Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9856ecc08f7a68ecc3f1e81ff7bcbc8c6c9b36e8bf6b100c1a9cd966baf831fa
+oid sha256:6d491515144e9c654ead1147ec8ad555e5f4a7d13875427ef8c4694752213ed0
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2aeca17026e449aa910bf320f1fe3722d83d928d417ef76902869386e17f70f
+oid sha256:ce1162670f0b586f1ae44f034ea0d472faf94323c72e83df415f15184795c5df
 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": 0.06512890094979647,
+  "epoch": 0.08683853459972862,
   "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": 107.239,
       "eval_steps_per_second": 53.619,
       "step": 15
+    },
+    {
+      "epoch": 0.06947082767978291,
+      "grad_norm": 2.7127010822296143,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.009,
+      "step": 16
+    },
+    {
+      "epoch": 0.07381275440976934,
+      "grad_norm": 2.4328489303588867,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.683,
+      "step": 17
+    },
+    {
+      "epoch": 0.07815468113975577,
+      "grad_norm": 3.2602317333221436,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.215,
+      "step": 18
+    },
+    {
+      "epoch": 0.0824966078697422,
+      "grad_norm": 3.8587803840637207,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.2797,
+      "step": 19
+    },
+    {
+      "epoch": 0.08683853459972862,
+      "grad_norm": 3.2040271759033203,
+      "learning_rate": 0.0,
+      "loss": 3.0642,
+      "step": 20
+    },
+    {
+      "epoch": 0.08683853459972862,
+      "eval_loss": 3.188815116882324,
+      "eval_runtime": 3.6622,
+      "eval_samples_per_second": 105.948,
+      "eval_steps_per_second": 52.974,
+      "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": 725661035003904.0,
+  "total_flos": 977193847750656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null