Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ee674c1b3d025e9a707fccb7f9841be8ed1ff375b426dae1029742ff124941
+oid sha256:3178be048696545f45fc304a1986cdc4eabce8a7ebf323b2a2fcecd391bec8f4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a358c6193f0a805261b62d4b0069e3b0e5a9af2dcd35268d30d42904876a9b
+oid sha256:63f2b1c6cb0e45cd6b7666acab853d01b2a48ca0b0afd38a81e9dc878ff58978
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.00020051130382475312,
+  "epoch": 0.00040102260764950624,
   "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": 12.055,
       "eval_steps_per_second": 6.028,
       "step": 10
+    },
+    {
+      "epoch": 0.000231359196720869,
+      "grad_norm": 3.690640449523926,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.8237,
+      "step": 15
+    },
+    {
+      "epoch": 0.00030847892896115864,
+      "grad_norm": 3.5385003089904785,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.509,
+      "step": 20
+    },
+    {
+      "epoch": 0.00030847892896115864,
+      "eval_loss": 1.5317597389221191,
+      "eval_runtime": 2264.3254,
+      "eval_samples_per_second": 12.056,
+      "eval_steps_per_second": 6.028,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003855986612014483,
+      "grad_norm": 2.908796548843384,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.5962,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null