Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22f381d28cd7b273fe0059baa66c53abca359ff65fd9355a42fa41ce75a8d5c
+oid sha256:40f959ebbe4ae2a3df9913cf5601aac56713a7f348e9716e41537f7b94226b0f
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671497551ed8457efa5a184752b24f63e10b8d85620f74468c12119abcdf4bbd
+oid sha256:230abf96d00c36ee1f358a29503910dfd3b98337db35ffe0ffc388a37cf6267e
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04b91ebb84c2b2ce59f23243bcad840c62f3f58a7479270a8b0cda9da80b109
+oid sha256:1e177607e9900e964a62c96b0923e9c25ec65b2d179187fe73b8403d497bebb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5224963715529753,
+  "epoch": 0.5747460087082729,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 35.272,
       "eval_steps_per_second": 4.5,
       "step": 90
+    },
+    {
+      "epoch": 0.5399129172714079,
+      "grad_norm": 0.32795748114585876,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.503,
+      "step": 93
+    },
+    {
+      "epoch": 0.5573294629898403,
+      "grad_norm": 0.3038257658481598,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.4698,
+      "step": 96
+    },
+    {
+      "epoch": 0.5747460087082729,
+      "grad_norm": 0.30126094818115234,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.4015,
+      "step": 99
+    },
+    {
+      "epoch": 0.5747460087082729,
+      "eval_loss": 0.4675796627998352,
+      "eval_runtime": 8.2149,
+      "eval_samples_per_second": 35.302,
+      "eval_steps_per_second": 4.504,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.882117805539328e+16,
+  "total_flos": 3.170329586093261e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null