Training in progress, step 2400, 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 sha256:52d94607563a1e7e8be832bb0b495ff4b7b5a4a4b278733a1dd3da5da29ba6d3
|
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 sha256:063ccd2305be10e4b71067500514679f94ef463f786066573a59292b2e4e4db2
|
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 sha256:688a7f37f54fa1fb861bc02578f12e64ab3b6a35a244786ef49db2d9934464e4
|
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 sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
|
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":
|
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,
|
@@ -150,13 +150,26 @@
|
|
150 |
"eval_samples_per_second": 7.953,
|
151 |
"eval_steps_per_second": 0.506,
|
152 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 200,
|
156 |
"max_steps": 2472,
|
157 |
"num_train_epochs": 12,
|
158 |
"save_steps": 200,
|
159 |
-
"total_flos": 7.
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|
162 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.650485436893204,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 2400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_samples_per_second": 7.953,
|
151 |
"eval_steps_per_second": 0.506,
|
152 |
"step": 2200
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 11.65,
|
156 |
+
"learning_rate": 0.0002,
|
157 |
+
"loss": 0.0245,
|
158 |
+
"step": 2400
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.65,
|
162 |
+
"eval_runtime": 21.7676,
|
163 |
+
"eval_samples_per_second": 7.948,
|
164 |
+
"eval_steps_per_second": 0.505,
|
165 |
+
"step": 2400
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 200,
|
169 |
"max_steps": 2472,
|
170 |
"num_train_epochs": 12,
|
171 |
"save_steps": 200,
|
172 |
+
"total_flos": 7.726720077791232e+17,
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
175 |
}
|