Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e8a26f3f57f3ca20fa5753a4b50a55eb51a1771ce64bd4d0897f6b4add7ecf
+oid sha256:78dac7535dac9a926aa3d6f1cede2677776554a31ae3b03733c9be34bb45feb8
 size 3380768360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6678e377e56ff4352948db5780be2cab954115593707e8eae935e841cfb4995
-size 1757617777
+oid sha256:6ddc11eef2343db6f5ad7d3c768a98ae313ab5bdd1d33c62a12390009d4c92aa
+size 1757899449

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccf6167c808ff7ae6fa6b87015b87701a77af18e7bc2a55dc01402d99d386a7
+oid sha256:97490d166ca8bc27bfa10807632f9ecb473b145cce74c93d287cde23f8af51fb
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fcc312b60864d5ca59d7feaf623987674e51ded74157218540ec0457a67c222
+oid sha256:69b592d4efa2ff6d0584dfc8cf30049181a8d5c8977939386b39d5882c0a494e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9407665505226481,
+  "epoch": 1.2508710801393728,
   "eval_steps": 30,
-  "global_step": 90,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,56 @@
       "eval_samples_per_second": 0.292,
       "eval_steps_per_second": 0.073,
       "step": 90
+    },
+    {
+      "epoch": 0.9930313588850174,
+      "grad_norm": 0.10834779590368271,
+      "learning_rate": 5.4217553302152237e-05,
+      "loss": 0.2944,
+      "step": 95
+    },
+    {
+      "epoch": 1.0418118466898956,
+      "grad_norm": 0.0633026584982872,
+      "learning_rate": 5e-05,
+      "loss": 0.2095,
+      "step": 100
+    },
+    {
+      "epoch": 1.0940766550522647,
+      "grad_norm": 0.07635607570409775,
+      "learning_rate": 4.578244669784777e-05,
+      "loss": 0.2058,
+      "step": 105
+    },
+    {
+      "epoch": 1.146341463414634,
+      "grad_norm": 0.0802493542432785,
+      "learning_rate": 4.15949552878926e-05,
+      "loss": 0.2232,
+      "step": 110
+    },
+    {
+      "epoch": 1.1986062717770034,
+      "grad_norm": 0.12653642892837524,
+      "learning_rate": 3.746737338706397e-05,
+      "loss": 0.2532,
+      "step": 115
+    },
+    {
+      "epoch": 1.2508710801393728,
+      "grad_norm": 0.07813160121440887,
+      "learning_rate": 3.3429121589068215e-05,
+      "loss": 0.2893,
+      "step": 120
+    },
+    {
+      "epoch": 1.2508710801393728,
+      "eval_loss": 0.239236518740654,
+      "eval_runtime": 1751.4721,
+      "eval_samples_per_second": 0.291,
+      "eval_steps_per_second": 0.073,
+      "step": 120
     }
   ],
   "logging_steps": 5,
@@ -184,7 +234,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.879999872679608e+17,
+  "total_flos": 7.763514566754386e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null