Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d14ac6ad51e55d0dc019420a6ca5bbcd36ee7ea8a81723595d771c44ddf3a3d
+oid sha256:87eceed1967c8bd0c320fd6eba1bedc93a96a7a1ed9418e240f2920ab4c1d79c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde3730dd93a1c897d6459260369cf98ccfa89ec60f06f7e18a1dccbeb9e8c77
+oid sha256:da0833dc932af47b53a1622f93720f7bfa8ebb586a7771cbabf0773b0c06f5cb
 size 250679090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb442123aba3d10024f2c4096c526480f6ecac2d4f9ab1997281b472d7f91d2
+oid sha256:40c68ffab4b21297e45ed3ee7d7dea552f1b0499ba35355fdd480197c38f72ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.1751474348937944e-05,
+  "epoch": 8.350294869787589e-05,
   "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": 9.871,
       "eval_steps_per_second": 9.871,
       "step": 3
+    },
+    {
+      "epoch": 5.56686324652506e-05,
+      "grad_norm": 4.169151782989502,
+      "learning_rate": 6e-05,
+      "loss": 5.5239,
+      "step": 4
+    },
+    {
+      "epoch": 6.958579058156325e-05,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 5.6624,
+      "step": 5
+    },
+    {
+      "epoch": 8.350294869787589e-05,
+      "grad_norm": 2.504304885864258,
+      "learning_rate": 8e-05,
+      "loss": 3.8521,
+      "step": 6
+    },
+    {
+      "epoch": 8.350294869787589e-05,
+      "eval_loss": 5.870975494384766,
+      "eval_runtime": 1533.6973,
+      "eval_samples_per_second": 9.864,
+      "eval_steps_per_second": 9.864,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 951987260620800.0,
+  "total_flos": 1903974521241600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null