Training in progress, step 462, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89eb8b5506b906a6926d8e9eca22e01089b1a5aa31aa0276c9e2b5e3bbac728
+oid sha256:c936e33e771d64f59c0320ef76f702c8baefb76b8a6061a149f15476d3954e7a
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8beaf170005db0771c982de7e9d403f811e69dfcf7962b6a164501a12a64ee78
+oid sha256:902a971a6dd3166551a11be2e45b39a3a9ecf36ab45d22f6eb5fc1988a7caf24
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4804117815270232,
+  "epoch": 0.5284529596797255,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 14.383,
       "eval_steps_per_second": 3.603,
       "step": 420
+    },
+    {
+      "epoch": 0.48384329425221617,
+      "grad_norm": NaN,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 0.0,
+      "step": 423
+    },
+    {
+      "epoch": 0.4872748069774092,
+      "grad_norm": NaN,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 0.0,
+      "step": 426
+    },
+    {
+      "epoch": 0.49070631970260226,
+      "grad_norm": NaN,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 0.0,
+      "step": 429
+    },
+    {
+      "epoch": 0.49413783242779524,
+      "grad_norm": NaN,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 0.0,
+      "step": 432
+    },
+    {
+      "epoch": 0.4975693451529883,
+      "grad_norm": NaN,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 0.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.5010008578781813,
+      "grad_norm": NaN,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 0.0,
+      "step": 438
+    },
+    {
+      "epoch": 0.5044323706033743,
+      "grad_norm": NaN,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 0.0,
+      "step": 441
+    },
+    {
+      "epoch": 0.5078638833285674,
+      "grad_norm": NaN,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 0.0,
+      "step": 444
+    },
+    {
+      "epoch": 0.5112953960537604,
+      "grad_norm": NaN,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 0.0,
+      "step": 447
+    },
+    {
+      "epoch": 0.5147269087789534,
+      "grad_norm": NaN,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.5181584215041464,
+      "grad_norm": NaN,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 0.0,
+      "step": 453
+    },
+    {
+      "epoch": 0.5215899342293394,
+      "grad_norm": NaN,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 0.0,
+      "step": 456
+    },
+    {
+      "epoch": 0.5250214469545325,
+      "grad_norm": NaN,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 0.0,
+      "step": 459
+    },
+    {
+      "epoch": 0.5284529596797255,
+      "grad_norm": NaN,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 0.0,
+      "step": 462
+    },
+    {
+      "epoch": 0.5284529596797255,
+      "eval_loss": NaN,
+      "eval_runtime": 102.5202,
+      "eval_samples_per_second": 14.368,
+      "eval_steps_per_second": 3.599,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.971932478439424e+17,
+  "total_flos": 6.569125726283366e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null