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:a50d1b89875b5f5630cf948093699f5ef45b1d04efb3f88685a232e47d23ff85
+oid sha256:f0e69cf2a2d99b898fd9719a66f1b4a971337f409874437310e1d6f9185ea843
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf7c47529ea42cd74d76868503cc37e5650183c4db381af7716bcc615dd1080
+oid sha256:afeed1f62e8919839e04ad30ff8672c9747f01e9cc0e471c772636ef6e8206d2
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 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": 0.001993559270050606,
+  "epoch": 0.003987118540101212,
   "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": 228.29,
       "eval_steps_per_second": 114.145,
       "step": 10
+    },
+    {
+      "epoch": 0.0023002606962122373,
+      "grad_norm": 0.08557874709367752,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.3689,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030670142616163166,
+      "grad_norm": 0.06665366142988205,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3697,
+      "step": 20
+    },
+    {
+      "epoch": 0.0030670142616163166,
+      "eval_loss": 10.36631965637207,
+      "eval_runtime": 12.2892,
+      "eval_samples_per_second": 223.448,
+      "eval_steps_per_second": 111.724,
+      "step": 20
+    },
+    {
+      "epoch": 0.003833767827020396,
+      "grad_norm": 0.059420373290777206,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3659,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 168101806080.0,
+  "total_flos": 336203612160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null