Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8f0393509d026cd8556e0b41bb37b85067f4ffe57a0517983c06193fa5140c
+oid sha256:ba93b783b81c2e94cabfc01234958ca8443cdf4654a18c8dc2c0d29444cdc8d3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3129c1e4ddab3a12625026063cc7de63f5cf08248031e5344dcc246cb2199469
+oid sha256:ebebcd39e38ed59af1f27b85e60ad31a5acd876b1a3267271cfd9b9d286fd46b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49042cfa15f50f0e29a9de76dfe4ab7fa1990c8701d0ade3fe5b0faa251bb2f
+oid sha256:2de9ef8658f2117d8362bfb287d6a2de136300b08418e7df9cafce40b50294c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721a82cc54baa1d744828761304c3f1e991f36bc90b1b9f92fe61ed53569abd0
+oid sha256:774252ad2ca59a173251c393bb9775b6ad50592c78a9adb425c0845b0166a283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0043836517188709356,
+  "epoch": 0.008767303437741871,
   "eval_steps": 40,
-  "global_step": 40,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 15.321,
       "eval_steps_per_second": 7.661,
       "step": 40
+    },
+    {
+      "epoch": 0.008767303437741871,
+      "grad_norm": 13.712140083312988,
+      "learning_rate": 2e-05,
+      "loss": 30.9777,
+      "step": 80
+    },
+    {
+      "epoch": 0.008767303437741871,
+      "eval_loss": 1.836449384689331,
+      "eval_runtime": 1003.1953,
+      "eval_samples_per_second": 15.32,
+      "eval_steps_per_second": 7.661,
+      "step": 80
     }
   ],
   "logging_steps": 40,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.605973017460736e+16,
+  "total_flos": 5.211946034921472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null