Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fca861420f0ad5c0848e9b13cf5e7420d253b4276136e8cae2f63e9a2cfdebe
+oid sha256:8256cfcc2138f8c5e2522fdc3cec6f5075e832b7647d7371547833e83c645eff
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c55616c8336615bc58b9446cf47eceb5927de42d46e6272895821f2774b4ee
+oid sha256:97c370e7024e44937b6b7d28794ee0207aaca801dcea1775a878eb6b83c4b4ae
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7161a5790eee520c7bb6847c9388e171f95f313053b113e0cc0fcff939cf1aba
+oid sha256:5948adcfadcdf90d782787a68dffd609a469cdec4b73d193db1ae958ffef8230
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a300aed554beec060b0af594f4af40ce5202e69105262c956d4925773aa44a
+oid sha256:22c5902aeb659e866c2f9d5285456b3ec93c4f9606d6d8a07bfb5108a2b23b90
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0056cf167cac5af0ae2178e574836ac791414a78b9763644dc3571d6e604931f
+oid sha256:fb0d55d8786b36e1ece9ad7369ace959bac4e99a49ce1f9660ae49ee864e113c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec243ae94db689e730493f6b489b6dda12c53a6ef1052ad96a69c5aeb5163c85
+oid sha256:54ddcaa52bc25a21e360e96ff3323201bbb79a024a2c78592e01dd6c12987421
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01283916802191218,
+  "epoch": 0.017118890695882908,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.0512,
       "step": 75
+    },
+    {
+      "epoch": 0.013010356928871009,
+      "grad_norm": 0.18966364860534668,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0527,
+      "step": 76
+    },
+    {
+      "epoch": 0.013181545835829839,
+      "grad_norm": 0.42172640562057495,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0497,
+      "step": 77
+    },
+    {
+      "epoch": 0.013352734742788667,
+      "grad_norm": 0.1608581691980362,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0509,
+      "step": 78
+    },
+    {
+      "epoch": 0.013523923649747496,
+      "grad_norm": 0.2545730173587799,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0504,
+      "step": 79
+    },
+    {
+      "epoch": 0.013695112556706326,
+      "grad_norm": 0.36740899085998535,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0533,
+      "step": 80
+    },
+    {
+      "epoch": 0.013866301463665154,
+      "grad_norm": 0.13530787825584412,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.052,
+      "step": 81
+    },
+    {
+      "epoch": 0.013866301463665154,
+      "eval_loss": 0.05141623690724373,
+      "eval_runtime": 283.9951,
+      "eval_samples_per_second": 69.283,
+      "eval_steps_per_second": 2.166,
+      "step": 81
+    },
+    {
+      "epoch": 0.014037490370623984,
+      "grad_norm": 0.3279196619987488,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0459,
+      "step": 82
+    },
+    {
+      "epoch": 0.014208679277582813,
+      "grad_norm": 0.20536935329437256,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0446,
+      "step": 83
+    },
+    {
+      "epoch": 0.014379868184541641,
+      "grad_norm": 0.2749428153038025,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0553,
+      "step": 84
+    },
+    {
+      "epoch": 0.014551057091500471,
+      "grad_norm": 0.2593681216239929,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0529,
+      "step": 85
+    },
+    {
+      "epoch": 0.0147222459984593,
+      "grad_norm": 0.2179667055606842,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.049,
+      "step": 86
+    },
+    {
+      "epoch": 0.014893434905418128,
+      "grad_norm": 0.34718865156173706,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0505,
+      "step": 87
+    },
+    {
+      "epoch": 0.015064623812376958,
+      "grad_norm": 0.12179748713970184,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0502,
+      "step": 88
+    },
+    {
+      "epoch": 0.015235812719335787,
+      "grad_norm": 0.1816815733909607,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0461,
+      "step": 89
+    },
+    {
+      "epoch": 0.015407001626294617,
+      "grad_norm": 0.14029575884342194,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0469,
+      "step": 90
+    },
+    {
+      "epoch": 0.015407001626294617,
+      "eval_loss": 0.05124485865235329,
+      "eval_runtime": 253.3449,
+      "eval_samples_per_second": 77.665,
+      "eval_steps_per_second": 2.428,
+      "step": 90
+    },
+    {
+      "epoch": 0.015578190533253445,
+      "grad_norm": 0.1396976262331009,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0517,
+      "step": 91
+    },
+    {
+      "epoch": 0.015749379440212274,
+      "grad_norm": 0.30177736282348633,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0451,
+      "step": 92
+    },
+    {
+      "epoch": 0.015920568347171104,
+      "grad_norm": 0.26903343200683594,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0489,
+      "step": 93
+    },
+    {
+      "epoch": 0.016091757254129934,
+      "grad_norm": 0.2131453901529312,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.047,
+      "step": 94
+    },
+    {
+      "epoch": 0.01626294616108876,
+      "grad_norm": 0.2197953313589096,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0482,
+      "step": 95
+    },
+    {
+      "epoch": 0.01643413506804759,
+      "grad_norm": 0.22142086923122406,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0536,
+      "step": 96
+    },
+    {
+      "epoch": 0.01660532397500642,
+      "grad_norm": 0.2176884561777115,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0506,
+      "step": 97
+    },
+    {
+      "epoch": 0.016776512881965248,
+      "grad_norm": 0.24009715020656586,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0508,
+      "step": 98
+    },
+    {
+      "epoch": 0.016947701788924078,
+      "grad_norm": 0.22042791545391083,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0508,
+      "step": 99
+    },
+    {
+      "epoch": 0.016947701788924078,
+      "eval_loss": 0.051198288798332214,
+      "eval_runtime": 253.6762,
+      "eval_samples_per_second": 77.563,
+      "eval_steps_per_second": 2.424,
+      "step": 99
+    },
+    {
+      "epoch": 0.017118890695882908,
+      "grad_norm": 0.13444502651691437,
+      "learning_rate": 0.0,
+      "loss": 0.0506,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.98328235065344e+17,
+  "total_flos": 2.64437646753792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null