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:ed9311dc17ebd790a5def34affb92e5fb598b88f82fdd85d9e335e90ea0b7305
+oid sha256:cb564c508e516b4f50ebdc547766efe9023a9fc3d6a4650d8c18b66953337fb2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac752dc107d45ccf14455d857b2ae1434a5ed78a726edf72bb663b26303ea6f
+oid sha256:0fd91e80266f6076fc87e31779ecab6ea7efe9d6981fb86bfcd4e1483cc5f58d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef8705777091b5febb6761ed1f2fd8d5cb1215cde180da2cde2fa76ba08767f
+oid sha256:53f4f45187e26a4049e655bf2331e2a9bcb87445e02e0e30a1e6d4e3a5463624
 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": 0.0007547279350933975,
+  "epoch": 0.001509455870186795,
   "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": 10.161,
       "eval_steps_per_second": 5.081,
       "step": 10
+    },
+    {
+      "epoch": 0.0008708399251077664,
+      "grad_norm": 8.471663475036621,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.3761,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011611199001436885,
+      "grad_norm": 2.556199550628662,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.5293,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011611199001436885,
+      "eval_loss": 0.24717071652412415,
+      "eval_runtime": 713.0601,
+      "eval_samples_per_second": 10.172,
+      "eval_steps_per_second": 5.087,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014513998751796108,
+      "grad_norm": 9.092192649841309,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.2606,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2728107266015232.0,
+  "total_flos": 5363736319623168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null