Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cbf55743cc3b9d6b99c82ed22447ad8ea2dd0d86404b6ab4ac0380900d9f1e
+oid sha256:fe7c84f6e55b9429c7e05cef125d93845bf2084b981c56d2e1fb15b69b3ed017
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564ed2993d6c139f41b5dfe894237e10f34698d42dde5baba6d4b618b27cd8b5
+oid sha256:6f7df36119342eda593dbba10d73968b64a011e26870a4d681db9b619503744d
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ce5ef9acff86ae6374f269f37432b1bde430e53865dd5ffb83ec737a6238e0
+oid sha256:bc199b8769c6ef33424c1dfa3a0e46fecfd2c2a374bbce153a825a1e1b8de595
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005823829167677748,
+  "epoch": 0.008735743751516622,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 94.083,
       "eval_steps_per_second": 47.041,
       "step": 6
+    },
+    {
+      "epoch": 0.006794467362290706,
+      "grad_norm": 3.587212324142456,
+      "learning_rate": 0.00014,
+      "loss": 4.593,
+      "step": 7
+    },
+    {
+      "epoch": 0.007765105556903664,
+      "grad_norm": 3.538506507873535,
+      "learning_rate": 0.00016,
+      "loss": 4.1848,
+      "step": 8
+    },
+    {
+      "epoch": 0.008735743751516622,
+      "grad_norm": 3.0586044788360596,
+      "learning_rate": 0.00018,
+      "loss": 4.1642,
+      "step": 9
+    },
+    {
+      "epoch": 0.008735743751516622,
+      "eval_loss": 3.8936328887939453,
+      "eval_runtime": 4.585,
+      "eval_samples_per_second": 94.656,
+      "eval_steps_per_second": 47.328,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 30006069166080.0,
+  "total_flos": 45437761880064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null