genejalston
commited on
Commit
•
dda6f9a
1
Parent(s):
7137b0d
Training in progress, step 4500, 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 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27067921a37fee0d19f4028e134500e11a69541e7407e731bb40a56cc505d70b
|
3 |
size 1625426996
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250759951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f43724ba26d90f26c6fa7c6257b5f31305081c875c6f1cb1e7d9392fa228616c
|
3 |
size 3250759951
|
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:b522d59ab588e3cc6831807abf2d80fc037a2c07e5377f87beac2d539a9ddad6
|
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:c2445916986110917930762c7eace8758b17e46062d1ea43946358ec21c772fc
|
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": 2.
|
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,
|
@@ -119,13 +119,27 @@
|
|
119 |
"eval_samples_per_second": 1.368,
|
120 |
"eval_steps_per_second": 0.343,
|
121 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 500,
|
125 |
"max_steps": 6000,
|
126 |
"num_train_epochs": 3,
|
127 |
"save_steps": 500,
|
128 |
-
"total_flos":
|
129 |
"trial_name": null,
|
130 |
"trial_params": null
|
131 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.25,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
119 |
"eval_samples_per_second": 1.368,
|
120 |
"eval_steps_per_second": 0.343,
|
121 |
"step": 4000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.25,
|
125 |
+
"learning_rate": 1.25e-05,
|
126 |
+
"loss": 0.0144,
|
127 |
+
"step": 4500
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 2.25,
|
131 |
+
"eval_loss": 5.14383602142334,
|
132 |
+
"eval_runtime": 367.2726,
|
133 |
+
"eval_samples_per_second": 1.359,
|
134 |
+
"eval_steps_per_second": 0.34,
|
135 |
+
"step": 4500
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 500,
|
139 |
"max_steps": 6000,
|
140 |
"num_train_epochs": 3,
|
141 |
"save_steps": 500,
|
142 |
+
"total_flos": 3808517033164800.0,
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
145 |
}
|