Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601d81db7c93c2ea504f132e9970637375e79edd88e96f84f99bf1fd12a57b07
+oid sha256:10ec0d0b862d7b79ad817c14b37e10b57f37abe447b8df6d55dd87aa0f8b5948
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1a92459e08c30498744659f802b168229e0b1b5bd3c5f11b04ce9d3d567fd47
+oid sha256:c2e108bdc1d5930b01314a0432e0fc3fb3a841152f706dfba6cc6fe7d7444ec0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74968f6eacae56c3351446820923d083b77de7c5ca923bbd174bbd8718b16a4a
+oid sha256:8638d85cdde5c23462d969d214eecf01b525c427bc497c4ed563ee511772f854
 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": 0.00023039739119261665,
+  "epoch": 0.0004607947823852333,
   "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": 11.812,
       "eval_steps_per_second": 5.906,
       "step": 10
+    },
+    {
+      "epoch": 0.00026584314368378843,
+      "grad_norm": 1.6904109716415405,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2922,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003544575249117179,
+      "grad_norm": 1.2493869066238403,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8623,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003544575249117179,
+      "eval_loss": 0.7036842107772827,
+      "eval_runtime": 2008.721,
+      "eval_samples_per_second": 11.827,
+      "eval_steps_per_second": 5.914,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004430719061396474,
+      "grad_norm": 1.8683321475982666,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7287,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2265756519628800.0,
+  "total_flos": 4572708612341760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null