Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06673d8935bbdea3be44732494ee63ebcbd7289b021381186dc05fb14661c542
+oid sha256:b4f7073f43b52055da68e307df7a59c9175eb2d0b862965b1c141271efad2c0d
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6227fe6670b0d842101e87b56491687c0b30ee60bb63293349608401e812824d
+oid sha256:8538cf2d4cd9c4f17d55a7012a5108fcebebdcbe0d6c2aed961035ea3653841d
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabbf9aa6a48b77d50a7a00b16119f45a1456a85f84a0bfe2dc898f9708a9cd8
+oid sha256:60505c0066267f0a629f4613b34409ae8d2c404b5e8d49ed993fe5ff891058dd
 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": 0.02449779519843214,
+  "epoch": 0.03266372693124286,
   "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": 10.3687,
       "step": 75
+    },
+    {
+      "epoch": 0.02482443246774457,
+      "grad_norm": 0.07405439764261246,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3693,
+      "step": 76
+    },
+    {
+      "epoch": 0.025151069737056997,
+      "grad_norm": 0.0959295704960823,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3671,
+      "step": 77
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 0.0648365393280983,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3704,
+      "step": 78
+    },
+    {
+      "epoch": 0.025804344275681856,
+      "grad_norm": 0.0828406810760498,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.368,
+      "step": 79
+    },
+    {
+      "epoch": 0.026130981544994283,
+      "grad_norm": 0.08714064955711365,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3676,
+      "step": 80
+    },
+    {
+      "epoch": 0.02645761881430671,
+      "grad_norm": 0.10075332224369049,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3672,
+      "step": 81
+    },
+    {
+      "epoch": 0.02645761881430671,
+      "eval_loss": 10.36816120147705,
+      "eval_runtime": 21.5241,
+      "eval_samples_per_second": 119.773,
+      "eval_steps_per_second": 15.006,
+      "step": 81
+    },
+    {
+      "epoch": 0.026784256083619142,
+      "grad_norm": 0.10861089080572128,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3657,
+      "step": 82
+    },
+    {
+      "epoch": 0.02711089335293157,
+      "grad_norm": 0.07788481563329697,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3682,
+      "step": 83
+    },
+    {
+      "epoch": 0.027437530622243998,
+      "grad_norm": 0.07634954899549484,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3706,
+      "step": 84
+    },
+    {
+      "epoch": 0.027764167891556425,
+      "grad_norm": 0.09162547439336777,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3662,
+      "step": 85
+    },
+    {
+      "epoch": 0.028090805160868856,
+      "grad_norm": 0.08597175776958466,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3692,
+      "step": 86
+    },
+    {
+      "epoch": 0.028417442430181284,
+      "grad_norm": 0.08688751608133316,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3656,
+      "step": 87
+    },
+    {
+      "epoch": 0.02874407969949371,
+      "grad_norm": 0.08870881795883179,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3652,
+      "step": 88
+    },
+    {
+      "epoch": 0.02907071696880614,
+      "grad_norm": 0.09233355522155762,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3674,
+      "step": 89
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "grad_norm": 0.08547327667474747,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3674,
+      "step": 90
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "eval_loss": 10.367944717407227,
+      "eval_runtime": 22.0868,
+      "eval_samples_per_second": 116.721,
+      "eval_steps_per_second": 14.624,
+      "step": 90
+    },
+    {
+      "epoch": 0.029723991507430998,
+      "grad_norm": 0.10347817093133926,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.366,
+      "step": 91
+    },
+    {
+      "epoch": 0.030050628776743426,
+      "grad_norm": 0.09250044822692871,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3687,
+      "step": 92
+    },
+    {
+      "epoch": 0.030377266046055854,
+      "grad_norm": 0.07645335793495178,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3715,
+      "step": 93
+    },
+    {
+      "epoch": 0.030703903315368285,
+      "grad_norm": 0.09881287068128586,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3702,
+      "step": 94
+    },
+    {
+      "epoch": 0.031030540584680712,
+      "grad_norm": 0.08971241861581802,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3699,
+      "step": 95
+    },
+    {
+      "epoch": 0.03135717785399314,
+      "grad_norm": 0.09617859870195389,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3684,
+      "step": 96
+    },
+    {
+      "epoch": 0.03168381512330557,
+      "grad_norm": 0.09534001350402832,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3673,
+      "step": 97
+    },
+    {
+      "epoch": 0.032010452392617995,
+      "grad_norm": 0.11082008481025696,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3673,
+      "step": 98
+    },
+    {
+      "epoch": 0.03233708966193043,
+      "grad_norm": 0.08359237015247345,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3677,
+      "step": 99
+    },
+    {
+      "epoch": 0.03233708966193043,
+      "eval_loss": 10.367908477783203,
+      "eval_runtime": 21.9179,
+      "eval_samples_per_second": 117.621,
+      "eval_steps_per_second": 14.737,
+      "step": 99
+    },
+    {
+      "epoch": 0.03266372693124286,
+      "grad_norm": 0.09743411839008331,
+      "learning_rate": 0.0,
+      "loss": 10.3647,
+      "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": 4498010406912.0,
+  "total_flos": 5884025241600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null