Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad4f6ffde5b05dc0eacad8c15aa197905f7b7d7592b83611335fafa9f49a121
+oid sha256:d054274f44c04f1cb8f3ab33c30249dd2cf113993c4e9651ce89e48cd42665dd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf7136e741013e15bc8ea4368966c1ba0e419594e2b1e751efe54db5dec8bfa
+oid sha256:fcc9301d9de80708cc0367b35b47ed5153ef0ec482ed0b5a05bf3966f5182764
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da48438bf8b8db74f61cc2142eb4dc056d3871064431f52d89f8375957ad02b7
+oid sha256:9dde5f7371be42cf51407aff626f454d59690f1327c931a33dba4d81c96a54e6
 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": 0.12281240405280934,
+  "epoch": 0.184218606079214,
   "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": 3.523,
       "eval_steps_per_second": 1.767,
       "step": 50
+    },
+    {
+      "epoch": 0.1252686521338655,
+      "grad_norm": 0.10938217490911484,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0813,
+      "step": 51
+    },
+    {
+      "epoch": 0.1277249002149217,
+      "grad_norm": 0.13226236402988434,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.091,
+      "step": 52
+    },
+    {
+      "epoch": 0.1301811482959779,
+      "grad_norm": 0.14732792973518372,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0968,
+      "step": 53
+    },
+    {
+      "epoch": 0.1326373963770341,
+      "grad_norm": 0.14260084927082062,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.079,
+      "step": 54
+    },
+    {
+      "epoch": 0.13509364445809027,
+      "grad_norm": 0.180017352104187,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0624,
+      "step": 55
+    },
+    {
+      "epoch": 0.13754989253914646,
+      "grad_norm": 0.1349073201417923,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0839,
+      "step": 56
+    },
+    {
+      "epoch": 0.14000614062020264,
+      "grad_norm": 0.16259907186031342,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0716,
+      "step": 57
+    },
+    {
+      "epoch": 0.14246238870125882,
+      "grad_norm": 0.14453484117984772,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0825,
+      "step": 58
+    },
+    {
+      "epoch": 0.144918636782315,
+      "grad_norm": 0.1296265572309494,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0613,
+      "step": 59
+    },
+    {
+      "epoch": 0.1473748848633712,
+      "grad_norm": 0.12627637386322021,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0769,
+      "step": 60
+    },
+    {
+      "epoch": 0.14983113294442738,
+      "grad_norm": 0.1232289969921112,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0708,
+      "step": 61
+    },
+    {
+      "epoch": 0.1522873810254836,
+      "grad_norm": 0.16237996518611908,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0958,
+      "step": 62
+    },
+    {
+      "epoch": 0.15474362910653977,
+      "grad_norm": 0.12401328235864639,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0845,
+      "step": 63
+    },
+    {
+      "epoch": 0.15719987718759595,
+      "grad_norm": 0.11931698769330978,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0764,
+      "step": 64
+    },
+    {
+      "epoch": 0.15965612526865214,
+      "grad_norm": 0.14114603400230408,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0805,
+      "step": 65
+    },
+    {
+      "epoch": 0.16211237334970832,
+      "grad_norm": 0.13311800360679626,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0756,
+      "step": 66
+    },
+    {
+      "epoch": 0.1645686214307645,
+      "grad_norm": 0.23211269080638885,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.108,
+      "step": 67
+    },
+    {
+      "epoch": 0.1670248695118207,
+      "grad_norm": 0.1735387146472931,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0848,
+      "step": 68
+    },
+    {
+      "epoch": 0.16948111759287687,
+      "grad_norm": 0.17347167432308197,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1041,
+      "step": 69
+    },
+    {
+      "epoch": 0.17193736567393306,
+      "grad_norm": 0.16924938559532166,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.094,
+      "step": 70
+    },
+    {
+      "epoch": 0.17439361375498924,
+      "grad_norm": 0.09490655362606049,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.056,
+      "step": 71
+    },
+    {
+      "epoch": 0.17684986183604545,
+      "grad_norm": 0.139134019613266,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0558,
+      "step": 72
+    },
+    {
+      "epoch": 0.17930610991710164,
+      "grad_norm": 0.112559013068676,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0791,
+      "step": 73
+    },
+    {
+      "epoch": 0.18176235799815782,
+      "grad_norm": 0.07158195972442627,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0466,
+      "step": 74
+    },
+    {
+      "epoch": 0.184218606079214,
+      "grad_norm": 0.1235809400677681,
+      "learning_rate": 0.0,
+      "loss": 0.0568,
+      "step": 75
+    },
+    {
+      "epoch": 0.184218606079214,
+      "eval_loss": 0.08785168826580048,
+      "eval_runtime": 97.4628,
+      "eval_samples_per_second": 3.519,
+      "eval_steps_per_second": 1.765,
+      "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": 7.975288298274816e+16,
+  "total_flos": 1.205566835785728e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null