Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c678508baa620999e77b560dd2808b8e025b226dd2cfddc736c1613d9011537d
+oid sha256:6df182f19c41d9c2b124cf4680a109e1b7037f8ea0d7230ff809a8c8d3eb2972
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1f37c6a12ac852d8482bc9dae65402d6829d81a784485248f60b2f20fc777a
+oid sha256:37c85b50034ac88ef4a8be2d680afbb41e1d2fa147be9e0b60d2fd6b01205784
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a6e54f9735ac650e1bce7d31fe07be9de05d82d7f44a83bbaaeae992231fe8
+oid sha256:20911ca91ea1cdbb81acbe54f05a1245788489144f858e8e56a7eb8a4d073e18
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008075370121130552,
+  "epoch": 0.016150740242261104,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.161,
       "eval_steps_per_second": 13.161,
       "step": 3
+    },
+    {
+      "epoch": 0.010767160161507403,
+      "grad_norm": 1.4571020603179932,
+      "learning_rate": 8e-05,
+      "loss": 0.7401,
+      "step": 4
+    },
+    {
+      "epoch": 0.013458950201884253,
+      "grad_norm": 1.4379603862762451,
+      "learning_rate": 0.0001,
+      "loss": 0.7416,
+      "step": 5
+    },
+    {
+      "epoch": 0.016150740242261104,
+      "grad_norm": 1.3622642755508423,
+      "learning_rate": 0.00012,
+      "loss": 0.6918,
+      "step": 6
+    },
+    {
+      "epoch": 0.016150740242261104,
+      "eval_loss": 0.5574197769165039,
+      "eval_runtime": 6.066,
+      "eval_samples_per_second": 13.023,
+      "eval_steps_per_second": 13.023,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 601108380647424.0,
+  "total_flos": 1387173186109440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null