Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e9cb39520de6c97dd8daa6d7fe73a7d1db36c97e4373a9ab4bd9c390e52c11
+oid sha256:25032b2e19e3de41e30b2481e1537dc791fc37203f8e8ea85ca0db525881517b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb90ae6d929a5bea3d77e0fca83076b4ebaf0255298cce0eda9a9957e793c5e
+oid sha256:0bd4e40b560608d2752118ec8ccc0d19663387a2a69bbcd8e2d092ee1e509517
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579360aedf9e1e6d78ecaf690eee9abae295d9f1032a5ecb7ca3cda426db0d8f
+oid sha256:2aaa6d8a69d8299a907823adc599422c15491312a4bfb634b6631045d063f404
 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": 0.019056693663649357,
+  "epoch": 0.028585040495474036,
   "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": 6.286,
       "eval_steps_per_second": 0.789,
       "step": 10
+    },
+    {
+      "epoch": 0.022868032396379228,
+      "grad_norm": 1.6127707958221436,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 2.5243,
+      "step": 12
+    },
+    {
+      "epoch": 0.028585040495474036,
+      "grad_norm": 1.2866557836532593,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.3552,
+      "step": 15
+    },
+    {
+      "epoch": 0.028585040495474036,
+      "eval_loss": 2.4209542274475098,
+      "eval_runtime": 140.5703,
+      "eval_samples_per_second": 6.289,
+      "eval_steps_per_second": 0.79,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.017027157491712e+16,
+  "total_flos": 4.525540736237568e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null