Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42cc29fdb0a937b24c5dbfede7b38f377a08639acc88a98637f53ea9423147d
+oid sha256:614e1f5db7ace5e7c0fbc123317ae6880ca9c41394d0594e2ff8f16c85a2aed7
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f188e6e66f93a0aedb36e65214cf8103c56a6fc686966637f94bd0e398473bac
+oid sha256:b14ecaf10f867d641510ce53dbd9769d9f0621e33faaf8ef0ef592d94d206124
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d8b404c7757cd0e1f61a34ff8e01b9566231cbcef6729e663ef610ad7df9ae
+oid sha256:e4326bed15afbe95f7975c90fd86a88b02f65eb2b3a84aa0cf7b3dd837f7ac4b
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4795389048991354,
+  "epoch": 0.7193083573487031,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 41.469,
       "eval_steps_per_second": 10.424,
       "step": 26
+    },
+    {
+      "epoch": 0.4979827089337176,
+      "grad_norm": NaN,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.5164265129682997,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.5348703170028818,
+      "grad_norm": NaN,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.5717579250720461,
+      "grad_norm": NaN,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5902017291066283,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.6086455331412104,
+      "grad_norm": NaN,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.6270893371757925,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.6455331412103746,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.6639769452449568,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.6824207492795389,
+      "grad_norm": NaN,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.700864553314121,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.7193083573487031,
+      "grad_norm": NaN,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.7193083573487031,
+      "eval_loss": NaN,
+      "eval_runtime": 8.8268,
+      "eval_samples_per_second": 41.464,
+      "eval_steps_per_second": 10.423,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.999169891434496e+16,
+  "total_flos": 4.498754837151744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null