Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2652abf1343e1bf9b730f48496d03ba8405c6af5a6d8eada9fc355ec1f463a47
+oid sha256:af70f7222c9cdf2e69819047e2aa13d72c772bd26f08a078d0fba3393893db62
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011d9daacc42eef1607de6984f671fd4615b13a3e9e574f97dfa2231ae2278b9
+oid sha256:1f592bfc075e83062ff92534db96d79b8185858049c8afbd40bd85c2d07d9aea
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786c2a878181864eaae3009c839540dd50237b1930f80d9955fbabc0ccf3cc14
+oid sha256:288a16e6d9d8c06d39eaaf028ab7ce6ab9c130eeb62c3121161c9ecb57cfd771
 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": 0.08620689655172414,
+  "epoch": 0.12931034482758622,
   "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": 10.871,
       "eval_steps_per_second": 1.394,
       "step": 10
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 12.58159065246582,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 3.2548,
+      "step": 12
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 14.037184715270996,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.3872,
+      "step": 15
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "eval_loss": 0.710814893245697,
+      "eval_runtime": 17.9839,
+      "eval_samples_per_second": 10.843,
+      "eval_steps_per_second": 1.39,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.430998008987648e+16,
+  "total_flos": 2.146497013481472e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null