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:b41b2828a6719d2653880e9164ae4fc661a8d76abad7b0061be6b920fa28bce0
+oid sha256:e43282d2310285a330fd830d897a409dc51cef354709ba19a4d74eea76d9078a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac0d8224d123cce2ef6f5dadf17d1fc156faa104f8c646a9887842e5764b1ff
+oid sha256:8813009bd5ce142bf01527baaf9542f27597dc4c01783e163a637108abb8b33f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175434b22fa8805eb7958ee3c6fa1d076bbb21655f587c1f0790cc944a1f8c55
+oid sha256:b8cfc124f811b176b8132abb98f8b0e115fca5fe7009eec811dad5ce88cdc4b1
 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": 0.012459506603538499,
+  "epoch": 0.016612675471384668,
   "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": 1.3661,
       "step": 75
+    },
+    {
+      "epoch": 0.012625633358252347,
+      "grad_norm": 0.9253103733062744,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8792,
+      "step": 76
+    },
+    {
+      "epoch": 0.012791760112966193,
+      "grad_norm": 0.8572337627410889,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4814,
+      "step": 77
+    },
+    {
+      "epoch": 0.01295788686768004,
+      "grad_norm": 0.9993001222610474,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9611,
+      "step": 78
+    },
+    {
+      "epoch": 0.013124013622393887,
+      "grad_norm": 1.4929710626602173,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0746,
+      "step": 79
+    },
+    {
+      "epoch": 0.013290140377107733,
+      "grad_norm": 0.9178129434585571,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.9345,
+      "step": 80
+    },
+    {
+      "epoch": 0.01345626713182158,
+      "grad_norm": 3.765681266784668,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.5544,
+      "step": 81
+    },
+    {
+      "epoch": 0.01345626713182158,
+      "eval_loss": 0.6383609175682068,
+      "eval_runtime": 675.7818,
+      "eval_samples_per_second": 7.501,
+      "eval_steps_per_second": 0.938,
+      "step": 81
+    },
+    {
+      "epoch": 0.013622393886535427,
+      "grad_norm": 0.6158009767532349,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9353,
+      "step": 82
+    },
+    {
+      "epoch": 0.013788520641249273,
+      "grad_norm": 1.4671916961669922,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0639,
+      "step": 83
+    },
+    {
+      "epoch": 0.01395464739596312,
+      "grad_norm": 0.7955529093742371,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.5659,
+      "step": 84
+    },
+    {
+      "epoch": 0.014120774150676967,
+      "grad_norm": 1.442224144935608,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1151,
+      "step": 85
+    },
+    {
+      "epoch": 0.014286900905390813,
+      "grad_norm": 8.284345626831055,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5541,
+      "step": 86
+    },
+    {
+      "epoch": 0.01445302766010466,
+      "grad_norm": 3.518461227416992,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.1257,
+      "step": 87
+    },
+    {
+      "epoch": 0.014619154414818506,
+      "grad_norm": 0.9966995120048523,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9855,
+      "step": 88
+    },
+    {
+      "epoch": 0.014785281169532353,
+      "grad_norm": 0.6061037182807922,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.334,
+      "step": 89
+    },
+    {
+      "epoch": 0.0149514079242462,
+      "grad_norm": 0.7604615092277527,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0108,
+      "step": 90
+    },
+    {
+      "epoch": 0.0149514079242462,
+      "eval_loss": 0.6369998455047607,
+      "eval_runtime": 675.7546,
+      "eval_samples_per_second": 7.501,
+      "eval_steps_per_second": 0.938,
+      "step": 90
+    },
+    {
+      "epoch": 0.015117534678960046,
+      "grad_norm": 0.8596745729446411,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0798,
+      "step": 91
+    },
+    {
+      "epoch": 0.015283661433673892,
+      "grad_norm": 1.0218279361724854,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4505,
+      "step": 92
+    },
+    {
+      "epoch": 0.01544978818838774,
+      "grad_norm": 0.8115531802177429,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.9605,
+      "step": 93
+    },
+    {
+      "epoch": 0.015615914943101586,
+      "grad_norm": 0.94814133644104,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8255,
+      "step": 94
+    },
+    {
+      "epoch": 0.015782041697815434,
+      "grad_norm": 0.9431392550468445,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.7101,
+      "step": 95
+    },
+    {
+      "epoch": 0.01594816845252928,
+      "grad_norm": 1.5731805562973022,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8258,
+      "step": 96
+    },
+    {
+      "epoch": 0.016114295207243126,
+      "grad_norm": 0.644458532333374,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.153,
+      "step": 97
+    },
+    {
+      "epoch": 0.016280421961956972,
+      "grad_norm": 3.3635175228118896,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6484,
+      "step": 98
+    },
+    {
+      "epoch": 0.016446548716670818,
+      "grad_norm": 1.0303000211715698,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3279,
+      "step": 99
+    },
+    {
+      "epoch": 0.016446548716670818,
+      "eval_loss": 0.6366809606552124,
+      "eval_runtime": 675.6737,
+      "eval_samples_per_second": 7.502,
+      "eval_steps_per_second": 0.938,
+      "step": 99
+    },
+    {
+      "epoch": 0.016612675471384668,
+      "grad_norm": 2.6675288677215576,
+      "learning_rate": 0.0,
+      "loss": 2.1576,
+      "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": 7.155367310838989e+16,
+  "total_flos": 9.638508478070784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null