Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6637b4864cca510c6039a0dff7cae9d5a6329de5b19fa8197dba8405ccd8040a
+oid sha256:d34e0d6246db12c76cc4ad5bc92a7b9b2fdfac9285a89ba8b8b5fe1e3509d6e8
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6575fb301d8b2bbe044bcde097f3b21329b5cbecd4fa49d5100f197e433746b7
+oid sha256:097a67bc7555c54d105813c12ce9f49132cd74141fa37dd1bed1f1590bc33fa9
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1e7b25f88ad2d6e9b2dde52d881fe797c0caa54c2ec512969749f9fe5f9fec
+oid sha256:b9ca8b5630baa77096061c41a92e38286d10ccb99a9551b39e70f2b1e0301198
 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": 1.5463917525773194,
+  "epoch": 2.0618556701030926,
   "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": 2.3334,
       "step": 75
+    },
+    {
+      "epoch": 1.5670103092783505,
+      "grad_norm": 0.7970970273017883,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.3437,
+      "step": 76
+    },
+    {
+      "epoch": 1.5876288659793816,
+      "grad_norm": 0.7679882049560547,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.2173,
+      "step": 77
+    },
+    {
+      "epoch": 1.6082474226804124,
+      "grad_norm": 0.8142104744911194,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.2157,
+      "step": 78
+    },
+    {
+      "epoch": 1.6288659793814433,
+      "grad_norm": 0.8778489828109741,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.4768,
+      "step": 79
+    },
+    {
+      "epoch": 1.6494845360824741,
+      "grad_norm": 0.8009780049324036,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.128,
+      "step": 80
+    },
+    {
+      "epoch": 1.670103092783505,
+      "grad_norm": 0.8642892241477966,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.3527,
+      "step": 81
+    },
+    {
+      "epoch": 1.670103092783505,
+      "eval_loss": 2.2726926803588867,
+      "eval_runtime": 0.428,
+      "eval_samples_per_second": 95.798,
+      "eval_steps_per_second": 14.019,
+      "step": 81
+    },
+    {
+      "epoch": 1.690721649484536,
+      "grad_norm": 0.7616624236106873,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0641,
+      "step": 82
+    },
+    {
+      "epoch": 1.7113402061855671,
+      "grad_norm": 0.8058216571807861,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.61,
+      "step": 83
+    },
+    {
+      "epoch": 1.731958762886598,
+      "grad_norm": 0.7998701333999634,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0878,
+      "step": 84
+    },
+    {
+      "epoch": 1.7525773195876289,
+      "grad_norm": 0.8615913391113281,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2409,
+      "step": 85
+    },
+    {
+      "epoch": 1.7731958762886597,
+      "grad_norm": 0.8412482738494873,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4182,
+      "step": 86
+    },
+    {
+      "epoch": 1.7938144329896906,
+      "grad_norm": 0.8457291126251221,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.2028,
+      "step": 87
+    },
+    {
+      "epoch": 1.8144329896907216,
+      "grad_norm": 0.895065426826477,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.3504,
+      "step": 88
+    },
+    {
+      "epoch": 1.8350515463917527,
+      "grad_norm": 0.768960177898407,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.0939,
+      "step": 89
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "grad_norm": 0.7762629389762878,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.2403,
+      "step": 90
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "eval_loss": 2.270183563232422,
+      "eval_runtime": 0.413,
+      "eval_samples_per_second": 99.268,
+      "eval_steps_per_second": 14.527,
+      "step": 90
+    },
+    {
+      "epoch": 1.8762886597938144,
+      "grad_norm": 0.796205997467041,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3044,
+      "step": 91
+    },
+    {
+      "epoch": 1.8969072164948453,
+      "grad_norm": 0.7898029088973999,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.2555,
+      "step": 92
+    },
+    {
+      "epoch": 1.9175257731958761,
+      "grad_norm": 0.786343514919281,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.3107,
+      "step": 93
+    },
+    {
+      "epoch": 1.9381443298969072,
+      "grad_norm": 0.7233936786651611,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1264,
+      "step": 94
+    },
+    {
+      "epoch": 1.9587628865979383,
+      "grad_norm": 0.7573835849761963,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.1235,
+      "step": 95
+    },
+    {
+      "epoch": 1.9793814432989691,
+      "grad_norm": 0.8158411383628845,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.3631,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1228227615356445,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 3.367,
+      "step": 97
+    },
+    {
+      "epoch": 2.020618556701031,
+      "grad_norm": 0.8564669489860535,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.226,
+      "step": 98
+    },
+    {
+      "epoch": 2.0412371134020617,
+      "grad_norm": 0.7765387296676636,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.2284,
+      "step": 99
+    },
+    {
+      "epoch": 2.0412371134020617,
+      "eval_loss": 2.268873929977417,
+      "eval_runtime": 0.4154,
+      "eval_samples_per_second": 98.694,
+      "eval_steps_per_second": 14.443,
+      "step": 99
+    },
+    {
+      "epoch": 2.0618556701030926,
+      "grad_norm": 0.7744645476341248,
+      "learning_rate": 0.0,
+      "loss": 2.1928,
+      "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": 1036943221063680.0,
+  "total_flos": 1379698511708160.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null