Training in progress, step 800, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abe1bf17d2c830d3b6c1fefae7af91dc7dfbf1bbe69e8797f01623084fb00dfc
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21689885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b4db910e4f4b09662424d25772c11728468d1ab1a6de02a58ce13e664159f8a
|
3 |
size 21689885
|
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 sha256:12574d8d1395ea85b59ecf9d193de877adf1de4ad027b7e75e021b6803126718
|
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 sha256:6bf7401d3bff0b343fef70975b8b910805ada55675fd63bf769da9640a3e5c96
|
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": 1.78,
|
99 |
"eval_steps_per_second": 0.223,
|
100 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 100,
|
104 |
"max_steps": 1686,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 100,
|
107 |
-
"total_flos": 2.
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.4222222222222223,
|
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": 1.78,
|
99 |
"eval_steps_per_second": 0.223,
|
100 |
"step": 700
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.42,
|
104 |
+
"learning_rate": 0.0001,
|
105 |
+
"loss": 0.5709,
|
106 |
+
"step": 800
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.42,
|
110 |
+
"eval_runtime": 1405.1361,
|
111 |
+
"eval_samples_per_second": 1.779,
|
112 |
+
"eval_steps_per_second": 0.223,
|
113 |
+
"step": 800
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 100,
|
117 |
"max_steps": 1686,
|
118 |
"num_train_epochs": 3,
|
119 |
"save_steps": 100,
|
120 |
+
"total_flos": 2.844481032290304e+17,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|