Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b68b02026392f6c63898d35bb0d8fb7819b1b21c86fa63a94b7f987ddd13204
+oid sha256:7a2bfeb56e744011e65a364b6e3ceb39537f4c15d878e3c603d9b6e0f8a260c5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7a0a65dc31a0ce005dd0554a933f8c357a6b95847aaf53ebc48a5c9bd1b810
+oid sha256:94f2f4155184b3dc3ab8fe6484da551201f53c03a853858f35187bc9a7836fd7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.0025083192588752695,
+  "epoch": 0.0033444256785003595,
   "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": 1.5045,
       "step": 75
+    },
+    {
+      "epoch": 0.0025417635156602734,
+      "grad_norm": 1.7105762958526611,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3942,
+      "step": 76
+    },
+    {
+      "epoch": 0.002575207772445277,
+      "grad_norm": 1.7119174003601074,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.2635,
+      "step": 77
+    },
+    {
+      "epoch": 0.0026086520292302805,
+      "grad_norm": 1.553362488746643,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2464,
+      "step": 78
+    },
+    {
+      "epoch": 0.002642096286015284,
+      "grad_norm": 1.757306456565857,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3831,
+      "step": 79
+    },
+    {
+      "epoch": 0.0026755405428002875,
+      "grad_norm": 1.9788403511047363,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2947,
+      "step": 80
+    },
+    {
+      "epoch": 0.0027089847995852914,
+      "grad_norm": 1.7730344533920288,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.2519,
+      "step": 81
+    },
+    {
+      "epoch": 0.0027089847995852914,
+      "eval_loss": 1.3251186609268188,
+      "eval_runtime": 2741.7754,
+      "eval_samples_per_second": 9.184,
+      "eval_steps_per_second": 1.148,
+      "step": 81
+    },
+    {
+      "epoch": 0.002742429056370295,
+      "grad_norm": 1.6482566595077515,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2612,
+      "step": 82
+    },
+    {
+      "epoch": 0.0027758733131552984,
+      "grad_norm": 1.8458375930786133,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4599,
+      "step": 83
+    },
+    {
+      "epoch": 0.002809317569940302,
+      "grad_norm": 1.6900582313537598,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.2102,
+      "step": 84
+    },
+    {
+      "epoch": 0.0028427618267253055,
+      "grad_norm": 2.316399574279785,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3149,
+      "step": 85
+    },
+    {
+      "epoch": 0.002876206083510309,
+      "grad_norm": 1.6527814865112305,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.1052,
+      "step": 86
+    },
+    {
+      "epoch": 0.002909650340295313,
+      "grad_norm": 1.7383328676223755,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.2462,
+      "step": 87
+    },
+    {
+      "epoch": 0.0029430945970803164,
+      "grad_norm": 1.8759413957595825,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.5503,
+      "step": 88
+    },
+    {
+      "epoch": 0.00297653885386532,
+      "grad_norm": 1.686247706413269,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4226,
+      "step": 89
+    },
+    {
+      "epoch": 0.0030099831106503235,
+      "grad_norm": 1.983102798461914,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.4,
+      "step": 90
+    },
+    {
+      "epoch": 0.0030099831106503235,
+      "eval_loss": 1.3215969800949097,
+      "eval_runtime": 2741.5437,
+      "eval_samples_per_second": 9.185,
+      "eval_steps_per_second": 1.148,
+      "step": 90
+    },
+    {
+      "epoch": 0.003043427367435327,
+      "grad_norm": 1.666930079460144,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4906,
+      "step": 91
+    },
+    {
+      "epoch": 0.003076871624220331,
+      "grad_norm": 1.5354820489883423,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.203,
+      "step": 92
+    },
+    {
+      "epoch": 0.0031103158810053344,
+      "grad_norm": 1.64034903049469,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3875,
+      "step": 93
+    },
+    {
+      "epoch": 0.003143760137790338,
+      "grad_norm": 2.111876964569092,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4371,
+      "step": 94
+    },
+    {
+      "epoch": 0.0031772043945753415,
+      "grad_norm": 1.6222939491271973,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4024,
+      "step": 95
+    },
+    {
+      "epoch": 0.003210648651360345,
+      "grad_norm": 1.8614100217819214,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3613,
+      "step": 96
+    },
+    {
+      "epoch": 0.003244092908145349,
+      "grad_norm": 1.6315127611160278,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.3897,
+      "step": 97
+    },
+    {
+      "epoch": 0.0032775371649303524,
+      "grad_norm": 1.4587796926498413,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1787,
+      "step": 98
+    },
+    {
+      "epoch": 0.003310981421715356,
+      "grad_norm": 1.7069193124771118,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3006,
+      "step": 99
+    },
+    {
+      "epoch": 0.003310981421715356,
+      "eval_loss": 1.3205249309539795,
+      "eval_runtime": 2741.3417,
+      "eval_samples_per_second": 9.185,
+      "eval_steps_per_second": 1.148,
+      "step": 99
+    },
+    {
+      "epoch": 0.0033444256785003595,
+      "grad_norm": 1.4645100831985474,
+      "learning_rate": 0.0,
+      "loss": 1.3523,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null