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:c55b9aa267024c4236b8dcf6ff6fa3371d178d7ed0ae726c1828b715412216b6
+oid sha256:b84151bdaf5cd9abf1151fe9784c97290185105506118ee30c070566261bce49
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0100e443f5a74beb0dc86674b97459a7b7ad5d69f417caff935ae7430fa81a5
+oid sha256:267ac58da8a4b723d8af620226c30765c2532070eb958da3b5ef9420691aa86a
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ed94d3f701716d000966a79dc83b9c7cb22d520c60aa3219af11d89dc9f6e3
+oid sha256:2be47f37ef8eb0f9c3403aefbbf05b0ff77745d10c80c1721e0e91833fc48e31
 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": 0.0021938151288866388,
+  "epoch": 0.0043876302577732776,
   "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": 9.005,
       "eval_steps_per_second": 4.504,
       "step": 10
+    },
+    {
+      "epoch": 0.0025313251487153526,
+      "grad_norm": 19.800888061523438,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.1909,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033751001982871365,
+      "grad_norm": 0.48582473397254944,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.1785,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033751001982871365,
+      "eval_loss": 0.47386130690574646,
+      "eval_runtime": 275.2918,
+      "eval_samples_per_second": 9.063,
+      "eval_steps_per_second": 4.533,
+      "step": 20
+    },
+    {
+      "epoch": 0.00421887524785892,
+      "grad_norm": 9.057249069213867,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3445,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2668111702523904.0,
+  "total_flos": 5336223405047808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null