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:ce6b48b659d6f7a0560c6a5579bb6e83eeff25eec40cff02a9558278f859c1a3
+oid sha256:702800a3e2a7ff15b7922a9ac899d02cfe4add22f2dd84b90e7285371beac5f6
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b48fffcb0aab870add57635818554129d2e5e6796da983ba9faef8a8bc5a54
+oid sha256:b9af8188ee5008ac51f75d063e187f17f7307f91641a1217893c95110bd008e4
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7390d69c035960909a3614dd1bb0738527d72c78eaafed1ea04f6c83d7885b4d
+oid sha256:9842831702632f624f0d8eca81553d1ceb1a47fa6fd1c3fa71fed9b149a9b02d
 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": 0.10252904989747096,
+  "epoch": 0.1367053998632946,
   "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": 10.3712,
       "step": 75
+    },
+    {
+      "epoch": 0.1038961038961039,
+      "grad_norm": 0.05715708062052727,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3724,
+      "step": 76
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.05752133950591087,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3749,
+      "step": 77
+    },
+    {
+      "epoch": 0.10663021189336978,
+      "grad_norm": 0.05503221973776817,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3729,
+      "step": 78
+    },
+    {
+      "epoch": 0.10799726589200273,
+      "grad_norm": 0.05126158893108368,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.375,
+      "step": 79
+    },
+    {
+      "epoch": 0.10936431989063568,
+      "grad_norm": 0.05652277544140816,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3714,
+      "step": 80
+    },
+    {
+      "epoch": 0.11073137388926863,
+      "grad_norm": 0.05654437467455864,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3755,
+      "step": 81
+    },
+    {
+      "epoch": 0.11073137388926863,
+      "eval_loss": 10.373574256896973,
+      "eval_runtime": 7.4889,
+      "eval_samples_per_second": 82.256,
+      "eval_steps_per_second": 10.282,
+      "step": 81
+    },
+    {
+      "epoch": 0.11209842788790157,
+      "grad_norm": 0.053494893014431,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3745,
+      "step": 82
+    },
+    {
+      "epoch": 0.11346548188653452,
+      "grad_norm": 0.052283793687820435,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3738,
+      "step": 83
+    },
+    {
+      "epoch": 0.11483253588516747,
+      "grad_norm": 0.05515560507774353,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3753,
+      "step": 84
+    },
+    {
+      "epoch": 0.11619958988380041,
+      "grad_norm": 0.06458757072687149,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.374,
+      "step": 85
+    },
+    {
+      "epoch": 0.11756664388243336,
+      "grad_norm": 0.05971672385931015,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.374,
+      "step": 86
+    },
+    {
+      "epoch": 0.11893369788106631,
+      "grad_norm": 0.055294219404459,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3703,
+      "step": 87
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": 0.0639239251613617,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3722,
+      "step": 88
+    },
+    {
+      "epoch": 0.12166780587833219,
+      "grad_norm": 0.06268282234668732,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3723,
+      "step": 89
+    },
+    {
+      "epoch": 0.12303485987696514,
+      "grad_norm": 0.0572989284992218,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3748,
+      "step": 90
+    },
+    {
+      "epoch": 0.12303485987696514,
+      "eval_loss": 10.373421669006348,
+      "eval_runtime": 7.487,
+      "eval_samples_per_second": 82.276,
+      "eval_steps_per_second": 10.284,
+      "step": 90
+    },
+    {
+      "epoch": 0.12440191387559808,
+      "grad_norm": 0.05932777374982834,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3744,
+      "step": 91
+    },
+    {
+      "epoch": 0.12576896787423103,
+      "grad_norm": 0.05577975884079933,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3739,
+      "step": 92
+    },
+    {
+      "epoch": 0.127136021872864,
+      "grad_norm": 0.05579007416963577,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3712,
+      "step": 93
+    },
+    {
+      "epoch": 0.12850307587149692,
+      "grad_norm": 0.060124702751636505,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3745,
+      "step": 94
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 0.05368928983807564,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3729,
+      "step": 95
+    },
+    {
+      "epoch": 0.13123718386876282,
+      "grad_norm": 0.06362160295248032,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3745,
+      "step": 96
+    },
+    {
+      "epoch": 0.13260423786739575,
+      "grad_norm": 0.05649407580494881,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3725,
+      "step": 97
+    },
+    {
+      "epoch": 0.1339712918660287,
+      "grad_norm": 0.06166595220565796,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3738,
+      "step": 98
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "grad_norm": 0.054897576570510864,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3746,
+      "step": 99
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "eval_loss": 10.37338924407959,
+      "eval_runtime": 7.5766,
+      "eval_samples_per_second": 81.303,
+      "eval_steps_per_second": 10.163,
+      "step": 99
+    },
+    {
+      "epoch": 0.1367053998632946,
+      "grad_norm": 0.05194012448191643,
+      "learning_rate": 0.0,
+      "loss": 10.3743,
+      "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": 7845366988800.0,
+  "total_flos": 10460489318400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null