Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e699f53036be930bd5a63812569f6cf296f07103e20241e7ef31901c03259100
+oid sha256:0832e76433f522c41934a6ebf36480ec199e619750aa7c4fb52e569647334046
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b279796636ec685c3a045acd09ad93e4f043d93e66a782c426447171d83721
+oid sha256:8ad4d32b6f9248fb1b25d9dfb397fcdc2fb2cbc217d245f1796c2c42e23fed52
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34899b4e0c2b02ca41e3b7d529ba4a9f07943c5a443b8133731540fec677b605
+oid sha256:db6537e434778211ceaf8a863d4d8984f5efaf5b467b798fc7ec30bbe158933e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024600246002460024,
+  "epoch": 0.02952029520295203,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 7.219,
       "eval_steps_per_second": 0.904,
       "step": 45
+    },
+    {
+      "epoch": 0.026240262402624025,
+      "grad_norm": 0.25208452343940735,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.609,
+      "step": 48
+    },
+    {
+      "epoch": 0.02788027880278803,
+      "grad_norm": 0.22854222357273102,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.696,
+      "step": 51
+    },
+    {
+      "epoch": 0.02952029520295203,
+      "grad_norm": 0.2772148847579956,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.6943,
+      "step": 54
+    },
+    {
+      "epoch": 0.02952029520295203,
+      "eval_loss": 0.631170928478241,
+      "eval_runtime": 426.7506,
+      "eval_samples_per_second": 7.22,
+      "eval_steps_per_second": 0.905,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1833584692232192e+17,
+  "total_flos": 1.421352351301632e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null