Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2453b22f077c9e633155bde5a44c5a5c92ddb254cf0fe9e618e76bbd38133b08
+oid sha256:1e87e440bf2e1846b30f0d4a6cbbc9312c6b661166524c7e788b4d7f64b7bb7e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79d76de3a27d79eb105caffe8c2ea0c9c2c134159ec637025bffdd723a230d4
+oid sha256:17b665f2f1d3260fc134690ee3cfdbc8cdb282b1a34ba3a82aee53429c8fe2db
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade06f0db401bf7db7e4bf579716041b8a433a97a601335efdecad97edb03945
+oid sha256:e537cc525318fa48a97713b6f30825cf7ad8337947272a02e54c5724bee9a3c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007586476804046121,
+  "epoch": 0.008670259204624138,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 7.043,
       "eval_steps_per_second": 0.881,
       "step": 63
+    },
+    {
+      "epoch": 0.007947737604238793,
+      "grad_norm": 12.176066398620605,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 5.5682,
+      "step": 66
+    },
+    {
+      "epoch": 0.008308998404431465,
+      "grad_norm": 15.984620094299316,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 5.8425,
+      "step": 69
+    },
+    {
+      "epoch": 0.008670259204624138,
+      "grad_norm": 13.588284492492676,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.1731,
+      "step": 72
+    },
+    {
+      "epoch": 0.008670259204624138,
+      "eval_loss": 1.423056721687317,
+      "eval_runtime": 1986.6579,
+      "eval_samples_per_second": 7.04,
+      "eval_steps_per_second": 0.88,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7718883660490342e+17,
+  "total_flos": 2.0250152754846106e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null