training state at step 35

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41379310344827586,
+  "epoch": 0.4827586206896552,
   "eval_steps": 1,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,81 @@
       "eval_samples_per_second": 1.144,
       "eval_steps_per_second": 0.572,
       "step": 29
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.320786237716675,
+      "learning_rate": 4.9790502530660635e-05,
+      "loss": 1.4691,
+      "step": 30
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "eval_loss": 0.9836109280586243,
+      "eval_runtime": 16.9043,
+      "eval_samples_per_second": 1.183,
+      "eval_steps_per_second": 0.592,
+      "step": 30
+    },
+    {
+      "epoch": 0.42758620689655175,
+      "grad_norm": 2.1385531425476074,
+      "learning_rate": 4.9734953280908904e-05,
+      "loss": 1.4696,
+      "step": 31
+    },
+    {
+      "epoch": 0.42758620689655175,
+      "eval_loss": 0.976610541343689,
+      "eval_runtime": 17.3486,
+      "eval_samples_per_second": 1.153,
+      "eval_steps_per_second": 0.576,
+      "step": 31
+    },
+    {
+      "epoch": 0.4413793103448276,
+      "grad_norm": 2.2254769802093506,
+      "learning_rate": 4.967291771834727e-05,
+      "loss": 1.531,
+      "step": 32
+    },
+    {
+      "epoch": 0.4413793103448276,
+      "eval_loss": 0.9718761444091797,
+      "eval_runtime": 17.5285,
+      "eval_samples_per_second": 1.141,
+      "eval_steps_per_second": 0.57,
+      "step": 32
+    },
+    {
+      "epoch": 0.45517241379310347,
+      "grad_norm": 2.34843373298645,
+      "learning_rate": 4.960441211072686e-05,
+      "loss": 1.5484,
+      "step": 33
+    },
+    {
+      "epoch": 0.45517241379310347,
+      "eval_loss": 0.9682589769363403,
+      "eval_runtime": 17.5952,
+      "eval_samples_per_second": 1.137,
+      "eval_steps_per_second": 0.568,
+      "step": 33
+    },
+    {
+      "epoch": 0.4689655172413793,
+      "grad_norm": 1.9610539674758911,
+      "learning_rate": 4.9529454422455976e-05,
+      "loss": 1.3204,
+      "step": 34
+    },
+    {
+      "epoch": 0.4689655172413793,
+      "eval_loss": 0.9610344767570496,
+      "eval_runtime": 17.6076,
+      "eval_samples_per_second": 1.136,
+      "eval_steps_per_second": 0.568,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -461,7 +536,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.786199396619059e+16,
+  "total_flos": 4.450920354589901e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null