Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c850d80387e35ae9402cf199f1ffe646cdd2ff501a277ee0fa93cef5863a581
+oid sha256:8c0b631f57fa5e1040a4197f03d00dd4e8074cb0111c69f7e4e6d4c1614a3175
 size 168149074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20e890e74cc474a749f7dc9ce6b2dee88aaaf8c34a06426aebf5c6a83d0b60a
+oid sha256:d517981fb1239875056a37232c549adb3ba8b785c8dbdc19794f8efed6f4c49f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c53fe6367258c05bc5bf6cb83193f3a28ee2a01262ac897cdfae2a4ce2cbe8
+oid sha256:7d2d26303580d01c4770109b5da08efd2fefa5831fc16d9e66248e2c910aa23f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8082686e713c3d03f98719bc84a4044b4b702fcfe0fb3482bfaab0d0e9d0eafa
+oid sha256:c1dc967e85a775067e5963d36fa86c5cc21127f990cd3262a9870a831ad20743
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2b7b671096ad3234acee503b57e34b1a9925ffdde8d1c88ce3d2fea18e79b4
+oid sha256:80304235ac45040dbdbf8b5a96db76f80984a0e317baa1e9b9e03a61574e331f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a125c681316bfce03f3558f5956b9c0ad33dcb35c93b2ae66a440f25335c8901
+oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2857142857142857,
+  "epoch": 0.35714285714285715,
   "eval_steps": 3,
-  "global_step": 12,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 32.029,
       "eval_steps_per_second": 8.007,
       "step": 12
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "eval_loss": NaN,
+      "eval_runtime": 1.127,
+      "eval_samples_per_second": 31.944,
+      "eval_steps_per_second": 7.986,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7755816782200832e+16,
+  "total_flos": 2.219477097775104e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null