Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc082dac1aeb46f9ac55ca99c65385b0e240df4c8f1cc27ede41faf0e12d5ff0
+oid sha256:2c879f385b422df3fca5228513f3bae4387ed9e62fd092ebca498251ff96dd82
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54e83455838b8285a80087d91dcce55188194c5a5c7c15f55ed356fc18324e1
+oid sha256:24a7fb993881a603ce7c7932d42c04cd7697ed7fbc569bff9d0a019e4b731376
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e300d124805e85d165696b1ab015335ceda48c16b90205e1b09c9d3b63767971
+oid sha256:fdfd1692f8c3e07bd7f0386306b8a4dc7984bed19ffb5f1fb77db39dc898e24a
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d79de33a1dadebecdc6710fbbebc54394b36ff40dc16ce7c4b9cd325b8d41b2
+oid sha256:2a64456a544b4e3b448418c8f8b53a190245445274955bebd8d3b8522bf98ccb
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f148927d78bff2b3194a8dac67d57033d9ed30fb38f0b33bdb5e3be6ecfc774
+oid sha256:7240fa7db242cb3d6601e7b6ac5c0a2f2bebee276959a658a3c866c5e8a6d292
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4194147067766931,
-  "global_step": 16000,
+  "epoch": 0.5242683834708665,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,11 +198,59 @@
       "learning_rate": 3.1271392346753284e-05,
       "loss": 1.4551,
       "step": 16000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.0269864639674983e-05,
+      "loss": 1.4527,
+      "step": 16500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9259403172138987e-05,
+      "loss": 1.4356,
+      "step": 17000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.82437623590975e-05,
+      "loss": 1.4362,
+      "step": 17500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7220593841620623e-05,
+      "loss": 1.432,
+      "step": 18000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6193660852983415e-05,
+      "loss": 1.4234,
+      "step": 18500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.516676307917844e-05,
+      "loss": 1.436,
+      "step": 19000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4137526132994945e-05,
+      "loss": 1.4238,
+      "step": 19500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3109751299304977e-05,
+      "loss": 1.41,
+      "step": 20000
     }
   ],
   "max_steps": 38148,
   "num_train_epochs": 1,
-  "total_flos": 1.7648755970310144e+16,
+  "total_flos": 2.203967601635328e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54e83455838b8285a80087d91dcce55188194c5a5c7c15f55ed356fc18324e1
+oid sha256:24a7fb993881a603ce7c7932d42c04cd7697ed7fbc569bff9d0a019e4b731376
 size 1944201353

runs/Jun16_15-16-02_9a4f5f66b33d/events.out.tfevents.1686930096.9a4f5f66b33d.224.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eef1ee6af72ade29844b19974c89874a0bb78d9690d67bd7b44fde532ddd478
-size 5718
+oid sha256:d3ddbc9058e2a8a8eb81aba89a2cdbd4db12323f86913da6db85e0ef1ec52a4e
+size 6998