Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eba3634c1ffd6e4ae0b701362ca12c1d63eebacdfef69ea70351fb0b4145497
+oid sha256:15534d3755a6a4e5e30be58ff2c4a2167b06163faa57b68008187ad1d7497fd7
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bd76d64c3e6ea4b1ab0c962168ce61ab91d5d71ea831738cb1f07f5a3d7646
+oid sha256:6489f32e9d976acd503d0b7c43cb423d90e76a6dcb755e2bf8df2eb2ca94cc0c
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2824a1e86e1f2ebb1954454acc2d65d06e39bdc1ec88097e15e38ec185b81b
+oid sha256:842160c84da2f20ba4769075d37abcad1cd79e1e28006529f9f33b1c2157a9d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013993026808307193,
+  "epoch": 0.0018657369077742926,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 16.017,
       "eval_steps_per_second": 4.005,
       "step": 15
+    },
+    {
+      "epoch": 0.0016791632169968632,
+      "grad_norm": 2.642324209213257,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.1533,
+      "step": 18
+    },
+    {
+      "epoch": 0.0018657369077742926,
+      "eval_loss": 1.0050814151763916,
+      "eval_runtime": 1127.5321,
+      "eval_samples_per_second": 16.013,
+      "eval_steps_per_second": 4.003,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.804021269528576e+16,
+  "total_flos": 2.4438711779328e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null