Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee45b1cdd36db68e069c53deed747e5e3c9036e3d4c63ed4c4799a594eda0d55
+oid sha256:08cca996b958b09becde0c477cf8c843ffccfae16b1df282d13d863d026847bf
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2668cd347986663a366567d5def91046d0f6ec5598af9e1847ba914d7328418
+oid sha256:758569d2c76262db35a2a99eb88d520ffc36b23c5cfbb2909c37f481cb919713
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6c14874f8ead57c2fa8d8a60d83f94c33e974fd2075d5b17518426868d7142
+oid sha256:c53416f50af32d04b9099560de94b7eda2ac7de98df5f4387b71785667ea642a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8977565a0b4b10da6945c32ba36caa3dc40fc9a4cdc4d66a537fb19aba96e0c7
+oid sha256:ff360a84775339d0d3e752ae059cb60f5332814e8f938b32d8d690f5d4087fc5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03178678403325386,
+  "epoch": 0.03423192126658109,
   "eval_steps": 34,
-  "global_step": 65,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -478,6 +478,49 @@
       "learning_rate": 0.000179801722728024,
       "loss": 1.1485,
       "step": 65
+    },
+    {
+      "epoch": 0.03227581147991931,
+      "grad_norm": 1.2176910638809204,
+      "learning_rate": 0.00017867449380334834,
+      "loss": 1.0743,
+      "step": 66
+    },
+    {
+      "epoch": 0.03276483892658476,
+      "grad_norm": 1.239547848701477,
+      "learning_rate": 0.00017752039761111297,
+      "loss": 1.0839,
+      "step": 67
+    },
+    {
+      "epoch": 0.0332538663732502,
+      "grad_norm": 1.4201483726501465,
+      "learning_rate": 0.00017633982827411032,
+      "loss": 1.1837,
+      "step": 68
+    },
+    {
+      "epoch": 0.0332538663732502,
+      "eval_loss": 1.062552571296692,
+      "eval_runtime": 1315.0047,
+      "eval_samples_per_second": 1.964,
+      "eval_steps_per_second": 0.655,
+      "step": 68
+    },
+    {
+      "epoch": 0.033742893819915645,
+      "grad_norm": 1.2789006233215332,
+      "learning_rate": 0.00017513318895568737,
+      "loss": 1.0102,
+      "step": 69
+    },
+    {
+      "epoch": 0.03423192126658109,
+      "grad_norm": 1.3672975301742554,
+      "learning_rate": 0.00017390089172206592,
+      "loss": 1.3682,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -497,7 +540,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.885320227107635e+17,
+  "total_flos": 3.1072679368851456e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null