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:ae15380e5a015aee8fe0634f5f8a02107527e75fc397a2a645f3165ac02dc3ab
+oid sha256:174be0c8cc55cbc3182fcfe9815c39cfab2ad9065ddd7823f6da02f39f078d46
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedf1f8255d9fdc2aebff126563d4193931c1011419245469cd7e918e6bb57ac
+oid sha256:17be0c05cdd3d164fd1d713db4c921cfaf0da6cfc936a897b4337e55fce0c8f3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d1a1af9eebbad8de3e56c442429cad586fb9a079791f4de0e7491c83d28f99
+oid sha256:bddc3e16ba10b689f5a09f48a5e61302f82026c2c5de0d3c6a025d056c9d14c2
 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": 0.007669495858472236,
+  "epoch": 0.010225994477962982,
   "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": 2.6126,
       "step": 75
+    },
+    {
+      "epoch": 0.007771755803251866,
+      "grad_norm": 1.0234791040420532,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.533,
+      "step": 76
+    },
+    {
+      "epoch": 0.007874015748031496,
+      "grad_norm": 1.0360850095748901,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.4713,
+      "step": 77
+    },
+    {
+      "epoch": 0.007976275692811126,
+      "grad_norm": 1.0210559368133545,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.4205,
+      "step": 78
+    },
+    {
+      "epoch": 0.008078535637590756,
+      "grad_norm": 0.8871889710426331,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.6196,
+      "step": 79
+    },
+    {
+      "epoch": 0.008180795582370386,
+      "grad_norm": 0.9322873950004578,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2584,
+      "step": 80
+    },
+    {
+      "epoch": 0.008283055527150016,
+      "grad_norm": 1.176164984703064,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.4431,
+      "step": 81
+    },
+    {
+      "epoch": 0.008283055527150016,
+      "eval_loss": 2.4726147651672363,
+      "eval_runtime": 1163.1453,
+      "eval_samples_per_second": 7.08,
+      "eval_steps_per_second": 0.886,
+      "step": 81
+    },
+    {
+      "epoch": 0.008385315471929645,
+      "grad_norm": 1.010968804359436,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.5265,
+      "step": 82
+    },
+    {
+      "epoch": 0.008487575416709275,
+      "grad_norm": 0.8548063039779663,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.4563,
+      "step": 83
+    },
+    {
+      "epoch": 0.008589835361488905,
+      "grad_norm": 1.004049301147461,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.4635,
+      "step": 84
+    },
+    {
+      "epoch": 0.008692095306268535,
+      "grad_norm": 0.9532461166381836,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4391,
+      "step": 85
+    },
+    {
+      "epoch": 0.008794355251048165,
+      "grad_norm": 0.9805513620376587,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4341,
+      "step": 86
+    },
+    {
+      "epoch": 0.008896615195827795,
+      "grad_norm": 1.1075679063796997,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.4997,
+      "step": 87
+    },
+    {
+      "epoch": 0.008998875140607425,
+      "grad_norm": 0.9395877718925476,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.464,
+      "step": 88
+    },
+    {
+      "epoch": 0.009101135085387053,
+      "grad_norm": 1.2045766115188599,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.5617,
+      "step": 89
+    },
+    {
+      "epoch": 0.009203395030166683,
+      "grad_norm": 1.315377116203308,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.3968,
+      "step": 90
+    },
+    {
+      "epoch": 0.009203395030166683,
+      "eval_loss": 2.470728874206543,
+      "eval_runtime": 1170.0038,
+      "eval_samples_per_second": 7.038,
+      "eval_steps_per_second": 0.88,
+      "step": 90
+    },
+    {
+      "epoch": 0.009305654974946313,
+      "grad_norm": 0.8424901366233826,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.4274,
+      "step": 91
+    },
+    {
+      "epoch": 0.009407914919725943,
+      "grad_norm": 1.1313508749008179,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.2425,
+      "step": 92
+    },
+    {
+      "epoch": 0.009510174864505573,
+      "grad_norm": 0.7366335391998291,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.3943,
+      "step": 93
+    },
+    {
+      "epoch": 0.009612434809285203,
+      "grad_norm": 1.0703266859054565,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.3269,
+      "step": 94
+    },
+    {
+      "epoch": 0.009714694754064833,
+      "grad_norm": 0.9565364122390747,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.3007,
+      "step": 95
+    },
+    {
+      "epoch": 0.009816954698844462,
+      "grad_norm": 1.0790512561798096,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.4291,
+      "step": 96
+    },
+    {
+      "epoch": 0.009919214643624092,
+      "grad_norm": 1.059862732887268,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.5832,
+      "step": 97
+    },
+    {
+      "epoch": 0.010021474588403722,
+      "grad_norm": 0.8314029574394226,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.4988,
+      "step": 98
+    },
+    {
+      "epoch": 0.010123734533183352,
+      "grad_norm": 1.1866036653518677,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.2939,
+      "step": 99
+    },
+    {
+      "epoch": 0.010123734533183352,
+      "eval_loss": 2.47027850151062,
+      "eval_runtime": 1167.6796,
+      "eval_samples_per_second": 7.052,
+      "eval_steps_per_second": 0.882,
+      "step": 99
+    },
+    {
+      "epoch": 0.010225994477962982,
+      "grad_norm": 1.085418462753296,
+      "learning_rate": 0.0,
+      "loss": 2.4049,
+      "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": 7.307589743070413e+16,
+  "total_flos": 9.718723414641869e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null