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:f3b8b1b55642a143eacbb181d8fb2466ea027be594903f7c9a1be031b99ea79c
+oid sha256:639e28172a3fbcdfd48ef53af86b83676778a4e5bf24a246f2e5df0c058cf58a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d9d1e22c2e653c4bdfce592ebc62bd4e623fb44b9b20a485bc4c683061c9c4
+oid sha256:5b4bb803aed5855921c318a4ce6e0e0b7888456262c0d633c55610249b85e39d
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
+oid sha256:a002c35283ee15865b652908226f5a02d99c68599148fb6605a660ea5c853706
 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": 0.009424577202994921,
+  "epoch": 0.010367034923294414,
   "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": 15.121,
       "eval_steps_per_second": 1.891,
       "step": 90
+    },
+    {
+      "epoch": 0.009738729776428085,
+      "grad_norm": 0.8841791152954102,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.7551,
+      "step": 93
+    },
+    {
+      "epoch": 0.010052882349861248,
+      "grad_norm": 1.0488734245300293,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.9505,
+      "step": 96
+    },
+    {
+      "epoch": 0.010367034923294414,
+      "grad_norm": 1.016286849975586,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 1.7912,
+      "step": 99
+    },
+    {
+      "epoch": 0.010367034923294414,
+      "eval_loss": 1.8335013389587402,
+      "eval_runtime": 1063.6527,
+      "eval_samples_per_second": 15.121,
+      "eval_steps_per_second": 1.891,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1762363598372864e+17,
+  "total_flos": 1.293859995821015e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null