Training in progress, step 18, 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 41581360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9679997ddbdf0aaf7627479ba9934040206c7023c174467ec71ba915828794d9
|
3 |
size 41581360
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21505540
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9040522376779c7a31146707300519e8d7d39213046e9f2cf4bbc480fe1e61aa
|
3 |
size 21505540
|
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 sha256:63236f8023b6c36bd0a9ae3afc0a7c5229575e92a00da93efffa78dfd33bdc3d
|
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:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -46,6 +46,14 @@
|
|
46 |
"eval_samples_per_second": 33.624,
|
47 |
"eval_steps_per_second": 4.348,
|
48 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
@@ -60,12 +68,12 @@
|
|
60 |
"should_evaluate": false,
|
61 |
"should_log": false,
|
62 |
"should_save": true,
|
63 |
-
"should_training_stop":
|
64 |
},
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
-
"total_flos": 1.
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.051094890510949,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 18,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 33.624,
|
47 |
"eval_steps_per_second": 4.348,
|
48 |
"step": 12
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.9343065693430657,
|
52 |
+
"eval_loss": 1.3059964179992676,
|
53 |
+
"eval_runtime": 3.4569,
|
54 |
+
"eval_samples_per_second": 33.556,
|
55 |
+
"eval_steps_per_second": 4.339,
|
56 |
+
"step": 16
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 10,
|
|
|
68 |
"should_evaluate": false,
|
69 |
"should_log": false,
|
70 |
"should_save": true,
|
71 |
+
"should_training_stop": true
|
72 |
},
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
+
"total_flos": 1.4902900455112704e+16,
|
77 |
"train_batch_size": 8,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|