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:cfa77c1a56bcb588b14e60f29f431099bba677212de666f993b9955740816f82
+oid sha256:ac0b7d156919a37c988e53f469a1df7dc4866dcd2b85cfa16bfcabde15c2edb7
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407b0cb8fd6416d20ee4932ad5367b27680a226debd24713b11ce9dda1e48a88
+oid sha256:083dd14063fbf44f3870ad86a757129deb39178385a545c965d728087937c59b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 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": 0.15706806282722513,
+  "epoch": 0.2094240837696335,
   "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": 2.6975,
       "step": 75
+    },
+    {
+      "epoch": 0.15916230366492146,
+      "grad_norm": 0.7345188856124878,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.6499,
+      "step": 76
+    },
+    {
+      "epoch": 0.1612565445026178,
+      "grad_norm": 0.7230733036994934,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.7264,
+      "step": 77
+    },
+    {
+      "epoch": 0.16335078534031414,
+      "grad_norm": 0.6331895589828491,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.6676,
+      "step": 78
+    },
+    {
+      "epoch": 0.16544502617801046,
+      "grad_norm": 0.5962709188461304,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.6949,
+      "step": 79
+    },
+    {
+      "epoch": 0.16753926701570682,
+      "grad_norm": 0.6756764650344849,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.5997,
+      "step": 80
+    },
+    {
+      "epoch": 0.16963350785340314,
+      "grad_norm": 0.5043853521347046,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.6372,
+      "step": 81
+    },
+    {
+      "epoch": 0.16963350785340314,
+      "eval_loss": 1.3571741580963135,
+      "eval_runtime": 54.507,
+      "eval_samples_per_second": 7.394,
+      "eval_steps_per_second": 0.936,
+      "step": 81
+    },
+    {
+      "epoch": 0.17172774869109947,
+      "grad_norm": 0.5730753540992737,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.7383,
+      "step": 82
+    },
+    {
+      "epoch": 0.17382198952879582,
+      "grad_norm": 0.6609073877334595,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.4678,
+      "step": 83
+    },
+    {
+      "epoch": 0.17591623036649215,
+      "grad_norm": 0.7464276552200317,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.7108,
+      "step": 84
+    },
+    {
+      "epoch": 0.17801047120418848,
+      "grad_norm": 0.6932152509689331,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.7522,
+      "step": 85
+    },
+    {
+      "epoch": 0.18010471204188483,
+      "grad_norm": 0.693647563457489,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.8346,
+      "step": 86
+    },
+    {
+      "epoch": 0.18219895287958116,
+      "grad_norm": 0.6403724551200867,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.8161,
+      "step": 87
+    },
+    {
+      "epoch": 0.18429319371727748,
+      "grad_norm": 0.6382010579109192,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.8568,
+      "step": 88
+    },
+    {
+      "epoch": 0.18638743455497384,
+      "grad_norm": 0.6189000010490417,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.6409,
+      "step": 89
+    },
+    {
+      "epoch": 0.18848167539267016,
+      "grad_norm": 0.66209876537323,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.7499,
+      "step": 90
+    },
+    {
+      "epoch": 0.18848167539267016,
+      "eval_loss": 1.3558423519134521,
+      "eval_runtime": 54.5491,
+      "eval_samples_per_second": 7.388,
+      "eval_steps_per_second": 0.935,
+      "step": 90
+    },
+    {
+      "epoch": 0.1905759162303665,
+      "grad_norm": 0.6726245880126953,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.5282,
+      "step": 91
+    },
+    {
+      "epoch": 0.19267015706806281,
+      "grad_norm": 0.6591723561286926,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.7147,
+      "step": 92
+    },
+    {
+      "epoch": 0.19476439790575917,
+      "grad_norm": 0.587321937084198,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.7536,
+      "step": 93
+    },
+    {
+      "epoch": 0.1968586387434555,
+      "grad_norm": 0.672417402267456,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.586,
+      "step": 94
+    },
+    {
+      "epoch": 0.19895287958115182,
+      "grad_norm": 0.6691716313362122,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.5708,
+      "step": 95
+    },
+    {
+      "epoch": 0.20104712041884817,
+      "grad_norm": 0.6790332198143005,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.6005,
+      "step": 96
+    },
+    {
+      "epoch": 0.2031413612565445,
+      "grad_norm": 0.6420785188674927,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.5068,
+      "step": 97
+    },
+    {
+      "epoch": 0.20523560209424083,
+      "grad_norm": 0.6517630219459534,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.6767,
+      "step": 98
+    },
+    {
+      "epoch": 0.20732984293193718,
+      "grad_norm": 0.6084813475608826,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.6547,
+      "step": 99
+    },
+    {
+      "epoch": 0.20732984293193718,
+      "eval_loss": 1.3555799722671509,
+      "eval_runtime": 54.5552,
+      "eval_samples_per_second": 7.387,
+      "eval_steps_per_second": 0.935,
+      "step": 99
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 0.6263311505317688,
+      "learning_rate": 0.0,
+      "loss": 2.6251,
+      "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": 4.90098483265536e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null