Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec21617278dd1d7faaa48a48d01ff72c5098fb9c0a0492af69a37ab67d6acbea
+oid sha256:dbf02fe76affb835569f707204a42e90fa8bde7b87bcafdd4ff43eccc516b20f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3cf85b625fd864d7bb72ff7e628d4b1779cb6be3374bde60f312e0ff80cc628
+oid sha256:5a639ef9fc9d05d8fe09be87e96c790f9ebbb683023200189ac91fb0653824c8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
+oid sha256:fdde6ac87a64995609da02d0ac08c227f29316a78167a5224ca4e6df927f97ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03594428635614797,
+  "epoch": 0.04792571514153063,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 7.666,
       "eval_steps_per_second": 3.839,
       "step": 15
+    },
+    {
+      "epoch": 0.0383405721132245,
+      "grad_norm": 0.20239923894405365,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8725,
+      "step": 16
+    },
+    {
+      "epoch": 0.040736857870301034,
+      "grad_norm": 0.19121764600276947,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8105,
+      "step": 17
+    },
+    {
+      "epoch": 0.043133143627377565,
+      "grad_norm": 0.19437186419963837,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8758,
+      "step": 18
+    },
+    {
+      "epoch": 0.0455294293844541,
+      "grad_norm": 0.20055896043777466,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.8736,
+      "step": 19
+    },
+    {
+      "epoch": 0.04792571514153063,
+      "grad_norm": 0.21000787615776062,
+      "learning_rate": 0.0,
+      "loss": 0.8396,
+      "step": 20
+    },
+    {
+      "epoch": 0.04792571514153063,
+      "eval_loss": 0.8422181010246277,
+      "eval_runtime": 91.6047,
+      "eval_samples_per_second": 7.674,
+      "eval_steps_per_second": 3.843,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.969148393422848e+16,
+  "total_flos": 2.628277562769408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null