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:f3814dc660832d55c2bb40d2ad3d99795436d8bc62ab17ac4e58f293371e60c9
+oid sha256:ac1d900e5665d90be2ebc52f44bac884da863e86902d851ac0ab9f815eaa163c
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0780a4ef307d8f6befe37e4468d68934340db91d4a6d7a386b0e46fc82b40e
+oid sha256:6913e935f5bae19b7cb3d63bd4cc755f185976cd0f486f9dfb0eeefec8bf8d44
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d619f0a0b38410fb70c6f171e70d6491ec81ae876beaf702a4465ab5b7139f
+oid sha256:216e12cbd761e9aca0f3cdd56a87b9a2e4dffe3121f3cc1f73c8df77d15b8d50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21666666666666667,
+  "epoch": 0.43333333333333335,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 127.352,
       "eval_steps_per_second": 16.037,
       "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.1337666511535645,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 5.4595,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 5.005618572235107,
+      "eval_runtime": 3.1314,
+      "eval_samples_per_second": 129.334,
+      "eval_steps_per_second": 16.287,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1426574259781632.0,
+  "total_flos": 2853148519563264.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null