Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73dd59698f98a274c45125ea6b8ea77f903244432140d8936ace3159600b11ec
+oid sha256:8f47e59ea3a866801886c7a763d96c9383d6e3df4a66e0006d9c4a2336a6c0be
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21c2bfa3716b73048dc4493da867c360c8d804a102bdb5b18683aa86c25a29b
+oid sha256:6e048ec1593a8287599f478330047f9423eebfd67c79fcf6cd84b8cb2ae49b65
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c01f14c6b63a27414312834b770ffaafebf9ddd5758a4e6ed410dfbc27ee19
+oid sha256:2ba1e7e26849c5bbbbaa4d837573c76c3dee1c073e882edaef0f85cec70bfae8
 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": 0.0005841055883178882,
+  "epoch": 0.0011682111766357765,
   "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": 15.366,
       "eval_steps_per_second": 7.683,
       "step": 10
+    },
+    {
+      "epoch": 0.0006739679865206403,
+      "grad_norm": 7.640130043029785,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.7507,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008986239820275204,
+      "grad_norm": 5.644228458404541,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.2997,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008986239820275204,
+      "eval_loss": 3.3383829593658447,
+      "eval_runtime": 609.2979,
+      "eval_samples_per_second": 15.382,
+      "eval_steps_per_second": 7.691,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011232799775344005,
+      "grad_norm": 6.619650840759277,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.1767,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1186983648952320.0,
+  "total_flos": 2386204242739200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null