Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b3be0182951c86ab42460fd53c9aa743551e8cfdb21ece00d88c9f586a6f29
+oid sha256:d9dae6138d55e8d27a95d83684775eee594f6fd145f270047346242ebbfc59dd
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c26181db70bd047925fea9057d6b33e535395c66393d6df5809713a687b5dc0
+oid sha256:aa92939fefd1dd4bfee81db8b7d625ee11c2781994bd33df060f1dfd2020b63c
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697e759ec8222aa0e23746189c36f77f94c8f2281dc9c6ce9c6f988295fcd33f
+oid sha256:b3929c2ea5412dacf6de43a4383df6849ffa1cfdcac23dc83a27b21a0dcc6861
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003717932829346883,
+  "epoch": 0.007435865658693766,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 5.578,
       "eval_steps_per_second": 2.791,
       "step": 15
+    },
+    {
+      "epoch": 0.00446151939521626,
+      "grad_norm": 0.7465487122535706,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6662,
+      "step": 18
+    },
+    {
+      "epoch": 0.004957243772462511,
+      "eval_loss": 0.6128036975860596,
+      "eval_runtime": 297.1192,
+      "eval_samples_per_second": 5.718,
+      "eval_steps_per_second": 2.861,
+      "step": 20
+    },
+    {
+      "epoch": 0.005205105961085636,
+      "grad_norm": 1.5202752351760864,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6669,
+      "step": 21
+    },
+    {
+      "epoch": 0.005948692526955013,
+      "grad_norm": 0.6265591979026794,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5783,
+      "step": 24
+    },
+    {
+      "epoch": 0.006196554715578138,
+      "eval_loss": 0.5611212253570557,
+      "eval_runtime": 146.0056,
+      "eval_samples_per_second": 11.637,
+      "eval_steps_per_second": 5.822,
+      "step": 25
+    },
+    {
+      "epoch": 0.006692279092824389,
+      "grad_norm": 0.6711304783821106,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5688,
+      "step": 27
+    },
+    {
+      "epoch": 0.007435865658693766,
+      "grad_norm": 0.5014675855636597,
+      "learning_rate": 0.0,
+      "loss": 0.5148,
+      "step": 30
+    },
+    {
+      "epoch": 0.007435865658693766,
+      "eval_loss": 0.5482997298240662,
+      "eval_runtime": 145.7456,
+      "eval_samples_per_second": 11.657,
+      "eval_steps_per_second": 5.832,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5123479405854720.0,
+  "total_flos": 1.016432204709888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null