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:dbf4f21aa3810103ddbfa201f85793fe45babffb4862816d77dae6b229b28be6
+oid sha256:dc6880761912109c4640d62032b7101d08e10e82c429b91bf9678d1d0a05e095
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bf193cbeeeba3a3e52cac3b191c88d9168f027d578bee1498233cb0ee4a317
+oid sha256:5431905bbdcdded2fd7022c32f96af9d0d24fd22111653b314bdf1830d0f1341
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b1ab07e875400565d9b78c4729ca04abaae08802b7a08c914faa48c37b5539
+oid sha256:95f8ed7abbdd53db6b07357e6235eaa549f9ca6d27959fe27220802df06eb70b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f36dbcbc06269a793d8b072894f5e0f7c087090a7ab52f4dd49aecf6761fb24
+oid sha256:e80cab9420637c493fa98aef2b010d1bdbc0f8dd893d7d6af97f25d1b0b222fe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91172359dd98debbe88ffe302079b897e6541d8b043d778e32b8ab2ca05df6dc
+oid sha256:25315eae8305e4c8cfa7fb9af5602a2072dc81ef06abec9340c5d5e39e119b79
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86d4d725a3b3341e1d9b4788847bd68bbfa21acfc83b036b889b79f213325a1
+oid sha256:bce9c92832638200bd760d3e56f755b72074229ed2cd45c26207c13afc4d34a0
 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": 1.3603107929229736,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03281378178835111,
+  "best_metric": 1.0854883193969727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06562756357670221,
   "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": 32.018,
       "eval_steps_per_second": 8.325,
       "step": 25
+    },
+    {
+      "epoch": 0.034126333059885154,
+      "grad_norm": 26.933135986328125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 18.5383,
+      "step": 26
+    },
+    {
+      "epoch": 0.035438884331419195,
+      "grad_norm": 30.999061584472656,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 18.441,
+      "step": 27
+    },
+    {
+      "epoch": 0.03675143560295324,
+      "grad_norm": 20.94573974609375,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 15.6716,
+      "step": 28
+    },
+    {
+      "epoch": 0.03806398687448728,
+      "grad_norm": 25.072898864746094,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 17.071,
+      "step": 29
+    },
+    {
+      "epoch": 0.03937653814602133,
+      "grad_norm": 23.025930404663086,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 16.3496,
+      "step": 30
+    },
+    {
+      "epoch": 0.04068908941755537,
+      "grad_norm": 26.014190673828125,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 17.2015,
+      "step": 31
+    },
+    {
+      "epoch": 0.04200164068908942,
+      "grad_norm": 20.014171600341797,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 14.6773,
+      "step": 32
+    },
+    {
+      "epoch": 0.043314191960623465,
+      "grad_norm": 23.506574630737305,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 16.2779,
+      "step": 33
+    },
+    {
+      "epoch": 0.044626743232157505,
+      "grad_norm": 25.26205825805664,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 16.0012,
+      "step": 34
+    },
+    {
+      "epoch": 0.04593929450369155,
+      "grad_norm": 29.862960815429688,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 18.4541,
+      "step": 35
+    },
+    {
+      "epoch": 0.04725184577522559,
+      "grad_norm": 28.182130813598633,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 16.4876,
+      "step": 36
+    },
+    {
+      "epoch": 0.04856439704675964,
+      "grad_norm": 37.49372863769531,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 20.8896,
+      "step": 37
+    },
+    {
+      "epoch": 0.04987694831829368,
+      "grad_norm": 28.0928897857666,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 19.2013,
+      "step": 38
+    },
+    {
+      "epoch": 0.05118949958982773,
+      "grad_norm": 28.46738624572754,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 16.2919,
+      "step": 39
+    },
+    {
+      "epoch": 0.052502050861361775,
+      "grad_norm": 26.468969345092773,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 14.6028,
+      "step": 40
+    },
+    {
+      "epoch": 0.053814602132895815,
+      "grad_norm": 25.202255249023438,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 14.2172,
+      "step": 41
+    },
+    {
+      "epoch": 0.05512715340442986,
+      "grad_norm": 26.603227615356445,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 15.9259,
+      "step": 42
+    },
+    {
+      "epoch": 0.0564397046759639,
+      "grad_norm": 24.310205459594727,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 13.7186,
+      "step": 43
+    },
+    {
+      "epoch": 0.05775225594749795,
+      "grad_norm": 22.25011444091797,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 12.9143,
+      "step": 44
+    },
+    {
+      "epoch": 0.05906480721903199,
+      "grad_norm": 23.197776794433594,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 15.8503,
+      "step": 45
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": 28.728227615356445,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 16.3657,
+      "step": 46
+    },
+    {
+      "epoch": 0.06168990976210008,
+      "grad_norm": 26.814016342163086,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 14.0175,
+      "step": 47
+    },
+    {
+      "epoch": 0.06300246103363413,
+      "grad_norm": 26.542957305908203,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 15.4604,
+      "step": 48
+    },
+    {
+      "epoch": 0.06431501230516817,
+      "grad_norm": 27.693466186523438,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 16.1903,
+      "step": 49
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 29.924348831176758,
+      "learning_rate": 1e-05,
+      "loss": 17.2409,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 1.0854883193969727,
+      "eval_runtime": 1.5526,
+      "eval_samples_per_second": 32.204,
+      "eval_steps_per_second": 8.373,
+      "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": 4.85137494048768e+16,
+  "total_flos": 9.70274988097536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null