Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba98e26b5ee87ecda454bc3bbc9a386dbdaf94bceeaee9a4788a6442212cbc63
+oid sha256:92f474fa76a6c7cd0c33d96e3d93a72caf76ba747e21e88b60fdaebcb1ce9079
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cb31a2c4c759c8c9630288ed315810a204ec4218892b77ad4f23626b00b881
+oid sha256:c1ebd985d63209828fea3322229af478a5091352951a73870b0c457ca370e57e
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a67aabb29a27a82eeab363acaf8fb3930efe4f67202870960cc3f7dd2705615
+oid sha256:058a686ff82e9731a00619efab18ca60ee6bec74300ac898863c4b13b3ea2b50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022959476523935256,
+  "epoch": 0.03443921478590288,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.947,
       "eval_steps_per_second": 1.973,
       "step": 50
+    },
+    {
+      "epoch": 0.02341866605441396,
+      "grad_norm": 1.049940824508667,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8132,
+      "step": 51
+    },
+    {
+      "epoch": 0.023877855584892665,
+      "grad_norm": 1.0071134567260742,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.7913,
+      "step": 52
+    },
+    {
+      "epoch": 0.02433704511537137,
+      "grad_norm": 0.8402441740036011,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.7837,
+      "step": 53
+    },
+    {
+      "epoch": 0.024796234645850075,
+      "grad_norm": 0.7800126075744629,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7519,
+      "step": 54
+    },
+    {
+      "epoch": 0.02525542417632878,
+      "grad_norm": 0.6317635774612427,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.7225,
+      "step": 55
+    },
+    {
+      "epoch": 0.025714613706807485,
+      "grad_norm": 0.5558218359947205,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.7201,
+      "step": 56
+    },
+    {
+      "epoch": 0.02617380323728619,
+      "grad_norm": 0.564495325088501,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7005,
+      "step": 57
+    },
+    {
+      "epoch": 0.026632992767764894,
+      "grad_norm": 0.4901668131351471,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.7271,
+      "step": 58
+    },
+    {
+      "epoch": 0.0270921822982436,
+      "grad_norm": 0.47251802682876587,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6856,
+      "step": 59
+    },
+    {
+      "epoch": 0.027551371828722304,
+      "grad_norm": 0.48661911487579346,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6638,
+      "step": 60
+    },
+    {
+      "epoch": 0.02801056135920101,
+      "grad_norm": 0.5135563611984253,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.621,
+      "step": 61
+    },
+    {
+      "epoch": 0.028469750889679714,
+      "grad_norm": 0.4911552965641022,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.6375,
+      "step": 62
+    },
+    {
+      "epoch": 0.02892894042015842,
+      "grad_norm": 0.522821843624115,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6292,
+      "step": 63
+    },
+    {
+      "epoch": 0.029388129950637127,
+      "grad_norm": 0.48059335350990295,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.6706,
+      "step": 64
+    },
+    {
+      "epoch": 0.029847319481115832,
+      "grad_norm": 0.5201355814933777,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.681,
+      "step": 65
+    },
+    {
+      "epoch": 0.030306509011594537,
+      "grad_norm": 0.5210537910461426,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6545,
+      "step": 66
+    },
+    {
+      "epoch": 0.03076569854207324,
+      "grad_norm": 0.5189217329025269,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6052,
+      "step": 67
+    },
+    {
+      "epoch": 0.031224888072551946,
+      "grad_norm": 0.559215784072876,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.6467,
+      "step": 68
+    },
+    {
+      "epoch": 0.03168407760303065,
+      "grad_norm": 0.5408816337585449,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6004,
+      "step": 69
+    },
+    {
+      "epoch": 0.03214326713350935,
+      "grad_norm": 0.5203858017921448,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.6152,
+      "step": 70
+    },
+    {
+      "epoch": 0.03260245666398806,
+      "grad_norm": 0.5649285316467285,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5943,
+      "step": 71
+    },
+    {
+      "epoch": 0.03306164619446677,
+      "grad_norm": 0.5590580105781555,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6372,
+      "step": 72
+    },
+    {
+      "epoch": 0.03352083572494547,
+      "grad_norm": 0.5505293011665344,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.5813,
+      "step": 73
+    },
+    {
+      "epoch": 0.03398002525542418,
+      "grad_norm": 0.5618359446525574,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.6209,
+      "step": 74
+    },
+    {
+      "epoch": 0.03443921478590288,
+      "grad_norm": 0.5541989207267761,
+      "learning_rate": 0.0,
+      "loss": 0.6078,
+      "step": 75
+    },
+    {
+      "epoch": 0.03443921478590288,
+      "eval_loss": 0.6394286155700684,
+      "eval_runtime": 464.4129,
+      "eval_samples_per_second": 3.949,
+      "eval_steps_per_second": 1.975,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.46010452164608e+16,
+  "total_flos": 1.119015678246912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null