Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca8743bd1d21a27cc815f4e04b23976405f2907fa0855f65dd0cfa438e58d4a
+oid sha256:f1e26bf3a339e3a31a9b595cef472952414206620319d72fb49f8f7b4bed1b61
 size 124606

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9fa68058b51f878a504fd869bbb0aa808d413159018713f726e15e22dcd754f
+oid sha256:04732c8c2e16f0dfe69365b1325d4a79b777de313cb9ad5a334db046def79d61
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038a1e0a8d7736898683844ad42a7d811149eb9e7edae3ca77503a590ed41213
+oid sha256:a8a51a76ac2870b6151b18050fb3209a9f46d244ed22a262eea2fe28a9b1969e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2064516129032258,
+  "epoch": 0.4129032258064516,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 393.51,
       "eval_steps_per_second": 99.072,
       "step": 13
+    },
+    {
+      "epoch": 0.22233250620347395,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.23821339950372208,
+      "grad_norm": NaN,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.2540942928039702,
+      "grad_norm": NaN,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.2699751861042184,
+      "grad_norm": NaN,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.2858560794044665,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.30173697270471467,
+      "grad_norm": NaN,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.3176178660049628,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.33349875930521095,
+      "grad_norm": NaN,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.34937965260545906,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.3652605459057072,
+      "grad_norm": NaN,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.38114143920595533,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.3970223325062035,
+      "grad_norm": NaN,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "eval_loss": NaN,
+      "eval_runtime": 1.0823,
+      "eval_samples_per_second": 392.688,
+      "eval_steps_per_second": 98.865,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 43390007771136.0,
+  "total_flos": 86780015542272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null