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:c9398ca1f244b98baf693cd2f0b87f6499445218c4ed1c30e34848feb13b22c7
+oid sha256:dadede353f4372c078a32b2bf026892fade378aa258378da7d187d2a68f266de
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71c407168f4c2269c0f69d47f80dfc3bf8958b3044b8a43c3de9a9c36f84d66
+oid sha256:e1abe00ee71c544cd30c0812ece91dff81f1d322f97557fa2d29ff51aa062c90
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfeb80672bc82fbc9cf7b55a6f4b05f3057992133a3ddf20f5677f3611342707
+oid sha256:8e7fb8194f244bb999a0fcd4213d2217d37e5555cee829c566323dc715912866
 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": 0.027972027972027972,
+  "epoch": 0.033566433566433566,
   "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": 10.048,
       "eval_steps_per_second": 1.257,
       "step": 45
+    },
+    {
+      "epoch": 0.029836829836829837,
+      "grad_norm": 2.5003011226654053,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 3.0484,
+      "step": 48
+    },
+    {
+      "epoch": 0.031701631701631705,
+      "grad_norm": 2.3574583530426025,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 3.1361,
+      "step": 51
+    },
+    {
+      "epoch": 0.033566433566433566,
+      "grad_norm": 2.1045308113098145,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 2.9611,
+      "step": 54
+    },
+    {
+      "epoch": 0.033566433566433566,
+      "eval_loss": 3.046522617340088,
+      "eval_runtime": 269.8245,
+      "eval_samples_per_second": 10.044,
+      "eval_steps_per_second": 1.256,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.088119223615488e+16,
+  "total_flos": 1.0905743068338586e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null