Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b569eefc4c6896d4d630b634639120775480c4921f003ac58425b50708b473b
+oid sha256:f360b7ad4ad730f4fa9bce7f2ea631339233584bd74af6ad41791d4820f21ebe
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f64a5da5ddaa1ef9e1ed90c4244d6efc7cf5a764dc2cd3078277eb72c73691
+oid sha256:24df988401d0e0304f7e1f2ae193afe449ecc27c6eb3f375636d948253ea8f74
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff6af0de44d2814b4db7f4a2ca86f793c003562b5d1e80c06593c1beec43281
+oid sha256:67e9e7b978e914c84d386479aa37cc1d7c932c264297fa6273686f760143c92a
 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": 0.013251858941323713,
+  "epoch": 0.015902230729588455,
   "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": 14.36,
       "eval_steps_per_second": 1.795,
       "step": 45
+    },
+    {
+      "epoch": 0.014135316204078627,
+      "grad_norm": 7.323680400848389,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 3.6858,
+      "step": 48
+    },
+    {
+      "epoch": 0.015018773466833541,
+      "grad_norm": 8.582962036132812,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 3.484,
+      "step": 51
+    },
+    {
+      "epoch": 0.015902230729588455,
+      "grad_norm": 7.271780490875244,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 3.4188,
+      "step": 54
+    },
+    {
+      "epoch": 0.015902230729588455,
+      "eval_loss": 0.8784601092338562,
+      "eval_runtime": 398.3464,
+      "eval_samples_per_second": 14.359,
+      "eval_steps_per_second": 1.795,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.330948626939904e+16,
+  "total_flos": 7.597138352327885e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null