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:ee3436edb90a0d37e4d2e20cbbacf18a266d5d07cef0b2c73d3c5ae4bcaa7cff
+oid sha256:57b8572ea6bcc71716daea56955573d8f840ee09afa2a670538e1e92f1cda1e2
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a93d594bb469f903a3aabf998f00aad0fcd2ede27a0935b8d33057f140cc7c
+oid sha256:8045801b952ad59a8de7f85fc3ef51586fe04f3ee8fb6f9a129952fcd30dd64d
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b835124e9438a67b4922362546d9917dd2ad1ecf9964a45797b5ccba615a520
+oid sha256:59df7afd136d7d297b97da3cc6a2058951d106b19caae0e204a9e3c56e836308
 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": 0.003305238803503553,
+  "epoch": 0.00495785820525533,
   "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": 7.0048,
       "step": 18
+    },
+    {
+      "epoch": 0.0034705007436787306,
+      "grad_norm": 18.893150329589844,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.83,
+      "step": 21
+    },
+    {
+      "epoch": 0.0039662865642042635,
+      "grad_norm": 12.152100563049316,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.4333,
+      "step": 24
+    },
+    {
+      "epoch": 0.0039662865642042635,
+      "eval_loss": 1.6485315561294556,
+      "eval_runtime": 165.7096,
+      "eval_samples_per_second": 15.376,
+      "eval_steps_per_second": 7.688,
+      "step": 24
+    },
+    {
+      "epoch": 0.004462072384729797,
+      "grad_norm": 9.412213325500488,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.8263,
+      "step": 27
+    },
+    {
+      "epoch": 0.00495785820525533,
+      "grad_norm": 25.07528305053711,
+      "learning_rate": 0.0,
+      "loss": 6.6015,
+      "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": 5777796587520000.0,
+  "total_flos": 8738917338624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null