Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e6ae29e1beda2d98937a2c2bdfcbe855cdaed6d575bb6ef4a8810daea3d441
+oid sha256:53d9160b015712ba94ccd85a7b38e39c58afc793a158f770b09eb7189a9c6199
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2075a26f248adfe8404c3f4984ec8eb634473c693deca725eedf47cc1341d610
+oid sha256:9efcba7e9aecbdd538c26d8c64ec462645f16419b09c47e88ffd8f039f2ae787
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824176984ad55e63482533637c9562406be551a7b54ccfb6e37dd38741558da7
+oid sha256:3e96cbbfd93d2129d3f0a3bd4543365323001975566244f444bd44373f63d1c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03687768899815612,
+  "epoch": 0.0430239704978488,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 12.715,
       "eval_steps_per_second": 1.595,
       "step": 30
+    },
+    {
+      "epoch": 0.040565457897971724,
+      "grad_norm": 1.404949426651001,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.4988,
+      "step": 33
+    },
+    {
+      "epoch": 0.0430239704978488,
+      "eval_loss": 0.4986587464809418,
+      "eval_runtime": 107.8743,
+      "eval_samples_per_second": 12.709,
+      "eval_steps_per_second": 1.594,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7141049335808e+16,
+  "total_flos": 5.468361722953728e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null