Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdc5d17300ac116dce8754738106bb968cf28014ce048dd417ded47e38f8cc1
+oid sha256:822a3c80b72678ebfdf7ef83e90110d3b854418c1b421e69b4162ba03af17cc7
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d170581f0c73adcdad375b28faf3843723b0be8f7a3fe528d57d1c638e4ded
+oid sha256:5285f5bc53e109a536ab780f8fafcaa9f9051fe41472a60c1f8d5c8cf06327a6
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027387880862718247,
+  "epoch": 0.03651717448362433,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 68.258,
       "eval_steps_per_second": 34.166,
       "step": 15
+    },
+    {
+      "epoch": 0.029213739586899462,
+      "grad_norm": 1.6469899415969849,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.8117,
+      "step": 16
+    },
+    {
+      "epoch": 0.03103959831108068,
+      "grad_norm": 1.5216410160064697,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.9194,
+      "step": 17
+    },
+    {
+      "epoch": 0.0328654570352619,
+      "grad_norm": 1.9741591215133667,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9926,
+      "step": 18
+    },
+    {
+      "epoch": 0.03469131575944311,
+      "grad_norm": 1.7542316913604736,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.8396,
+      "step": 19
+    },
+    {
+      "epoch": 0.03651717448362433,
+      "grad_norm": 2.0134270191192627,
+      "learning_rate": 0.0,
+      "loss": 1.9055,
+      "step": 20
+    },
+    {
+      "epoch": 0.03651717448362433,
+      "eval_loss": 1.9492886066436768,
+      "eval_runtime": 13.5317,
+      "eval_samples_per_second": 68.21,
+      "eval_steps_per_second": 34.142,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4331570410291200.0,
+  "total_flos": 5753633148764160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null