Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff8fc6754256e849681d0d4a156abd0ca4d2c199551fe822d67587a96aebbc0
+oid sha256:95b4d31956f026751b7d57641b9fd1c2dd91cac3b6a8dfdc40461921f3ffe64c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d98975f94a340e65dda70cf3ba315e25ea6911d40a299fabc046f37ad4998ff
+oid sha256:12be1ad8deede594320aae6b84265d8bce1fd0f5a4c1cfc7aba0dda623199a5d
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ccfd88f620eb832cdc95b7c73f631ee104fb7843f178a425bf2208b904d28d
+oid sha256:9f03fbef729f64ddf68b55e06f01e7bb1d8bf0494ed9ac87477f34ab984a1d9b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03444034440344403,
+  "epoch": 0.03936039360393604,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 7.222,
       "eval_steps_per_second": 0.905,
       "step": 63
+    },
+    {
+      "epoch": 0.03608036080360803,
+      "grad_norm": 0.21537937223911285,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.5806,
+      "step": 66
+    },
+    {
+      "epoch": 0.03772037720377204,
+      "grad_norm": 0.21624986827373505,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.5876,
+      "step": 69
+    },
+    {
+      "epoch": 0.03936039360393604,
+      "grad_norm": 0.2545225918292999,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.6063,
+      "step": 72
+    },
+    {
+      "epoch": 0.03936039360393604,
+      "eval_loss": 0.6232536435127258,
+      "eval_runtime": 426.6611,
+      "eval_samples_per_second": 7.221,
+      "eval_steps_per_second": 0.905,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6527352922112e+17,
+  "total_flos": 1.8808127625363456e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null