Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f680424ffa5568e24254ea407ddc5c197e30e7cf4556b2ec4f7895c746446371
+oid sha256:7b88984ff2c255a6aea22336623112adf560ad5da70b2277d2487cc88b911fc5
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918d631cbc6eecaf056cd2b8806360f341e211c539121dfd64f8b9d97ee6482b
+oid sha256:950cb4c0ae702d83a6bfc0ebb6c274a359cc8c647b23a5847551fa2d6e41311a
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd658cec9622954e85e5fe0ba5a170bd144a31d594124a29fc9c7983d5adc53
+oid sha256:bc5b46941094ef30ee274a3b487078fe515f123e828c349f90e03dee41cc38e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14523449319213314,
+  "epoch": 0.16338880484114976,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 17.564,
       "eval_steps_per_second": 2.209,
       "step": 72
+    },
+    {
+      "epoch": 0.15128593040847202,
+      "grad_norm": 0.07840047776699066,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 1.3625,
+      "step": 75
+    },
+    {
+      "epoch": 0.1573373676248109,
+      "grad_norm": 0.08086764067411423,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 1.3874,
+      "step": 78
+    },
+    {
+      "epoch": 0.16338880484114976,
+      "grad_norm": 0.06452049314975739,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 1.3141,
+      "step": 81
+    },
+    {
+      "epoch": 0.16338880484114976,
+      "eval_loss": 1.3048590421676636,
+      "eval_runtime": 47.4887,
+      "eval_samples_per_second": 17.583,
+      "eval_steps_per_second": 2.211,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.611388488862925e+16,
+  "total_flos": 5.18781204997079e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null