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:c0acf33062b6fa01e5023408826a08a68ebbe4f9d25036821e8a37117665eb83
+oid sha256:67f335ad51383fe9d96215bf8c29dda0c33f08def8f5ce1a5fa62baa732d0d6a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37faa4e718ac855dfa67ed13dfbf638a0f8c14a0fe613ccb91403340543551ed
+oid sha256:fefa57ae3498996966aa6f87d04c3a11f5b0cde88755ee7f1c412bfc8f6f2843
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158ffbe0f2ee7fc6dccf80a7f7ec48588fcc581cde4740f9b308f9b2d4098f5c
+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": 0.00020710722976821248,
+  "epoch": 0.00041421445953642496,
   "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": 27.39,
       "eval_steps_per_second": 13.697,
       "step": 3
+    },
+    {
+      "epoch": 0.0002761429730242833,
+      "grad_norm": 1.0205483436584473,
+      "learning_rate": 8e-05,
+      "loss": 0.6226,
+      "step": 4
+    },
+    {
+      "epoch": 0.00034517871628035417,
+      "grad_norm": 0.9916964769363403,
+      "learning_rate": 0.0001,
+      "loss": 0.6296,
+      "step": 5
+    },
+    {
+      "epoch": 0.00041421445953642496,
+      "grad_norm": 1.6199209690093994,
+      "learning_rate": 0.00012,
+      "loss": 0.8327,
+      "step": 6
+    },
+    {
+      "epoch": 0.00041421445953642496,
+      "eval_loss": 1.1207962036132812,
+      "eval_runtime": 222.9444,
+      "eval_samples_per_second": 27.357,
+      "eval_steps_per_second": 13.681,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 693598672650240.0,
+  "total_flos": 1387197345300480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null