Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8084f2694e163a264197d7917f8d6fbea3e2ec65874835e7d4e56335957eb8c
+oid sha256:3b9705d75e04e79f442070339578517dc2e6f516e00a94dd394384686fce30a6
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848e7d31a743661e7df912c621c94a4704b71638c5d095b79f9ff7d8ed390f9c
+oid sha256:68204ea20f0d7a84b3754b263f46f7691530122dd1b703a18f589ed01aea2ec4
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95ca45a493e6ca4c3e96903e02caca906defc4426d872c5bf2434b8480c5e21
+oid sha256:01738b384345accfc82372a3908d7339f76b4fef68d7cfd75e37d12036567351
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027320791628369775,
+  "epoch": 0.0030356435142633083,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 30.14,
       "eval_steps_per_second": 3.768,
       "step": 81
+    },
+    {
+      "epoch": 0.0028332672799790876,
+      "grad_norm": 0.2881883382797241,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.7495,
+      "step": 84
+    },
+    {
+      "epoch": 0.002934455397121198,
+      "grad_norm": 0.2536965012550354,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.8133,
+      "step": 87
+    },
+    {
+      "epoch": 0.0030356435142633083,
+      "grad_norm": 0.28757724165916443,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.7783,
+      "step": 90
+    },
+    {
+      "epoch": 0.0030356435142633083,
+      "eval_loss": 0.8145592212677002,
+      "eval_runtime": 1657.575,
+      "eval_samples_per_second": 30.124,
+      "eval_steps_per_second": 3.766,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.514567510884352e+16,
+  "total_flos": 2.769289934064845e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null