Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c725c39d410e1cc86077d7037eccfb1be8bb11272ac6e5efd6875bdedc89021
+oid sha256:c833f4567205fae09ccf95ff9485e8c936a0ce569c97a442b56869d07ef13894
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66edb06bd47771e6d9d855e27d846d8f6ad27273a7f3a5f599e5a946407406b
+oid sha256:efdecbba0e2e9923af95e4af803ccf010b0df7a76ec09354bb81ebab1ff4fd3f
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd50a23e6f0664128e73c6e676519a860b8250545aa786d69bfea11d765b5b5e
+oid sha256:23b0e1108b1c57e2ba1b7ccdcbd6bb769bad920c152da3b8f6a04fd19ca3c616
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01349983125210935,
+  "epoch": 0.020249746878164023,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 4.335,
       "eval_steps_per_second": 0.542,
       "step": 10
+    },
+    {
+      "epoch": 0.01619979750253122,
+      "grad_norm": 12.475789070129395,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 10.8456,
+      "step": 12
+    },
+    {
+      "epoch": 0.020249746878164023,
+      "grad_norm": 11.72419261932373,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 8.899,
+      "step": 15
+    },
+    {
+      "epoch": 0.020249746878164023,
+      "eval_loss": 1.7485647201538086,
+      "eval_runtime": 287.8964,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 0.542,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6277546018471936e+16,
+  "total_flos": 3.925000544531251e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null