Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818e3a782cd131f9a2101893643ffc923f8196c6dc1e8aad27720e388aa08b26
+oid sha256:f48a151b584f5008f1c72978912a2275b0c4f1edf1606a539861bf864dfd230b
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4ba7fcc317343c7709076076a2ff23d82c71a8be4d13be2b321793d732fbe9
+oid sha256:e37ead208f73a2663808f1f8aa9d3b8d9a9e975b01e7195d0d1358d16b53968d
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afeea0ce49de64f437fda23a757ba1b8cfd792e9c29274af6f204cff283f842
+oid sha256:92fdd6b5f2e28afc51fd80c32f71916e1018bf8338120774e0b31ca75b69ea3f
 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": 0.013752975403332451,
+  "epoch": 0.027505950806664903,
   "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": 25.135,
       "eval_steps_per_second": 12.567,
       "step": 10
+    },
+    {
+      "epoch": 0.015868817773075906,
+      "grad_norm": 1.0881882905960083,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.404,
+      "step": 15
+    },
+    {
+      "epoch": 0.02115842369743454,
+      "grad_norm": 0.8857386708259583,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.2675,
+      "step": 20
+    },
+    {
+      "epoch": 0.02115842369743454,
+      "eval_loss": 1.2028179168701172,
+      "eval_runtime": 15.7734,
+      "eval_samples_per_second": 25.232,
+      "eval_steps_per_second": 12.616,
+      "step": 20
+    },
+    {
+      "epoch": 0.026448029621793177,
+      "grad_norm": 0.8890538811683655,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.1529,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 231499225890816.0,
+  "total_flos": 460772497686528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null