Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50218b374ff07ac1494864558562436669c0f01382cb6c7f4eb3f45d35b2e422
+oid sha256:396717f43fa8bde25d3cbdc47aaec23a40a478866ab55b5619c33350374e911b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac69258dcc56c67c5ab30e7926804e49b24ae1f0cf5c0e79fb6bc7b78dee9e2
+oid sha256:b4068b04aa57f0b0ffd152cd55ec6e46a95044b4bd5a37f125f0e54b2e510b79
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8e37d13f94a9a10e4913ceeeb7ab15034a5d23e49b769101fb006141e6e364
+oid sha256:3f562ed09e83a44c0c0f1d4edeacdf5360cdb35220d6ce1c456f0bb07534f4a7
 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": 0.007471235742391792,
+  "epoch": 0.009961647656522389,
   "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": 1.3523,
       "step": 75
+    },
+    {
+      "epoch": 0.007570852218957015,
+      "grad_norm": 0.856013298034668,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4357,
+      "step": 76
+    },
+    {
+      "epoch": 0.007670468695522239,
+      "grad_norm": 0.7908009886741638,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4971,
+      "step": 77
+    },
+    {
+      "epoch": 0.0077700851720874636,
+      "grad_norm": 0.6581637859344482,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3045,
+      "step": 78
+    },
+    {
+      "epoch": 0.007869701648652687,
+      "grad_norm": 0.7885287404060364,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4768,
+      "step": 79
+    },
+    {
+      "epoch": 0.00796931812521791,
+      "grad_norm": 0.8533726334571838,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.813,
+      "step": 80
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "grad_norm": 0.7847617864608765,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.6292,
+      "step": 81
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "eval_loss": 0.7664384245872498,
+      "eval_runtime": 883.1996,
+      "eval_samples_per_second": 9.572,
+      "eval_steps_per_second": 1.197,
+      "step": 81
+    },
+    {
+      "epoch": 0.008168551078348359,
+      "grad_norm": 0.6186761856079102,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2958,
+      "step": 82
+    },
+    {
+      "epoch": 0.008268167554913582,
+      "grad_norm": 0.5993787050247192,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3766,
+      "step": 83
+    },
+    {
+      "epoch": 0.008367784031478807,
+      "grad_norm": 0.6269441246986389,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3048,
+      "step": 84
+    },
+    {
+      "epoch": 0.00846740050804403,
+      "grad_norm": 0.7146202325820923,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4853,
+      "step": 85
+    },
+    {
+      "epoch": 0.008567016984609254,
+      "grad_norm": 0.7214375138282776,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4497,
+      "step": 86
+    },
+    {
+      "epoch": 0.008666633461174479,
+      "grad_norm": 0.7088419795036316,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5205,
+      "step": 87
+    },
+    {
+      "epoch": 0.008766249937739702,
+      "grad_norm": 0.7890331745147705,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6061,
+      "step": 88
+    },
+    {
+      "epoch": 0.008865866414304925,
+      "grad_norm": 0.75309157371521,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.6513,
+      "step": 89
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "grad_norm": 0.6757559776306152,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3202,
+      "step": 90
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "eval_loss": 0.7658533453941345,
+      "eval_runtime": 883.1032,
+      "eval_samples_per_second": 9.573,
+      "eval_steps_per_second": 1.197,
+      "step": 90
+    },
+    {
+      "epoch": 0.009065099367435374,
+      "grad_norm": 0.7671038508415222,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6385,
+      "step": 91
+    },
+    {
+      "epoch": 0.009164715844000597,
+      "grad_norm": 0.6452928185462952,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3193,
+      "step": 92
+    },
+    {
+      "epoch": 0.009264332320565822,
+      "grad_norm": 0.6585118174552917,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.2951,
+      "step": 93
+    },
+    {
+      "epoch": 0.009363948797131046,
+      "grad_norm": 0.7894080281257629,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6466,
+      "step": 94
+    },
+    {
+      "epoch": 0.009463565273696269,
+      "grad_norm": 0.6712362170219421,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5096,
+      "step": 95
+    },
+    {
+      "epoch": 0.009563181750261494,
+      "grad_norm": 0.7802687883377075,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3291,
+      "step": 96
+    },
+    {
+      "epoch": 0.009662798226826717,
+      "grad_norm": 0.6751720905303955,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5444,
+      "step": 97
+    },
+    {
+      "epoch": 0.00976241470339194,
+      "grad_norm": 0.6705344319343567,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4777,
+      "step": 98
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "grad_norm": 0.6760139465332031,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4916,
+      "step": 99
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "eval_loss": 0.7657371759414673,
+      "eval_runtime": 883.7398,
+      "eval_samples_per_second": 9.566,
+      "eval_steps_per_second": 1.196,
+      "step": 99
+    },
+    {
+      "epoch": 0.009961647656522389,
+      "grad_norm": 0.6802321076393127,
+      "learning_rate": 0.0,
+      "loss": 1.5107,
+      "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": 9.648701542760448e+16,
+  "total_flos": 1.2886094823555072e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null