Training in progress, step 168, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab2bb080e5725a185604043d94dc96dc2a08209f1ccfd6774368070e427a0bd
+oid sha256:989778e8b698fad8d462e0852da070f835c82e6a80c1d783c731e18e64ac3858
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7fc9ab5117b3ad2472c2713dd00b876ee8e863af5152843580583959e449f9
+oid sha256:227df882c930be630d395f6b4c56c1219f58848060d5754624d5ed8ec643b762
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00328545513b592b6bf311a002e087bb048e374276594cf37ee8782d28887fc
+oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0066966954996611795,
+  "epoch": 0.008928927332881573,
   "eval_steps": 42,
-  "global_step": 126,
+  "global_step": 168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -333,6 +333,112 @@
       "eval_samples_per_second": 13.371,
       "eval_steps_per_second": 1.672,
       "step": 126
+    },
+    {
+      "epoch": 0.0068561406306054925,
+      "grad_norm": NaN,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 0.007015585761549806,
+      "grad_norm": NaN,
+      "learning_rate": 8.54684960502629e-05,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 0.00717503089249412,
+      "grad_norm": NaN,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.007334476023438434,
+      "grad_norm": NaN,
+      "learning_rate": 8.408689080954998e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.007493921154382748,
+      "grad_norm": NaN,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.0076533662853270614,
+      "grad_norm": NaN,
+      "learning_rate": 8.265484918766243e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.007812811416271376,
+      "grad_norm": NaN,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.00797225654721569,
+      "grad_norm": NaN,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.008131701678160004,
+      "grad_norm": NaN,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 0.008291146809104318,
+      "grad_norm": NaN,
+      "learning_rate": 7.964800392625129e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.008450591940048631,
+      "grad_norm": NaN,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.008610037070992945,
+      "grad_norm": NaN,
+      "learning_rate": 7.807764934001874e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.008769482201937259,
+      "grad_norm": NaN,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.008928927332881573,
+      "grad_norm": NaN,
+      "learning_rate": 7.646574989618938e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.008928927332881573,
+      "eval_loss": NaN,
+      "eval_runtime": 2369.2438,
+      "eval_samples_per_second": 13.375,
+      "eval_steps_per_second": 1.672,
+      "step": 168
     }
   ],
   "logging_steps": 3,
@@ -352,7 +458,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9233548129009664e+17,
+  "total_flos": 2.5607017999210906e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null