Training in progress, step 2000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +783 -3
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 570000656
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426d7e07904562b030954257df3a97f8defc52a3b3f8f71b1cde18e564ee171d
|
| 3 |
size 570000656
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1622091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a0a32f5d1bf567e9fc2ba59487de369f339f5eea4ef028fe0f31d0c0cb98edf
|
| 3 |
size 1622091
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e14ff92f96becdbeb5487f99d7ddf445377fa9e0cf26c509d26dcdda8dda4eb
|
| 3 |
size 14469
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b3b858a8e1fc823f8b335258ee5a142d5ac713702244632e817f8c711dde36
|
| 3 |
size 14469
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6305ac41261f1e3d9a36c1818bd7b0c4f8ff17d3a56955165c03afb92fc012a3
|
| 3 |
size 14469
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:102a7772ed0ef2cbf3e31a1f454019a02f49f37a163ba61752bc355834a4113b
|
| 3 |
size 14469
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db6daefd2cb9a57fc97380fb035a02993579458af49ced2a638594a6730c5a2d
|
| 3 |
size 14469
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3adf184d9b179f67fff9f70487bcfede88d0750afc2dd8f349df8c0442d1f1ef
|
| 3 |
size 14469
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c67b44c92a6cca46465ad4fd2c5d45e9ba9eb46e0ba1eb0503dffae9d07f232
|
| 3 |
size 14469
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5242c3a32ebcec1868cf5addc107971648be3c61be747a2573e805dd0d2fe195
|
| 3 |
size 14469
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:074e17e831b4334f72a1e890890f90f90aa8764a8732ce7610d754e86a088066
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": false,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -788,6 +788,786 @@
|
|
| 788 |
"eval_samples_per_second": 1.784,
|
| 789 |
"eval_steps_per_second": 0.446,
|
| 790 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 10,
|
|
@@ -807,7 +1587,7 @@
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
-
"total_flos":
|
| 811 |
"train_batch_size": 1,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.18181818181818182,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": false,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 788 |
"eval_samples_per_second": 1.784,
|
| 789 |
"eval_steps_per_second": 0.446,
|
| 790 |
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.09181818181818181,
|
| 794 |
+
"grad_norm": 4381165223936.0,
|
| 795 |
+
"learning_rate": 9.793828205468903e-06,
|
| 796 |
+
"loss": 30.489773559570313,
|
| 797 |
+
"step": 1010
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.09272727272727273,
|
| 801 |
+
"grad_norm": 7098638270464.0,
|
| 802 |
+
"learning_rate": 9.789750323596107e-06,
|
| 803 |
+
"loss": 30.310159301757814,
|
| 804 |
+
"step": 1020
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.09363636363636364,
|
| 808 |
+
"grad_norm": 7115639357440.0,
|
| 809 |
+
"learning_rate": 9.785633373203691e-06,
|
| 810 |
+
"loss": 30.755490112304688,
|
| 811 |
+
"step": 1030
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.09454545454545454,
|
| 815 |
+
"grad_norm": 5234526519296.0,
|
| 816 |
+
"learning_rate": 9.781477387872353e-06,
|
| 817 |
+
"loss": 30.480865478515625,
|
| 818 |
+
"step": 1040
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.09545454545454546,
|
| 822 |
+
"grad_norm": 21593254264832.0,
|
| 823 |
+
"learning_rate": 9.777282401501182e-06,
|
| 824 |
+
"loss": 30.507177734375,
|
| 825 |
+
"step": 1050
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.09636363636363636,
|
| 829 |
+
"grad_norm": 13908608811008.0,
|
| 830 |
+
"learning_rate": 9.773048448307397e-06,
|
| 831 |
+
"loss": 30.405853271484375,
|
| 832 |
+
"step": 1060
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.09727272727272727,
|
| 836 |
+
"grad_norm": 6315089854464.0,
|
| 837 |
+
"learning_rate": 9.768775562826048e-06,
|
| 838 |
+
"loss": 30.191403198242188,
|
| 839 |
+
"step": 1070
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.09818181818181818,
|
| 843 |
+
"grad_norm": 5838569734144.0,
|
| 844 |
+
"learning_rate": 9.764463779909748e-06,
|
| 845 |
+
"loss": 29.98668518066406,
|
| 846 |
+
"step": 1080
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.09909090909090909,
|
| 850 |
+
"grad_norm": 5027172188160.0,
|
| 851 |
+
"learning_rate": 9.760113134728383e-06,
|
| 852 |
+
"loss": 30.168685913085938,
|
| 853 |
+
"step": 1090
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.1,
|
| 857 |
+
"grad_norm": 6847641681920.0,
|
| 858 |
+
"learning_rate": 9.755723662768829e-06,
|
| 859 |
+
"loss": 30.630303955078126,
|
| 860 |
+
"step": 1100
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.1,
|
| 864 |
+
"eval_loss": 30.31258773803711,
|
| 865 |
+
"eval_runtime": 2.2676,
|
| 866 |
+
"eval_samples_per_second": 1.764,
|
| 867 |
+
"eval_steps_per_second": 0.441,
|
| 868 |
+
"step": 1100
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.1009090909090909,
|
| 872 |
+
"grad_norm": 10138593263616.0,
|
| 873 |
+
"learning_rate": 9.751295399834654e-06,
|
| 874 |
+
"loss": 30.400457763671874,
|
| 875 |
+
"step": 1110
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.10181818181818182,
|
| 879 |
+
"grad_norm": 1873908596736.0,
|
| 880 |
+
"learning_rate": 9.746828382045843e-06,
|
| 881 |
+
"loss": 30.39214172363281,
|
| 882 |
+
"step": 1120
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.10272727272727272,
|
| 886 |
+
"grad_norm": 2132046249984.0,
|
| 887 |
+
"learning_rate": 9.742322645838479e-06,
|
| 888 |
+
"loss": 30.495956420898438,
|
| 889 |
+
"step": 1130
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.10363636363636364,
|
| 893 |
+
"grad_norm": 9749846294528.0,
|
| 894 |
+
"learning_rate": 9.737778227964469e-06,
|
| 895 |
+
"loss": 30.675448608398437,
|
| 896 |
+
"step": 1140
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.10454545454545454,
|
| 900 |
+
"grad_norm": 2964184629248.0,
|
| 901 |
+
"learning_rate": 9.733195165491229e-06,
|
| 902 |
+
"loss": 30.388763427734375,
|
| 903 |
+
"step": 1150
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.10545454545454545,
|
| 907 |
+
"grad_norm": 11201202356224.0,
|
| 908 |
+
"learning_rate": 9.728573495801393e-06,
|
| 909 |
+
"loss": 30.802352905273438,
|
| 910 |
+
"step": 1160
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.10636363636363637,
|
| 914 |
+
"grad_norm": 7261218930688.0,
|
| 915 |
+
"learning_rate": 9.723913256592496e-06,
|
| 916 |
+
"loss": 30.62236328125,
|
| 917 |
+
"step": 1170
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.10727272727272727,
|
| 921 |
+
"grad_norm": 7669089304576.0,
|
| 922 |
+
"learning_rate": 9.719214485876677e-06,
|
| 923 |
+
"loss": 31.039337158203125,
|
| 924 |
+
"step": 1180
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.10818181818181818,
|
| 928 |
+
"grad_norm": 3061822259200.0,
|
| 929 |
+
"learning_rate": 9.714477221980361e-06,
|
| 930 |
+
"loss": 30.47221984863281,
|
| 931 |
+
"step": 1190
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.10909090909090909,
|
| 935 |
+
"grad_norm": 12230697418752.0,
|
| 936 |
+
"learning_rate": 9.709701503543954e-06,
|
| 937 |
+
"loss": 30.745584106445314,
|
| 938 |
+
"step": 1200
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.10909090909090909,
|
| 942 |
+
"eval_loss": 30.373546600341797,
|
| 943 |
+
"eval_runtime": 2.2361,
|
| 944 |
+
"eval_samples_per_second": 1.789,
|
| 945 |
+
"eval_steps_per_second": 0.447,
|
| 946 |
+
"step": 1200
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.11,
|
| 950 |
+
"grad_norm": 4175631220736.0,
|
| 951 |
+
"learning_rate": 9.70488736952152e-06,
|
| 952 |
+
"loss": 31.123672485351562,
|
| 953 |
+
"step": 1210
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.11090909090909092,
|
| 957 |
+
"grad_norm": 3132377268224.0,
|
| 958 |
+
"learning_rate": 9.70003485918047e-06,
|
| 959 |
+
"loss": 30.429144287109374,
|
| 960 |
+
"step": 1220
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.11181818181818182,
|
| 964 |
+
"grad_norm": 10804191559680.0,
|
| 965 |
+
"learning_rate": 9.695144012101238e-06,
|
| 966 |
+
"loss": 30.479348754882814,
|
| 967 |
+
"step": 1230
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.11272727272727273,
|
| 971 |
+
"grad_norm": 1749328592896.0,
|
| 972 |
+
"learning_rate": 9.690214868176959e-06,
|
| 973 |
+
"loss": 30.477676391601562,
|
| 974 |
+
"step": 1240
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.11363636363636363,
|
| 978 |
+
"grad_norm": 11384572084224.0,
|
| 979 |
+
"learning_rate": 9.685247467613141e-06,
|
| 980 |
+
"loss": 31.031317138671874,
|
| 981 |
+
"step": 1250
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.11454545454545455,
|
| 985 |
+
"grad_norm": 10482409799680.0,
|
| 986 |
+
"learning_rate": 9.680241850927344e-06,
|
| 987 |
+
"loss": 30.4051025390625,
|
| 988 |
+
"step": 1260
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.11545454545454545,
|
| 992 |
+
"grad_norm": 4815250784256.0,
|
| 993 |
+
"learning_rate": 9.675198058948844e-06,
|
| 994 |
+
"loss": 30.68555603027344,
|
| 995 |
+
"step": 1270
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.11636363636363636,
|
| 999 |
+
"grad_norm": 15365955387392.0,
|
| 1000 |
+
"learning_rate": 9.670116132818298e-06,
|
| 1001 |
+
"loss": 30.3914306640625,
|
| 1002 |
+
"step": 1280
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.11727272727272728,
|
| 1006 |
+
"grad_norm": 6781031940096.0,
|
| 1007 |
+
"learning_rate": 9.664996113987415e-06,
|
| 1008 |
+
"loss": 30.56275634765625,
|
| 1009 |
+
"step": 1290
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.11818181818181818,
|
| 1013 |
+
"grad_norm": 3305072754688.0,
|
| 1014 |
+
"learning_rate": 9.659838044218612e-06,
|
| 1015 |
+
"loss": 30.5663818359375,
|
| 1016 |
+
"step": 1300
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.11818181818181818,
|
| 1020 |
+
"eval_loss": 30.511932373046875,
|
| 1021 |
+
"eval_runtime": 2.2289,
|
| 1022 |
+
"eval_samples_per_second": 1.795,
|
| 1023 |
+
"eval_steps_per_second": 0.449,
|
| 1024 |
+
"step": 1300
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.1190909090909091,
|
| 1028 |
+
"grad_norm": 2636002361344.0,
|
| 1029 |
+
"learning_rate": 9.65464196558468e-06,
|
| 1030 |
+
"loss": 31.185601806640626,
|
| 1031 |
+
"step": 1310
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.12,
|
| 1035 |
+
"grad_norm": 5977038913536.0,
|
| 1036 |
+
"learning_rate": 9.64940792046843e-06,
|
| 1037 |
+
"loss": 30.778460693359374,
|
| 1038 |
+
"step": 1320
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.12090909090909091,
|
| 1042 |
+
"grad_norm": 8069467078656.0,
|
| 1043 |
+
"learning_rate": 9.64413595156236e-06,
|
| 1044 |
+
"loss": 31.10213623046875,
|
| 1045 |
+
"step": 1330
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.12181818181818181,
|
| 1049 |
+
"grad_norm": 8260079321088.0,
|
| 1050 |
+
"learning_rate": 9.638826101868297e-06,
|
| 1051 |
+
"loss": 30.64208984375,
|
| 1052 |
+
"step": 1340
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.12272727272727273,
|
| 1056 |
+
"grad_norm": 1883967979520.0,
|
| 1057 |
+
"learning_rate": 9.633478414697051e-06,
|
| 1058 |
+
"loss": 30.968768310546874,
|
| 1059 |
+
"step": 1350
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.12363636363636364,
|
| 1063 |
+
"grad_norm": 5390394720256.0,
|
| 1064 |
+
"learning_rate": 9.628092933668062e-06,
|
| 1065 |
+
"loss": 30.793280029296874,
|
| 1066 |
+
"step": 1360
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.12454545454545454,
|
| 1070 |
+
"grad_norm": 3483799126016.0,
|
| 1071 |
+
"learning_rate": 9.62266970270904e-06,
|
| 1072 |
+
"loss": 31.143099975585937,
|
| 1073 |
+
"step": 1370
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.12545454545454546,
|
| 1077 |
+
"grad_norm": 5412520198144.0,
|
| 1078 |
+
"learning_rate": 9.617208766055613e-06,
|
| 1079 |
+
"loss": 31.14643249511719,
|
| 1080 |
+
"step": 1380
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.12636363636363637,
|
| 1084 |
+
"grad_norm": 5890521432064.0,
|
| 1085 |
+
"learning_rate": 9.611710168250961e-06,
|
| 1086 |
+
"loss": 30.540472412109374,
|
| 1087 |
+
"step": 1390
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.12727272727272726,
|
| 1091 |
+
"grad_norm": 2935032119296.0,
|
| 1092 |
+
"learning_rate": 9.606173954145453e-06,
|
| 1093 |
+
"loss": 30.9363037109375,
|
| 1094 |
+
"step": 1400
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.12727272727272726,
|
| 1098 |
+
"eval_loss": 30.66790008544922,
|
| 1099 |
+
"eval_runtime": 2.2296,
|
| 1100 |
+
"eval_samples_per_second": 1.794,
|
| 1101 |
+
"eval_steps_per_second": 0.449,
|
| 1102 |
+
"step": 1400
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.12818181818181817,
|
| 1106 |
+
"grad_norm": 14951601143808.0,
|
| 1107 |
+
"learning_rate": 9.600600168896285e-06,
|
| 1108 |
+
"loss": 31.166165161132813,
|
| 1109 |
+
"step": 1410
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.1290909090909091,
|
| 1113 |
+
"grad_norm": 18465345765376.0,
|
| 1114 |
+
"learning_rate": 9.594988857967107e-06,
|
| 1115 |
+
"loss": 30.707781982421874,
|
| 1116 |
+
"step": 1420
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.13,
|
| 1120 |
+
"grad_norm": 11442516393984.0,
|
| 1121 |
+
"learning_rate": 9.589340067127657e-06,
|
| 1122 |
+
"loss": 31.122097778320313,
|
| 1123 |
+
"step": 1430
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.13090909090909092,
|
| 1127 |
+
"grad_norm": 5658760445952.0,
|
| 1128 |
+
"learning_rate": 9.583653842453385e-06,
|
| 1129 |
+
"loss": 30.8050048828125,
|
| 1130 |
+
"step": 1440
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1318181818181818,
|
| 1134 |
+
"grad_norm": 9346052259840.0,
|
| 1135 |
+
"learning_rate": 9.577930230325073e-06,
|
| 1136 |
+
"loss": 31.267306518554687,
|
| 1137 |
+
"step": 1450
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.13272727272727272,
|
| 1141 |
+
"grad_norm": 17905546690560.0,
|
| 1142 |
+
"learning_rate": 9.572169277428466e-06,
|
| 1143 |
+
"loss": 31.230621337890625,
|
| 1144 |
+
"step": 1460
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.13363636363636364,
|
| 1148 |
+
"grad_norm": 9790963056640.0,
|
| 1149 |
+
"learning_rate": 9.566371030753882e-06,
|
| 1150 |
+
"loss": 30.92609558105469,
|
| 1151 |
+
"step": 1470
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.13454545454545455,
|
| 1155 |
+
"grad_norm": 9170735595520.0,
|
| 1156 |
+
"learning_rate": 9.56053553759584e-06,
|
| 1157 |
+
"loss": 31.646261596679686,
|
| 1158 |
+
"step": 1480
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.13545454545454547,
|
| 1162 |
+
"grad_norm": 22038278307840.0,
|
| 1163 |
+
"learning_rate": 9.554662845552657e-06,
|
| 1164 |
+
"loss": 30.207147216796876,
|
| 1165 |
+
"step": 1490
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.13636363636363635,
|
| 1169 |
+
"grad_norm": 11540973486080.0,
|
| 1170 |
+
"learning_rate": 9.548753002526076e-06,
|
| 1171 |
+
"loss": 31.0428955078125,
|
| 1172 |
+
"step": 1500
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.13636363636363635,
|
| 1176 |
+
"eval_loss": 30.903549194335938,
|
| 1177 |
+
"eval_runtime": 2.219,
|
| 1178 |
+
"eval_samples_per_second": 1.803,
|
| 1179 |
+
"eval_steps_per_second": 0.451,
|
| 1180 |
+
"step": 1500
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.13727272727272727,
|
| 1184 |
+
"grad_norm": 12314027753472.0,
|
| 1185 |
+
"learning_rate": 9.542806056720871e-06,
|
| 1186 |
+
"loss": 31.15526123046875,
|
| 1187 |
+
"step": 1510
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.13818181818181818,
|
| 1191 |
+
"grad_norm": 15213582614528.0,
|
| 1192 |
+
"learning_rate": 9.536822056644446e-06,
|
| 1193 |
+
"loss": 31.196783447265624,
|
| 1194 |
+
"step": 1520
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.1390909090909091,
|
| 1198 |
+
"grad_norm": 5029657837568.0,
|
| 1199 |
+
"learning_rate": 9.530801051106449e-06,
|
| 1200 |
+
"loss": 30.717410278320312,
|
| 1201 |
+
"step": 1530
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.14,
|
| 1205 |
+
"grad_norm": 3814568230912.0,
|
| 1206 |
+
"learning_rate": 9.524743089218371e-06,
|
| 1207 |
+
"loss": 31.505865478515624,
|
| 1208 |
+
"step": 1540
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.1409090909090909,
|
| 1212 |
+
"grad_norm": 11058694586368.0,
|
| 1213 |
+
"learning_rate": 9.518648220393143e-06,
|
| 1214 |
+
"loss": 31.2138427734375,
|
| 1215 |
+
"step": 1550
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.14181818181818182,
|
| 1219 |
+
"grad_norm": 16550942736384.0,
|
| 1220 |
+
"learning_rate": 9.512516494344733e-06,
|
| 1221 |
+
"loss": 30.97614440917969,
|
| 1222 |
+
"step": 1560
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.14272727272727273,
|
| 1226 |
+
"grad_norm": 14170502201344.0,
|
| 1227 |
+
"learning_rate": 9.506347961087746e-06,
|
| 1228 |
+
"loss": 31.417559814453124,
|
| 1229 |
+
"step": 1570
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.14363636363636365,
|
| 1233 |
+
"grad_norm": 14292605730816.0,
|
| 1234 |
+
"learning_rate": 9.500142670937007e-06,
|
| 1235 |
+
"loss": 31.37445983886719,
|
| 1236 |
+
"step": 1580
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.14454545454545453,
|
| 1240 |
+
"grad_norm": 19206800146432.0,
|
| 1241 |
+
"learning_rate": 9.49390067450716e-06,
|
| 1242 |
+
"loss": 31.374490356445314,
|
| 1243 |
+
"step": 1590
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.14545454545454545,
|
| 1247 |
+
"grad_norm": 27451564490752.0,
|
| 1248 |
+
"learning_rate": 9.487622022712249e-06,
|
| 1249 |
+
"loss": 31.736862182617188,
|
| 1250 |
+
"step": 1600
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.14545454545454545,
|
| 1254 |
+
"eval_loss": 31.390056610107422,
|
| 1255 |
+
"eval_runtime": 2.2392,
|
| 1256 |
+
"eval_samples_per_second": 1.786,
|
| 1257 |
+
"eval_steps_per_second": 0.447,
|
| 1258 |
+
"step": 1600
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.14636363636363636,
|
| 1262 |
+
"grad_norm": 10258579718144.0,
|
| 1263 |
+
"learning_rate": 9.481306766765305e-06,
|
| 1264 |
+
"loss": 31.774203491210937,
|
| 1265 |
+
"step": 1610
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.14727272727272728,
|
| 1269 |
+
"grad_norm": 10325241888768.0,
|
| 1270 |
+
"learning_rate": 9.474954958177926e-06,
|
| 1271 |
+
"loss": 31.747982788085938,
|
| 1272 |
+
"step": 1620
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.1481818181818182,
|
| 1276 |
+
"grad_norm": 13619729268736.0,
|
| 1277 |
+
"learning_rate": 9.468566648759864e-06,
|
| 1278 |
+
"loss": 31.699578857421876,
|
| 1279 |
+
"step": 1630
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.14909090909090908,
|
| 1283 |
+
"grad_norm": 11932865134592.0,
|
| 1284 |
+
"learning_rate": 9.46214189061859e-06,
|
| 1285 |
+
"loss": 32.11009826660156,
|
| 1286 |
+
"step": 1640
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.15,
|
| 1290 |
+
"grad_norm": 19572193230848.0,
|
| 1291 |
+
"learning_rate": 9.455680736158881e-06,
|
| 1292 |
+
"loss": 31.782620239257813,
|
| 1293 |
+
"step": 1650
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.1509090909090909,
|
| 1297 |
+
"grad_norm": 3280040361984.0,
|
| 1298 |
+
"learning_rate": 9.449183238082384e-06,
|
| 1299 |
+
"loss": 31.564590454101562,
|
| 1300 |
+
"step": 1660
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.15181818181818182,
|
| 1304 |
+
"grad_norm": 7981176979456.0,
|
| 1305 |
+
"learning_rate": 9.442649449387195e-06,
|
| 1306 |
+
"loss": 32.106405639648436,
|
| 1307 |
+
"step": 1670
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.15272727272727274,
|
| 1311 |
+
"grad_norm": 11420098887680.0,
|
| 1312 |
+
"learning_rate": 9.436079423367413e-06,
|
| 1313 |
+
"loss": 31.888082885742186,
|
| 1314 |
+
"step": 1680
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.15363636363636363,
|
| 1318 |
+
"grad_norm": 5575196278784.0,
|
| 1319 |
+
"learning_rate": 9.429473213612724e-06,
|
| 1320 |
+
"loss": 32.15013122558594,
|
| 1321 |
+
"step": 1690
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.15454545454545454,
|
| 1325 |
+
"grad_norm": 14530922938368.0,
|
| 1326 |
+
"learning_rate": 9.422830874007944e-06,
|
| 1327 |
+
"loss": 32.137445068359376,
|
| 1328 |
+
"step": 1700
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.15454545454545454,
|
| 1332 |
+
"eval_loss": 32.02363586425781,
|
| 1333 |
+
"eval_runtime": 2.2508,
|
| 1334 |
+
"eval_samples_per_second": 1.777,
|
| 1335 |
+
"eval_steps_per_second": 0.444,
|
| 1336 |
+
"step": 1700
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.15545454545454546,
|
| 1340 |
+
"grad_norm": 3318463332352.0,
|
| 1341 |
+
"learning_rate": 9.416152458732595e-06,
|
| 1342 |
+
"loss": 32.3702392578125,
|
| 1343 |
+
"step": 1710
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.15636363636363637,
|
| 1347 |
+
"grad_norm": 30810249887744.0,
|
| 1348 |
+
"learning_rate": 9.409438022260457e-06,
|
| 1349 |
+
"loss": 32.926510620117185,
|
| 1350 |
+
"step": 1720
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1572727272727273,
|
| 1354 |
+
"grad_norm": 21961272983552.0,
|
| 1355 |
+
"learning_rate": 9.40268761935912e-06,
|
| 1356 |
+
"loss": 32.80148620605469,
|
| 1357 |
+
"step": 1730
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.15818181818181817,
|
| 1361 |
+
"grad_norm": 7398799966208.0,
|
| 1362 |
+
"learning_rate": 9.395901305089545e-06,
|
| 1363 |
+
"loss": 32.54508666992187,
|
| 1364 |
+
"step": 1740
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.1590909090909091,
|
| 1368 |
+
"grad_norm": 19706209632256.0,
|
| 1369 |
+
"learning_rate": 9.38907913480561e-06,
|
| 1370 |
+
"loss": 32.26361999511719,
|
| 1371 |
+
"step": 1750
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.16,
|
| 1375 |
+
"grad_norm": 4903741685760.0,
|
| 1376 |
+
"learning_rate": 9.382221164153656e-06,
|
| 1377 |
+
"loss": 31.852926635742186,
|
| 1378 |
+
"step": 1760
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.16090909090909092,
|
| 1382 |
+
"grad_norm": 5960596193280.0,
|
| 1383 |
+
"learning_rate": 9.37532744907204e-06,
|
| 1384 |
+
"loss": 32.537167358398435,
|
| 1385 |
+
"step": 1770
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1618181818181818,
|
| 1389 |
+
"grad_norm": 20588651347968.0,
|
| 1390 |
+
"learning_rate": 9.368398045790679e-06,
|
| 1391 |
+
"loss": 32.38728332519531,
|
| 1392 |
+
"step": 1780
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.16272727272727272,
|
| 1396 |
+
"grad_norm": 12039432962048.0,
|
| 1397 |
+
"learning_rate": 9.361433010830578e-06,
|
| 1398 |
+
"loss": 32.65169982910156,
|
| 1399 |
+
"step": 1790
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.16363636363636364,
|
| 1403 |
+
"grad_norm": 5257930735616.0,
|
| 1404 |
+
"learning_rate": 9.354432401003387e-06,
|
| 1405 |
+
"loss": 33.31449584960937,
|
| 1406 |
+
"step": 1800
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.16363636363636364,
|
| 1410 |
+
"eval_loss": 32.65924072265625,
|
| 1411 |
+
"eval_runtime": 2.2228,
|
| 1412 |
+
"eval_samples_per_second": 1.8,
|
| 1413 |
+
"eval_steps_per_second": 0.45,
|
| 1414 |
+
"step": 1800
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.16454545454545455,
|
| 1418 |
+
"grad_norm": 19231353602048.0,
|
| 1419 |
+
"learning_rate": 9.347396273410926e-06,
|
| 1420 |
+
"loss": 32.776092529296875,
|
| 1421 |
+
"step": 1810
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.16545454545454547,
|
| 1425 |
+
"grad_norm": 16898675703808.0,
|
| 1426 |
+
"learning_rate": 9.340324685444721e-06,
|
| 1427 |
+
"loss": 33.000860595703124,
|
| 1428 |
+
"step": 1820
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.16636363636363635,
|
| 1432 |
+
"grad_norm": 68008458321920.0,
|
| 1433 |
+
"learning_rate": 9.333217694785543e-06,
|
| 1434 |
+
"loss": 32.81432189941406,
|
| 1435 |
+
"step": 1830
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.16727272727272727,
|
| 1439 |
+
"grad_norm": 15164053127168.0,
|
| 1440 |
+
"learning_rate": 9.326075359402926e-06,
|
| 1441 |
+
"loss": 33.27540893554688,
|
| 1442 |
+
"step": 1840
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.16818181818181818,
|
| 1446 |
+
"grad_norm": 22001701879808.0,
|
| 1447 |
+
"learning_rate": 9.3188977375547e-06,
|
| 1448 |
+
"loss": 33.165444946289064,
|
| 1449 |
+
"step": 1850
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.1690909090909091,
|
| 1453 |
+
"grad_norm": 22931172229120.0,
|
| 1454 |
+
"learning_rate": 9.31168488778652e-06,
|
| 1455 |
+
"loss": 33.036984252929685,
|
| 1456 |
+
"step": 1860
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.17,
|
| 1460 |
+
"grad_norm": 34937067536384.0,
|
| 1461 |
+
"learning_rate": 9.304436868931384e-06,
|
| 1462 |
+
"loss": 33.12846069335937,
|
| 1463 |
+
"step": 1870
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.1709090909090909,
|
| 1467 |
+
"grad_norm": 17089225031680.0,
|
| 1468 |
+
"learning_rate": 9.297153740109149e-06,
|
| 1469 |
+
"loss": 33.338644409179686,
|
| 1470 |
+
"step": 1880
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.17181818181818181,
|
| 1474 |
+
"grad_norm": 16702327750656.0,
|
| 1475 |
+
"learning_rate": 9.289835560726054e-06,
|
| 1476 |
+
"loss": 32.967626953125,
|
| 1477 |
+
"step": 1890
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.17272727272727273,
|
| 1481 |
+
"grad_norm": 47055904964608.0,
|
| 1482 |
+
"learning_rate": 9.28248239047424e-06,
|
| 1483 |
+
"loss": 33.560003662109374,
|
| 1484 |
+
"step": 1900
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.17272727272727273,
|
| 1488 |
+
"eval_loss": 33.12340545654297,
|
| 1489 |
+
"eval_runtime": 2.2364,
|
| 1490 |
+
"eval_samples_per_second": 1.789,
|
| 1491 |
+
"eval_steps_per_second": 0.447,
|
| 1492 |
+
"step": 1900
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.17363636363636364,
|
| 1496 |
+
"grad_norm": 39783350927360.0,
|
| 1497 |
+
"learning_rate": 9.275094289331255e-06,
|
| 1498 |
+
"loss": 33.179928588867185,
|
| 1499 |
+
"step": 1910
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.17454545454545456,
|
| 1503 |
+
"grad_norm": 24787021725696.0,
|
| 1504 |
+
"learning_rate": 9.267671317559564e-06,
|
| 1505 |
+
"loss": 33.633059692382815,
|
| 1506 |
+
"step": 1920
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.17545454545454545,
|
| 1510 |
+
"grad_norm": 59121021747200.0,
|
| 1511 |
+
"learning_rate": 9.260213535706064e-06,
|
| 1512 |
+
"loss": 33.45337829589844,
|
| 1513 |
+
"step": 1930
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.17636363636363636,
|
| 1517 |
+
"grad_norm": 38006677307392.0,
|
| 1518 |
+
"learning_rate": 9.252721004601587e-06,
|
| 1519 |
+
"loss": 33.815695190429686,
|
| 1520 |
+
"step": 1940
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.17727272727272728,
|
| 1524 |
+
"grad_norm": 23238140755968.0,
|
| 1525 |
+
"learning_rate": 9.245193785360407e-06,
|
| 1526 |
+
"loss": 33.58963623046875,
|
| 1527 |
+
"step": 1950
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.1781818181818182,
|
| 1531 |
+
"grad_norm": 16146431475712.0,
|
| 1532 |
+
"learning_rate": 9.237631939379731e-06,
|
| 1533 |
+
"loss": 33.774557495117186,
|
| 1534 |
+
"step": 1960
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.17909090909090908,
|
| 1538 |
+
"grad_norm": 73825001668608.0,
|
| 1539 |
+
"learning_rate": 9.230035528339212e-06,
|
| 1540 |
+
"loss": 32.61050720214844,
|
| 1541 |
+
"step": 1970
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.18,
|
| 1545 |
+
"grad_norm": 77602744172544.0,
|
| 1546 |
+
"learning_rate": 9.222404614200437e-06,
|
| 1547 |
+
"loss": 34.036373901367185,
|
| 1548 |
+
"step": 1980
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.1809090909090909,
|
| 1552 |
+
"grad_norm": 52128609468416.0,
|
| 1553 |
+
"learning_rate": 9.214739259206424e-06,
|
| 1554 |
+
"loss": 33.779693603515625,
|
| 1555 |
+
"step": 1990
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.18181818181818182,
|
| 1559 |
+
"grad_norm": 4887862050816.0,
|
| 1560 |
+
"learning_rate": 9.207039525881117e-06,
|
| 1561 |
+
"loss": 33.33510131835938,
|
| 1562 |
+
"step": 2000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.18181818181818182,
|
| 1566 |
+
"eval_loss": 33.294410705566406,
|
| 1567 |
+
"eval_runtime": 2.2304,
|
| 1568 |
+
"eval_samples_per_second": 1.793,
|
| 1569 |
+
"eval_steps_per_second": 0.448,
|
| 1570 |
+
"step": 2000
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 10,
|
|
|
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
+
"total_flos": 9059847634944000.0,
|
| 1591 |
"train_batch_size": 1,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|