Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84dc19866663b90543a5cc28be1f6e8bff087836139765f45314465458b8abcc
+oid sha256:eefc043abf545b1a9056c0abf733392ba05d898ea8ec803b6799e50eeaa1f44c
 size 84962944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f351de7fa9c7c965f3987cce588d1a1045c4b50b8b4c5da49e74ba84d14ecc
+oid sha256:68c8d28949f0d88f53c349673f9eb37b7c9d7b5324f0fea87d89f07ce4a3d0bf
 size 43387339

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ab9d84b07e05a0de6cf94054dbda159d79b30eff688eeb5d3abec7ce76ed9f
+oid sha256:3da3a8ea9a349e34715a0e680e246db9bce3ac95cfe61981f857abc88096d4e9
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f8b0b08f6088c90a3341aa1b8a14244d3700ce315516380355bdd802a502a0
+oid sha256:8098b00a7c8df434ccbc8255df3dab9ab568965934b2c15b0908bddeb0e9b559
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 110,
-  "best_metric": 1.211287498474121,
-  "best_model_checkpoint": "./outputs/ctrl_abort_real_right/checkpoint-110",
-  "epoch": 0.23567220139260847,
+  "best_global_step": 120,
+  "best_metric": 1.2101209163665771,
+  "best_model_checkpoint": "./outputs/ctrl_abort_real_right/checkpoint-120",
+  "epoch": 0.2570969469737547,
   "eval_steps": 5,
-  "global_step": 110,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -954,6 +954,92 @@
       "eval_samples_per_second": 13.609,
       "eval_steps_per_second": 6.805,
       "step": 110
+    },
+    {
+      "epoch": 0.2378146759507231,
+      "grad_norm": 0.696169912815094,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 1.1758,
+      "step": 111
+    },
+    {
+      "epoch": 0.2399571505088377,
+      "grad_norm": 0.6544473767280579,
+      "learning_rate": 1.6426572649021477e-07,
+      "loss": 1.1242,
+      "step": 112
+    },
+    {
+      "epoch": 0.24209962506695232,
+      "grad_norm": 0.8569499254226685,
+      "learning_rate": 1.2994041528833267e-07,
+      "loss": 1.2727,
+      "step": 113
+    },
+    {
+      "epoch": 0.24424209962506696,
+      "grad_norm": 0.85068279504776,
+      "learning_rate": 9.958719453803278e-08,
+      "loss": 1.2417,
+      "step": 114
+    },
+    {
+      "epoch": 0.24638457418318158,
+      "grad_norm": 0.8679143786430359,
+      "learning_rate": 7.32308207615351e-08,
+      "loss": 1.2296,
+      "step": 115
+    },
+    {
+      "epoch": 0.24638457418318158,
+      "eval_loss": 1.2105430364608765,
+      "eval_runtime": 1.1269,
+      "eval_samples_per_second": 14.198,
+      "eval_steps_per_second": 7.099,
+      "step": 115
+    },
+    {
+      "epoch": 0.2485270487412962,
+      "grad_norm": 0.674493670463562,
+      "learning_rate": 5.089279059533658e-08,
+      "loss": 1.1677,
+      "step": 116
+    },
+    {
+      "epoch": 0.25066952329941083,
+      "grad_norm": 0.6304970979690552,
+      "learning_rate": 3.25913232572489e-08,
+      "loss": 1.1482,
+      "step": 117
+    },
+    {
+      "epoch": 0.25281199785752545,
+      "grad_norm": 0.6986701488494873,
+      "learning_rate": 1.834134568654333e-08,
+      "loss": 1.1476,
+      "step": 118
+    },
+    {
+      "epoch": 0.25495447241564007,
+      "grad_norm": 0.6568459868431091,
+      "learning_rate": 8.15448036932176e-09,
+      "loss": 1.109,
+      "step": 119
+    },
+    {
+      "epoch": 0.2570969469737547,
+      "grad_norm": 0.8193196654319763,
+      "learning_rate": 2.0390358590538507e-09,
+      "loss": 1.1736,
+      "step": 120
+    },
+    {
+      "epoch": 0.2570969469737547,
+      "eval_loss": 1.2101209163665771,
+      "eval_runtime": 1.4407,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 5.553,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -977,12 +1063,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.08491123136e+16,
+  "total_flos": 1.1935339253376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null