Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d8b5ae33d9aa362075369994a6d146fbf7c6c1b1f1cf3b76551725dad16ba3
+oid sha256:3a2bc9dc217e949a45472cf4c030d76d91a0b73b76d65f6de7e55a9d31fd82d3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7898c72de732d2072fb8ed074b1c679e84a8aca4f42a75b3fca183a3b9ae8c61
+oid sha256:c45aba703df92032fa7ec3b4056c72780bffa3d8c55b840991662003c570cce5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d58a77b7e7abf4f99c2b253ea7d0012eb34f29163a114391e783f09fc5bd6f
+oid sha256:8638d85cdde5c23462d969d214eecf01b525c427bc497c4ed563ee511772f854
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011163349863678323,
+  "epoch": 0.0022326699727356646,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 1.288,
       "eval_steps_per_second": 0.644,
       "step": 10
+    },
+    {
+      "epoch": 0.001288078830424422,
+      "grad_norm": 13.235127449035645,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 9.7988,
+      "step": 15
+    },
+    {
+      "epoch": 0.001717438440565896,
+      "grad_norm": 20.243595123291016,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.6174,
+      "step": 20
+    },
+    {
+      "epoch": 0.001717438440565896,
+      "eval_loss": 1.4080783128738403,
+      "eval_runtime": 3229.1069,
+      "eval_samples_per_second": 1.519,
+      "eval_steps_per_second": 0.759,
+      "step": 20
+    },
+    {
+      "epoch": 0.00214679805070737,
+      "grad_norm": 18.120956420898438,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 5.2192,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2198789733482496.0,
+  "total_flos": 4519734452158464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null