devvanshhh
commited on
Commit
•
36af7dc
1
Parent(s):
80bdab9
Training in progress, epoch 11, 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 sha256:400735020fcee2fd716a867c067f55ca183eb12b1e74d2a1a2c1730dba48be71
|
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 sha256:12b25070751eb9d47332ba1d65a83caf709ea5f22a7fedaf0aee6b59670abc6e
|
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 sha256:3a1aff5535259d50f42bb34ca17fb77c771f3e098af3d15205d2752082429c74
|
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 sha256:432ec222b9cee1338a39477e5b2f382e8bd3e0d73f458cb15f3c05fcd29ac2c3
|
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,
|
@@ -173,13 +173,32 @@
|
|
173 |
"eval_samples_per_second": 1.98,
|
174 |
"eval_steps_per_second": 0.252,
|
175 |
"step": 3280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
176 |
}
|
177 |
],
|
178 |
"logging_steps": 500,
|
179 |
"max_steps": 3936,
|
180 |
"num_train_epochs": 12,
|
181 |
"save_steps": 500,
|
182 |
-
"total_flos": 2.
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|
185 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3608,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
173 |
"eval_samples_per_second": 1.98,
|
174 |
"eval_steps_per_second": 0.252,
|
175 |
"step": 3280
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 10.67,
|
179 |
+
"learning_rate": 2.334047109207709e-06,
|
180 |
+
"loss": 0.7168,
|
181 |
+
"step": 3500
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 11.0,
|
185 |
+
"eval_gen_len": 10.618556701030927,
|
186 |
+
"eval_loss": 0.6601226925849915,
|
187 |
+
"eval_rouge1": 34.0539,
|
188 |
+
"eval_rouge2": 25.5073,
|
189 |
+
"eval_rougeL": 30.329,
|
190 |
+
"eval_rougeLsum": 30.6828,
|
191 |
+
"eval_runtime": 146.8209,
|
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": 2.7039563986305024e+16,
|
202 |
"trial_name": null,
|
203 |
"trial_params": null
|
204 |
}
|