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:d88253bc2b5332725631e687ecc87e02694085dc9aa71b7961213eba3f607b9a
+oid sha256:af95ccf557f13a06778dd7d2589ae2d031534e23c548935268db09a6a5ea18f5
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711611d0d17c023cddd6132601f261b139f9a7f14d4e603072d8aaf8fff7545e
+oid sha256:800e380777c7a27bfdfd6e1094fda5c77b978d1fc79ccd68cdb13335953aad16
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1e9d7576e79dd381098b714973a1693ea325ff713e44ab0042ddfdcff6a369
+oid sha256:89ec0b3464ec81ffe0d2e0c854af74e40aa80a3e3c07ab295b4748b49a1ed383
 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": 0.0016603481196557546,
+  "epoch": 0.0022137974928743394,
   "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": 6.644,
       "eval_steps_per_second": 0.831,
       "step": 15
+    },
+    {
+      "epoch": 0.0019924177435869054,
+      "grad_norm": 18.248498916625977,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.9639,
+      "step": 18
+    },
+    {
+      "epoch": 0.0022137974928743394,
+      "eval_loss": 0.33800774812698364,
+      "eval_runtime": 2289.3613,
+      "eval_samples_per_second": 6.646,
+      "eval_steps_per_second": 0.831,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.1343397134336e+16,
+  "total_flos": 5.5124529512448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null