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:f4b88ee46ebec14296f0c4c194208de9cb7b86d15d3574327f2168f099232b49
+oid sha256:421df45b71d63d41d9151f33085175882b64dfe14c9dd6038cbe60098946a62f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2726a0d1155fdab2f2f22e17bed026a8b906a5fb6cb8104265c92c96f3211a34
+oid sha256:d08c1b4bdd07fe1eedc03634213b7a210f91095825225b0fa65cb0f98e9d1b8c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
+oid sha256:3eba564523b8e7170117124c450887f82a78e23aad68f44ac77face0466e16e2
 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": 0.013187927973624143,
+  "epoch": 0.026375855947248287,
   "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": 5.688,
       "eval_steps_per_second": 2.851,
       "step": 10
+    },
+    {
+      "epoch": 0.01521683996956632,
+      "grad_norm": 10.42927074432373,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 5.0509,
+      "step": 15
+    },
+    {
+      "epoch": 0.02028911995942176,
+      "grad_norm": 10.226600646972656,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.1741,
+      "step": 20
+    },
+    {
+      "epoch": 0.02028911995942176,
+      "eval_loss": 1.1783760786056519,
+      "eval_runtime": 73.8495,
+      "eval_samples_per_second": 5.62,
+      "eval_steps_per_second": 2.817,
+      "step": 20
+    },
+    {
+      "epoch": 0.0253613999492772,
+      "grad_norm": 7.611446857452393,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.3569,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4556941443465216.0,
+  "total_flos": 9070066142281728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null