Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b5832ee3eb5bd559e333d4cb2b4608907fd12e24b827793858e69a530ec24bc
+oid sha256:73706efd5f852d1b2bb6748855e36802ad5721baecb82744684d7f6b9667e213
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb14e90b010a484ebd668a3dd7b4a7b208ab72dfa60d0b816c3fe45d020151c6
+oid sha256:d5bc0ea944136b656b000434db1783e76ec94014b180debbb70883414e9b9e3c
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fbc3efa8e92d1313f06ac63dbf530b35b72069b22696ed3247968087ed28f8
+oid sha256:eb043b8699b5ddac2bc2d42499da09f74ed04c051c178c123a91c2944f44c2ca
 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": 0.36663611365719523,
+  "epoch": 0.5499541704857929,
   "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": 6.031,
       "eval_steps_per_second": 3.042,
       "step": 50
+    },
+    {
+      "epoch": 0.37396883593033914,
+      "grad_norm": 1.148086428642273,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6821,
+      "step": 51
+    },
+    {
+      "epoch": 0.38130155820348305,
+      "grad_norm": 2.4862043857574463,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.6769,
+      "step": 52
+    },
+    {
+      "epoch": 0.38863428047662696,
+      "grad_norm": 0.7579915523529053,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.666,
+      "step": 53
+    },
+    {
+      "epoch": 0.39596700274977087,
+      "grad_norm": 1.9005545377731323,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6863,
+      "step": 54
+    },
+    {
+      "epoch": 0.4032997250229148,
+      "grad_norm": 2.0019586086273193,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.7327,
+      "step": 55
+    },
+    {
+      "epoch": 0.4106324472960587,
+      "grad_norm": 2.00166916847229,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.6643,
+      "step": 56
+    },
+    {
+      "epoch": 0.41796516956920254,
+      "grad_norm": 2.7452757358551025,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6479,
+      "step": 57
+    },
+    {
+      "epoch": 0.42529789184234645,
+      "grad_norm": 1.244705319404602,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.6638,
+      "step": 58
+    },
+    {
+      "epoch": 0.43263061411549036,
+      "grad_norm": 3.0463991165161133,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6492,
+      "step": 59
+    },
+    {
+      "epoch": 0.4399633363886343,
+      "grad_norm": 2.052518606185913,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7053,
+      "step": 60
+    },
+    {
+      "epoch": 0.4472960586617782,
+      "grad_norm": 3.5137293338775635,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.7722,
+      "step": 61
+    },
+    {
+      "epoch": 0.4546287809349221,
+      "grad_norm": 3.2491636276245117,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.7338,
+      "step": 62
+    },
+    {
+      "epoch": 0.461961503208066,
+      "grad_norm": 1.8555599451065063,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6871,
+      "step": 63
+    },
+    {
+      "epoch": 0.4692942254812099,
+      "grad_norm": 1.7213964462280273,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.7098,
+      "step": 64
+    },
+    {
+      "epoch": 0.4766269477543538,
+      "grad_norm": 1.661662220954895,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.715,
+      "step": 65
+    },
+    {
+      "epoch": 0.48395967002749773,
+      "grad_norm": 2.6130359172821045,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7181,
+      "step": 66
+    },
+    {
+      "epoch": 0.4912923923006416,
+      "grad_norm": 2.4682836532592773,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7384,
+      "step": 67
+    },
+    {
+      "epoch": 0.4986251145737855,
+      "grad_norm": 1.5685425996780396,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.6928,
+      "step": 68
+    },
+    {
+      "epoch": 0.5059578368469294,
+      "grad_norm": 2.4822793006896973,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6647,
+      "step": 69
+    },
+    {
+      "epoch": 0.5132905591200734,
+      "grad_norm": 1.0878037214279175,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.7076,
+      "step": 70
+    },
+    {
+      "epoch": 0.5206232813932172,
+      "grad_norm": 1.6217339038848877,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6875,
+      "step": 71
+    },
+    {
+      "epoch": 0.5279560036663611,
+      "grad_norm": 2.876856565475464,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.737,
+      "step": 72
+    },
+    {
+      "epoch": 0.535288725939505,
+      "grad_norm": 2.342238187789917,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.7185,
+      "step": 73
+    },
+    {
+      "epoch": 0.5426214482126489,
+      "grad_norm": 1.9597443342208862,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.7164,
+      "step": 74
+    },
+    {
+      "epoch": 0.5499541704857929,
+      "grad_norm": 2.002971649169922,
+      "learning_rate": 0.0,
+      "loss": 0.6642,
+      "step": 75
+    },
+    {
+      "epoch": 0.5499541704857929,
+      "eval_loss": 0.685459315776825,
+      "eval_runtime": 19.0667,
+      "eval_samples_per_second": 6.031,
+      "eval_steps_per_second": 3.042,
+      "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