Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cd4e2ff3597c9a84cd86fdff71310e28e87fbb1fa93dfe8c776e3dfdaea617
+oid sha256:0c6b5d49ebff26d0db6c55d49f7b2c58b9eecc36f0c55493e2365ea0b09b632b
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9744b7b47421f6dc97dffa9348c620c377115d1cf0bba27c50a6381017f19c1
+oid sha256:8b24d1acca4e040d04c2f1a8da3463cc56085b66569a24467ef97415ab7f022a
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bee8eba7a626a13e66d9d401b6bdd9fc3763ec9f692ff081001c59590105542
+oid sha256:b56f761c5296edcd40120139ab9f60be88eda88cf340171c8ca9c3135a0ebb92
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043af8f3a081fc868ec36ec0abb825fc05ab23a289091b7c5dfe5395fd1e827b
+oid sha256:911f13b6bf46f66ea718fe9b047dae3c3853f69ae059735c65a2eff2cb1a866e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f24bc50b5e8ff1f8aecfc3c3666444b9ef4ecf3c5f9468e95c0217198f2b9b42
+oid sha256:6248291c0e8bb407479a75b243e2490caef1c2fb93f5db8fddef40f2fec069b2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56fd9e7ea0bd4f7156b7b7e6317d15243dd9beb7c6ac6f08b04df6825a3dcca
+oid sha256:49bfdf9ada65b901b7355a35ebb5a9605a21bd59240062daa4b467b8f09e8e04
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.707274436950684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2679169457468185,
+  "best_metric": 11.683328628540039,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.535833891493637,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 437.25,
       "eval_steps_per_second": 113.685,
       "step": 25
+    },
+    {
+      "epoch": 0.27863362357669125,
+      "grad_norm": 0.6378116011619568,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7108,
+      "step": 26
+    },
+    {
+      "epoch": 0.289350301406564,
+      "grad_norm": 0.5049313902854919,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7114,
+      "step": 27
+    },
+    {
+      "epoch": 0.3000669792364367,
+      "grad_norm": 0.48692914843559265,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7181,
+      "step": 28
+    },
+    {
+      "epoch": 0.31078365706630945,
+      "grad_norm": 0.4770529270172119,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.705,
+      "step": 29
+    },
+    {
+      "epoch": 0.3215003348961822,
+      "grad_norm": 0.5465254187583923,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.6971,
+      "step": 30
+    },
+    {
+      "epoch": 0.3322170127260549,
+      "grad_norm": 0.5846957564353943,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.688,
+      "step": 31
+    },
+    {
+      "epoch": 0.34293369055592765,
+      "grad_norm": 0.6031647324562073,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.6896,
+      "step": 32
+    },
+    {
+      "epoch": 0.3536503683858004,
+      "grad_norm": 0.593400776386261,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.6974,
+      "step": 33
+    },
+    {
+      "epoch": 0.3643670462156731,
+      "grad_norm": 0.653511106967926,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.6989,
+      "step": 34
+    },
+    {
+      "epoch": 0.3750837240455459,
+      "grad_norm": 0.6714555621147156,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.6787,
+      "step": 35
+    },
+    {
+      "epoch": 0.38580040187541864,
+      "grad_norm": 0.6866130828857422,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.6906,
+      "step": 36
+    },
+    {
+      "epoch": 0.3965170797052914,
+      "grad_norm": 0.7554149031639099,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.6774,
+      "step": 37
+    },
+    {
+      "epoch": 0.4072337575351641,
+      "grad_norm": 0.6247978210449219,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.6914,
+      "step": 38
+    },
+    {
+      "epoch": 0.41795043536503684,
+      "grad_norm": 0.6444849967956543,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.6864,
+      "step": 39
+    },
+    {
+      "epoch": 0.4286671131949096,
+      "grad_norm": 0.5599631667137146,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7007,
+      "step": 40
+    },
+    {
+      "epoch": 0.4393837910247823,
+      "grad_norm": 0.5610001683235168,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7048,
+      "step": 41
+    },
+    {
+      "epoch": 0.45010046885465504,
+      "grad_norm": 0.6208688616752625,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.6906,
+      "step": 42
+    },
+    {
+      "epoch": 0.4608171466845278,
+      "grad_norm": 0.589806854724884,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.6843,
+      "step": 43
+    },
+    {
+      "epoch": 0.4715338245144005,
+      "grad_norm": 0.6590961217880249,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.6723,
+      "step": 44
+    },
+    {
+      "epoch": 0.4822505023442733,
+      "grad_norm": 0.6476118564605713,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.686,
+      "step": 45
+    },
+    {
+      "epoch": 0.49296718017414604,
+      "grad_norm": 0.7357048988342285,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.6814,
+      "step": 46
+    },
+    {
+      "epoch": 0.5036838580040187,
+      "grad_norm": 0.6685858964920044,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.684,
+      "step": 47
+    },
+    {
+      "epoch": 0.5144005358338914,
+      "grad_norm": 0.7207851409912109,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.677,
+      "step": 48
+    },
+    {
+      "epoch": 0.5251172136637642,
+      "grad_norm": 0.7620865702629089,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.6855,
+      "step": 49
+    },
+    {
+      "epoch": 0.535833891493637,
+      "grad_norm": 0.8084555268287659,
+      "learning_rate": 1e-05,
+      "loss": 11.6791,
+      "step": 50
+    },
+    {
+      "epoch": 0.535833891493637,
+      "eval_loss": 11.683328628540039,
+      "eval_runtime": 0.1143,
+      "eval_samples_per_second": 437.419,
+      "eval_steps_per_second": 113.729,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null