Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74121a33870863020c6c424358f849b3f018cee9231c574ab6ea3a30292d3f80
+oid sha256:e6807051f868ff5e52140ca7463211cda6fa3e3d93dfc6ede994b752577ecba8
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96e7c825a5d10ae8ba0c8df525041458bb348440867c5780f0a9d2fc73eea4a
+oid sha256:c4a0d7461b4a37a06895a2d5f59e2427a1d28e8bbca513004882f724f63acb88
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f18edac6b8e6aebc762d0d0eae840b1a8c079ac2c23ad98eca81ba298b872e
+oid sha256:b239528483bf0e4e2a2fb4c0c7c5615f3fd845040c23ff619d08eb03a93385b8
 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": 1.056338028169014,
+  "epoch": 1.408450704225352,
   "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": 0.2165,
       "step": 75
+    },
+    {
+      "epoch": 1.0704225352112675,
+      "grad_norm": 1.3345345258712769,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2566,
+      "step": 76
+    },
+    {
+      "epoch": 1.084507042253521,
+      "grad_norm": 1.357326865196228,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2707,
+      "step": 77
+    },
+    {
+      "epoch": 1.0985915492957747,
+      "grad_norm": 2.931936264038086,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6957,
+      "step": 78
+    },
+    {
+      "epoch": 1.1126760563380282,
+      "grad_norm": 2.4827914237976074,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4223,
+      "step": 79
+    },
+    {
+      "epoch": 1.1267605633802817,
+      "grad_norm": 2.4220685958862305,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.478,
+      "step": 80
+    },
+    {
+      "epoch": 1.1408450704225352,
+      "grad_norm": 2.1512362957000732,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2542,
+      "step": 81
+    },
+    {
+      "epoch": 1.1408450704225352,
+      "eval_loss": 0.21234546601772308,
+      "eval_runtime": 9.4442,
+      "eval_samples_per_second": 6.353,
+      "eval_steps_per_second": 0.847,
+      "step": 81
+    },
+    {
+      "epoch": 1.1549295774647887,
+      "grad_norm": 1.6278406381607056,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2572,
+      "step": 82
+    },
+    {
+      "epoch": 1.1690140845070423,
+      "grad_norm": 1.5953154563903809,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1924,
+      "step": 83
+    },
+    {
+      "epoch": 1.1830985915492958,
+      "grad_norm": 1.5416163206100464,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.185,
+      "step": 84
+    },
+    {
+      "epoch": 1.1971830985915493,
+      "grad_norm": 1.5798075199127197,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2692,
+      "step": 85
+    },
+    {
+      "epoch": 1.2112676056338028,
+      "grad_norm": 1.769407033920288,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2251,
+      "step": 86
+    },
+    {
+      "epoch": 1.2253521126760563,
+      "grad_norm": 2.33671236038208,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.4008,
+      "step": 87
+    },
+    {
+      "epoch": 1.2394366197183098,
+      "grad_norm": 1.8504016399383545,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3855,
+      "step": 88
+    },
+    {
+      "epoch": 1.2535211267605635,
+      "grad_norm": 1.7060935497283936,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.4009,
+      "step": 89
+    },
+    {
+      "epoch": 1.267605633802817,
+      "grad_norm": 1.8813802003860474,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2404,
+      "step": 90
+    },
+    {
+      "epoch": 1.267605633802817,
+      "eval_loss": 0.20611844956874847,
+      "eval_runtime": 9.4431,
+      "eval_samples_per_second": 6.354,
+      "eval_steps_per_second": 0.847,
+      "step": 90
+    },
+    {
+      "epoch": 1.2816901408450705,
+      "grad_norm": 1.9265403747558594,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3005,
+      "step": 91
+    },
+    {
+      "epoch": 1.295774647887324,
+      "grad_norm": 1.6377530097961426,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2781,
+      "step": 92
+    },
+    {
+      "epoch": 1.3098591549295775,
+      "grad_norm": 1.4389159679412842,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2537,
+      "step": 93
+    },
+    {
+      "epoch": 1.323943661971831,
+      "grad_norm": 3.6935126781463623,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2267,
+      "step": 94
+    },
+    {
+      "epoch": 1.3380281690140845,
+      "grad_norm": 2.6031153202056885,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.4039,
+      "step": 95
+    },
+    {
+      "epoch": 1.352112676056338,
+      "grad_norm": 2.799368143081665,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6262,
+      "step": 96
+    },
+    {
+      "epoch": 1.3661971830985915,
+      "grad_norm": 3.3648576736450195,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3489,
+      "step": 97
+    },
+    {
+      "epoch": 1.380281690140845,
+      "grad_norm": 1.266348123550415,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2577,
+      "step": 98
+    },
+    {
+      "epoch": 1.3943661971830985,
+      "grad_norm": 1.641231894493103,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.3046,
+      "step": 99
+    },
+    {
+      "epoch": 1.3943661971830985,
+      "eval_loss": 0.2067137062549591,
+      "eval_runtime": 9.4426,
+      "eval_samples_per_second": 6.354,
+      "eval_steps_per_second": 0.847,
+      "step": 99
+    },
+    {
+      "epoch": 1.408450704225352,
+      "grad_norm": 2.615276575088501,
+      "learning_rate": 0.0,
+      "loss": 0.23,
+      "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": 9.497940581154816e+16,
+  "total_flos": 1.2671855562326016e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null