Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b85eb8f4dcc6cc20ab962f9d9513045ed6acdf4c83cbf5d74fff8219bdb0fef
+oid sha256:ee8e843e383090a0bd99b9a25a49de8a591b081cb79181107fc52c7e7eee5bf1
 size 60010048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ac365dbc242dfa1c6448b8b7f958383412616854244556f3cd2886e9b2a3ca
+oid sha256:6b14088d75129bb819104dde94281eee0aa005d589ab6daeb40473f41991a2d3
 size 120213058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8362fa668aec4ba26ddde0e55cfbebab1a8fd26f6a59aa8582b09887e3610a
+oid sha256:389c3b7139ebcc36dcd0fe790aaec22ee7c52b0a254eec7f0d187dd81a2e38b9
 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": 2.689473867416382,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.0110803324099723,
+  "best_metric": 2.6855108737945557,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.014773776546629732,
   "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": 11.607,
       "eval_steps_per_second": 5.804,
       "step": 75
+    },
+    {
+      "epoch": 0.011228070175438596,
+      "grad_norm": 0.5013121962547302,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 2.6454,
+      "step": 76
+    },
+    {
+      "epoch": 0.011375807940904894,
+      "grad_norm": 0.6422709226608276,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 2.7858,
+      "step": 77
+    },
+    {
+      "epoch": 0.01152354570637119,
+      "grad_norm": 0.5303881764411926,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 2.5976,
+      "step": 78
+    },
+    {
+      "epoch": 0.011671283471837489,
+      "grad_norm": 0.7301583290100098,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 2.5867,
+      "step": 79
+    },
+    {
+      "epoch": 0.011819021237303785,
+      "grad_norm": 0.6291911005973816,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 2.7627,
+      "step": 80
+    },
+    {
+      "epoch": 0.011966759002770083,
+      "grad_norm": 0.5394213795661926,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.6842,
+      "step": 81
+    },
+    {
+      "epoch": 0.01211449676823638,
+      "grad_norm": 0.6252685189247131,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 2.8988,
+      "step": 82
+    },
+    {
+      "epoch": 0.012262234533702678,
+      "grad_norm": 0.607553243637085,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 2.7113,
+      "step": 83
+    },
+    {
+      "epoch": 0.012409972299168974,
+      "grad_norm": 0.6846975088119507,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 2.6447,
+      "step": 84
+    },
+    {
+      "epoch": 0.012557710064635273,
+      "grad_norm": 0.6939342021942139,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 2.9223,
+      "step": 85
+    },
+    {
+      "epoch": 0.012705447830101569,
+      "grad_norm": 0.6672337651252747,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 2.8346,
+      "step": 86
+    },
+    {
+      "epoch": 0.012853185595567867,
+      "grad_norm": 0.7558186650276184,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 2.8925,
+      "step": 87
+    },
+    {
+      "epoch": 0.013000923361034164,
+      "grad_norm": 0.7285046577453613,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 2.75,
+      "step": 88
+    },
+    {
+      "epoch": 0.013148661126500462,
+      "grad_norm": 0.8400636315345764,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 2.8976,
+      "step": 89
+    },
+    {
+      "epoch": 0.013296398891966758,
+      "grad_norm": 0.7853424549102783,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 3.1096,
+      "step": 90
+    },
+    {
+      "epoch": 0.013444136657433057,
+      "grad_norm": 0.7648143172264099,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 2.9453,
+      "step": 91
+    },
+    {
+      "epoch": 0.013591874422899353,
+      "grad_norm": 0.8376665711402893,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 2.8444,
+      "step": 92
+    },
+    {
+      "epoch": 0.013739612188365651,
+      "grad_norm": 0.8066268563270569,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 2.993,
+      "step": 93
+    },
+    {
+      "epoch": 0.013887349953831948,
+      "grad_norm": 0.9552287459373474,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 2.8803,
+      "step": 94
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 0.8276549577713013,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 2.8189,
+      "step": 95
+    },
+    {
+      "epoch": 0.014182825484764542,
+      "grad_norm": 0.8577640056610107,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 3.1154,
+      "step": 96
+    },
+    {
+      "epoch": 0.01433056325023084,
+      "grad_norm": 0.8612611889839172,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 2.4841,
+      "step": 97
+    },
+    {
+      "epoch": 0.014478301015697137,
+      "grad_norm": 0.9725845456123352,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 2.7285,
+      "step": 98
+    },
+    {
+      "epoch": 0.014626038781163435,
+      "grad_norm": 1.032256841659546,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 3.125,
+      "step": 99
+    },
+    {
+      "epoch": 0.014773776546629732,
+      "grad_norm": 1.573689341545105,
+      "learning_rate": 0.0,
+      "loss": 2.9277,
+      "step": 100
+    },
+    {
+      "epoch": 0.014773776546629732,
+      "eval_loss": 2.6855108737945557,
+      "eval_runtime": 245.6241,
+      "eval_samples_per_second": 11.603,
+      "eval_steps_per_second": 5.802,
+      "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": 1.9093763653632e+16,
+  "total_flos": 2.5458351538176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null