Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461e45f062291593664f70f6350c999f75a86d1146a5dff273e077ddfff916cb
+oid sha256:85b376ad1f20e0a96dc6d12291a3fceb54fcaf654a80ae376f5b4307170c059e
 size 102812592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a9fef1f8a913abe85e14637a08b6b249ebd62b1c4ae2c9fb0b1a7a6bb01bba
+oid sha256:b54654c28522bbd52905a8893cdc09b061b1ff02c48cc79ab69f1d0c8fbb6c05
 size 205850474

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1fb422c59d5580726dafb7c0759e8ded729b26f46035e173f05331834f6b74
+oid sha256:fd778f01e70aadc89439ba0d91a94104c295c30c9876d3c62bb03d5aa427f028
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002033657023742946,
+  "epoch": 0.004067314047485892,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 17.891,
       "eval_steps_per_second": 8.95,
       "step": 10
+    },
+    {
+      "epoch": 0.0024403884284915347,
+      "grad_norm": 3.7128841876983643,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.445,
+      "step": 12
+    },
+    {
+      "epoch": 0.0030504855356144186,
+      "grad_norm": 2.098191261291504,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.3757,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030504855356144186,
+      "eval_loss": 1.521304965019226,
+      "eval_runtime": 115.7149,
+      "eval_samples_per_second": 17.897,
+      "eval_steps_per_second": 8.953,
+      "step": 15
+    },
+    {
+      "epoch": 0.0036605826427373025,
+      "grad_norm": 1.6114972829818726,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4386,
+      "step": 18
+    },
+    {
+      "epoch": 0.004067314047485892,
+      "eval_loss": 1.4969481229782104,
+      "eval_runtime": 115.7084,
+      "eval_samples_per_second": 17.898,
+      "eval_steps_per_second": 8.954,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1527977732997120.0,
+  "total_flos": 3055955465994240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null