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:e51e8de3a073805df165b190669d256dff44f88d59b3179afae968f17fcfc6bb
+oid sha256:a8f72bb98da71de6ed9d33eff582c9975f7111040e782c585361aaec028ad472
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0109d301cfbb3652f6eca760a1f95817bb8818cad442aa64cb5fd92ee4bbbf
+oid sha256:ad42813e0c2e5c60f68462649ecf32f7fd6217169d2aecbe3a6c67355dfa2d3c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95769943b503fd37e5ac516a17484f5788998a9cd717e8fc51b80176db1e71d3
+oid sha256:c5e58f6d1cdeebe1d7aa57259944c3c801316bbcd010a1ab4fe7f9d624ecf2bd
 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": 0.0003024785792813807,
+  "epoch": 0.0006049571585627614,
   "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": 16.341,
       "eval_steps_per_second": 8.171,
       "step": 10
+    },
+    {
+      "epoch": 0.00034901374532467005,
+      "grad_norm": 4.00037956237793,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.947,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004653516604328934,
+      "grad_norm": 3.7681870460510254,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.3056,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004653516604328934,
+      "eval_loss": 2.6043853759765625,
+      "eval_runtime": 1107.0056,
+      "eval_samples_per_second": 16.348,
+      "eval_steps_per_second": 8.174,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005816895755411168,
+      "grad_norm": 2.936751365661621,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.2767,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2183365373460480.0,
+  "total_flos": 4366730746920960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null