Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1132b3b3d30fdd06f039a4f2513671b769a1a3e0a44f4d2c38d6c09f09711eca
+oid sha256:2e5a68b511b82a2a8a2b074d8679cdc86402f4d80aae49a8ce9fcee8ac917063
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43468d13e471ba94ddb2d7826f4ce779aa8ed6698d4e298ae751478620c26f0
+oid sha256:0738a224ce4f75fce6844fabf6823d2c0cc5345ecf63314f8172233f74e8f9cb
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2043fcab6393039914b1ae1d41f0b06c9cc65053e1770339d2cdf1b4d4fcd1
+oid sha256:534fd80f4a36921aa36f02966232895e27318825fe994a2792a763901e8e85a0
 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": 0.011284722222222222,
+  "epoch": 0.022569444444444444,
   "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": 28.426,
       "eval_steps_per_second": 14.243,
       "step": 10
+    },
+    {
+      "epoch": 0.013020833333333334,
+      "grad_norm": 2.2388646602630615,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.6183,
+      "step": 15
+    },
+    {
+      "epoch": 0.017361111111111112,
+      "grad_norm": 3.2893173694610596,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.1206,
+      "step": 20
+    },
+    {
+      "epoch": 0.017361111111111112,
+      "eval_loss": 2.4937543869018555,
+      "eval_runtime": 16.1492,
+      "eval_samples_per_second": 30.033,
+      "eval_steps_per_second": 15.047,
+      "step": 20
+    },
+    {
+      "epoch": 0.021701388888888888,
+      "grad_norm": 3.498352289199829,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.8513,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 411303432683520.0,
+  "total_flos": 822606865367040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null