Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ea01ec53484c007a96238d8fabd6ba4cc40c22b0aea8f219691d4a7019f9aa
+oid sha256:c892d890dc103ed278b6c33c6f35360fe6646f8c9c991d284501ce1dfa347ff4
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f22a8c3f1540e44f74b760e5cb5f0d204f6d24c03e40330b99bf38987b3bdc8
+oid sha256:e06b49ea52f533427e65bbb6fbcf9393a036a7fdeae0c3e78d15860d04b6a55d
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbf6b84eafc16b75329a008654c608bbbb4763f339107eca51386c43f126cb7
+oid sha256:ef89dd1ea24dc1a0aa6da43465b16623f89869e0f69ca8c779116080f3f850e1
 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": 2.2222222222222223,
+  "epoch": 2.4444444444444446,
   "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": 68.33,
       "eval_steps_per_second": 8.913,
       "step": 90
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.20254096388816833,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.8373,
+      "step": 93
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.20453697443008423,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.9392,
+      "step": 96
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.1803455650806427,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.0326,
+      "step": 99
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "eval_loss": 1.8957442045211792,
+      "eval_runtime": 1.0119,
+      "eval_samples_per_second": 68.192,
+      "eval_steps_per_second": 8.895,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5717061280727040.0,
+  "total_flos": 6289164702842880.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null