Training in progress, step 24, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9414035a263696e37060fa959a03ec8e17fc44763468a3b5369ba73a6ac77878
+oid sha256:a86ba9385bb768d29deab79937c811ef79a601d619335c9e94af62c9f11709ce
 size 70667778

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b56707cf0118f1c71ed1325203a29952e82af4ced399f22eab06a5f52bf685e
+oid sha256:ff1de991a5e8b028670d79166d941671fcf1f558f0044b08eaf5154d066f0048
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac52da7845dfee7f009bf115e99d18473acfef24b7a31c6c60182154e212e940
+oid sha256:0a5995616407d184ecedacf74ac31cd0731474c7e2323f03405d89945bad93ff
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab5119e8dfb2acf8726e3995087ca3cdec10190f996fbdc638954b26a5cddc2
+oid sha256:b375860c66674ec9637bb873a1ff676ec525ee5502840d2f1d554d4237b8f0c4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.256,
+  "epoch": 0.512,
   "eval_steps": 12,
-  "global_step": 12,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -107,6 +107,98 @@
       "eval_samples_per_second": 21.668,
       "eval_steps_per_second": 5.486,
       "step": 12
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": NaN,
+      "learning_rate": 3.6e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 3.8e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": NaN,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": NaN,
+      "learning_rate": 4.8e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.512,
+      "eval_loss": NaN,
+      "eval_runtime": 3.751,
+      "eval_samples_per_second": 21.061,
+      "eval_steps_per_second": 5.332,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -126,7 +218,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1730290321981440.0,
+  "total_flos": 3460580643962880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null