Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4d1c16296b071ec3a2b815192e8bd14f0d42e71fac3f2d42759285f0449c37
+oid sha256:5b4827bf814d93979847eda273afed5a2d3d9cf03ebbeb82c036c174e1cdcd04
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0343bf680d08631d759f8087c4787475b73f20cfdd75e60f7216db7ffae5f4a1
+oid sha256:b14254a82d99be76962726e55a6ed3cb74b174f93620fccfee3f3f98fe3971ae
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d4bcc9b910e0171949214bd732d010c12fc93e2a03117f9c5907b98ae437d9
+oid sha256:f632e2079add108f52a2db7f62849eb0493d1479ba89bc73ef8b7f86025f79c2
 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": 0.6284409761428833,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0005227719459662916,
+  "best_metric": 0.5366438627243042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0010455438919325833,
   "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": 1.533,
       "eval_steps_per_second": 0.767,
       "step": 25
+    },
+    {
+      "epoch": 0.0005436828238049433,
+      "grad_norm": 5.4153666496276855,
+      "learning_rate": 0.0001,
+      "loss": 1.5584,
+      "step": 26
+    },
+    {
+      "epoch": 0.000564593701643595,
+      "grad_norm": 6.259101867675781,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.7488,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005855045794822466,
+      "grad_norm": 12.589021682739258,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.656,
+      "step": 28
+    },
+    {
+      "epoch": 0.0006064154573208983,
+      "grad_norm": 9.121499061584473,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.6182,
+      "step": 29
+    },
+    {
+      "epoch": 0.00062732633515955,
+      "grad_norm": 5.4948811531066895,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.559,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006482372129982016,
+      "grad_norm": 5.062642574310303,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.3702,
+      "step": 31
+    },
+    {
+      "epoch": 0.0006691480908368533,
+      "grad_norm": 5.497698783874512,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.8375,
+      "step": 32
+    },
+    {
+      "epoch": 0.000690058968675505,
+      "grad_norm": 5.75498628616333,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.0671,
+      "step": 33
+    },
+    {
+      "epoch": 0.0007109698465141566,
+      "grad_norm": 5.468430995941162,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.65,
+      "step": 34
+    },
+    {
+      "epoch": 0.0007318807243528083,
+      "grad_norm": 4.2582316398620605,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.4368,
+      "step": 35
+    },
+    {
+      "epoch": 0.00075279160219146,
+      "grad_norm": 6.38806676864624,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.3039,
+      "step": 36
+    },
+    {
+      "epoch": 0.0007737024800301117,
+      "grad_norm": 3.6482889652252197,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.5586,
+      "step": 37
+    },
+    {
+      "epoch": 0.0007946133578687634,
+      "grad_norm": 5.09956169128418,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.7368,
+      "step": 38
+    },
+    {
+      "epoch": 0.000815524235707415,
+      "grad_norm": 5.076972484588623,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.6412,
+      "step": 39
+    },
+    {
+      "epoch": 0.0008364351135460667,
+      "grad_norm": 6.101807594299316,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.5805,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008573459913847184,
+      "grad_norm": 4.0696516036987305,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.672,
+      "step": 41
+    },
+    {
+      "epoch": 0.00087825686922337,
+      "grad_norm": 3.7810137271881104,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.5105,
+      "step": 42
+    },
+    {
+      "epoch": 0.0008991677470620217,
+      "grad_norm": 7.680418491363525,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.2028,
+      "step": 43
+    },
+    {
+      "epoch": 0.0009200786249006734,
+      "grad_norm": 3.578308343887329,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.3772,
+      "step": 44
+    },
+    {
+      "epoch": 0.000940989502739325,
+      "grad_norm": 5.286886692047119,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.9604,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009619003805779767,
+      "grad_norm": 2.970261812210083,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.4176,
+      "step": 46
+    },
+    {
+      "epoch": 0.0009828112584166283,
+      "grad_norm": 4.12028694152832,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.6855,
+      "step": 47
+    },
+    {
+      "epoch": 0.00100372213625528,
+      "grad_norm": 129.763427734375,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.814,
+      "step": 48
+    },
+    {
+      "epoch": 0.0010246330140939316,
+      "grad_norm": 466.90252685546875,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 11.2703,
+      "step": 49
+    },
+    {
+      "epoch": 0.0010455438919325833,
+      "grad_norm": 478.4462585449219,
+      "learning_rate": 0.0,
+      "loss": 9.6762,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010455438919325833,
+      "eval_loss": 0.5366438627243042,
+      "eval_runtime": 13132.4903,
+      "eval_samples_per_second": 1.533,
+      "eval_steps_per_second": 0.767,
+      "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