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:ed182cfba10f32a256dba2e57c3237f99a84a43c747f40a7d3df958cf2c61f15
+oid sha256:32dea6e4e5170bfb423ca466356b99863c849a950e791108c0205c7bb7b1f100
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62fb5046a37f60de37bda587fa373e149dd913bc4528bb6950497b63a91e85f5
+oid sha256:2b1dde45273ec86fa7d6c95c2bf4f8b7d4b52d5be2737d8b606563c8e6e26622
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fe2cb579250223e5605209364eda9a1e54f87ddb866ab9aac82baf67f204b3
+oid sha256:5a0b87dc282dad728c66b4d753e6ae2f4448e4e08a282ac0123430e0e1dc3035
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00816326530612245,
+  "epoch": 0.012244897959183673,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 4.1099,
       "step": 18
+    },
+    {
+      "epoch": 0.008571428571428572,
+      "grad_norm": 1.987960696220398,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.4062,
+      "step": 21
+    },
+    {
+      "epoch": 0.009795918367346938,
+      "grad_norm": 1.5989941358566284,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.8699,
+      "step": 24
+    },
+    {
+      "epoch": 0.009795918367346938,
+      "eval_loss": 0.9915894269943237,
+      "eval_runtime": 71.3937,
+      "eval_samples_per_second": 14.455,
+      "eval_steps_per_second": 7.228,
+      "step": 24
+    },
+    {
+      "epoch": 0.011020408163265306,
+      "grad_norm": 2.049525499343872,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.1971,
+      "step": 27
+    },
+    {
+      "epoch": 0.012244897959183673,
+      "grad_norm": 2.069650411605835,
+      "learning_rate": 0.0,
+      "loss": 3.7882,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.200613496979456e+16,
+  "total_flos": 1.772334209826816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null