Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6edd74da50391d4fc5e07505d76d42499020416716e240c908786b1ae485cba
+oid sha256:974949f77f0a14b4199397c8ba5e2711f830212568ab0bfb2ed01e6c7250c7e0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b58e27905531bb921c4c1187368754f40781cdf1fe952949208c6067d3e472
+oid sha256:e0bc4aa4048af27fec57240e1206a51560d0aa8ae57d2f6ef5d4a90bcda27d0b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00568e605ceafffef2ed3ab927c41a9d69ed991c2bf18e3c9eabc53dd3833d46
+oid sha256:c150e7a0df1bbdf6fa35b33f81ebbc56fd08d0eb855b36785312a07efa2d1cde
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77b562cb3719c814c3e7999705d44634b14e0d87d91aa14ab1d432f7d2fd6c1
+oid sha256:15a153ae523f6f915c8c717e9164535eda8efd532a3b2e2efaf3c667d39d242b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05877366487708392,
+  "epoch": 0.0734670810963549,
   "eval_steps": 13,
-  "global_step": 52,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,42 @@
       "eval_samples_per_second": 6.626,
       "eval_steps_per_second": 0.832,
       "step": 52
+    },
+    {
+      "epoch": 0.061034190449279456,
+      "grad_norm": 1.0566143989562988,
+      "learning_rate": 3.8772424536302564e-05,
+      "loss": 0.555,
+      "step": 54
+    },
+    {
+      "epoch": 0.06442497880757277,
+      "grad_norm": 1.0105335712432861,
+      "learning_rate": 3.7337705451608674e-05,
+      "loss": 0.5633,
+      "step": 57
+    },
+    {
+      "epoch": 0.06781576716586607,
+      "grad_norm": 1.0776220560073853,
+      "learning_rate": 3.5847093477938956e-05,
+      "loss": 0.5251,
+      "step": 60
+    },
+    {
+      "epoch": 0.07120655552415937,
+      "grad_norm": 1.2005013227462769,
+      "learning_rate": 3.4307341460048633e-05,
+      "loss": 0.5479,
+      "step": 63
+    },
+    {
+      "epoch": 0.0734670810963549,
+      "eval_loss": 0.13397091627120972,
+      "eval_runtime": 224.8,
+      "eval_samples_per_second": 6.628,
+      "eval_steps_per_second": 0.832,
+      "step": 65
     }
   ],
   "logging_steps": 3,
@@ -185,7 +221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.462511032294441e+17,
+  "total_flos": 1.8281387903680512e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null