training state at step 85

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.103448275862069,
+  "epoch": 1.1724137931034484,
   "eval_steps": 1,
-  "global_step": 80,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1162,6 +1162,81 @@
       "eval_samples_per_second": 1.107,
       "eval_steps_per_second": 0.554,
       "step": 79
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 2.047912836074829,
+      "learning_rate": 4.997050398198977e-05,
+      "loss": 1.0507,
+      "step": 80
+    },
+    {
+      "epoch": 1.103448275862069,
+      "eval_loss": 0.7239590883255005,
+      "eval_runtime": 18.4343,
+      "eval_samples_per_second": 1.085,
+      "eval_steps_per_second": 0.542,
+      "step": 80
+    },
+    {
+      "epoch": 1.1172413793103448,
+      "grad_norm": 2.004422664642334,
+      "learning_rate": 4.9947570655942796e-05,
+      "loss": 0.9516,
+      "step": 81
+    },
+    {
+      "epoch": 1.1172413793103448,
+      "eval_loss": 0.7144821882247925,
+      "eval_runtime": 18.3983,
+      "eval_samples_per_second": 1.087,
+      "eval_steps_per_second": 0.544,
+      "step": 81
+    },
+    {
+      "epoch": 1.1310344827586207,
+      "grad_norm": 2.013328790664673,
+      "learning_rate": 4.991809526186424e-05,
+      "loss": 1.0593,
+      "step": 82
+    },
+    {
+      "epoch": 1.1310344827586207,
+      "eval_loss": 0.7059406638145447,
+      "eval_runtime": 18.2362,
+      "eval_samples_per_second": 1.097,
+      "eval_steps_per_second": 0.548,
+      "step": 82
+    },
+    {
+      "epoch": 1.1448275862068966,
+      "grad_norm": 2.068134069442749,
+      "learning_rate": 4.988208552916535e-05,
+      "loss": 1.1188,
+      "step": 83
+    },
+    {
+      "epoch": 1.1448275862068966,
+      "eval_loss": 0.7021835446357727,
+      "eval_runtime": 18.1868,
+      "eval_samples_per_second": 1.1,
+      "eval_steps_per_second": 0.55,
+      "step": 83
+    },
+    {
+      "epoch": 1.1586206896551725,
+      "grad_norm": 2.2628672122955322,
+      "learning_rate": 4.983955090077444e-05,
+      "loss": 1.1473,
+      "step": 84
+    },
+    {
+      "epoch": 1.1586206896551725,
+      "eval_loss": 0.6942790150642395,
+      "eval_runtime": 18.1494,
+      "eval_samples_per_second": 1.102,
+      "eval_steps_per_second": 0.551,
+      "step": 84
     }
   ],
   "logging_steps": 1,
@@ -1181,7 +1256,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0083257447114342e+17,
+  "total_flos": 1.074128969822208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null