Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a5d0fe066ffa93cff2ce666eac60a71cc401ba96a6b8dcbc1678ac2c78714b
+oid sha256:7404b5935550ed5a18d7edb03d9e0f31877cd0609d647ec35b4277445386f6e2
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422ea9fef3dca06cb7e139f9dd806e7bc0a80c88e3881a1598bc6b0b686c0fa3
+oid sha256:d9f26bc58d8e10fa4237ad3874ef72c73be7de4d8e5e7c1a4abf0380eba41135
 size 40131268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8544242e3f788be29e662c88830e08ff5706a9604518162edf02980d267fa66
+oid sha256:8a9922144a3e9bbcf32a09ebab19d59f109f9c8c21b03b0a568e3488dd7acde7
 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": 0.3037974683544304,
+  "epoch": 0.3341772151898734,
   "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": 26.254,
       "eval_steps_per_second": 3.315,
       "step": 90
+    },
+    {
+      "epoch": 0.3139240506329114,
+      "grad_norm": 0.5063574910163879,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.9341,
+      "step": 93
+    },
+    {
+      "epoch": 0.3240506329113924,
+      "grad_norm": 0.5072469711303711,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.9095,
+      "step": 96
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 0.48717790842056274,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.9301,
+      "step": 99
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "eval_loss": 0.9075644016265869,
+      "eval_runtime": 18.987,
+      "eval_samples_per_second": 26.281,
+      "eval_steps_per_second": 3.318,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.885912614240256e+16,
+  "total_flos": 4.269584998937395e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null