Training in progress, step 7218, 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 sha256:5b0a9042f3253fdbb267a98e3bcff3d2d441cce03a6d521048afc215d4734013
|
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:e7b71432067a8dee241bd701bd9b33dfd82f69944502d1db8569142726fede15
|
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:baee9ac0f1a03f42e267057f8e2d3689e05b84512ae566f4c571faada02afe98
|
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 sha256:520a9ff89fbc48ded31f1ed6a5a1bc8a1e85cb67f3c218f09905603c40da8b0e
|
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,
|
@@ -135,12 +135,12 @@
|
|
135 |
"should_evaluate": false,
|
136 |
"should_log": false,
|
137 |
"should_save": true,
|
138 |
-
"should_training_stop":
|
139 |
},
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
-
"total_flos": 1.
|
144 |
"train_batch_size": 4,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7218,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
135 |
"should_evaluate": false,
|
136 |
"should_log": false,
|
137 |
"should_save": true,
|
138 |
+
"should_training_stop": true
|
139 |
},
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
+
"total_flos": 1.758000534257664e+16,
|
144 |
"train_batch_size": 4,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|