Training in progress, step 210, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989778e8b698fad8d462e0852da070f835c82e6a80c1d783c731e18e64ac3858
+oid sha256:d48f02537ae2e81d3c8124f997d691ee108d3dc0b12e1ad53b612c4e57ddd73e
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227df882c930be630d395f6b4c56c1219f58848060d5754624d5ed8ec643b762
+oid sha256:492da289a127a48721163632337bf0651c18833a78d45796b5cf96803839e7ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
+oid sha256:4bd95a1db0e917ddf11b12a343f06e907fcec4b81104002e2471b4778587b465
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008928927332881573,
+  "epoch": 0.011161159166101966,
   "eval_steps": 42,
-  "global_step": 168,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -439,6 +439,112 @@
       "eval_samples_per_second": 13.375,
       "eval_steps_per_second": 1.672,
       "step": 168
+    },
+    {
+      "epoch": 0.009088372463825886,
+      "grad_norm": NaN,
+      "learning_rate": 7.564496387029532e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 0.0092478175947702,
+      "grad_norm": NaN,
+      "learning_rate": 7.481469062821252e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 0.009407262725714514,
+      "grad_norm": NaN,
+      "learning_rate": 7.39752373250527e-05,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 0.009566707856658828,
+      "grad_norm": NaN,
+      "learning_rate": 7.312691451204178e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.009726152987603142,
+      "grad_norm": NaN,
+      "learning_rate": 7.227003602163295e-05,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 0.009885598118547455,
+      "grad_norm": NaN,
+      "learning_rate": 7.14049188514063e-05,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 0.01004504324949177,
+      "grad_norm": NaN,
+      "learning_rate": 7.05318830467969e-05,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 0.010204488380436083,
+      "grad_norm": NaN,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 0.010363933511380397,
+      "grad_norm": NaN,
+      "learning_rate": 6.876335024396872e-05,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.01052337864232471,
+      "grad_norm": NaN,
+      "learning_rate": 6.786850750493006e-05,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 0.010682823773269024,
+      "grad_norm": NaN,
+      "learning_rate": 6.696705440782938e-05,
+      "loss": 0.0,
+      "step": 201
+    },
+    {
+      "epoch": 0.010842268904213338,
+      "grad_norm": NaN,
+      "learning_rate": 6.605932444038229e-05,
+      "loss": 0.0,
+      "step": 204
+    },
+    {
+      "epoch": 0.011001714035157652,
+      "grad_norm": NaN,
+      "learning_rate": 6.514565341239861e-05,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 0.011161159166101966,
+      "grad_norm": NaN,
+      "learning_rate": 6.422637933155162e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.011161159166101966,
+      "eval_loss": NaN,
+      "eval_runtime": 2369.0806,
+      "eval_samples_per_second": 13.376,
+      "eval_steps_per_second": 1.672,
+      "step": 210
     }
   ],
   "logging_steps": 3,
@@ -458,7 +564,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5607017999210906e+17,
+  "total_flos": 3.198048786941215e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null