Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3666e7a6ea93596993c6d4f0f8e772092acd93b430c0d983f1f9a02f3d327917
+oid sha256:2c850d80387e35ae9402cf199f1ffe646cdd2ff501a277ee0fa93cef5863a581
 size 168149074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7702a621041ab17939550eac6430a3e9aa07ce6772648c1fbdb7268e1b01c9
+oid sha256:b20e890e74cc474a749f7dc9ce6b2dee88aaaf8c34a06426aebf5c6a83d0b60a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e1a13078c908bc2f98627872b482fdc1df86c5723e3c94011a1c6fa67d609d
+oid sha256:97c53fe6367258c05bc5bf6cb83193f3a28ee2a01262ac897cdfae2a4ce2cbe8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49d0a5a1be8d097e2f2422239656e8d0f9ab68e169fb94db3b15958b67c5cb5
+oid sha256:8082686e713c3d03f98719bc84a4044b4b702fcfe0fb3482bfaab0d0e9d0eafa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117498f142890dae2994492453bf6b6e9a451a0e3fd4382bc37ecfff4455b98c
+oid sha256:7a2b7b671096ad3234acee503b57e34b1a9925ffdde8d1c88ce3d2fea18e79b4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:a125c681316bfce03f3558f5956b9c0ad33dcb35c93b2ae66a440f25335c8901
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21428571428571427,
+  "epoch": 0.2857142857142857,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 31.994,
       "eval_steps_per_second": 7.999,
       "step": 9
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_loss": NaN,
+      "eval_runtime": 1.124,
+      "eval_samples_per_second": 32.029,
+      "eval_steps_per_second": 8.007,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3316862586650624e+16,
+  "total_flos": 1.7755816782200832e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null