Training in progress, step 78, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e27c7ca276dab3b694b57a434df8e3d6893b7178979b1cac675c9ec8f60e479
+oid sha256:c1a71acfb6d4b2e67e14a0a94145dd571edcee7a4a0a7465524db480b4f1d9fa
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34c31e1a088ba21fbeeda48d254b861c5ec0f4870c287a673f116c47f5ce695
+oid sha256:a36fb42f8a18ebd6fe10bfd465c98efa16fe456c6841de6fd1a7d506f68c0fbd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1efa6b5fe80dcfbe062f5d7edc55d1dd44809f7d923ce612aa87101548ec21
+oid sha256:6c92c501f0c4a9123fc8a015c0ef0273054caea0a6d5ebb564fbcba98901fbea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb438ab9499d5178d553290d304fad6bd105cd4f59f8f03d9657a249b7bd5f14
+oid sha256:a4d6e5f76805b36e4d76ee2a3b48ba3bedb1c2bda79be4f5c70f809dd0d57438
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1818181818181819,
+  "epoch": 1.4181818181818182,
   "eval_steps": 13,
-  "global_step": 65,
+  "global_step": 78,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,49 @@
       "eval_samples_per_second": 9.959,
       "eval_steps_per_second": 1.285,
       "step": 65
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6527738571166992,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.179,
+      "step": 66
+    },
+    {
+      "epoch": 1.2545454545454544,
+      "grad_norm": 0.7428808808326721,
+      "learning_rate": 6.22170203068947e-05,
+      "loss": 0.174,
+      "step": 69
+    },
+    {
+      "epoch": 1.309090909090909,
+      "grad_norm": 0.6538995504379272,
+      "learning_rate": 5.8927844739931834e-05,
+      "loss": 0.16,
+      "step": 72
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6126785278320312,
+      "learning_rate": 5.559822380516539e-05,
+      "loss": 0.1336,
+      "step": 75
+    },
+    {
+      "epoch": 1.4181818181818182,
+      "grad_norm": 0.718612551689148,
+      "learning_rate": 5.2243241517525754e-05,
+      "loss": 0.132,
+      "step": 78
+    },
+    {
+      "epoch": 1.4181818181818182,
+      "eval_loss": 0.23752006888389587,
+      "eval_runtime": 9.3452,
+      "eval_samples_per_second": 9.952,
+      "eval_steps_per_second": 1.284,
+      "step": 78
     }
   ],
   "logging_steps": 3,
@@ -221,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4684436868104192e+17,
+  "total_flos": 1.7663751186127258e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null