Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69edb7b329608d6b1d3183ba37ba4186db9f018d4bb62f0c2ed9e19c4c97ab80
+oid sha256:f597a68929d53afdf5dacec9652085b90fc59c5afbb75960b017be11e4b38f90
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ce4693f06bbc7475ac9333231251ce4cf5b7a225e6d95323e0a0b2cbb77905
+oid sha256:b093ac1a7ba3cda501bc88c4de45ca816fabfb0702d1890c71e73496314c33fb
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24d2e8e76f08f48de18a7fab9b899f70eefc96fde5f6bcaf00a77bccbaf0ea5
+oid sha256:a5e717201d39f8e947c7438e56742107d4ff7183f3a8c98baef7b90093b80014
 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": 0.010301490282260834,
+  "epoch": 0.013735320376347778,
   "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": 0.0765,
       "step": 75
+    },
+    {
+      "epoch": 0.01043884348602431,
+      "grad_norm": 3.519460439682007,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1264,
+      "step": 76
+    },
+    {
+      "epoch": 0.010576196689787789,
+      "grad_norm": 2.8444440364837646,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1523,
+      "step": 77
+    },
+    {
+      "epoch": 0.010713549893551267,
+      "grad_norm": 1.7805485725402832,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1548,
+      "step": 78
+    },
+    {
+      "epoch": 0.010850903097314745,
+      "grad_norm": 1.9851247072219849,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0466,
+      "step": 79
+    },
+    {
+      "epoch": 0.010988256301078223,
+      "grad_norm": 1.056861400604248,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1007,
+      "step": 80
+    },
+    {
+      "epoch": 0.011125609504841701,
+      "grad_norm": 0.8655954599380493,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0206,
+      "step": 81
+    },
+    {
+      "epoch": 0.011125609504841701,
+      "eval_loss": 0.09324146062135696,
+      "eval_runtime": 1386.804,
+      "eval_samples_per_second": 4.421,
+      "eval_steps_per_second": 0.553,
+      "step": 81
+    },
+    {
+      "epoch": 0.011262962708605178,
+      "grad_norm": 0.9096500277519226,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0326,
+      "step": 82
+    },
+    {
+      "epoch": 0.011400315912368656,
+      "grad_norm": 1.0668306350708008,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0314,
+      "step": 83
+    },
+    {
+      "epoch": 0.011537669116132134,
+      "grad_norm": 5.761446475982666,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1446,
+      "step": 84
+    },
+    {
+      "epoch": 0.011675022319895612,
+      "grad_norm": 5.004864692687988,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1498,
+      "step": 85
+    },
+    {
+      "epoch": 0.01181237552365909,
+      "grad_norm": 2.5033371448516846,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0368,
+      "step": 86
+    },
+    {
+      "epoch": 0.011949728727422566,
+      "grad_norm": 1.4886705875396729,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0313,
+      "step": 87
+    },
+    {
+      "epoch": 0.012087081931186044,
+      "grad_norm": 1.317595362663269,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.048,
+      "step": 88
+    },
+    {
+      "epoch": 0.012224435134949523,
+      "grad_norm": 0.48926466703414917,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0107,
+      "step": 89
+    },
+    {
+      "epoch": 0.012361788338713,
+      "grad_norm": 2.002946615219116,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0945,
+      "step": 90
+    },
+    {
+      "epoch": 0.012361788338713,
+      "eval_loss": 0.08057644218206406,
+      "eval_runtime": 1386.6647,
+      "eval_samples_per_second": 4.421,
+      "eval_steps_per_second": 0.553,
+      "step": 90
+    },
+    {
+      "epoch": 0.012499141542476479,
+      "grad_norm": 0.8445478677749634,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0213,
+      "step": 91
+    },
+    {
+      "epoch": 0.012636494746239957,
+      "grad_norm": 0.6270654201507568,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0154,
+      "step": 92
+    },
+    {
+      "epoch": 0.012773847950003433,
+      "grad_norm": 0.5323001146316528,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0109,
+      "step": 93
+    },
+    {
+      "epoch": 0.012911201153766911,
+      "grad_norm": 0.3020775616168976,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0106,
+      "step": 94
+    },
+    {
+      "epoch": 0.01304855435753039,
+      "grad_norm": 0.866532027721405,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0143,
+      "step": 95
+    },
+    {
+      "epoch": 0.013185907561293867,
+      "grad_norm": 0.9964131116867065,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0153,
+      "step": 96
+    },
+    {
+      "epoch": 0.013323260765057346,
+      "grad_norm": 0.48639726638793945,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0137,
+      "step": 97
+    },
+    {
+      "epoch": 0.013460613968820822,
+      "grad_norm": 2.183847188949585,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1435,
+      "step": 98
+    },
+    {
+      "epoch": 0.0135979671725843,
+      "grad_norm": 2.3848156929016113,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.103,
+      "step": 99
+    },
+    {
+      "epoch": 0.0135979671725843,
+      "eval_loss": 0.07801946997642517,
+      "eval_runtime": 1386.496,
+      "eval_samples_per_second": 4.422,
+      "eval_steps_per_second": 0.553,
+      "step": 99
+    },
+    {
+      "epoch": 0.013735320376347778,
+      "grad_norm": 0.5589208602905273,
+      "learning_rate": 0.0,
+      "loss": 0.021,
+      "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": 3.918303489687552e+16,
+  "total_flos": 5.235380292943872e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null