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:afafcedac5219c41c83af7fbb126bd862c8283c9e0b8bc8692fce52d58fc2c18
+oid sha256:52e00c49b5e72b4784d127e740485cb5bc9e145c054e41adeff1a6cee49d3875
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a867722bc3c2745bec589dbfffffdf4f3ace188bb7b33e8123708a31f9adab
+oid sha256:d2f55197f88a6ff26f8186efd850021bc9ba0fab4629b4de10275a65b38f8f6a
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c85a3e86945eca350bbcbb9c4ce48839fd38d8fe6ae786859fedb9124a918d
+oid sha256:1db625fad6b59f17c03a681d56cda5f5ee78a789cd8f8542d1df29d9a434ece8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e2f62dce90a0c205733cf54d908b440422ef1e10f92fe2dc0c15b42bb9e944
+oid sha256:4ca2bc8e2e3e864b1e3ce6bc6bcacac42e7ba9d319456c6ad573711be889b275
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c66652c40512bddf4643ad798ee94ed6d3813a022a8b66e3ebe6d500c229df
+oid sha256:a482ed1a0e3d932146690d6f7ec0d0e3f4cc3187321300dbb374d17f2ff45d15
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d05c15f64c070fe37e3d0262d1c68030668856eb3d67fdb1783b4519fd3734
+oid sha256:e18e56768fb61d255e3cce7db4ad4005a234543e7c67d6d81f8c09c5d3746d69
 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": 11.909122467041016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0217758179541619,
+  "best_metric": 11.8941650390625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0435516359083238,
   "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": 122.78,
       "eval_steps_per_second": 31.923,
       "step": 25
+    },
+    {
+      "epoch": 0.02264685067232838,
+      "grad_norm": 0.3583414852619171,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9017,
+      "step": 26
+    },
+    {
+      "epoch": 0.023517883390494855,
+      "grad_norm": 0.3218832314014435,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.903,
+      "step": 27
+    },
+    {
+      "epoch": 0.02438891610866133,
+      "grad_norm": 0.33500561118125916,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9,
+      "step": 28
+    },
+    {
+      "epoch": 0.02525994882682781,
+      "grad_norm": 0.3144049048423767,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.904,
+      "step": 29
+    },
+    {
+      "epoch": 0.026130981544994283,
+      "grad_norm": 0.33048567175865173,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9027,
+      "step": 30
+    },
+    {
+      "epoch": 0.02700201426316076,
+      "grad_norm": 0.3038746118545532,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.8999,
+      "step": 31
+    },
+    {
+      "epoch": 0.027873046981327237,
+      "grad_norm": 0.2892683744430542,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9014,
+      "step": 32
+    },
+    {
+      "epoch": 0.02874407969949371,
+      "grad_norm": 0.32294026017189026,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.8961,
+      "step": 33
+    },
+    {
+      "epoch": 0.029615112417660187,
+      "grad_norm": 0.3208608627319336,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.8962,
+      "step": 34
+    },
+    {
+      "epoch": 0.030486145135826665,
+      "grad_norm": 0.2977166175842285,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.896,
+      "step": 35
+    },
+    {
+      "epoch": 0.03135717785399314,
+      "grad_norm": 0.305480033159256,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.8966,
+      "step": 36
+    },
+    {
+      "epoch": 0.03222821057215962,
+      "grad_norm": 0.3342093527317047,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.893,
+      "step": 37
+    },
+    {
+      "epoch": 0.03309924329032609,
+      "grad_norm": 0.34257322549819946,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.8929,
+      "step": 38
+    },
+    {
+      "epoch": 0.03397027600849257,
+      "grad_norm": 0.3188397288322449,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.8923,
+      "step": 39
+    },
+    {
+      "epoch": 0.03484130872665905,
+      "grad_norm": 0.3122134804725647,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.8898,
+      "step": 40
+    },
+    {
+      "epoch": 0.03571234144482552,
+      "grad_norm": 0.3161143362522125,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.8928,
+      "step": 41
+    },
+    {
+      "epoch": 0.036583374162992,
+      "grad_norm": 0.3282131552696228,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.8886,
+      "step": 42
+    },
+    {
+      "epoch": 0.037454406881158475,
+      "grad_norm": 0.3042701780796051,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.8902,
+      "step": 43
+    },
+    {
+      "epoch": 0.03832543959932495,
+      "grad_norm": 0.27346542477607727,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.893,
+      "step": 44
+    },
+    {
+      "epoch": 0.039196472317491425,
+      "grad_norm": 0.29086118936538696,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.8937,
+      "step": 45
+    },
+    {
+      "epoch": 0.040067505035657904,
+      "grad_norm": 0.31170573830604553,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.8936,
+      "step": 46
+    },
+    {
+      "epoch": 0.040938537753824375,
+      "grad_norm": 0.313886433839798,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.8857,
+      "step": 47
+    },
+    {
+      "epoch": 0.04180957047199085,
+      "grad_norm": 0.29732245206832886,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.888,
+      "step": 48
+    },
+    {
+      "epoch": 0.04268060319015733,
+      "grad_norm": 0.30892470479011536,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.8872,
+      "step": 49
+    },
+    {
+      "epoch": 0.0435516359083238,
+      "grad_norm": 0.3599565923213959,
+      "learning_rate": 1e-05,
+      "loss": 11.8921,
+      "step": 50
+    },
+    {
+      "epoch": 0.0435516359083238,
+      "eval_loss": 11.8941650390625,
+      "eval_runtime": 0.4156,
+      "eval_samples_per_second": 120.304,
+      "eval_steps_per_second": 31.279,
+      "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": 209520242458624.0,
+  "total_flos": 419171026862080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null