training state at step 30

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3448275862068966,
+  "epoch": 0.41379310344827586,
   "eval_steps": 1,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -367,6 +367,81 @@
       "eval_samples_per_second": 1.138,
       "eval_steps_per_second": 0.569,
       "step": 24
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.2879106998443604,
+      "learning_rate": 4.997050398198977e-05,
+      "loss": 1.5164,
+      "step": 25
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 1.0196115970611572,
+      "eval_runtime": 17.9439,
+      "eval_samples_per_second": 1.115,
+      "eval_steps_per_second": 0.557,
+      "step": 25
+    },
+    {
+      "epoch": 0.3586206896551724,
+      "grad_norm": 2.319134473800659,
+      "learning_rate": 4.9947570655942796e-05,
+      "loss": 1.5282,
+      "step": 26
+    },
+    {
+      "epoch": 0.3586206896551724,
+      "eval_loss": 1.013381004333496,
+      "eval_runtime": 17.7628,
+      "eval_samples_per_second": 1.126,
+      "eval_steps_per_second": 0.563,
+      "step": 26
+    },
+    {
+      "epoch": 0.3724137931034483,
+      "grad_norm": 2.259608745574951,
+      "learning_rate": 4.991809526186424e-05,
+      "loss": 1.4901,
+      "step": 27
+    },
+    {
+      "epoch": 0.3724137931034483,
+      "eval_loss": 1.0091207027435303,
+      "eval_runtime": 17.619,
+      "eval_samples_per_second": 1.135,
+      "eval_steps_per_second": 0.568,
+      "step": 27
+    },
+    {
+      "epoch": 0.38620689655172413,
+      "grad_norm": 2.2252631187438965,
+      "learning_rate": 4.988208552916535e-05,
+      "loss": 1.5518,
+      "step": 28
+    },
+    {
+      "epoch": 0.38620689655172413,
+      "eval_loss": 1.0063353776931763,
+      "eval_runtime": 17.4778,
+      "eval_samples_per_second": 1.144,
+      "eval_steps_per_second": 0.572,
+      "step": 28
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.2154901027679443,
+      "learning_rate": 4.983955090077444e-05,
+      "loss": 1.4682,
+      "step": 29
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.99261075258255,
+      "eval_runtime": 17.4894,
+      "eval_samples_per_second": 1.144,
+      "eval_steps_per_second": 0.572,
+      "step": 29
     }
   ],
   "logging_steps": 1,
@@ -386,7 +461,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.128103443541197e+16,
+  "total_flos": 3.786199396619059e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null