Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42cb1eb3ed5419c374edc8e4af60fb61b18e60bff030198976f7699d434f27b1
+oid sha256:451e616b1fc7111154b4c6c484d149a1d54d15d8a1816c425685ee0cb49b9846
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e44c3f4c1267fcd8bba6ab71707e54926eb0eaa928fb57bc499d084873eeee
+oid sha256:cd394891a4caa2d2e40b197fc4fb6891bec7c94a7165acbdc042ab42e88789b8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
+oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
 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": 0.0031790670660879136,
+  "epoch": 0.006358134132175827,
   "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": 9.049,
       "eval_steps_per_second": 4.524,
       "step": 10
+    },
+    {
+      "epoch": 0.0036681543070245155,
+      "grad_norm": 16.83527946472168,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.4507,
+      "step": 15
+    },
+    {
+      "epoch": 0.00489087240936602,
+      "grad_norm": 5.885318756103516,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.5604,
+      "step": 20
+    },
+    {
+      "epoch": 0.00489087240936602,
+      "eval_loss": 0.14171117544174194,
+      "eval_runtime": 190.6068,
+      "eval_samples_per_second": 9.034,
+      "eval_steps_per_second": 4.517,
+      "step": 20
+    },
+    {
+      "epoch": 0.006113590511707526,
+      "grad_norm": 3.527186632156372,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1274,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null