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:a4833f6ebd6d0e9864dc020e1d3136af1ddec8bdf53c9c15860c2d6711cdcd5d
+oid sha256:219f98fdea6e4bad0d5a53ad00e1054a61d0dffc2598a9723d873e9d3148952a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459ae6d72cfd0b303b42a4cd1bdaffafdb46d1a40cbcbcd167fc7737b38ce6f0
+oid sha256:6354f1284b1e2e5df27cc4d3ed4a8ecc2c746d9760ac7fdeb1e11034224d1de2
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b28d32e44f1b86535ab5c43f746f36446a2f15908fbf88502e3cd1ccb9dd7ad
+oid sha256:9e17e59518a33349d3e7ccb2a3d6202e23618632431c2022d3d7024a72198bc7
 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": 0.05693199789140749,
+  "epoch": 0.0632577754348972,
   "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": 7.111,
       "eval_steps_per_second": 0.89,
       "step": 81
+    },
+    {
+      "epoch": 0.05904059040590406,
+      "grad_norm": 0.19214046001434326,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.7157,
+      "step": 84
+    },
+    {
+      "epoch": 0.061149182920400634,
+      "grad_norm": 0.20953665673732758,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.7124,
+      "step": 87
+    },
+    {
+      "epoch": 0.0632577754348972,
+      "grad_norm": 0.18339523673057556,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.7001,
+      "step": 90
+    },
+    {
+      "epoch": 0.0632577754348972,
+      "eval_loss": 0.708888828754425,
+      "eval_runtime": 336.9158,
+      "eval_samples_per_second": 7.115,
+      "eval_steps_per_second": 0.89,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1419449387057152e+17,
+  "total_flos": 2.379938820784128e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null