Training in progress, step 3609, 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 891558696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee2938fb5f0e4c2227e884418950000716dc74607d93281e3c8d920bdcbb8be8
|
| 3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1783272762
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2ef7ef671c227d06372122da16cc668552155a31e26538b36ee94632c4589f
|
| 3 |
size 1783272762
|
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 sha256:34064347e453570353e8680855135f6c0ee25c62110523a1148e32a7da7f74e8
|
| 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 sha256:5d737f5f263d9c1de39c44cd6658d6d8320e72a3080c7ef6cd6438f14f851810
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -86,12 +86,12 @@
|
|
| 86 |
"should_evaluate": false,
|
| 87 |
"should_log": false,
|
| 88 |
"should_save": true,
|
| 89 |
-
"should_training_stop":
|
| 90 |
},
|
| 91 |
"attributes": {}
|
| 92 |
}
|
| 93 |
},
|
| 94 |
-
"total_flos": 1.
|
| 95 |
"train_batch_size": 8,
|
| 96 |
"trial_name": null,
|
| 97 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3609,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 86 |
"should_evaluate": false,
|
| 87 |
"should_log": false,
|
| 88 |
"should_save": true,
|
| 89 |
+
"should_training_stop": true
|
| 90 |
},
|
| 91 |
"attributes": {}
|
| 92 |
}
|
| 93 |
},
|
| 94 |
+
"total_flos": 1.758000534257664e+16,
|
| 95 |
"train_batch_size": 8,
|
| 96 |
"trial_name": null,
|
| 97 |
"trial_params": null
|