Training in progress, step 143, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bab5d72981e47677ba7684e8cd3fae37040400aa8bac37bf81762e339478b9
+oid sha256:de5359a0bb8a59b81c50f4e1c9f908552b691f062fc36c8780f9083f0fa9fa4a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e995c2d7fcce2a965e868612f149f264b8568bb4ae703c7a74f350a4edd815b
+oid sha256:9c9e4879fb670c02c005cb2c07fbebefe20227272e4b6872afb519cd932cdff2
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f08fcc7c6d0fb430357ce223cfcb24bd8f8402de822cacacf80e67d804372
+oid sha256:09eab6461849a2249375bae3390cbfb47d6f7a331d1576b4923c38f6b0c00b92
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507bfe4270aab5b2aa070e93d9c3404af996914dd61586771e0cc504e5b0252c
+oid sha256:431c6c53bdba57f808cd9c2e6f738bda5a26247416d68b6f96cb4f3eef6f54ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1469341621927098,
+  "epoch": 0.16162757841198078,
   "eval_steps": 13,
-  "global_step": 130,
+  "global_step": 143,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -396,6 +396,42 @@
       "eval_samples_per_second": 6.63,
       "eval_steps_per_second": 0.832,
       "step": 130
+    },
+    {
+      "epoch": 0.14919468776490535,
+      "grad_norm": 1.0372916460037231,
+      "learning_rate": 2.0118056862137357e-06,
+      "loss": 0.4873,
+      "step": 132
+    },
+    {
+      "epoch": 0.15258547612319864,
+      "grad_norm": 1.11273992061615,
+      "learning_rate": 1.4029167422908107e-06,
+      "loss": 0.5262,
+      "step": 135
+    },
+    {
+      "epoch": 0.15597626448149193,
+      "grad_norm": 0.9660788774490356,
+      "learning_rate": 9.009284826036691e-07,
+      "loss": 0.5585,
+      "step": 138
+    },
+    {
+      "epoch": 0.15936705283978525,
+      "grad_norm": 1.1789458990097046,
+      "learning_rate": 5.08115039419113e-07,
+      "loss": 0.4771,
+      "step": 141
+    },
+    {
+      "epoch": 0.16162757841198078,
+      "eval_loss": 0.127611443400383,
+      "eval_runtime": 225.1337,
+      "eval_samples_per_second": 6.618,
+      "eval_steps_per_second": 0.831,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.6562775807361024e+17,
+  "total_flos": 4.0219053388097126e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null