Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189fbc9395719e60d6550327269a856cc15c1e29099ab00bfd701c4f21e2e011
+oid sha256:d8fc98a5549f3485c681667fc746b2246749d74823462f0d5986ba0dd75f2628
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc1c02530bd4e977feb06ab96497a9aba172d34eb315aebe466d3b2f9312616
+oid sha256:3a32b9f76243044f0bfeb02b6f76a7594005a579739ee78c727362a76be22e1b
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
+oid sha256:c659e4505005131eab7ea0ee74ff9e2fee448c1f7e5a9dc766af93a6f64c72a6
 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": 0.26501766784452296,
+  "epoch": 0.35335689045936397,
   "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": 2.7786,
       "step": 75
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 2.9842982292175293,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.8045,
+      "step": 76
+    },
+    {
+      "epoch": 0.27208480565371024,
+      "grad_norm": 2.914149761199951,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.9885,
+      "step": 77
+    },
+    {
+      "epoch": 0.2756183745583039,
+      "grad_norm": 2.9864964485168457,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.8352,
+      "step": 78
+    },
+    {
+      "epoch": 0.2791519434628975,
+      "grad_norm": 2.934354782104492,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.6339,
+      "step": 79
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 3.1368119716644287,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.9582,
+      "step": 80
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "grad_norm": 2.8849451541900635,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.5189,
+      "step": 81
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "eval_loss": 2.7373812198638916,
+      "eval_runtime": 7.2612,
+      "eval_samples_per_second": 32.915,
+      "eval_steps_per_second": 4.132,
+      "step": 81
+    },
+    {
+      "epoch": 0.28975265017667845,
+      "grad_norm": 3.1763510704040527,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.947,
+      "step": 82
+    },
+    {
+      "epoch": 0.29328621908127206,
+      "grad_norm": 3.013666868209839,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.8198,
+      "step": 83
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 2.9492177963256836,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.903,
+      "step": 84
+    },
+    {
+      "epoch": 0.3003533568904594,
+      "grad_norm": 3.1559722423553467,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.6751,
+      "step": 85
+    },
+    {
+      "epoch": 0.303886925795053,
+      "grad_norm": 3.237069845199585,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.9631,
+      "step": 86
+    },
+    {
+      "epoch": 0.30742049469964666,
+      "grad_norm": 2.846069097518921,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.413,
+      "step": 87
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 3.15340518951416,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7726,
+      "step": 88
+    },
+    {
+      "epoch": 0.31448763250883394,
+      "grad_norm": 3.0977818965911865,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.6706,
+      "step": 89
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "grad_norm": 3.072103500366211,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.8401,
+      "step": 90
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "eval_loss": 2.7312164306640625,
+      "eval_runtime": 7.2728,
+      "eval_samples_per_second": 32.862,
+      "eval_steps_per_second": 4.125,
+      "step": 90
+    },
+    {
+      "epoch": 0.3215547703180212,
+      "grad_norm": 3.2932465076446533,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.7885,
+      "step": 91
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 3.051379919052124,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.856,
+      "step": 92
+    },
+    {
+      "epoch": 0.3286219081272085,
+      "grad_norm": 3.6405014991760254,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.0182,
+      "step": 93
+    },
+    {
+      "epoch": 0.3321554770318021,
+      "grad_norm": 3.0637409687042236,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.74,
+      "step": 94
+    },
+    {
+      "epoch": 0.33568904593639576,
+      "grad_norm": 2.782472610473633,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.4952,
+      "step": 95
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 2.91768479347229,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.5299,
+      "step": 96
+    },
+    {
+      "epoch": 0.34275618374558303,
+      "grad_norm": 3.1842963695526123,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.8131,
+      "step": 97
+    },
+    {
+      "epoch": 0.3462897526501767,
+      "grad_norm": 3.0471694469451904,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.6119,
+      "step": 98
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "grad_norm": 3.2010068893432617,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.7762,
+      "step": 99
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "eval_loss": 2.730311870574951,
+      "eval_runtime": 7.274,
+      "eval_samples_per_second": 32.857,
+      "eval_steps_per_second": 4.124,
+      "step": 99
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 2.9649581909179688,
+      "learning_rate": 0.0,
+      "loss": 2.8928,
+      "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": 7257919271731200.0,
+  "total_flos": 9677225695641600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null