Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b966f868ca6e8b59d918ea5da30d6143ec9cf9206f53d865d584e6fcf91a85
+oid sha256:98905e7d37a8aa0d6df45ba681f3a2a4359e4336604bee4ffc227150b9806c95
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0192be81a8255a50847d7878ded22fea3e78a98e59b81e8f7905980afa787bd6
+oid sha256:49deef8f299a331a25efff71e9b859f94ea84d718be78b8227128ff95c29df0d
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b430ed7388c9c2514355d3ab898365b059abd7800c2ef04ec1bea56dd145ef8
+oid sha256:25c509aaa365c9873a5507cd533df3abf62268c415e299cebaee5bfc9f5cea8a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033739456419868794,
+  "epoch": 0.06747891283973759,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 34.996,
       "eval_steps_per_second": 4.433,
       "step": 9
+    },
+    {
+      "epoch": 0.04498594189315839,
+      "grad_norm": 0.2559334337711334,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 2.0606,
+      "step": 12
+    },
+    {
+      "epoch": 0.056232427366447985,
+      "grad_norm": 0.15697269141674042,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 2.0357,
+      "step": 15
+    },
+    {
+      "epoch": 0.06747891283973759,
+      "grad_norm": 0.16153453290462494,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 2.005,
+      "step": 18
+    },
+    {
+      "epoch": 0.06747891283973759,
+      "eval_loss": 2.0186078548431396,
+      "eval_runtime": 12.902,
+      "eval_samples_per_second": 34.878,
+      "eval_steps_per_second": 4.418,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2882117805539328.0,
+  "total_flos": 5844294439010304.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null