Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282ec72bbf86311e437533f0945e36d2de0a32fcffbb1d9a3eac9bf3a0a95d58
+oid sha256:92265d12a584ba5e1ca98dad8f70b99ef54e03e8c4b6831f9301af4c971fd43b
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0015eaa7c83ee52a684332b5c267cc7da93fea567b2baeb57a9b182e12d1beb0
+oid sha256:4a2228365e17169e509ebe52385f51321ca3d6221ed41508f8341c3e2331420b
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22eb049858741d0446f5141132cbaa4a21e005113ef62d567590227c7e5fb963
+oid sha256:b48b39a0e824b1a3c18c1be18c454fa0b89a07e7ba413d8629bdab8b716f86c9
 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": 0.0003070763379965631,
+  "epoch": 0.0006141526759931262,
   "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": 16.34,
       "eval_steps_per_second": 8.17,
       "step": 10
+    },
+    {
+      "epoch": 0.0003543188515344959,
+      "grad_norm": 1.2811824083328247,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.4537,
+      "step": 15
+    },
+    {
+      "epoch": 0.00047242513537932787,
+      "grad_norm": 1.3264565467834473,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1594,
+      "step": 20
+    },
+    {
+      "epoch": 0.00047242513537932787,
+      "eval_loss": 2.0356850624084473,
+      "eval_runtime": 1094.5602,
+      "eval_samples_per_second": 16.286,
+      "eval_steps_per_second": 8.143,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005905314192241598,
+      "grad_norm": 1.7341872453689575,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0475,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1988618012590080.0,
+  "total_flos": 4059240891678720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null