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:f30960e60996a50fa5fdb4957a646f26a039e633cbfd6afdcde9f61f0413e06f
+oid sha256:c4c07084ad297661c7fea892dcd22f91bbdce71668a51e2217202de7ae3b65ea
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5021af618caa6e613343ae3b2379fa4b9b4641c7931d8fb35c3e58b4ab4ffa
+oid sha256:f1c302c943f0a74366dbfcacbdc97c03e95ad90244a87f490ed2df1f853c0368
 size 9568884

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": 0.08714596949891068,
+  "epoch": 0.11619462599854757,
   "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": 69.437,
       "eval_steps_per_second": 34.719,
       "step": 15
+    },
+    {
+      "epoch": 0.09295570079883805,
+      "grad_norm": 1.2568418979644775,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5991,
+      "step": 16
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 1.415218472480774,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6339,
+      "step": 17
+    },
+    {
+      "epoch": 0.10457516339869281,
+      "grad_norm": 1.306711196899414,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5651,
+      "step": 18
+    },
+    {
+      "epoch": 0.11038489469862019,
+      "grad_norm": 1.4163092374801636,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5494,
+      "step": 19
+    },
+    {
+      "epoch": 0.11619462599854757,
+      "grad_norm": 1.318520426750183,
+      "learning_rate": 0.0,
+      "loss": 0.6674,
+      "step": 20
+    },
+    {
+      "epoch": 0.11619462599854757,
+      "eval_loss": 0.6370882987976074,
+      "eval_runtime": 4.169,
+      "eval_samples_per_second": 69.561,
+      "eval_steps_per_second": 34.781,
+      "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": 534228982824960.0,
+  "total_flos": 712305310433280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null