Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7e8ea3a4ce13bdeaa6b68ca72120908ba87f364ace871d8875419404d62481
+oid sha256:8a2c5f7541c1a55d556c5e25fb9096cfb2f8ed796bb903fbd550ce275e1569b9
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4637ecfcf9bacd75171efabbe12a2d56c8da4f0e02618c2c3175acf51419631
+oid sha256:4d9d5f34d91adf5a41e1ecb87ba53505f9c0843ea8490c5839352edfee740ede
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06cfc16252f43c81f18fd0a8262d6bf6266bd4708e7bb4dbc5fbdff6bfac384
+oid sha256:58773aa41399824975a7a2195b45e8c69889f3c5ff968b7e22209b4ebc50e78a
 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": 7.495559111703187e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0003233148828306865,
+  "best_metric": 3.5156401281710714e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.000646629765661373,
   "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": 8.0,
       "eval_steps_per_second": 4.0,
       "step": 25
+    },
+    {
+      "epoch": 0.0003362474781439139,
+      "grad_norm": 0.006929947063326836,
+      "learning_rate": 0.0001,
+      "loss": 0.0001,
+      "step": 26
+    },
+    {
+      "epoch": 0.0003491800734571414,
+      "grad_norm": 0.004468102473765612,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0001,
+      "step": 27
+    },
+    {
+      "epoch": 0.00036211266877036883,
+      "grad_norm": 0.001515953685157001,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0003750452640835963,
+      "grad_norm": 0.004584501497447491,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0001,
+      "step": 29
+    },
+    {
+      "epoch": 0.00038797785939682374,
+      "grad_norm": 0.003514234907925129,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0001,
+      "step": 30
+    },
+    {
+      "epoch": 0.0004009104547100512,
+      "grad_norm": 0.003772181225940585,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.00041384305002327865,
+      "grad_norm": 0.0021776333451271057,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0001,
+      "step": 32
+    },
+    {
+      "epoch": 0.00042677564533650614,
+      "grad_norm": 0.002284293994307518,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.00043970824064973356,
+      "grad_norm": 0.002807403914630413,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.00045264083596296105,
+      "grad_norm": 0.00221768650226295,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.00046557343127618853,
+      "grad_norm": 0.00265073892660439,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.00047850602658941596,
+      "grad_norm": 0.0032683610916137695,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.0004914386219026434,
+      "grad_norm": 0.0017475264612585306,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0005043712172158709,
+      "grad_norm": 0.002534898929297924,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.0005173038125290984,
+      "grad_norm": 0.0014598339330404997,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005302364078423258,
+      "grad_norm": 0.0030341579113155603,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.0005431690031555532,
+      "grad_norm": 0.0016653327038511634,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0005561015984687808,
+      "grad_norm": 0.0010284342570230365,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0005690341937820082,
+      "grad_norm": 0.0015539777232334018,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.0005819667890952356,
+      "grad_norm": 0.0010054032318294048,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.000594899384408463,
+      "grad_norm": 0.001314558438025415,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0006078319797216906,
+      "grad_norm": 0.0010848251404240727,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.000620764575034918,
+      "grad_norm": 0.0015894053503870964,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0006336971703481454,
+      "grad_norm": 0.0016238840762525797,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.000646629765661373,
+      "grad_norm": 0.0026105751749128103,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.000646629765661373,
+      "eval_loss": 3.5156401281710714e-05,
+      "eval_runtime": 4069.9805,
+      "eval_samples_per_second": 8.0,
+      "eval_steps_per_second": 4.0,
+      "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": 6531344184115200.0,
+  "total_flos": 1.30626883682304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null