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:f4d402b9cb7024a53d6777302f6924d7e8c7f6921e591c0a78b4357ae0a75fa4
+oid sha256:856fd25c9ffe4bea399e147d3f5d702ed7f9f3f9216bb96a9209ba576e80f4d9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcc5209d3528a3bf27446fb10f8d9cec9db364f2df732b74b78cac2f62bae42
+oid sha256:fced3c8b068d8137bca445a9bb684d2e002c4a2bbfabdc43445c4e98d43b76b2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7f64ab8cf96f1118762f8652227986903e4e175b8bcf5e33b2a546271ec0ca
+oid sha256:8356e0eedb914506be9d6834a09dc3748c48d92697d3720f05ef898a38d1c12e
 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": 0.00026202413645410797,
+  "epoch": 0.0005240482729082159,
   "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": 10.892,
       "eval_steps_per_second": 5.446,
       "step": 10
+    },
+    {
+      "epoch": 0.0003023355420624323,
+      "grad_norm": 1.3019169569015503,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.163,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004031140560832431,
+      "grad_norm": 0.7878373861312866,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3866,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004031140560832431,
+      "eval_loss": 1.1855676174163818,
+      "eval_runtime": 1921.0938,
+      "eval_samples_per_second": 10.874,
+      "eval_steps_per_second": 5.437,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005038925701040538,
+      "grad_norm": 1.455486536026001,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.3197,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3606650283884544.0,
+  "total_flos": 6982105036750848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null