Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478eb6c8ec36ccf7a95261416884a9e007fd2624ab68cd9ab47dd9089afce0f4
+oid sha256:0d3cf549091814a2e94d0ca02da739a5e2129fbaf14e110386440a838c938d92
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8ea8c6c14467eb7f8c6b96215b583ed164dc1f1bc7fb4bb750c7065bba7314
+oid sha256:6dc8c380335b84923a3e5952717949d42c87aad320d29b1b3eea6efee1e82c79
 size 111412180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab7b84937cb43e29cbe41d19932eb50f0c47f3de93a9a1a0224f28860d65a56
+oid sha256:83950a2b3a1937dea706b22117ea318a758e2ef3bdb2c793eeb57fcb5b7f5b5f
 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": 0.028241939279830548,
+  "epoch": 0.031066133207813602,
   "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": 10.982,
       "eval_steps_per_second": 1.373,
       "step": 90
+    },
+    {
+      "epoch": 0.0291833372558249,
+      "grad_norm": 0.472822904586792,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.4227,
+      "step": 93
+    },
+    {
+      "epoch": 0.03012473523181925,
+      "grad_norm": 0.44283923506736755,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.5095,
+      "step": 96
+    },
+    {
+      "epoch": 0.031066133207813602,
+      "grad_norm": 0.5067503452301025,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 1.3896,
+      "step": 99
+    },
+    {
+      "epoch": 0.031066133207813602,
+      "eval_loss": 1.4326143264770508,
+      "eval_runtime": 488.4784,
+      "eval_samples_per_second": 10.989,
+      "eval_steps_per_second": 1.374,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5298276082948506e+17,
+  "total_flos": 1.682386594163589e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null