a
|
| 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,
|
|
@@ -63,6 +63,14 @@
|
|
| 63 |
"eval_samples_per_second": 37.071,
|
| 64 |
"eval_steps_per_second": 9.268,
|
| 65 |
"step": 154
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
}
|
| 67 |
],
|
| 68 |
"logging_steps": 500,
|
|
@@ -82,7 +90,7 @@
|
|
| 82 |
"attributes": {}
|
| 83 |
}
|
| 84 |
},
|
| 85 |
-
"total_flos":
|
| 86 |
"train_batch_size": 16,
|
| 87 |
"trial_name": null,
|
| 88 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.350898027420044,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-176",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 176,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 63 |
"eval_samples_per_second": 37.071,
|
| 64 |
"eval_steps_per_second": 9.268,
|
| 65 |
"step": 154
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 8.0,
|
| 69 |
+
"eval_loss": 1.350898027420044,
|
| 70 |
+
"eval_runtime": 8.0696,
|
| 71 |
+
"eval_samples_per_second": 37.177,
|
| 72 |
+
"eval_steps_per_second": 9.294,
|
| 73 |
+
"step": 176
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 500,
|
|
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
+
"total_flos": 5675360919552000.0,
|
| 94 |
"train_batch_size": 16,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|