Training in progress, step 10, 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 sha256:188447b7ea74a861624769b8aa8fa0af8e13159a5253f25686b71770564d8f97
|
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 20814996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad4a742dd114abb5b5c5a2d053eab18b486cce42b8256da2dd78000aa334721e
|
3 |
size 20814996
|
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 sha256:5bb935c2d08b8902f656e6d9a77a383395851960248fb4a387b33658b6121ae1
|
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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
|
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": 0.
|
5 |
"eval_steps": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -142,6 +142,21 @@
|
|
142 |
"eval_samples_per_second": 8.255,
|
143 |
"eval_steps_per_second": 8.255,
|
144 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"logging_steps": 1,
|
@@ -156,12 +171,12 @@
|
|
156 |
"should_evaluate": false,
|
157 |
"should_log": false,
|
158 |
"should_save": true,
|
159 |
-
"should_training_stop":
|
160 |
},
|
161 |
"attributes": {}
|
162 |
}
|
163 |
},
|
164 |
-
"total_flos":
|
165 |
"train_batch_size": 1,
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007416334476684898,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
142 |
"eval_samples_per_second": 8.255,
|
143 |
"eval_steps_per_second": 8.255,
|
144 |
"step": 9
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.007416334476684898,
|
148 |
+
"grad_norm": 27.74460220336914,
|
149 |
+
"learning_rate": 0.0002,
|
150 |
+
"loss": 11.843,
|
151 |
+
"step": 10
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.007416334476684898,
|
155 |
+
"eval_loss": 1.3354620933532715,
|
156 |
+
"eval_runtime": 68.7847,
|
157 |
+
"eval_samples_per_second": 8.258,
|
158 |
+
"eval_steps_per_second": 8.258,
|
159 |
+
"step": 10
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 1,
|
|
|
171 |
"should_evaluate": false,
|
172 |
"should_log": false,
|
173 |
"should_save": true,
|
174 |
+
"should_training_stop": true
|
175 |
},
|
176 |
"attributes": {}
|
177 |
}
|
178 |
},
|
179 |
+
"total_flos": 813146528808960.0,
|
180 |
"train_batch_size": 1,
|
181 |
"trial_name": null,
|
182 |
"trial_params": null
|