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:b0d08bf1932be66c0a659065a94bc187539126ae1939ba122e256a678a9293db
+oid sha256:80918c08105035ea88d6cb0c34991fddff00de8df45e725f72e1d5422b3c6382
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da889ef761f0418e6974f38d942f1bb999f7aabd73139c2c818cc7331087694b
+oid sha256:ae89df48b96cd8fe5faa942a4b2d932d62a69c1273e4ab247b4e890dd13bfc24
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248712a5decb3b47f14c817410f68ae3dcb6d1a62f88ddf27a26784310c3c468
+oid sha256:0c1d96cde2528cb65764bc1cddb5ce2357e25ee30c1a604a32145b8b5593048b
 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": 3.6264519691467285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01853911753800519,
+  "best_metric": 3.311112642288208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03707823507601038,
   "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": 3.182,
       "eval_steps_per_second": 1.591,
       "step": 25
+    },
+    {
+      "epoch": 0.0192806822395254,
+      "grad_norm": 5.769565105438232,
+      "learning_rate": 0.0001,
+      "loss": 3.8071,
+      "step": 26
+    },
+    {
+      "epoch": 0.020022246941045607,
+      "grad_norm": 5.704461574554443,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 3.2958,
+      "step": 27
+    },
+    {
+      "epoch": 0.020763811642565813,
+      "grad_norm": 5.851852893829346,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 3.9264,
+      "step": 28
+    },
+    {
+      "epoch": 0.021505376344086023,
+      "grad_norm": 5.5478715896606445,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 4.3509,
+      "step": 29
+    },
+    {
+      "epoch": 0.02224694104560623,
+      "grad_norm": 6.7844367027282715,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.4878,
+      "step": 30
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 5.998141765594482,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 4.4051,
+      "step": 31
+    },
+    {
+      "epoch": 0.023730070448646643,
+      "grad_norm": 5.847940444946289,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.4056,
+      "step": 32
+    },
+    {
+      "epoch": 0.024471635150166853,
+      "grad_norm": 5.002828598022461,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 3.02,
+      "step": 33
+    },
+    {
+      "epoch": 0.02521319985168706,
+      "grad_norm": 4.438299179077148,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.562,
+      "step": 34
+    },
+    {
+      "epoch": 0.025954764553207266,
+      "grad_norm": 5.450693607330322,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.7356,
+      "step": 35
+    },
+    {
+      "epoch": 0.026696329254727477,
+      "grad_norm": 4.7872314453125,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 3.2078,
+      "step": 36
+    },
+    {
+      "epoch": 0.027437893956247683,
+      "grad_norm": 6.174244403839111,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.46,
+      "step": 37
+    },
+    {
+      "epoch": 0.02817945865776789,
+      "grad_norm": 5.326364040374756,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.9328,
+      "step": 38
+    },
+    {
+      "epoch": 0.028921023359288096,
+      "grad_norm": 5.555682182312012,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 3.7987,
+      "step": 39
+    },
+    {
+      "epoch": 0.029662588060808306,
+      "grad_norm": 6.068312168121338,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.3475,
+      "step": 40
+    },
+    {
+      "epoch": 0.030404152762328513,
+      "grad_norm": 5.438655376434326,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.974,
+      "step": 41
+    },
+    {
+      "epoch": 0.03114571746384872,
+      "grad_norm": 5.173154830932617,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 3.0526,
+      "step": 42
+    },
+    {
+      "epoch": 0.03188728216536893,
+      "grad_norm": 5.596974849700928,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 3.4781,
+      "step": 43
+    },
+    {
+      "epoch": 0.03262884686688913,
+      "grad_norm": 4.907413959503174,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.716,
+      "step": 44
+    },
+    {
+      "epoch": 0.03337041156840934,
+      "grad_norm": 6.975232124328613,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.4974,
+      "step": 45
+    },
+    {
+      "epoch": 0.03411197626992955,
+      "grad_norm": 6.564231872558594,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 3.3458,
+      "step": 46
+    },
+    {
+      "epoch": 0.034853540971449756,
+      "grad_norm": 9.936782836914062,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 3.1931,
+      "step": 47
+    },
+    {
+      "epoch": 0.035595105672969966,
+      "grad_norm": 8.084567070007324,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.0752,
+      "step": 48
+    },
+    {
+      "epoch": 0.036336670374490176,
+      "grad_norm": 6.863251686096191,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.0839,
+      "step": 49
+    },
+    {
+      "epoch": 0.03707823507601038,
+      "grad_norm": 7.218696117401123,
+      "learning_rate": 0.0,
+      "loss": 4.2556,
+      "step": 50
+    },
+    {
+      "epoch": 0.03707823507601038,
+      "eval_loss": 3.311112642288208,
+      "eval_runtime": 178.6967,
+      "eval_samples_per_second": 3.179,
+      "eval_steps_per_second": 1.589,
+      "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": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null