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:cb0d2ed2d9c26c570d0150bf9b092910a05ff4148a345d7336144ed892c4fcc3
+oid sha256:3a3b378ded7d251b9c338c61ebd7ce062425b18539a30fe96aeb5264b6535e09
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ca3a9b5eb73cfc04f283a948c519dc660f6a3cec14647d5845b1693c6126de
+oid sha256:fcb7f26d21cea799fb528e55d5925825fb2c07e1850901b158bf005d8fb64ad9
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b2a66e442e94d63dda11f4f2c3193b2239e5d9a69ff09c372aa154df12d926
+oid sha256:118ae0c27d69a17419cf62ae7b5f551c0bcae03a4fd04575f08293c1bb0a73b9
 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": 0.007990165949600492,
+  "epoch": 0.015980331899200985,
   "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": 86.465,
       "eval_steps_per_second": 43.296,
       "step": 10
+    },
+    {
+      "epoch": 0.00921942224953903,
+      "grad_norm": 1991.4852294921875,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 130.4381,
+      "step": 15
+    },
+    {
+      "epoch": 0.012292562999385371,
+      "grad_norm": 642.9652099609375,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 99.3049,
+      "step": 20
+    },
+    {
+      "epoch": 0.012292562999385371,
+      "eval_loss": 32.11423873901367,
+      "eval_runtime": 7.9533,
+      "eval_samples_per_second": 86.128,
+      "eval_steps_per_second": 43.127,
+      "step": 20
+    },
+    {
+      "epoch": 0.015365703749231715,
+      "grad_norm": 820.176513671875,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 36.4627,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22703700443136.0,
+  "total_flos": 47345521655808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null