Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e5699feca64cc2226c5b64b1095bcbd944ffb7e9587dd14b6c2ed5f8ac4862
+oid sha256:ef1b00c2738c8c50c8073dd715a29c58949af6b803a71c831c2907093b5ddf74
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e13f6b3448207d37acf9822394ff148baae6a6488d93722d66015bf2e47f4d
+oid sha256:b24e0dcadf6021364075a9a3b1829590a517d02fb7db649f01416c87d0e4a74e
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79faadec78d9324db85426283c4b0dad06a82789063bcf0172acc0f8f8dae27
+oid sha256:58e5f31706ad31f4bcf35dc7d26da44ecde745fbea34c5bd206578e6660fd7cc
 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": 0.010790396547073105,
+  "epoch": 0.016185594820609658,
   "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": 7.2151,
       "step": 18
+    },
+    {
+      "epoch": 0.01132991637442676,
+      "grad_norm": 2.173295497894287,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.8568,
+      "step": 21
+    },
+    {
+      "epoch": 0.012948475856487725,
+      "grad_norm": 2.8592050075531006,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.9924,
+      "step": 24
+    },
+    {
+      "epoch": 0.012948475856487725,
+      "eval_loss": 1.7228505611419678,
+      "eval_runtime": 26.6676,
+      "eval_samples_per_second": 29.286,
+      "eval_steps_per_second": 14.662,
+      "step": 24
+    },
+    {
+      "epoch": 0.014567035338548692,
+      "grad_norm": 2.179098606109619,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.6299,
+      "step": 27
+    },
+    {
+      "epoch": 0.016185594820609658,
+      "grad_norm": 2.3229246139526367,
+      "learning_rate": 0.0,
+      "loss": 6.8717,
+      "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": 307163125776384.0,
+  "total_flos": 458848619986944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null