Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2a6529fd91eb20b6aec3adb94960c74c2804d3425e74bd27caa37164848cf4
+oid sha256:7747fd41cab114d6a80d10f436fffa01608659cae45328704a894150a7a1ee42
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876d7341e92b92fab4ee5f19e69ed1c87e8b1fedfaef133bd63e24fba0af5b6b
+oid sha256:cc282ea662d9be1d1c346d0878d1ff4484f3f04a8e34c52bcf876e3707be3cba
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f863b02a4562f0a8e9c7d699075c016c42b87ea89bc71285895edbb55836da4
+oid sha256:abd3884f16f1269c0ca48b7b452b6b8d5d53d42be555761e3851bf0ccd7561f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3432657926102503,
+  "epoch": 0.38617401668653156,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 14.927,
       "eval_steps_per_second": 1.898,
       "step": 72
+    },
+    {
+      "epoch": 0.3575685339690107,
+      "grad_norm": 0.7805127501487732,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1241,
+      "step": 75
+    },
+    {
+      "epoch": 0.37187127532777114,
+      "grad_norm": 0.7199813723564148,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.1669,
+      "step": 78
+    },
+    {
+      "epoch": 0.38617401668653156,
+      "grad_norm": 0.8319717049598694,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1235,
+      "step": 81
+    },
+    {
+      "epoch": 0.38617401668653156,
+      "eval_loss": 2.2104547023773193,
+      "eval_runtime": 23.7384,
+      "eval_samples_per_second": 14.913,
+      "eval_steps_per_second": 1.896,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.98734416492626e+16,
+  "total_flos": 1.1206920845131776e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null