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:cf52c1cb72ef80ad3ad0bdee1c595c8497946fb3887ff3de78c54066c51d7683
+oid sha256:dd9fae950605399670899d250a3ab006ce580c5f68a9e713befe9b4c4983a15c
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55526d89c3aae561046db5549ad32b127d5bb590a8e40d7bf9697fc3ff481ad8
+oid sha256:8b41f8aed4777a6b31a58a09271c3eca18405ce418b7a7ebeffdba46408bf0a1
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1d644a4a39d949387b662bdefaee2232811c755c916d4547d1e6e803c86cf5
+oid sha256:03234c59276a3926e42276e51b5f8ade5ed5a056f62f458d656d76b351955cf2
 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": 0.007050860204945004,
+  "epoch": 0.00940114693992667,
   "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": 0.461,
       "step": 75
+    },
+    {
+      "epoch": 0.00714487167434427,
+      "grad_norm": 0.6586530804634094,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.47,
+      "step": 76
+    },
+    {
+      "epoch": 0.007238883143743537,
+      "grad_norm": 0.6268256902694702,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.3882,
+      "step": 77
+    },
+    {
+      "epoch": 0.007332894613142803,
+      "grad_norm": 0.9291857481002808,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4392,
+      "step": 78
+    },
+    {
+      "epoch": 0.00742690608254207,
+      "grad_norm": 0.647275984287262,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4699,
+      "step": 79
+    },
+    {
+      "epoch": 0.007520917551941337,
+      "grad_norm": 0.9980822205543518,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4285,
+      "step": 80
+    },
+    {
+      "epoch": 0.007614929021340603,
+      "grad_norm": 0.8482042551040649,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.5776,
+      "step": 81
+    },
+    {
+      "epoch": 0.007614929021340603,
+      "eval_loss": 0.48237743973731995,
+      "eval_runtime": 252.7768,
+      "eval_samples_per_second": 35.438,
+      "eval_steps_per_second": 4.431,
+      "step": 81
+    },
+    {
+      "epoch": 0.007708940490739871,
+      "grad_norm": 0.8040179014205933,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5144,
+      "step": 82
+    },
+    {
+      "epoch": 0.007802951960139137,
+      "grad_norm": 1.0259931087493896,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6373,
+      "step": 83
+    },
+    {
+      "epoch": 0.007896963429538403,
+      "grad_norm": 0.68227219581604,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.4367,
+      "step": 84
+    },
+    {
+      "epoch": 0.00799097489893767,
+      "grad_norm": 0.7292605042457581,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3914,
+      "step": 85
+    },
+    {
+      "epoch": 0.008084986368336938,
+      "grad_norm": 0.7981929779052734,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.4296,
+      "step": 86
+    },
+    {
+      "epoch": 0.008178997837736204,
+      "grad_norm": 0.8670974373817444,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.5271,
+      "step": 87
+    },
+    {
+      "epoch": 0.008273009307135471,
+      "grad_norm": 0.7809897065162659,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5128,
+      "step": 88
+    },
+    {
+      "epoch": 0.008367020776534737,
+      "grad_norm": 0.8482014536857605,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.5015,
+      "step": 89
+    },
+    {
+      "epoch": 0.008461032245934004,
+      "grad_norm": 0.837470531463623,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5296,
+      "step": 90
+    },
+    {
+      "epoch": 0.008461032245934004,
+      "eval_loss": 0.47757917642593384,
+      "eval_runtime": 254.8488,
+      "eval_samples_per_second": 35.15,
+      "eval_steps_per_second": 4.395,
+      "step": 90
+    },
+    {
+      "epoch": 0.00855504371533327,
+      "grad_norm": 0.7973629832267761,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.457,
+      "step": 91
+    },
+    {
+      "epoch": 0.008649055184732538,
+      "grad_norm": 0.8676332235336304,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5536,
+      "step": 92
+    },
+    {
+      "epoch": 0.008743066654131803,
+      "grad_norm": 0.9171940088272095,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5606,
+      "step": 93
+    },
+    {
+      "epoch": 0.00883707812353107,
+      "grad_norm": 0.80989009141922,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4564,
+      "step": 94
+    },
+    {
+      "epoch": 0.008931089592930338,
+      "grad_norm": 0.6417605876922607,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.42,
+      "step": 95
+    },
+    {
+      "epoch": 0.009025101062329604,
+      "grad_norm": 0.8094590306282043,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4697,
+      "step": 96
+    },
+    {
+      "epoch": 0.009119112531728871,
+      "grad_norm": 0.838222861289978,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.4577,
+      "step": 97
+    },
+    {
+      "epoch": 0.009213124001128137,
+      "grad_norm": 0.6396716833114624,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4427,
+      "step": 98
+    },
+    {
+      "epoch": 0.009307135470527405,
+      "grad_norm": 0.6989951729774475,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4577,
+      "step": 99
+    },
+    {
+      "epoch": 0.009307135470527405,
+      "eval_loss": 0.4766019582748413,
+      "eval_runtime": 254.5056,
+      "eval_samples_per_second": 35.198,
+      "eval_steps_per_second": 4.401,
+      "step": 99
+    },
+    {
+      "epoch": 0.00940114693992667,
+      "grad_norm": 0.6284540295600891,
+      "learning_rate": 0.0,
+      "loss": 0.4063,
+      "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": 7720265790259200.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null