Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2fc12336adce739348a07a3a6d78256e08ed2f2ba0caa26c2e107c245655cb
+oid sha256:69e975ac42f4cb220c6a93b3254bfed3ea990d88331af38d20dcaa8936e6fc02
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:201dffbeafdcb3736d3f42bf8fc9643c657e36567ebd673ad90dfe9ffc9fd21c
+oid sha256:99892fdd42af73d61cae66561cb2a510d6f82db6d904917352e7780d6b0ded4a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10b30c9eb6fa58f462effd0387a91e467102f189329d79b95990979c2e03389
+oid sha256:e5e6d6df32af28965e521ce09e49489f0f73a73e437d8780fef6228a2797f791
 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": 0.005981576743629621,
+  "epoch": 0.007975435658172828,
   "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": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.006061331100211349,
+      "grad_norm": 5.963899612426758,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0601,
+      "step": 76
+    },
+    {
+      "epoch": 0.0061410854567930774,
+      "grad_norm": 0.037896182388067245,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0006,
+      "step": 77
+    },
+    {
+      "epoch": 0.006220839813374806,
+      "grad_norm": 0.24905402958393097,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0033,
+      "step": 78
+    },
+    {
+      "epoch": 0.006300594169956534,
+      "grad_norm": 0.02116982452571392,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0003,
+      "step": 79
+    },
+    {
+      "epoch": 0.006380348526538262,
+      "grad_norm": 0.001493555959314108,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.00646010288311999,
+      "grad_norm": 0.04112343490123749,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0002,
+      "step": 81
+    },
+    {
+      "epoch": 0.00646010288311999,
+      "eval_loss": 0.03697933256626129,
+      "eval_runtime": 553.647,
+      "eval_samples_per_second": 19.072,
+      "eval_steps_per_second": 2.384,
+      "step": 81
+    },
+    {
+      "epoch": 0.006539857239701719,
+      "grad_norm": 0.852574348449707,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0052,
+      "step": 82
+    },
+    {
+      "epoch": 0.006619611596283447,
+      "grad_norm": 5.428268909454346,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1395,
+      "step": 83
+    },
+    {
+      "epoch": 0.006699365952865175,
+      "grad_norm": 0.053005896508693695,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0007,
+      "step": 84
+    },
+    {
+      "epoch": 0.0067791203094469035,
+      "grad_norm": 1.3258788585662842,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0071,
+      "step": 85
+    },
+    {
+      "epoch": 0.006858874666028632,
+      "grad_norm": 0.125382199883461,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0009,
+      "step": 86
+    },
+    {
+      "epoch": 0.00693862902261036,
+      "grad_norm": 0.025496359914541245,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0003,
+      "step": 87
+    },
+    {
+      "epoch": 0.007018383379192089,
+      "grad_norm": 7.4097113609313965,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1218,
+      "step": 88
+    },
+    {
+      "epoch": 0.007098137735773817,
+      "grad_norm": 0.0033981853630393744,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.007177892092355545,
+      "grad_norm": 0.38592103123664856,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0025,
+      "step": 90
+    },
+    {
+      "epoch": 0.007177892092355545,
+      "eval_loss": 0.03521589934825897,
+      "eval_runtime": 553.4928,
+      "eval_samples_per_second": 19.077,
+      "eval_steps_per_second": 2.385,
+      "step": 90
+    },
+    {
+      "epoch": 0.007257646448937273,
+      "grad_norm": 0.0367887020111084,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0004,
+      "step": 91
+    },
+    {
+      "epoch": 0.007337400805519001,
+      "grad_norm": 0.030135678127408028,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0003,
+      "step": 92
+    },
+    {
+      "epoch": 0.0074171551621007295,
+      "grad_norm": 0.30348286032676697,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0022,
+      "step": 93
+    },
+    {
+      "epoch": 0.007496909518682458,
+      "grad_norm": 0.007436178158968687,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 0.007576663875264187,
+      "grad_norm": 3.1514601707458496,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1337,
+      "step": 95
+    },
+    {
+      "epoch": 0.007656418231845915,
+      "grad_norm": 4.589775085449219,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2785,
+      "step": 96
+    },
+    {
+      "epoch": 0.007736172588427643,
+      "grad_norm": 1.7154332399368286,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0127,
+      "step": 97
+    },
+    {
+      "epoch": 0.007815926945009372,
+      "grad_norm": 4.0604634284973145,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0165,
+      "step": 98
+    },
+    {
+      "epoch": 0.0078956813015911,
+      "grad_norm": 10.015667915344238,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1357,
+      "step": 99
+    },
+    {
+      "epoch": 0.0078956813015911,
+      "eval_loss": 0.03452092781662941,
+      "eval_runtime": 553.3103,
+      "eval_samples_per_second": 19.083,
+      "eval_steps_per_second": 2.386,
+      "step": 99
+    },
+    {
+      "epoch": 0.007975435658172828,
+      "grad_norm": 13.142882347106934,
+      "learning_rate": 0.0,
+      "loss": 0.1644,
+      "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": 5.601248990881382e+16,
+  "total_flos": 7.455967199782502e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null