Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f8d31b386d851c63588e69996a91f05001b5cec6a5ee9faca9658c9fe646c4
+oid sha256:bd4fe95a33e8eb6b26398664868d21139eb0dd3c1d6c364ba8aabf7f4e64bcd3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b848136cb491975c8b32b7b52d86be4dcad0ac815c32c888743266e1cc3009a1
+oid sha256:01ccc8b629e4aa1786f7f2a282a8ee56612a6356d10ffc3b8899b5aa9da54086
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9afd89781a51d597dbea42578ed20dd87af91f24b2c8ed574d84057f40bf94d
+oid sha256:0b03e90faa1967f18f72061550dc7b793bd6230a686d92c6466c314f9d209bd4
 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": 0.007013757755597518,
+  "epoch": 0.014027515511195037,
   "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": 16.076,
       "eval_steps_per_second": 8.049,
       "step": 10
+    },
+    {
+      "epoch": 0.008092797410304829,
+      "grad_norm": 8.243408203125,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 8.0358,
+      "step": 15
+    },
+    {
+      "epoch": 0.010790396547073105,
+      "grad_norm": 8.477263450622559,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 8.5592,
+      "step": 20
+    },
+    {
+      "epoch": 0.010790396547073105,
+      "eval_loss": 2.0519731044769287,
+      "eval_runtime": 48.3623,
+      "eval_samples_per_second": 16.149,
+      "eval_steps_per_second": 8.085,
+      "step": 20
+    },
+    {
+      "epoch": 0.013487995683841382,
+      "grad_norm": 7.101188659667969,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.3489,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2322287466381312.0,
+  "total_flos": 4600758188113920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null