Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18794b1451d2d1b671e470c35fee1e43717e7bd2da685d699a8886a4c0e7a918
+oid sha256:9371fe8a47c21a2ad57ead143693ada0ce1cdf8d832bdbc54481415e169565b0
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e931f8bcebcb56904b4b39ad2a7a59911baa7760fb04ea47173a9f2481d808
+oid sha256:fe03c2b424801a8ea9d6f38f0fd3b5c668433fc0e75ee6ad6ce947126b2c2446
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0157d26a6c9880b1ce48a0bee6735b6a2e075272af9c2ec140c34f306deed1f1
+oid sha256:875cc80f5d170fa1121c26562fc04de720d828ce782c9d29bd2e7b6e67614c5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12485549132947976,
+  "epoch": 0.16647398843930636,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 15.617,
       "eval_steps_per_second": 1.968,
       "step": 27
+    },
+    {
+      "epoch": 0.13872832369942195,
+      "grad_norm": 13.057132720947266,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 8.9095,
+      "step": 30
+    },
+    {
+      "epoch": 0.15260115606936417,
+      "grad_norm": 13.501303672790527,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 9.0641,
+      "step": 33
+    },
+    {
+      "epoch": 0.16647398843930636,
+      "grad_norm": 13.990789413452148,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 8.5,
+      "step": 36
+    },
+    {
+      "epoch": 0.16647398843930636,
+      "eval_loss": 2.281359910964966,
+      "eval_runtime": 23.3762,
+      "eval_samples_per_second": 15.614,
+      "eval_steps_per_second": 1.968,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5348150659055616e+16,
+  "total_flos": 4.713086754540749e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null