Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e51a826e3a348d91f2e3c6bc1bfbf0351759a41302f488aac45fd366ce0b992
+oid sha256:71fcd97ffc0fe4dbdb7535f7932d351929c186f43b6ebc6f7286917b67b1cf22
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90075753040be139af295a3b0e1222565ad7f4c748771324e789d9537651dd17
+oid sha256:8d156fbf1e9c5e860ad659fbca36cbf61b0176ef1ca77bec4f3e63a3d7dc883d
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d13bc736ce695399d5bf3a3eccb31ba576fb61419a871868f8cdd664e27a54
+oid sha256:576b86e2b74badf1a00f891c3758b8e51ef72173de72323b5083decd7fb5abe9
 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": 1.0661097764968872,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015503875968992248,
+  "best_metric": 0.9526658654212952,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.031007751937984496,
   "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": 13.793,
       "eval_steps_per_second": 6.907,
       "step": 25
+    },
+    {
+      "epoch": 0.01612403100775194,
+      "grad_norm": 8.87413501739502,
+      "learning_rate": 0.0001,
+      "loss": 0.3182,
+      "step": 26
+    },
+    {
+      "epoch": 0.01674418604651163,
+      "grad_norm": 42.767024993896484,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.2834,
+      "step": 27
+    },
+    {
+      "epoch": 0.017364341085271316,
+      "grad_norm": 19.86754608154297,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.8135,
+      "step": 28
+    },
+    {
+      "epoch": 0.017984496124031007,
+      "grad_norm": 12.222258567810059,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.0754,
+      "step": 29
+    },
+    {
+      "epoch": 0.018604651162790697,
+      "grad_norm": 8.531135559082031,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.4594,
+      "step": 30
+    },
+    {
+      "epoch": 0.019224806201550388,
+      "grad_norm": 9.130881309509277,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.4618,
+      "step": 31
+    },
+    {
+      "epoch": 0.01984496124031008,
+      "grad_norm": 12.017380714416504,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.0726,
+      "step": 32
+    },
+    {
+      "epoch": 0.020465116279069766,
+      "grad_norm": 8.987724304199219,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4383,
+      "step": 33
+    },
+    {
+      "epoch": 0.021085271317829456,
+      "grad_norm": 14.123013496398926,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7477,
+      "step": 34
+    },
+    {
+      "epoch": 0.021705426356589147,
+      "grad_norm": 7.6661529541015625,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.2971,
+      "step": 35
+    },
+    {
+      "epoch": 0.022325581395348838,
+      "grad_norm": 12.411150932312012,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.4651,
+      "step": 36
+    },
+    {
+      "epoch": 0.022945736434108528,
+      "grad_norm": 5.422929763793945,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.3783,
+      "step": 37
+    },
+    {
+      "epoch": 0.023565891472868215,
+      "grad_norm": 2.851478338241577,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0853,
+      "step": 38
+    },
+    {
+      "epoch": 0.024186046511627906,
+      "grad_norm": 7.006505966186523,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.7307,
+      "step": 39
+    },
+    {
+      "epoch": 0.024806201550387597,
+      "grad_norm": 13.194289207458496,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.3757,
+      "step": 40
+    },
+    {
+      "epoch": 0.025426356589147287,
+      "grad_norm": 11.843560218811035,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.2397,
+      "step": 41
+    },
+    {
+      "epoch": 0.026046511627906978,
+      "grad_norm": 11.480189323425293,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6359,
+      "step": 42
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 8.796479225158691,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.9612,
+      "step": 43
+    },
+    {
+      "epoch": 0.027286821705426356,
+      "grad_norm": 15.973198890686035,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.157,
+      "step": 44
+    },
+    {
+      "epoch": 0.027906976744186046,
+      "grad_norm": 13.505546569824219,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.8184,
+      "step": 45
+    },
+    {
+      "epoch": 0.028527131782945737,
+      "grad_norm": 14.637463569641113,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.9088,
+      "step": 46
+    },
+    {
+      "epoch": 0.029147286821705427,
+      "grad_norm": 21.357471466064453,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.7652,
+      "step": 47
+    },
+    {
+      "epoch": 0.029767441860465118,
+      "grad_norm": 18.96230125427246,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.2635,
+      "step": 48
+    },
+    {
+      "epoch": 0.030387596899224805,
+      "grad_norm": 15.090560913085938,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.2206,
+      "step": 49
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 21.638938903808594,
+      "learning_rate": 0.0,
+      "loss": 3.67,
+      "step": 50
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "eval_loss": 0.9526658654212952,
+      "eval_runtime": 49.2321,
+      "eval_samples_per_second": 13.792,
+      "eval_steps_per_second": 6.906,
+      "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": 1802385752064000.0,
+  "total_flos": 3604771504128000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null