Training in progress, step 1500, 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 6298560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f5ca07529681e0bc4addcb6798581a52d610599a0087c8ac83d5002cb149ead
|
3 |
size 6298560
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12611145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd3a1ed1c807642a86b3a985b4117ab3926fc76a490dc651edbc5e79f94a2d57
|
3 |
size 12611145
|
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 sha256:8e2a97244d4c9e36a92ce9603501239216f8b35c73f1c473a49ecf7c2bcaecde
|
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:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch":
|
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,
|
@@ -203,6 +203,20 @@
|
|
203 |
"eval_samples_per_second": 4.109,
|
204 |
"eval_steps_per_second": 0.515,
|
205 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
@@ -210,7 +224,7 @@
|
|
210 |
"num_input_tokens_seen": 0,
|
211 |
"num_train_epochs": 3,
|
212 |
"save_steps": 100,
|
213 |
-
"total_flos": 4.
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
216 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2038506269454956,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1500",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
203 |
"eval_samples_per_second": 4.109,
|
204 |
"eval_steps_per_second": 0.515,
|
205 |
"step": 1400
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.0,
|
209 |
+
"learning_rate": 0.0002,
|
210 |
+
"loss": 0.9818,
|
211 |
+
"step": 1500
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 2.0,
|
215 |
+
"eval_loss": 1.2038506269454956,
|
216 |
+
"eval_runtime": 470.1258,
|
217 |
+
"eval_samples_per_second": 4.105,
|
218 |
+
"eval_steps_per_second": 0.515,
|
219 |
+
"step": 1500
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 100,
|
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 3,
|
226 |
"save_steps": 100,
|
227 |
+
"total_flos": 4.991433715954483e+16,
|
228 |
"trial_name": null,
|
229 |
"trial_params": null
|
230 |
}
|