Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6117b047293fd3cea2c17794f5409f821759e0127535c2a4550caf5d06937a14
+oid sha256:d409c531db69afa3ec5a01c4830731b710e4444053f6165295b87f411e9eb775
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d21626f1947fa0daf05391763527f63a1ff741023005b3a8aaac78a61cfe6bd7
+oid sha256:9ad61f14c6a86841fffa52a54a1000e69101ca5b5bc2cb063bf7c0a04541b9d7
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a8ab407dfd89381c2ae2ff96543437cf7ce6c83f2378c0f553cde7c133e6c8
+oid sha256:a93ac096fb899f41af78dcf1c80105d0f813944ea332310fb0aa9384a7a8e065
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6299811005592346,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.10980966325036604,
+  "best_metric": 0.6224383115768433,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.14641288433382138,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 3.716,
       "eval_steps_per_second": 1.858,
       "step": 75
+    },
+    {
+      "epoch": 0.11127379209370425,
+      "grad_norm": 0.800595760345459,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 0.6418,
+      "step": 76
+    },
+    {
+      "epoch": 0.11273792093704246,
+      "grad_norm": 0.8185175657272339,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 0.6344,
+      "step": 77
+    },
+    {
+      "epoch": 0.11420204978038068,
+      "grad_norm": 0.8200536966323853,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 0.6307,
+      "step": 78
+    },
+    {
+      "epoch": 0.11566617862371889,
+      "grad_norm": 0.8251193165779114,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 0.6243,
+      "step": 79
+    },
+    {
+      "epoch": 0.1171303074670571,
+      "grad_norm": 0.7931867241859436,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.5778,
+      "step": 80
+    },
+    {
+      "epoch": 0.11859443631039532,
+      "grad_norm": 0.8764688372612,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6503,
+      "step": 81
+    },
+    {
+      "epoch": 0.12005856515373353,
+      "grad_norm": 0.8642603158950806,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 0.6904,
+      "step": 82
+    },
+    {
+      "epoch": 0.12152269399707175,
+      "grad_norm": 0.7701883316040039,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 0.5929,
+      "step": 83
+    },
+    {
+      "epoch": 0.12298682284040996,
+      "grad_norm": 0.813798725605011,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 0.6174,
+      "step": 84
+    },
+    {
+      "epoch": 0.12445095168374817,
+      "grad_norm": 0.8495608568191528,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.6403,
+      "step": 85
+    },
+    {
+      "epoch": 0.1259150805270864,
+      "grad_norm": 0.850382924079895,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 0.5469,
+      "step": 86
+    },
+    {
+      "epoch": 0.1273792093704246,
+      "grad_norm": 0.8462463617324829,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 0.6733,
+      "step": 87
+    },
+    {
+      "epoch": 0.12884333821376281,
+      "grad_norm": 0.8402328491210938,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 0.5709,
+      "step": 88
+    },
+    {
+      "epoch": 0.13030746705710103,
+      "grad_norm": 0.9025482535362244,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 0.6922,
+      "step": 89
+    },
+    {
+      "epoch": 0.13177159590043924,
+      "grad_norm": 0.7909383177757263,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.5907,
+      "step": 90
+    },
+    {
+      "epoch": 0.13323572474377746,
+      "grad_norm": 0.7756696343421936,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 0.5443,
+      "step": 91
+    },
+    {
+      "epoch": 0.13469985358711567,
+      "grad_norm": 0.837628185749054,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 0.6027,
+      "step": 92
+    },
+    {
+      "epoch": 0.13616398243045388,
+      "grad_norm": 0.8768534660339355,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 0.6742,
+      "step": 93
+    },
+    {
+      "epoch": 0.1376281112737921,
+      "grad_norm": 0.7963073253631592,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 0.5903,
+      "step": 94
+    },
+    {
+      "epoch": 0.1390922401171303,
+      "grad_norm": 0.8839337229728699,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.6328,
+      "step": 95
+    },
+    {
+      "epoch": 0.14055636896046853,
+      "grad_norm": 0.9011049270629883,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 0.6805,
+      "step": 96
+    },
+    {
+      "epoch": 0.14202049780380674,
+      "grad_norm": 0.8585094213485718,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 0.5341,
+      "step": 97
+    },
+    {
+      "epoch": 0.14348462664714495,
+      "grad_norm": 0.8849230408668518,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 0.6161,
+      "step": 98
+    },
+    {
+      "epoch": 0.14494875549048317,
+      "grad_norm": 0.9133574366569519,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 0.6795,
+      "step": 99
+    },
+    {
+      "epoch": 0.14641288433382138,
+      "grad_norm": 0.9264809489250183,
+      "learning_rate": 0.0,
+      "loss": 0.6004,
+      "step": 100
+    },
+    {
+      "epoch": 0.14641288433382138,
+      "eval_loss": 0.6224383115768433,
+      "eval_runtime": 77.4968,
+      "eval_samples_per_second": 3.716,
+      "eval_steps_per_second": 1.858,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.01589487157248e+16,
+  "total_flos": 4.02119316209664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null