Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b70e663e792013c958fd44186a28914cfbe692355e07eb6aedfd002cc6070f3
+oid sha256:b5f38e134dc206774ce1d9317ee743cbd60fe8866ff6cd49b5221202e0b03db6
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691cbf7a96073e210fc46b91f7dea1f95a9628a197df3f1a8262dea650a0f921
+oid sha256:1293ab8adaf11431079c5f9602906657ec065906eeabd6fee72dcf40bedb9ccc
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
+oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
 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": 0.022837066315327184,
+  "epoch": 0.04567413263065437,
   "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": 168.168,
       "eval_steps_per_second": 84.084,
       "step": 10
+    },
+    {
+      "epoch": 0.026350461133069828,
+      "grad_norm": 0.4372434914112091,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 44.3201,
+      "step": 15
+    },
+    {
+      "epoch": 0.03513394817742644,
+      "grad_norm": 0.4354489743709564,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 44.3119,
+      "step": 20
+    },
+    {
+      "epoch": 0.03513394817742644,
+      "eval_loss": 11.077805519104004,
+      "eval_runtime": 1.4987,
+      "eval_samples_per_second": 160.137,
+      "eval_steps_per_second": 80.068,
+      "step": 20
+    },
+    {
+      "epoch": 0.04391743522178305,
+      "grad_norm": 0.45061734318733215,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 44.3135,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 11206656000.0,
+  "total_flos": 23533977600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null