Training in progress, step 600, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40036040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69ec429dbc5975696429d62eacbf437f435c1ad5b172ed93653d653dfa3a062a
|
| 3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20524127
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f922466890e5661f14d3bf78bd8d343252bad551c57cd92aa314721fde9f63e
|
| 3 |
size 20524127
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:155e0bcc656baebb0cf52b6d1d7132f430389610ae4c996795e913a18d99755a
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8d35059d85341a60a5de1f3d03e1d2de2567877022fe78e41439726275de277
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 60,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -124,13 +124,26 @@
|
|
| 124 |
"eval_samples_per_second": 1.915,
|
| 125 |
"eval_steps_per_second": 0.239,
|
| 126 |
"step": 540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
}
|
| 128 |
],
|
| 129 |
"logging_steps": 60,
|
| 130 |
"max_steps": 1011,
|
| 131 |
"num_train_epochs": 3,
|
| 132 |
"save_steps": 60,
|
| 133 |
-
"total_flos":
|
| 134 |
"trial_name": null,
|
| 135 |
"trial_params": null
|
| 136 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7777777777777777,
|
| 5 |
"eval_steps": 60,
|
| 6 |
+
"global_step": 600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 124 |
"eval_samples_per_second": 1.915,
|
| 125 |
"eval_steps_per_second": 0.239,
|
| 126 |
"step": 540
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.78,
|
| 130 |
+
"learning_rate": 0.0002,
|
| 131 |
+
"loss": 0.5487,
|
| 132 |
+
"step": 600
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.78,
|
| 136 |
+
"eval_runtime": 312.5543,
|
| 137 |
+
"eval_samples_per_second": 1.92,
|
| 138 |
+
"eval_steps_per_second": 0.24,
|
| 139 |
+
"step": 600
|
| 140 |
}
|
| 141 |
],
|
| 142 |
"logging_steps": 60,
|
| 143 |
"max_steps": 1011,
|
| 144 |
"num_train_epochs": 3,
|
| 145 |
"save_steps": 60,
|
| 146 |
+
"total_flos": 9.96606493065216e+16,
|
| 147 |
"trial_name": null,
|
| 148 |
"trial_params": null
|
| 149 |
}
|