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:b559f23a8399f96cf6f7a2cf696509bb93418d3ab73975af1aeb19722a0290da
+oid sha256:3e445d76ae58d11894e69b613547df1819fcf18427849ec8b2c068c26778b66c
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cb98bf8ad8ac67c293503939b4b61b906ba776d25139d14b34ec6a8fecb014
+oid sha256:7268dda5b03338ee90fab01cf04c935d05698d3f1c2e51882d0bac98fbc92ad5
 size 111412180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0a4eb6a1d6fa858649d397f2ec03945eb291b9496e83e68d41abb19befc091
+oid sha256:fabe282c318f809f95f678d3b5880b0fa8c959a134bd1d0319f0df983d97fc58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12121212121212122,
+  "epoch": 0.24242424242424243,
   "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": 11.092,
       "eval_steps_per_second": 1.42,
       "step": 9
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.07933423668146133,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.003,
+      "step": 12
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.016316216439008713,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0004,
+      "step": 15
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.0206525269895792,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0003,
+      "step": 18
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "eval_loss": 0.0002653657866176218,
+      "eval_runtime": 11.2826,
+      "eval_samples_per_second": 11.079,
+      "eval_steps_per_second": 1.418,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5255898586873856e+16,
+  "total_flos": 3.051179717374771e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null