Training in progress, step 800, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c95845485e25b4e71d2c0bc5fd4f1468902c7f8a03ea37a4f2495fe5034eefc9
|
3 |
size 160285149
|
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:c4244fea4c4b2cbbec2a91bf09236d9029134586c67149d0cb24583dee45401f
|
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 sha256:0ae1d68d95f8f78dc7a2b9834f2969479f23c5f9f0407eda9de530dc2ff5cbfe
|
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": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -98,13 +98,26 @@
|
|
98 |
"eval_samples_per_second": 1.903,
|
99 |
"eval_steps_per_second": 0.238,
|
100 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 100,
|
104 |
"max_steps": 2025,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 100,
|
107 |
-
"total_flos": 1.
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1851851851851851,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"eval_samples_per_second": 1.903,
|
99 |
"eval_steps_per_second": 0.238,
|
100 |
"step": 700
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.19,
|
104 |
+
"learning_rate": 0.0,
|
105 |
+
"loss": 8.4584,
|
106 |
+
"step": 800
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.19,
|
110 |
+
"eval_runtime": 787.875,
|
111 |
+
"eval_samples_per_second": 1.904,
|
112 |
+
"eval_steps_per_second": 0.239,
|
113 |
+
"step": 800
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 100,
|
117 |
"max_steps": 2025,
|
118 |
"num_train_epochs": 3,
|
119 |
"save_steps": 100,
|
120 |
+
"total_flos": 1.66592319062016e+17,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|