Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f677b61053670a8596d2df369dd25e88f3415a8384a3ccb30e19bfa224abfa9b
+oid sha256:368f6e128196ba20ff6f212e43a3cb9d4f631b4aaaea747c668b026bbf4c227e
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280978d258590502c6dbc2d4e51a96d724811888733c12e36a1b3b8598b78749
+oid sha256:46fc85bc4faaad1e8d122cff7d5cf4a1a1ad3964bf64f5ab8326acdd107f9e83
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
+oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05779383161989442,
+  "epoch": 0.08669074742984162,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 366.524,
       "eval_steps_per_second": 45.831,
       "step": 20
+    },
+    {
+      "epoch": 0.0666851903306474,
+      "grad_norm": 1.0241162776947021,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 165.9956,
+      "step": 30
+    },
+    {
+      "epoch": 0.0666851903306474,
+      "eval_loss": 10.374114990234375,
+      "eval_runtime": 8.104,
+      "eval_samples_per_second": 374.015,
+      "eval_steps_per_second": 46.767,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21353126166528.0,
+  "total_flos": 32029689249792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null