Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13be8127352ab94757b1eb6d5489615f6c0f3bda29b91c22d76f33ed5f1829b7
+oid sha256:2652abf1343e1bf9b730f48496d03ba8405c6af5a6d8eada9fc355ec1f463a47
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712499cebafafcfe394245629f7af02a4cfdcbef5a8eb46713f4bfbb4deb1850
+oid sha256:011d9daacc42eef1607de6984f671fd4615b13a3e9e574f97dfa2231ae2278b9
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434672bc320e504dce8f6e74bfb7b702b872a8235385e50588f42567e4f518d8
+oid sha256:786c2a878181864eaae3009c839540dd50237b1930f80d9955fbabc0ccf3cc14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04310344827586207,
+  "epoch": 0.08620689655172414,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 10.912,
       "eval_steps_per_second": 1.399,
       "step": 5
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 23.90378761291504,
+      "learning_rate": 6e-05,
+      "loss": 5.3623,
+      "step": 6
+    },
+    {
+      "epoch": 0.07758620689655173,
+      "grad_norm": 28.774568557739258,
+      "learning_rate": 9e-05,
+      "loss": 4.0848,
+      "step": 9
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "eval_loss": 0.7605625987052917,
+      "eval_runtime": 17.9379,
+      "eval_samples_per_second": 10.871,
+      "eval_steps_per_second": 1.394,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7154990044938240.0,
+  "total_flos": 1.430998008987648e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null