Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5995e42ac8e31345d8b79497f9769cdaa82dcaffc026f6a84dc85998a3f5e3
+oid sha256:7c42c6d4351b7cb5b2ca616a904310748c0b8bae3cdd531ce6371bbcb02941e3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b0d8817f5bb5259b6f8d1c4b03657030976a2381a9565a387471de96a2f200
+oid sha256:f82e4ab5bf0328544cf23475f5d90bfb3ad74e7b34551a11968eb6b1b74fdb9f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17bfc03d6cf297c814764c3509d2f8c90b9257c36dc20b18f74a9c76a8f0238
+oid sha256:883282ec1042f5d86ab3689aa84987d49f9ce467f1797aa846e4a8f53f7f78fa
 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": 0.000599409811877536,
+  "epoch": 0.001198819623755072,
   "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": 14.308,
       "eval_steps_per_second": 7.154,
       "step": 10
+    },
+    {
+      "epoch": 0.0006916267060125415,
+      "grad_norm": 4.243373394012451,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.7296,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009221689413500553,
+      "grad_norm": 0.13427194952964783,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.1732,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009221689413500553,
+      "eval_loss": 0.2060871124267578,
+      "eval_runtime": 637.7861,
+      "eval_samples_per_second": 14.318,
+      "eval_steps_per_second": 7.159,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011527111766875691,
+      "grad_norm": 0.10090111941099167,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0025,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2453740518899712.0,
+  "total_flos": 4819847447838720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null