Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e4a0ce1a491934418e6f4710ac3d42222e97de23ab5116e984442b53f75e20
+oid sha256:340c20e04abafb6315b11749a01bd3f58d7f1353f4dfdbe7bd5bfc6760bec134
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab87d6d19502706755356ad753f1517a727090c10a1424130b8c39c9a365d5d
+oid sha256:d71acb756adc1183623404f1798b70e592fbe12a6a4d45dc35f86d59889e1587
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada9b88cecb69c9d2d8d4079789122084e4f2f601b6cf82350a60242621e3280
+oid sha256:d99c1d1224da0412675feecfbb86d16ad950c12e50186da4fa4c819eb75a71b9
 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": 0.0003934356770498377,
+  "epoch": 0.0007868713540996754,
   "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": 14.796,
       "eval_steps_per_second": 7.398,
       "step": 10
+    },
+    {
+      "epoch": 0.0004539642427498127,
+      "grad_norm": 6.808655738830566,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1243,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006052856569997503,
+      "grad_norm": 4.205870151519775,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0565,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006052856569997503,
+      "eval_loss": 0.8383878469467163,
+      "eval_runtime": 946.9426,
+      "eval_samples_per_second": 14.693,
+      "eval_steps_per_second": 7.347,
+      "step": 20
+    },
+    {
+      "epoch": 0.0007566070712496879,
+      "grad_norm": 3.0068631172180176,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4534,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null