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:fc077c1259197837226a789d735f018558c88609e92afc03d24393aaa86c6bff
+oid sha256:68913d84892d3858fb9abf74c31181a3333dc7ca38a5b31684cfc99e99414c31
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de9a5b157968ef5bda3cba5cf5d6b0450772f07cc260f74bd60ddbed6d9b5e9
+oid sha256:2a435c4428c0ef485f02b81658cd570d7a494bf33d09783f1076f98242fd1ac1
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372b6df161a2e1d25ff90cff7b2229f932a23f64d77a8a0200337f4a9fd0ba45
+oid sha256:b20b810bbff08c53880fe8d9f68c3b26b73045caeb0ce540722b11f3250e5fc6
 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": 0.0012809774843572943,
+  "epoch": 0.0025619549687145885,
   "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": 52.969,
       "eval_steps_per_second": 26.49,
       "step": 10
+    },
+    {
+      "epoch": 0.0014780509434891855,
+      "grad_norm": 2.931530714035034,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.336,
+      "step": 15
+    },
+    {
+      "epoch": 0.001970734591318914,
+      "grad_norm": 3.130262851715088,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.6173,
+      "step": 20
+    },
+    {
+      "epoch": 0.001970734591318914,
+      "eval_loss": 3.208744525909424,
+      "eval_runtime": 80.8453,
+      "eval_samples_per_second": 52.854,
+      "eval_steps_per_second": 26.433,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024634182391486425,
+      "grad_norm": 4.077453136444092,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.9028,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69442617212928.0,
+  "total_flos": 139742550687744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null