Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185f086f22f385c92df728d926d88f92b3966675c29ee7943d1058d42d0a5ca1
+oid sha256:9c28e0b2e5a6d265f1cf5c5ac331c294be25844132959130bd0233ed820cef3e
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a71bc2eeae32e4c96c9f659c825ff481f23d9c49df07b993538276e451b211
+oid sha256:8c1060544c8c42cbe474ba208c97cc681d6e3ea665dfb5379ae9ca6ff6e90c12
 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": 0.1057,
       "step": 75
+    },
+    {
+      "epoch": 0.01043884348602431,
+      "grad_norm": 2.810657262802124,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1014,
+      "step": 76
+    },
+    {
+      "epoch": 0.010576196689787789,
+      "grad_norm": 2.7257590293884277,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1751,
+      "step": 77
+    },
+    {
+      "epoch": 0.010713549893551267,
+      "grad_norm": 2.120305061340332,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1735,
+      "step": 78
+    },
+    {
+      "epoch": 0.010850903097314745,
+      "grad_norm": 1.8682059049606323,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0433,
+      "step": 79
+    },
+    {
+      "epoch": 0.010988256301078223,
+      "grad_norm": 1.0465031862258911,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1019,
+      "step": 80
+    },
+    {
+      "epoch": 0.011125609504841701,
+      "grad_norm": 1.4673629999160767,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0376,
+      "step": 81
+    },
+    {
+      "epoch": 0.011125609504841701,
+      "eval_loss": 0.09728392958641052,
+      "eval_runtime": 1498.9976,
+      "eval_samples_per_second": 4.09,
+      "eval_steps_per_second": 0.512,
+      "step": 81
+    },
+    {
+      "epoch": 0.011262962708605178,
+      "grad_norm": 1.0142756700515747,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0356,
+      "step": 82
+    },
+    {
+      "epoch": 0.011400315912368656,
+      "grad_norm": 1.2843859195709229,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0466,
+      "step": 83
+    },
+    {
+      "epoch": 0.011537669116132134,
+      "grad_norm": 4.476285457611084,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1879,
+      "step": 84
+    },
+    {
+      "epoch": 0.011675022319895612,
+      "grad_norm": 4.4546332359313965,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1602,
+      "step": 85
+    },
+    {
+      "epoch": 0.01181237552365909,
+      "grad_norm": 3.740358352661133,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0667,
+      "step": 86
+    },
+    {
+      "epoch": 0.011949728727422566,
+      "grad_norm": 1.2667216062545776,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0298,
+      "step": 87
+    },
+    {
+      "epoch": 0.012087081931186044,
+      "grad_norm": 1.5209143161773682,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.051,
+      "step": 88
+    },
+    {
+      "epoch": 0.012224435134949523,
+      "grad_norm": 0.6315830945968628,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0155,
+      "step": 89
+    },
+    {
+      "epoch": 0.012361788338713,
+      "grad_norm": 2.6171979904174805,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1119,
+      "step": 90
+    },
+    {
+      "epoch": 0.012361788338713,
+      "eval_loss": 0.08409945666790009,
+      "eval_runtime": 1498.4857,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 0.512,
+      "step": 90
+    },
+    {
+      "epoch": 0.012499141542476479,
+      "grad_norm": 0.7829715013504028,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0263,
+      "step": 91
+    },
+    {
+      "epoch": 0.012636494746239957,
+      "grad_norm": 1.01038658618927,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0265,
+      "step": 92
+    },
+    {
+      "epoch": 0.012773847950003433,
+      "grad_norm": 0.4501360356807709,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0112,
+      "step": 93
+    },
+    {
+      "epoch": 0.012911201153766911,
+      "grad_norm": 0.3697107434272766,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0121,
+      "step": 94
+    },
+    {
+      "epoch": 0.01304855435753039,
+      "grad_norm": 1.2892919778823853,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0215,
+      "step": 95
+    },
+    {
+      "epoch": 0.013185907561293867,
+      "grad_norm": 1.3150074481964111,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0209,
+      "step": 96
+    },
+    {
+      "epoch": 0.013323260765057346,
+      "grad_norm": 0.9793353080749512,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0262,
+      "step": 97
+    },
+    {
+      "epoch": 0.013460613968820822,
+      "grad_norm": 2.4705395698547363,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.143,
+      "step": 98
+    },
+    {
+      "epoch": 0.0135979671725843,
+      "grad_norm": 2.2415056228637695,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1183,
+      "step": 99
+    },
+    {
+      "epoch": 0.0135979671725843,
+      "eval_loss": 0.08113499730825424,
+      "eval_runtime": 1498.1084,
+      "eval_samples_per_second": 4.092,
+      "eval_steps_per_second": 0.512,
+      "step": 99
+    },
+    {
+      "epoch": 0.013735320376347778,
+      "grad_norm": 0.6419519186019897,
+      "learning_rate": 0.0,
+      "loss": 0.0252,
+      "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