Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77f3e5d1289bba64d0fe9d2b1eb1b3bbc31b8fab083e6c9fc03003a927967cd
+oid sha256:9b776cef4a8b110f29f03f1f2a505ab26816d15755d261cab864eced6635967f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58d0ffe0e12c31a8e225eb979c810b76c5a6019aa5dee8426d03333ec1a6d33
+oid sha256:db7cd6507b3e6336497c085dcdbab5771e4bc873fa652e44ade43922d4c8c091
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698a2a174d63a3686e64f723632c723119c5cfbfc1884cf988ecbf3863d7db38
+oid sha256:d24904fc57fd2178e69b645251775fb3fd05ea113003861d10791be78a06f1a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021534320323014805,
+  "epoch": 0.03230148048452221,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 7.812,
       "eval_steps_per_second": 7.812,
       "step": 8
+    },
+    {
+      "epoch": 0.024226110363391656,
+      "grad_norm": 1.7297841310501099,
+      "learning_rate": 0.00018,
+      "loss": 0.3654,
+      "step": 9
+    },
+    {
+      "epoch": 0.026917900403768506,
+      "grad_norm": 1.6552913188934326,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 10
+    },
+    {
+      "epoch": 0.029609690444145357,
+      "grad_norm": 1.50761079788208,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.4244,
+      "step": 11
+    },
+    {
+      "epoch": 0.03230148048452221,
+      "grad_norm": 1.431064248085022,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.2788,
+      "step": 12
+    },
+    {
+      "epoch": 0.03230148048452221,
+      "eval_loss": 0.32530486583709717,
+      "eval_runtime": 10.0708,
+      "eval_samples_per_second": 7.844,
+      "eval_steps_per_second": 7.844,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3431228686467072.0,
+  "total_flos": 5007739164033024.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null