Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5488cc2e2b855a246cfb63a50d8e8f62e912de203053a9124406a57805938220
+oid sha256:7f00756ac3598db3d64c5e55a7e103fcd8ecd7c8f53e624cf8cce7c30d8e663a
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f4ef5ed08eb2a58ab44fea060c07d35f388a4461044c12983e01f9306bd62d
+oid sha256:c2dfcff41ff0be65f50a8e8c719de8b8395a45d283f4aac0ea4ccc6bf3246152
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb815a3dacb7e60bd913a1d3d924db89cf28af23f33eb9fe2eaa870fd378154
+oid sha256:5aacb11315407deb4f1300c1eaa532979331b62cbad78dd83ecc21dd8a8600c3
 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": 0.0608187134502924,
+  "epoch": 0.1216374269005848,
   "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": 31.626,
       "eval_steps_per_second": 15.813,
       "step": 10
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 1.6386820077896118,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.9657,
+      "step": 15
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 1.2416112422943115,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.7649,
+      "step": 20
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "eval_loss": 1.619399905204773,
+      "eval_runtime": 2.8407,
+      "eval_samples_per_second": 31.683,
+      "eval_steps_per_second": 15.841,
+      "step": 20
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 1.6186881065368652,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6088,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 583322874937344.0,
+  "total_flos": 1184686663532544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null