Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ecc7bdd58a75fe1b57ba7dfb1b17796c2a09732bb5893d1753d23949350aa2
+oid sha256:6fc8f4602745be077c44fc35faea9166f3e459e2af25b055282b5724c36b0a9a
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f3633db7291df8992f656353048962a18e3cfda7e137e0e19548eff3a8dfea
+oid sha256:0288502b2a5162cedaae80ddea1efd04739be493ac79b6916e501959d52b175f
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70684c965e92ff4e320b4a4e5eb9628a9b3a8d1cc201394a3310766125ffae4a
+oid sha256:870dd88386b67d494ac7728913d80ab7557a5e2d3159dd0234dda109e9932f9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00407760392226663,
+  "epoch": 0.006116405883399945,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 33.01,
       "eval_steps_per_second": 16.505,
       "step": 126
+    },
+    {
+      "epoch": 0.00420705166583065,
+      "grad_norm": 1.0912537574768066,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.9974,
+      "step": 130
+    },
+    {
+      "epoch": 0.0045306710247407,
+      "grad_norm": 1.250145673751831,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 1.0415,
+      "step": 140
+    },
+    {
+      "epoch": 0.00485429038365075,
+      "grad_norm": 0.9472258687019348,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 0.9525,
+      "step": 150
+    },
+    {
+      "epoch": 0.0051779097425608,
+      "grad_norm": 1.0649255514144897,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 1.0185,
+      "step": 160
+    },
+    {
+      "epoch": 0.00550152910147085,
+      "grad_norm": 0.9161511659622192,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 0.9475,
+      "step": 170
+    },
+    {
+      "epoch": 0.0058251484603809,
+      "grad_norm": 0.6044164299964905,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.8716,
+      "step": 180
+    },
+    {
+      "epoch": 0.006116405883399945,
+      "eval_loss": 0.9692186117172241,
+      "eval_runtime": 197.0697,
+      "eval_samples_per_second": 33.014,
+      "eval_steps_per_second": 16.507,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.208605382541312e+16,
+  "total_flos": 1.808464671670272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null