devvanshhh
commited on
Commit
•
9ba1d10
1
Parent(s):
cf2492b
Training in progress, epoch 12, 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 37789864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b39562bf427d2a14b5278ad43a0b8be088c158fd3de46de79501404d07885173
|
3 |
size 37789864
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2621690
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0309fe537640614eb19988b94262e2fbf484182e0f5036ae7fe3736022f612c3
|
3 |
size 2621690
|
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 sha256:19d9bf9b0a1962ed7239b7fb41a831a9e35d8bd60ad1aaa789f6a72c727c8389
|
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:e907a32d891d5bba451595d59dde8ebe68b20c4630644ad86acf1c518e70a940
|
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":
|
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,
|
@@ -192,13 +192,26 @@
|
|
192 |
"eval_samples_per_second": 1.982,
|
193 |
"eval_steps_per_second": 0.252,
|
194 |
"step": 3608
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
195 |
}
|
196 |
],
|
197 |
"logging_steps": 500,
|
198 |
"max_steps": 3936,
|
199 |
"num_train_epochs": 12,
|
200 |
"save_steps": 500,
|
201 |
-
"total_flos": 2.
|
202 |
"trial_name": null,
|
203 |
"trial_params": null
|
204 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3936,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
192 |
"eval_samples_per_second": 1.982,
|
193 |
"eval_steps_per_second": 0.252,
|
194 |
"step": 3608
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 12.0,
|
198 |
+
"eval_gen_len": 10.532646048109966,
|
199 |
+
"eval_loss": 0.6593531370162964,
|
200 |
+
"eval_rouge1": 34.2696,
|
201 |
+
"eval_rouge2": 25.7973,
|
202 |
+
"eval_rougeL": 30.5609,
|
203 |
+
"eval_rougeLsum": 30.9651,
|
204 |
+
"eval_runtime": 145.5529,
|
205 |
+
"eval_samples_per_second": 1.999,
|
206 |
+
"eval_steps_per_second": 0.254,
|
207 |
+
"step": 3936
|
208 |
}
|
209 |
],
|
210 |
"logging_steps": 500,
|
211 |
"max_steps": 3936,
|
212 |
"num_train_epochs": 12,
|
213 |
"save_steps": 500,
|
214 |
+
"total_flos": 2.949770616687821e+16,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|
217 |
}
|