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:cfef193180ecb30f2b563605011b33ace49d374e3299a717116f51b9654e999f
+oid sha256:f33f37bdd060d657064ae674ddd6157b8345ae988ffb9a3ecbfcc6d23bbf27a0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5555067b5330722f06ce2fa89fed6c291202f17e375d7e19be0ce7ee3e0aecaf
+oid sha256:fcceb5f1b3f9e95e0b4b135670b6205e93ba7fb7b263c6df75c3510610968c5e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 size 14244

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": 0.04991680532445923,
+  "epoch": 0.06655574043261231,
   "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": 0.274,
       "step": 75
+    },
+    {
+      "epoch": 0.05058236272878536,
+      "grad_norm": 5.972333908081055,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.3983,
+      "step": 76
+    },
+    {
+      "epoch": 0.05124792013311148,
+      "grad_norm": 4.970418930053711,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2292,
+      "step": 77
+    },
+    {
+      "epoch": 0.0519134775374376,
+      "grad_norm": 3.250725030899048,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1587,
+      "step": 78
+    },
+    {
+      "epoch": 0.052579034941763726,
+      "grad_norm": 1.929383397102356,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1082,
+      "step": 79
+    },
+    {
+      "epoch": 0.05324459234608985,
+      "grad_norm": 2.099276304244995,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1091,
+      "step": 80
+    },
+    {
+      "epoch": 0.05391014975041598,
+      "grad_norm": 4.829376220703125,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2974,
+      "step": 81
+    },
+    {
+      "epoch": 0.05391014975041598,
+      "eval_loss": 0.21195295453071594,
+      "eval_runtime": 128.9352,
+      "eval_samples_per_second": 9.811,
+      "eval_steps_per_second": 1.233,
+      "step": 81
+    },
+    {
+      "epoch": 0.054575707154742095,
+      "grad_norm": 3.0689616203308105,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1708,
+      "step": 82
+    },
+    {
+      "epoch": 0.05524126455906822,
+      "grad_norm": 3.2259533405303955,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2147,
+      "step": 83
+    },
+    {
+      "epoch": 0.055906821963394346,
+      "grad_norm": 3.743279457092285,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2843,
+      "step": 84
+    },
+    {
+      "epoch": 0.056572379367720464,
+      "grad_norm": 3.8382668495178223,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1838,
+      "step": 85
+    },
+    {
+      "epoch": 0.05723793677204659,
+      "grad_norm": 3.651982307434082,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1764,
+      "step": 86
+    },
+    {
+      "epoch": 0.057903494176372715,
+      "grad_norm": 6.519517421722412,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2541,
+      "step": 87
+    },
+    {
+      "epoch": 0.05856905158069883,
+      "grad_norm": 3.807999849319458,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2566,
+      "step": 88
+    },
+    {
+      "epoch": 0.05923460898502496,
+      "grad_norm": 3.6574578285217285,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1891,
+      "step": 89
+    },
+    {
+      "epoch": 0.059900166389351084,
+      "grad_norm": 3.1083388328552246,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2098,
+      "step": 90
+    },
+    {
+      "epoch": 0.059900166389351084,
+      "eval_loss": 0.19934000074863434,
+      "eval_runtime": 128.9277,
+      "eval_samples_per_second": 9.812,
+      "eval_steps_per_second": 1.233,
+      "step": 90
+    },
+    {
+      "epoch": 0.0605657237936772,
+      "grad_norm": 3.158428430557251,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1998,
+      "step": 91
+    },
+    {
+      "epoch": 0.06123128119800333,
+      "grad_norm": 3.8215372562408447,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2293,
+      "step": 92
+    },
+    {
+      "epoch": 0.06189683860232945,
+      "grad_norm": 4.208840370178223,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3915,
+      "step": 93
+    },
+    {
+      "epoch": 0.06256239600665557,
+      "grad_norm": 3.0414741039276123,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1946,
+      "step": 94
+    },
+    {
+      "epoch": 0.0632279534109817,
+      "grad_norm": 3.209970474243164,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1571,
+      "step": 95
+    },
+    {
+      "epoch": 0.06389351081530782,
+      "grad_norm": 5.132108688354492,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4325,
+      "step": 96
+    },
+    {
+      "epoch": 0.06455906821963395,
+      "grad_norm": 3.055175304412842,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.168,
+      "step": 97
+    },
+    {
+      "epoch": 0.06522462562396007,
+      "grad_norm": 2.978544235229492,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1467,
+      "step": 98
+    },
+    {
+      "epoch": 0.06589018302828618,
+      "grad_norm": 2.435636043548584,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.154,
+      "step": 99
+    },
+    {
+      "epoch": 0.06589018302828618,
+      "eval_loss": 0.1956445723772049,
+      "eval_runtime": 128.9252,
+      "eval_samples_per_second": 9.812,
+      "eval_steps_per_second": 1.233,
+      "step": 99
+    },
+    {
+      "epoch": 0.06655574043261231,
+      "grad_norm": 4.698106288909912,
+      "learning_rate": 0.0,
+      "loss": 0.2,
+      "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": 4.9582058766336e+16,
+  "total_flos": 6.6109411688448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null