Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662a49c27c194193585adb00617d45c53ea3b726728083cfeaf7bc2f58bd1ff1
+oid sha256:7a16e1c85c334fc7eada6b24ff37be32e2525b190ded3df237d851388d56011f
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c23b9373550f3bc72edb6c39d14081b7b340f709f79c644756e75b5befb37b
+oid sha256:656a791ad7bc5b47caf10ca8b9723d8ffde109e7723b75b7c6e0b82de6a39a88
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5ccb91bc863285e4b6a29afacd6382c0b78a1a6c2bd0f12c46edbbd9bbfaf5
+oid sha256:04fd270e669bc9caccdd1fc28fe53bb7f40c11badb883404c1759d887caa66cd
 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": 0.007396870554765292,
+  "epoch": 0.014793741109530583,
   "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": 29.981,
       "eval_steps_per_second": 14.991,
       "step": 10
+    },
+    {
+      "epoch": 0.008534850640113799,
+      "grad_norm": 1.1251591444015503,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.321,
+      "step": 15
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "grad_norm": 1.4248967170715332,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1071,
+      "step": 20
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "eval_loss": 2.175661563873291,
+      "eval_runtime": 24.7074,
+      "eval_samples_per_second": 29.951,
+      "eval_steps_per_second": 14.975,
+      "step": 20
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 1.6990677118301392,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0976,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 117975567040512.0,
+  "total_flos": 240403042271232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null