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:ed8c2ccdddc1cad9d8a07f48c876fed0d42a47263b746e9a3db9c1254e8e7ac9
+oid sha256:796bc67de81bbe1310feabb48945f5402deb012f97bc9e997a7a35147e91d4f5
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1e74a7c814e01fa3689b3a50e4ab6d804d2e4dae9ebe44530bd9423c8be47c
+oid sha256:d33f2e844352c9fe788379f77f6554aa6f00fd6547182d713c17edaa44e2c4ba
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df39d950c848edf06ddc44337bcda461f437550743c932459d37fa2b0c5b0d66
+oid sha256:11f0a30926f234c2a4db9e467908574bcd4eb62fb1cc00a7f5b42a5dbe9aadf5
 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": 0.005528973950026581,
+  "epoch": 0.011057947900053162,
   "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": 23.562,
       "eval_steps_per_second": 11.781,
       "step": 10
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 8.405237197875977,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 5.7595,
+      "step": 15
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": 3.423091411590576,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.2915,
+      "step": 20
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 3.1996655464172363,
+      "eval_runtime": 41.9043,
+      "eval_samples_per_second": 23.625,
+      "eval_steps_per_second": 11.813,
+      "step": 20
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 4.0305705070495605,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.7952,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 599951778250752.0,
+  "total_flos": 1248548295278592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null