Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663925bed6ba8b3bbe59020859f97e284fe0325138795e5e62dec3c8bd7cc460
+oid sha256:da18b88a8944b458c8dae1ca3be8c65c46ba525155f298061e71f9fe745ed85b
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132ec7d2df7ed8c349fcdd109e275f05514c669d68cb903adf4de832cea72ccb
+oid sha256:78a68f965a8dc6a056b4b77b2f33f281953c07f050443f6023a9a0f5917b867d
 size 1663290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae7ea429f3e44d20701513020b1a327873eaf55a7493d83e01ce4ef5a7f7732
+oid sha256:d2e5197db00518b2a55473e50a0c89e45ba4d24176a4f91da2761e23b54a63f8
 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": 0.17094017094017094,
+  "epoch": 0.22792022792022792,
   "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": 117.251,
       "eval_steps_per_second": 15.052,
       "step": 15
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 17.917509078979492,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 5.0732,
+      "step": 18
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "eval_loss": 3.6343350410461426,
+      "eval_runtime": 1.2596,
+      "eval_samples_per_second": 117.498,
+      "eval_steps_per_second": 15.084,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12101269585920.0,
+  "total_flos": 16843659018240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null