Training in progress, step 1800, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8fe0cdc0f550da5cb5f95b67c8c47c08e0a5a8d09316be7c2d35a660c0525b6
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffbb66ee85d84388dc537ba459d1d683d483121595dc07e7d88dca038331c701
|
3 |
size 126034975
|
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 sha256:15edfc3f6e4bed87231187d21339fedb19ea6cebd85e0c2de62e5263b5cd6aa8
|
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:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
|
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": 4.
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -111,13 +111,26 @@
|
|
111 |
"eval_samples_per_second": 2.751,
|
112 |
"eval_steps_per_second": 0.176,
|
113 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 200,
|
117 |
"max_steps": 2232,
|
118 |
"num_train_epochs": 6,
|
119 |
"save_steps": 200,
|
120 |
-
"total_flos":
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.838709677419355,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
111 |
"eval_samples_per_second": 2.751,
|
112 |
"eval_steps_per_second": 0.176,
|
113 |
"step": 1600
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.84,
|
117 |
+
"learning_rate": 0.0002,
|
118 |
+
"loss": 0.028,
|
119 |
+
"step": 1800
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 4.84,
|
123 |
+
"eval_runtime": 113.8547,
|
124 |
+
"eval_samples_per_second": 2.749,
|
125 |
+
"eval_steps_per_second": 0.176,
|
126 |
+
"step": 1800
|
127 |
}
|
128 |
],
|
129 |
"logging_steps": 200,
|
130 |
"max_steps": 2232,
|
131 |
"num_train_epochs": 6,
|
132 |
"save_steps": 200,
|
133 |
+
"total_flos": 8.575441357529088e+17,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|