Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbd533dccb77e0785bfd785c08160c33c48af3e1618c6fbf736240de3d65215
+oid sha256:1da79dec41e9caaf2d20b580a1ac8be900b1e85557bca920a1c58e08451ac8e0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd6641d202d84fd9c4a931b1c22e5c8fda108a40e8f1b7c343a952a7374b7d4
+oid sha256:762a3d12f753b73f0c00d35f5b00752d21a8b8f5d0fc51ea2dcbe0f76a88c334
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d2bf6b77f8850a276f23712d3998c1486d4cad7b87b73826a884c0e5e13663
+oid sha256:9e478801f2cd9f8bd09cce418d420a98278e1a79e573fedc7ca263d51e55cf66
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
+oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01745267885787616,
+  "epoch": 0.021815848572345205,
   "eval_steps": 17,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,6 +201,56 @@
       "eval_samples_per_second": 13.293,
       "eval_steps_per_second": 1.663,
       "step": 68
+    },
+    {
+      "epoch": 0.017709335899903755,
+      "grad_norm": 0.3993850648403168,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 2.2755,
+      "step": 69
+    },
+    {
+      "epoch": 0.018479307025986526,
+      "grad_norm": 0.3162781000137329,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 2.3094,
+      "step": 72
+    },
+    {
+      "epoch": 0.019249278152069296,
+      "grad_norm": 0.33009400963783264,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 2.3131,
+      "step": 75
+    },
+    {
+      "epoch": 0.02001924927815207,
+      "grad_norm": 0.30170515179634094,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 2.2769,
+      "step": 78
+    },
+    {
+      "epoch": 0.02078922040423484,
+      "grad_norm": 0.36391210556030273,
+      "learning_rate": 6.932495846462261e-05,
+      "loss": 2.3464,
+      "step": 81
+    },
+    {
+      "epoch": 0.021559191530317615,
+      "grad_norm": 0.34589123725891113,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 2.3523,
+      "step": 84
+    },
+    {
+      "epoch": 0.021815848572345205,
+      "eval_loss": 2.3070456981658936,
+      "eval_runtime": 494.1111,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.662,
+      "step": 85
     }
   ],
   "logging_steps": 3,
@@ -220,7 +270,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.855498037336474e+16,
+  "total_flos": 1.2294651397747507e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null