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:f9e3cd2d403245bc31b08e0d6ccbfe0f93cacafdb0c7f0f9a7c42f833b4f1170
+oid sha256:7b05c2f146a9e732d136a9cf93a954cdb7ab9b27b717ca48f3ff486d4b4fa004
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c408f52c91c8842973c56f97ee90c1e9a706163b6dc66960d89b0cf9283d6408
+oid sha256:b5e30507b63d4f0e650e23ef325cf918eff2276c920ecc6994ccb136bafcec72
 size 551070514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6a2d08a9fe7b381c65df837b4d044c5d317b4626debdfe82da9ab57aabd1b6
+oid sha256:1d6a4fa850709cbe44f764a89349eb1391cfbbe77c4d54bb3fe7ddf9adc8e755
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8502498269081116,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.002375127663111892,
+  "best_metric": 0.7584860920906067,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.004750255326223784,
   "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": 1.587,
       "eval_steps_per_second": 0.794,
       "step": 25
+    },
+    {
+      "epoch": 0.002470132769636368,
+      "grad_norm": 1.0211113691329956,
+      "learning_rate": 0.0001,
+      "loss": 0.8823,
+      "step": 26
+    },
+    {
+      "epoch": 0.002565137876160844,
+      "grad_norm": 1.151694893836975,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.1089,
+      "step": 27
+    },
+    {
+      "epoch": 0.0026601429826853193,
+      "grad_norm": 0.9132530093193054,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.84,
+      "step": 28
+    },
+    {
+      "epoch": 0.002755148089209795,
+      "grad_norm": 1.1803406476974487,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.0719,
+      "step": 29
+    },
+    {
+      "epoch": 0.0028501531957342706,
+      "grad_norm": 0.8904761672019958,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.8608,
+      "step": 30
+    },
+    {
+      "epoch": 0.0029451583022587465,
+      "grad_norm": 1.3807132244110107,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.962,
+      "step": 31
+    },
+    {
+      "epoch": 0.003040163408783222,
+      "grad_norm": 1.1357879638671875,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.7063,
+      "step": 32
+    },
+    {
+      "epoch": 0.003135168515307698,
+      "grad_norm": 1.1685482263565063,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.9068,
+      "step": 33
+    },
+    {
+      "epoch": 0.0032301736218321737,
+      "grad_norm": 1.0558769702911377,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4999,
+      "step": 34
+    },
+    {
+      "epoch": 0.003325178728356649,
+      "grad_norm": 1.7948107719421387,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.8978,
+      "step": 35
+    },
+    {
+      "epoch": 0.003420183834881125,
+      "grad_norm": 1.4935179948806763,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.7973,
+      "step": 36
+    },
+    {
+      "epoch": 0.0035151889414056004,
+      "grad_norm": 1.5740504264831543,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.9597,
+      "step": 37
+    },
+    {
+      "epoch": 0.0036101940479300763,
+      "grad_norm": 1.39761483669281,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.6634,
+      "step": 38
+    },
+    {
+      "epoch": 0.0037051991544545517,
+      "grad_norm": 1.5975027084350586,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.8412,
+      "step": 39
+    },
+    {
+      "epoch": 0.0038002042609790276,
+      "grad_norm": 2.129999876022339,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.7558,
+      "step": 40
+    },
+    {
+      "epoch": 0.0038952093675035035,
+      "grad_norm": 1.4718657732009888,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.5216,
+      "step": 41
+    },
+    {
+      "epoch": 0.003990214474027979,
+      "grad_norm": 1.4572190046310425,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6439,
+      "step": 42
+    },
+    {
+      "epoch": 0.004085219580552454,
+      "grad_norm": 1.629568099975586,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.9076,
+      "step": 43
+    },
+    {
+      "epoch": 0.004180224687076931,
+      "grad_norm": 2.349888563156128,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.919,
+      "step": 44
+    },
+    {
+      "epoch": 0.004275229793601406,
+      "grad_norm": 2.274378776550293,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7348,
+      "step": 45
+    },
+    {
+      "epoch": 0.004370234900125882,
+      "grad_norm": 2.520500898361206,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.0448,
+      "step": 46
+    },
+    {
+      "epoch": 0.004465240006650358,
+      "grad_norm": 2.631470203399658,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.8736,
+      "step": 47
+    },
+    {
+      "epoch": 0.004560245113174833,
+      "grad_norm": 2.3336336612701416,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.0823,
+      "step": 48
+    },
+    {
+      "epoch": 0.004655250219699309,
+      "grad_norm": 4.0723981857299805,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.0683,
+      "step": 49
+    },
+    {
+      "epoch": 0.004750255326223784,
+      "grad_norm": 6.658047199249268,
+      "learning_rate": 0.0,
+      "loss": 1.7212,
+      "step": 50
+    },
+    {
+      "epoch": 0.004750255326223784,
+      "eval_loss": 0.7584860920906067,
+      "eval_runtime": 2792.4222,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.794,
+      "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": 6.980017310190797e+16,
+  "total_flos": 1.3890925538102477e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null