Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9c9988eb95110d6bbb0f40f363f8865bdec434ba073f7b14685ea49654fb07
+oid sha256:f82a0e647ad38679dd4f36c38458bb12d20d28c824fcf217917d85815a44d866
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc8eb602935fd30627db4a815df8a8d74c2b36e2716d6edd4a65010321fe2a4
+oid sha256:24bf76a1459ab26225ffae9aa44b6fdeac92ed39edd41d8c9e0b3221838bccf1
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.528169014084507,
+  "epoch": 0.704225352112676,
   "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": 10.3506,
       "step": 75
+    },
+    {
+      "epoch": 0.5352112676056338,
+      "grad_norm": 0.4924846887588501,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3339,
+      "step": 76
+    },
+    {
+      "epoch": 0.5422535211267606,
+      "grad_norm": 0.433089017868042,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.326,
+      "step": 77
+    },
+    {
+      "epoch": 0.5492957746478874,
+      "grad_norm": 0.47787341475486755,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3411,
+      "step": 78
+    },
+    {
+      "epoch": 0.5563380281690141,
+      "grad_norm": 0.4763740599155426,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3519,
+      "step": 79
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 0.4627920985221863,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3142,
+      "step": 80
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "grad_norm": 0.45368728041648865,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.329,
+      "step": 81
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "eval_loss": 10.343488693237305,
+      "eval_runtime": 0.4128,
+      "eval_samples_per_second": 290.723,
+      "eval_steps_per_second": 36.34,
+      "step": 81
+    },
+    {
+      "epoch": 0.5774647887323944,
+      "grad_norm": 0.5440958142280579,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3666,
+      "step": 82
+    },
+    {
+      "epoch": 0.5845070422535211,
+      "grad_norm": 0.5889712572097778,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.33,
+      "step": 83
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": 0.44246238470077515,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3423,
+      "step": 84
+    },
+    {
+      "epoch": 0.5985915492957746,
+      "grad_norm": 0.4974898099899292,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.2996,
+      "step": 85
+    },
+    {
+      "epoch": 0.6056338028169014,
+      "grad_norm": 0.44511786103248596,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3347,
+      "step": 86
+    },
+    {
+      "epoch": 0.6126760563380281,
+      "grad_norm": 0.49932533502578735,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3229,
+      "step": 87
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 0.5125223398208618,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3135,
+      "step": 88
+    },
+    {
+      "epoch": 0.6267605633802817,
+      "grad_norm": 0.5311346054077148,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3467,
+      "step": 89
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "grad_norm": 0.47513583302497864,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3413,
+      "step": 90
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "eval_loss": 10.342093467712402,
+      "eval_runtime": 0.4072,
+      "eval_samples_per_second": 294.689,
+      "eval_steps_per_second": 36.836,
+      "step": 90
+    },
+    {
+      "epoch": 0.6408450704225352,
+      "grad_norm": 0.4879860281944275,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3247,
+      "step": 91
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": 0.4435056746006012,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3496,
+      "step": 92
+    },
+    {
+      "epoch": 0.6549295774647887,
+      "grad_norm": 0.4078325629234314,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3403,
+      "step": 93
+    },
+    {
+      "epoch": 0.6619718309859155,
+      "grad_norm": 0.4901764988899231,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3486,
+      "step": 94
+    },
+    {
+      "epoch": 0.6690140845070423,
+      "grad_norm": 0.5062358975410461,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3274,
+      "step": 95
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.4807267189025879,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3403,
+      "step": 96
+    },
+    {
+      "epoch": 0.6830985915492958,
+      "grad_norm": 0.4300658106803894,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3333,
+      "step": 97
+    },
+    {
+      "epoch": 0.6901408450704225,
+      "grad_norm": 0.49888625741004944,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3342,
+      "step": 98
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "grad_norm": 0.42185673117637634,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3364,
+      "step": 99
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "eval_loss": 10.341872215270996,
+      "eval_runtime": 0.4363,
+      "eval_samples_per_second": 275.027,
+      "eval_steps_per_second": 34.378,
+      "step": 99
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 0.4972395896911621,
+      "learning_rate": 0.0,
+      "loss": 10.3264,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null