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:c064d4db9d089e2c6f2ec37f2d8b30d8488206bb2f92e62e4f18f6b762197cdf
+oid sha256:30b7bfacaf313366bb02097f3b5bade516ee53af089c36263ada001d89d6dab4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d31dc239827789c9910138bdaf1a211cd2b52995591c608ecf024b85a15a76
+oid sha256:e48a27c2057a96994946590e90d7089e63dcde2b707cc13b5ce3e5cc425580a3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433e9a3862d737a26c021fdd0fa00ebfd4b90549bcab46647e2ad8f93fc72960
+oid sha256:0b11a8448fed25484d489c9e14122b096516ae2e86d0a4a8e186677cb9cacb2a
 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": 5.01399564743042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007040766035344645,
+  "best_metric": 4.958001136779785,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01408153207068929,
   "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": 3.703,
       "eval_steps_per_second": 1.853,
       "step": 25
+    },
+    {
+      "epoch": 0.0073223966767584315,
+      "grad_norm": 22.809677124023438,
+      "learning_rate": 0.0001,
+      "loss": 19.6608,
+      "step": 26
+    },
+    {
+      "epoch": 0.007604027318172217,
+      "grad_norm": 26.614421844482422,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 20.0502,
+      "step": 27
+    },
+    {
+      "epoch": 0.007885657959586003,
+      "grad_norm": 22.92184066772461,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 20.2952,
+      "step": 28
+    },
+    {
+      "epoch": 0.008167288600999788,
+      "grad_norm": 25.129104614257812,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 20.0264,
+      "step": 29
+    },
+    {
+      "epoch": 0.008448919242413575,
+      "grad_norm": 25.90605354309082,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 20.6772,
+      "step": 30
+    },
+    {
+      "epoch": 0.008730549883827361,
+      "grad_norm": 23.097158432006836,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 19.3772,
+      "step": 31
+    },
+    {
+      "epoch": 0.009012180525241146,
+      "grad_norm": 19.780305862426758,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 19.4421,
+      "step": 32
+    },
+    {
+      "epoch": 0.009293811166654932,
+      "grad_norm": 23.319713592529297,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 19.4254,
+      "step": 33
+    },
+    {
+      "epoch": 0.009575441808068718,
+      "grad_norm": 25.547657012939453,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 20.5563,
+      "step": 34
+    },
+    {
+      "epoch": 0.009857072449482503,
+      "grad_norm": 22.37945556640625,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 21.7697,
+      "step": 35
+    },
+    {
+      "epoch": 0.01013870309089629,
+      "grad_norm": 25.38311195373535,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 21.9471,
+      "step": 36
+    },
+    {
+      "epoch": 0.010420333732310076,
+      "grad_norm": 20.930171966552734,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 21.8591,
+      "step": 37
+    },
+    {
+      "epoch": 0.01070196437372386,
+      "grad_norm": 30.409629821777344,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 23.305,
+      "step": 38
+    },
+    {
+      "epoch": 0.010983595015137647,
+      "grad_norm": 19.549955368041992,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 22.0507,
+      "step": 39
+    },
+    {
+      "epoch": 0.011265225656551433,
+      "grad_norm": 25.194637298583984,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 22.3263,
+      "step": 40
+    },
+    {
+      "epoch": 0.011546856297965218,
+      "grad_norm": 24.036544799804688,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 22.2299,
+      "step": 41
+    },
+    {
+      "epoch": 0.011828486939379004,
+      "grad_norm": 24.677072525024414,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 22.3443,
+      "step": 42
+    },
+    {
+      "epoch": 0.01211011758079279,
+      "grad_norm": 23.8966121673584,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 22.0331,
+      "step": 43
+    },
+    {
+      "epoch": 0.012391748222206575,
+      "grad_norm": 21.31231117248535,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 21.334,
+      "step": 44
+    },
+    {
+      "epoch": 0.012673378863620362,
+      "grad_norm": 22.37716293334961,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 22.0767,
+      "step": 45
+    },
+    {
+      "epoch": 0.012955009505034148,
+      "grad_norm": 22.888154983520508,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 22.6545,
+      "step": 46
+    },
+    {
+      "epoch": 0.013236640146447933,
+      "grad_norm": 21.42641830444336,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 24.4605,
+      "step": 47
+    },
+    {
+      "epoch": 0.01351827078786172,
+      "grad_norm": 22.642194747924805,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 24.1472,
+      "step": 48
+    },
+    {
+      "epoch": 0.013799901429275506,
+      "grad_norm": 31.944076538085938,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 23.9481,
+      "step": 49
+    },
+    {
+      "epoch": 0.01408153207068929,
+      "grad_norm": 50.73974609375,
+      "learning_rate": 0.0,
+      "loss": 26.5203,
+      "step": 50
+    },
+    {
+      "epoch": 0.01408153207068929,
+      "eval_loss": 4.958001136779785,
+      "eval_runtime": 403.6789,
+      "eval_samples_per_second": 3.703,
+      "eval_steps_per_second": 1.853,
+      "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": 3.51564749340672e+16,
+  "total_flos": 7.03129498681344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null