Training in progress, step 1500
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101537765
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a10cb34cf7dbb7af44bdb9cb96dfdb3259896556bb26f9f7efab451322dc92c7
|
| 3 |
size 101537765
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50783921
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19d1674f8348f66f7b609132b675da3830f352bd6006b5476a8eddd63b9f5969
|
| 3 |
size 50783921
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:161a19621de4200192d7bfc0821c090063f1431ba8769f731b08d1a533e974c1
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7742c7cf903d3708345c83d32a6f77a19180823f5d84e5428ea951093f5c213
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -12,11 +12,31 @@
|
|
| 12 |
"learning_rate": 1.6825396825396828e-05,
|
| 13 |
"loss": 4.4387,
|
| 14 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
| 16 |
],
|
| 17 |
"max_steps": 3150,
|
| 18 |
"num_train_epochs": 3,
|
| 19 |
-
"total_flos":
|
| 20 |
"trial_name": null,
|
| 21 |
"trial_params": null
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.4285714285714286,
|
| 5 |
+
"global_step": 1500,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 12 |
"learning_rate": 1.6825396825396828e-05,
|
| 13 |
"loss": 4.4387,
|
| 14 |
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.95,
|
| 18 |
+
"learning_rate": 1.3650793650793652e-05,
|
| 19 |
+
"loss": 3.5954,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_loss": 3.0800042152404785,
|
| 25 |
+
"eval_runtime": 6.2492,
|
| 26 |
+
"eval_samples_per_second": 327.561,
|
| 27 |
+
"eval_steps_per_second": 20.483,
|
| 28 |
+
"step": 1050
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.43,
|
| 32 |
+
"learning_rate": 1.0476190476190477e-05,
|
| 33 |
+
"loss": 3.224,
|
| 34 |
+
"step": 1500
|
| 35 |
}
|
| 36 |
],
|
| 37 |
"max_steps": 3150,
|
| 38 |
"num_train_epochs": 3,
|
| 39 |
+
"total_flos": 261981867400704.0,
|
| 40 |
"trial_name": null,
|
| 41 |
"trial_params": null
|
| 42 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50783921
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19d1674f8348f66f7b609132b675da3830f352bd6006b5476a8eddd63b9f5969
|
| 3 |
size 50783921
|
runs/Jan15_03-37-15_17a47eed43af/events.out.tfevents.1642217843.17a47eed43af.73.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3f60ba6f925bf9ea876c6b9a8abeae8e6823672d43cdfdd7c5747291a075fa9
|
| 3 |
+
size 4233
|