Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a19b98d62fb904cffcdc301355e586fd53215d21a5f5a0d29b2fc346aca1906
+oid sha256:424a3df412cf8c918ef0a8e92eca1c66eae42c30a32d6ce71544d5ee966f5989
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92aa298a1e7abcd0bfeb5304fc5b2f2d4525902e6a1845231d2cf0a06c850fab
+oid sha256:c494268409b65803dfc49cec96f6902874637c488c64ba4527e1a39031ded2c7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26de26af28a2f1f0737bbb567d821cbade1dbd88fac5f3ff990ed41adb85f07c
+oid sha256:0170ac6e43387e4421d0f20421c57b816b53cdb93b7e860b5657d28983a51482
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.137462876537972,
+  "epoch": 0.15273652948663555,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 13.69,
       "eval_steps_per_second": 1.723,
       "step": 81
+    },
+    {
+      "epoch": 0.14255409418752651,
+      "grad_norm": 0.4353705644607544,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.3578,
+      "step": 84
+    },
+    {
+      "epoch": 0.14764531183708104,
+      "grad_norm": 0.5827435851097107,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.3565,
+      "step": 87
+    },
+    {
+      "epoch": 0.15273652948663555,
+      "grad_norm": 0.45924094319343567,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.3456,
+      "step": 90
+    },
+    {
+      "epoch": 0.15273652948663555,
+      "eval_loss": 0.3645370602607727,
+      "eval_runtime": 72.5734,
+      "eval_samples_per_second": 13.683,
+      "eval_steps_per_second": 1.722,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.205566835785728e+17,
+  "total_flos": 1.3391065468266086e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null