Training in progress, step 75, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a29e4e1f3cb214f38716ce14886a527c74777aa1cefd39e09f39254703d066de
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc4cbd70f8cc553d41f6f5cd7a19646f4d29fc16b3d3283faf0af5df960f788
|
3 |
size 37965300
|
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 sha256:761c1e23b989e2bf545b499c46fefe6057b00ee23e3142751017f2522af6f8d3
|
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 sha256:95a2dfe0396f96ddebe3df871573bf02bf12ab98dab497f42ddce910ec27ff38
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
-
"epoch": 0.
|
6 |
"eval_steps": 500,
|
7 |
-
"global_step":
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
@@ -21,12 +21,12 @@
|
|
21 |
"should_evaluate": false,
|
22 |
"should_log": false,
|
23 |
"should_save": true,
|
24 |
-
"should_training_stop":
|
25 |
},
|
26 |
"attributes": {}
|
27 |
}
|
28 |
},
|
29 |
-
"total_flos": 1.
|
30 |
"train_batch_size": 2,
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.07340347443112308,
|
6 |
"eval_steps": 500,
|
7 |
+
"global_step": 75,
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
|
|
21 |
"should_evaluate": false,
|
22 |
"should_log": false,
|
23 |
"should_save": true,
|
24 |
+
"should_training_stop": true
|
25 |
},
|
26 |
"attributes": {}
|
27 |
}
|
28 |
},
|
29 |
+
"total_flos": 1.6795759778463744e+16,
|
30 |
"train_batch_size": 2,
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|