Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856506355103297fb037fe51efacc35d8b8b222c65cf9dd6b33f5a5666d36aed
+oid sha256:831eb6ff7c7ec07a949a88e1b1f9e6543e8e00f453ee5afdd7004975f252ff77
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c854d9ce9e0cafed79e215ac6014c8088122a9f966bdd1c64c3dcf472b0ba8
+oid sha256:37ffaf58eee7e49d66e40334a90197f3b16b3ad935288baf459cbc6ded3d09e3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ba2173c152f94714fb9f1e41fd4ca1e5e7fe0bc567e9b87b39fd86183b2acc
+oid sha256:bacace43e547c94b41abff4056126eb4e9b430747001acf89e0e67ee0e4b31ad
 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": 0.0009804106412262675,
+  "epoch": 0.001960821282452535,
   "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": 8.504,
       "eval_steps_per_second": 4.252,
       "step": 10
+    },
+    {
+      "epoch": 0.0011312430475687702,
+      "grad_norm": 2.0114729404449463,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.9863,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015083240634250269,
+      "grad_norm": 1.6664632558822632,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7031,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015083240634250269,
+      "eval_loss": 0.6721987724304199,
+      "eval_runtime": 656.6676,
+      "eval_samples_per_second": 8.504,
+      "eval_steps_per_second": 4.252,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018854050792812835,
+      "grad_norm": 1.5729988813400269,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6764,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4577671514161152.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null