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:aab2387fdd6a8e464b27a1aa9043e815d919c49be3ee3abffcaa83a8d8bbe1aa
+oid sha256:caa0c336076aed6ec761839d4f1377929e27180502db2da45c1240c1b9b06f2c
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb50653a4354ad57c1e5a610e26fa8c56356a5db5aa5b838c290fcd2697bb6b
+oid sha256:53ea94289d88104e58e46450e4b9f6dc5c06f5133c4b7a6c210b8370bbcbb23e
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68051133b224d14b3a05a71fdf735aea34a69ab4dbb15889b8b2a3e7e2765474
+oid sha256:2c0b685af4713b728ab0078e5715a41026b78380d2a13b592850d0cb90750bb1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e7078462b285fe3a7c395fee40a5cfca1374e399178c1e02d06c1f2117c63d
+oid sha256:1c2de72519579dfbcb1c11cc4240685f7638dc6b686b130a87e89127d89216c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c74ac7f9ace065c1b611a206d33b5c8169e48671262216d25d007e2fce6e13
+oid sha256:6a32acc284c918884645b6f88831b507926064147740f2a2ea25c6a0bf1b12e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:401958eefff1f69ab390c2e9495e4c1267a3489a25dc6f86819fb797b3889bbd
+oid sha256:a0b8730a7a2b117c1714f8a4785fa9557d28e88e10df3edf6a0233baab0b5be8
 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": 9.314793586730957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08210180623973727,
+  "best_metric": 9.062572479248047,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16420361247947454,
   "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": 90.714,
       "eval_steps_per_second": 23.586,
       "step": 25
+    },
+    {
+      "epoch": 0.08538587848932677,
+      "grad_norm": 2.5130350589752197,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 9.1092,
+      "step": 26
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 2.114590644836426,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 9.197,
+      "step": 27
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 2.1008377075195312,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.2731,
+      "step": 28
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 2.0370545387268066,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 9.4849,
+      "step": 29
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 2.0477921962738037,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 9.3548,
+      "step": 30
+    },
+    {
+      "epoch": 0.10180623973727422,
+      "grad_norm": 2.033531665802002,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 9.2227,
+      "step": 31
+    },
+    {
+      "epoch": 0.10509031198686371,
+      "grad_norm": 2.0999460220336914,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.204,
+      "step": 32
+    },
+    {
+      "epoch": 0.10837438423645321,
+      "grad_norm": 2.2290875911712646,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.1827,
+      "step": 33
+    },
+    {
+      "epoch": 0.1116584564860427,
+      "grad_norm": 2.2694082260131836,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.1508,
+      "step": 34
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 2.420377731323242,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 8.8894,
+      "step": 35
+    },
+    {
+      "epoch": 0.11822660098522167,
+      "grad_norm": 2.9713902473449707,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.0052,
+      "step": 36
+    },
+    {
+      "epoch": 0.12151067323481117,
+      "grad_norm": 3.350985050201416,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 8.9528,
+      "step": 37
+    },
+    {
+      "epoch": 0.12479474548440066,
+      "grad_norm": 2.2344725131988525,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 8.8451,
+      "step": 38
+    },
+    {
+      "epoch": 0.12807881773399016,
+      "grad_norm": 2.1066842079162598,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 9.112,
+      "step": 39
+    },
+    {
+      "epoch": 0.13136288998357964,
+      "grad_norm": 1.8320448398590088,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 9.1202,
+      "step": 40
+    },
+    {
+      "epoch": 0.13464696223316913,
+      "grad_norm": 1.908353567123413,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 9.2423,
+      "step": 41
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 1.8999229669570923,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.167,
+      "step": 42
+    },
+    {
+      "epoch": 0.1412151067323481,
+      "grad_norm": 1.8419102430343628,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.1372,
+      "step": 43
+    },
+    {
+      "epoch": 0.1444991789819376,
+      "grad_norm": 1.9281691312789917,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.1061,
+      "step": 44
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 1.9718252420425415,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.0683,
+      "step": 45
+    },
+    {
+      "epoch": 0.1510673234811166,
+      "grad_norm": 2.044898509979248,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 8.9936,
+      "step": 46
+    },
+    {
+      "epoch": 0.15435139573070608,
+      "grad_norm": 2.419887065887451,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 8.8617,
+      "step": 47
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "grad_norm": 2.657135009765625,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 8.9259,
+      "step": 48
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 3.4543638229370117,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 9.0371,
+      "step": 49
+    },
+    {
+      "epoch": 0.16420361247947454,
+      "grad_norm": 4.0607452392578125,
+      "learning_rate": 1e-05,
+      "loss": 8.7464,
+      "step": 50
+    },
+    {
+      "epoch": 0.16420361247947454,
+      "eval_loss": 9.062572479248047,
+      "eval_runtime": 0.5413,
+      "eval_samples_per_second": 92.373,
+      "eval_steps_per_second": 24.017,
+      "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": 116006898892800.0,
+  "total_flos": 232013797785600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null