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:d0d4c120a35d30d3d9d6571e8a4e339eee77afb129657e147918e4aaa712d66a
+oid sha256:5320b7fce8b976a4c91975b945a374a548afda5a26affbdd7a9f229a0f45289a
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353bd2702cac2dfff7ffc9de2e09d5fc3a4b8dc254dad794c7cfd7d1e5afd20d
+oid sha256:549dc509885972ac208b2fd3a189d8eaa792df86d7cec9992e03cea51030fac1
 size 800394282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f67b2f6b00f3d2a77ca7d734eac5db40c7fc95258208204efafe23dc315a4d
+oid sha256:e060743d045d06c1f86fd4518818c9cf5423797573206079ef342a04f4e55ea8
 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": 0.04575611988103409,
+  "epoch": 0.06863417982155114,
   "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": 3.394,
       "eval_steps_per_second": 1.699,
       "step": 50
+    },
+    {
+      "epoch": 0.04667124227865477,
+      "grad_norm": 10.542644500732422,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5443,
+      "step": 51
+    },
+    {
+      "epoch": 0.04758636467627545,
+      "grad_norm": 5.551739692687988,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.2044,
+      "step": 52
+    },
+    {
+      "epoch": 0.048501487073896135,
+      "grad_norm": 7.962470054626465,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.3918,
+      "step": 53
+    },
+    {
+      "epoch": 0.04941660947151681,
+      "grad_norm": 9.332234382629395,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6089,
+      "step": 54
+    },
+    {
+      "epoch": 0.050331731869137496,
+      "grad_norm": 7.265214443206787,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4531,
+      "step": 55
+    },
+    {
+      "epoch": 0.05124685426675818,
+      "grad_norm": 7.815890789031982,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.3726,
+      "step": 56
+    },
+    {
+      "epoch": 0.05216197666437886,
+      "grad_norm": 7.1828765869140625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3523,
+      "step": 57
+    },
+    {
+      "epoch": 0.05307709906199954,
+      "grad_norm": 8.059473037719727,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.4862,
+      "step": 58
+    },
+    {
+      "epoch": 0.053992221459620224,
+      "grad_norm": 6.242551326751709,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4128,
+      "step": 59
+    },
+    {
+      "epoch": 0.05490734385724091,
+      "grad_norm": 4.751944065093994,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3559,
+      "step": 60
+    },
+    {
+      "epoch": 0.055822466254861584,
+      "grad_norm": 3.4567954540252686,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.2912,
+      "step": 61
+    },
+    {
+      "epoch": 0.05673758865248227,
+      "grad_norm": 5.8354692459106445,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.4136,
+      "step": 62
+    },
+    {
+      "epoch": 0.05765271105010295,
+      "grad_norm": 5.292219638824463,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3484,
+      "step": 63
+    },
+    {
+      "epoch": 0.058567833447723636,
+      "grad_norm": 5.4359846115112305,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.4286,
+      "step": 64
+    },
+    {
+      "epoch": 0.05948295584534431,
+      "grad_norm": 3.9820847511291504,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.2672,
+      "step": 65
+    },
+    {
+      "epoch": 0.060398078242964996,
+      "grad_norm": 5.325780868530273,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4854,
+      "step": 66
+    },
+    {
+      "epoch": 0.06131320064058568,
+      "grad_norm": 2.7474725246429443,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1493,
+      "step": 67
+    },
+    {
+      "epoch": 0.06222832303820636,
+      "grad_norm": 0.031556036323308945,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0002,
+      "step": 68
+    },
+    {
+      "epoch": 0.06314344543582705,
+      "grad_norm": 1.6410260200500488,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0273,
+      "step": 69
+    },
+    {
+      "epoch": 0.06405856783344772,
+      "grad_norm": 0.6467976570129395,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0064,
+      "step": 70
+    },
+    {
+      "epoch": 0.0649736902310684,
+      "grad_norm": 0.680183470249176,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0023,
+      "step": 71
+    },
+    {
+      "epoch": 0.06588881262868909,
+      "grad_norm": 3.648841619491577,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0219,
+      "step": 72
+    },
+    {
+      "epoch": 0.06680393502630977,
+      "grad_norm": 3.311021089553833,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0454,
+      "step": 73
+    },
+    {
+      "epoch": 0.06771905742393045,
+      "grad_norm": 0.4128534495830536,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.002,
+      "step": 74
+    },
+    {
+      "epoch": 0.06863417982155114,
+      "grad_norm": 0.006412339396774769,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 75
+    },
+    {
+      "epoch": 0.06863417982155114,
+      "eval_loss": 0.11607871204614639,
+      "eval_runtime": 271.5587,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 1.698,
+      "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": 7.71809951612928e+16,
+  "total_flos": 1.157714927419392e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null