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:af8a1dcb2716215ec93a51f1d21e1ddf76faf04b63e63fdfd769565cfe2a280d
+oid sha256:51d5d427b82dc47a47f7fa034046072361fd6449cdcc8e579c525b342ed8052e
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb6e205bb8ffd714dfe6f0634aeb22042cfadac22ba187fa8a4fb7fec452db1
+oid sha256:582d11501e78d1d32c24f0aab8d86c4d311da65b46bca2a17ba6f2b1ac65d8be
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d52f5e083c5c6a97fb5a4977705e08c8639d5f8411b35ea64fb396a47c3c5ca
+oid sha256:6f462ed8965a274f70ede3ac65fe41c6204e13558c89cd7209bbda1b5149acd1
 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": 3.2420172691345215,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003833767827020396,
+  "best_metric": 3.1727869510650635,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007667535654040792,
   "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": 4.876,
       "eval_steps_per_second": 2.438,
       "step": 25
+    },
+    {
+      "epoch": 0.003987118540101212,
+      "grad_norm": 2.5246529579162598,
+      "learning_rate": 0.0001,
+      "loss": 3.4743,
+      "step": 26
+    },
+    {
+      "epoch": 0.004140469253182027,
+      "grad_norm": 2.2808432579040527,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.5311,
+      "step": 27
+    },
+    {
+      "epoch": 0.004293819966262843,
+      "grad_norm": 3.2546892166137695,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.9244,
+      "step": 28
+    },
+    {
+      "epoch": 0.004447170679343659,
+      "grad_norm": 3.6420068740844727,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 3.8467,
+      "step": 29
+    },
+    {
+      "epoch": 0.004600521392424475,
+      "grad_norm": 3.000694990158081,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.6467,
+      "step": 30
+    },
+    {
+      "epoch": 0.00475387210550529,
+      "grad_norm": 3.8289284706115723,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 3.0787,
+      "step": 31
+    },
+    {
+      "epoch": 0.004907222818586106,
+      "grad_norm": 2.4866862297058105,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.0888,
+      "step": 32
+    },
+    {
+      "epoch": 0.005060573531666922,
+      "grad_norm": 4.410055160522461,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.6185,
+      "step": 33
+    },
+    {
+      "epoch": 0.005213924244747738,
+      "grad_norm": 3.6001877784729004,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.1256,
+      "step": 34
+    },
+    {
+      "epoch": 0.005367274957828554,
+      "grad_norm": 2.8873212337493896,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.9412,
+      "step": 35
+    },
+    {
+      "epoch": 0.00552062567090937,
+      "grad_norm": 2.546860456466675,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.6947,
+      "step": 36
+    },
+    {
+      "epoch": 0.005673976383990186,
+      "grad_norm": 3.3024210929870605,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.747,
+      "step": 37
+    },
+    {
+      "epoch": 0.005827327097071002,
+      "grad_norm": 2.899991512298584,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.6494,
+      "step": 38
+    },
+    {
+      "epoch": 0.005980677810151817,
+      "grad_norm": 2.936243772506714,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.5826,
+      "step": 39
+    },
+    {
+      "epoch": 0.006134028523232633,
+      "grad_norm": 4.207485675811768,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.1752,
+      "step": 40
+    },
+    {
+      "epoch": 0.006287379236313449,
+      "grad_norm": 3.71284556388855,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 3.7207,
+      "step": 41
+    },
+    {
+      "epoch": 0.006440729949394265,
+      "grad_norm": 4.887681007385254,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 3.5925,
+      "step": 42
+    },
+    {
+      "epoch": 0.00659408066247508,
+      "grad_norm": 4.211059093475342,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.6441,
+      "step": 43
+    },
+    {
+      "epoch": 0.006747431375555896,
+      "grad_norm": 7.138034820556641,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.9675,
+      "step": 44
+    },
+    {
+      "epoch": 0.006900782088636712,
+      "grad_norm": 5.270826816558838,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.8757,
+      "step": 45
+    },
+    {
+      "epoch": 0.007054132801717528,
+      "grad_norm": 4.441748142242432,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.7692,
+      "step": 46
+    },
+    {
+      "epoch": 0.0072074835147983435,
+      "grad_norm": 4.473811149597168,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.4088,
+      "step": 47
+    },
+    {
+      "epoch": 0.007360834227879159,
+      "grad_norm": 4.914578914642334,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.8022,
+      "step": 48
+    },
+    {
+      "epoch": 0.007514184940959976,
+      "grad_norm": 6.2961812019348145,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.0815,
+      "step": 49
+    },
+    {
+      "epoch": 0.007667535654040792,
+      "grad_norm": 7.806097030639648,
+      "learning_rate": 0.0,
+      "loss": 2.7287,
+      "step": 50
+    },
+    {
+      "epoch": 0.007667535654040792,
+      "eval_loss": 3.1727869510650635,
+      "eval_runtime": 563.243,
+      "eval_samples_per_second": 4.875,
+      "eval_steps_per_second": 2.438,
+      "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": 1.37856974585856e+16,
+  "total_flos": 2.75713949171712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null