Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f0379d7d5c41ef834d47611a76d222b73978812fa859107e5afedda34d82fd
+oid sha256:b6994e89a3aba715236da51317d08636ceb1fef3f1dc941bddc41893c1946705
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264da79bcf428fc2314ce7cba76d7e74ef2542cef15b9143156b46cabe5deb61
+oid sha256:9ba0c30d59fcb038154c2aa994353aaaf34225e49aeb6bacfbf85bd684012641
 size 100824826

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbeadfc0684ceb6214a6d0763eaf26bd6da75d2aa571951ea52ae144ae1aed65
+oid sha256:28ead1dc612d0828c741f27367b607218d5454f0eeec1edf509fec9000c0823f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d616388fb2ad0b2430197767d5964f493bebf6c42e13151fc993b81571387fd5
+oid sha256:7e8247969e9bf67cdbde21bd094b435abcdb0f4db583d078300b382f8493a5f7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a706d71309a57a82a1c115823114ba00883e6c8d0e8a3c3764c599e8cf60a74a
+oid sha256:572e93d00955924c04fc85449c1960b143d26cb3626b37d6b5dc61a511935465
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72aa2613e5dfe21bbf57d2dcd748965869d81b29aebeeb2a22ed53604779e42
+oid sha256:59ccfe212cf9b36bb9a518ce041dfd22a27a000bbcad6624e1311c0050527def
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4176831245422363,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.43045466774280333,
+  "best_metric": 1.3889018297195435,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.645682001614205,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 56.568,
       "eval_steps_per_second": 14.708,
       "step": 50
+    },
+    {
+      "epoch": 0.4390637610976594,
+      "grad_norm": 15.413543701171875,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 53.126,
+      "step": 51
+    },
+    {
+      "epoch": 0.4476728544525155,
+      "grad_norm": 12.024312973022461,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 47.2167,
+      "step": 52
+    },
+    {
+      "epoch": 0.4562819478073715,
+      "grad_norm": 12.30172348022461,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 47.4088,
+      "step": 53
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 11.294939041137695,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 56.6595,
+      "step": 54
+    },
+    {
+      "epoch": 0.47350013451708367,
+      "grad_norm": 10.662542343139648,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 53.2404,
+      "step": 55
+    },
+    {
+      "epoch": 0.4821092278719397,
+      "grad_norm": 15.208189010620117,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 64.9003,
+      "step": 56
+    },
+    {
+      "epoch": 0.4907183212267958,
+      "grad_norm": 11.187201499938965,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 64.3199,
+      "step": 57
+    },
+    {
+      "epoch": 0.49932741458165186,
+      "grad_norm": 12.230656623840332,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 56.6661,
+      "step": 58
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 13.200939178466797,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 52.3994,
+      "step": 59
+    },
+    {
+      "epoch": 0.516545601291364,
+      "grad_norm": 14.380305290222168,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 49.6387,
+      "step": 60
+    },
+    {
+      "epoch": 0.5251546946462201,
+      "grad_norm": 17.927627563476562,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 42.8506,
+      "step": 61
+    },
+    {
+      "epoch": 0.5337637880010762,
+      "grad_norm": 21.359195709228516,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 27.11,
+      "step": 62
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 27.922710418701172,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 34.2575,
+      "step": 63
+    },
+    {
+      "epoch": 0.5509819747107882,
+      "grad_norm": 12.698566436767578,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 47.1511,
+      "step": 64
+    },
+    {
+      "epoch": 0.5595910680656443,
+      "grad_norm": 18.216020584106445,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 50.3791,
+      "step": 65
+    },
+    {
+      "epoch": 0.5682001614205004,
+      "grad_norm": 10.784895896911621,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 57.2583,
+      "step": 66
+    },
+    {
+      "epoch": 0.5768092547753565,
+      "grad_norm": 11.434226036071777,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 46.796,
+      "step": 67
+    },
+    {
+      "epoch": 0.5854183481302125,
+      "grad_norm": 15.327218055725098,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 52.9113,
+      "step": 68
+    },
+    {
+      "epoch": 0.5940274414850686,
+      "grad_norm": 11.83072566986084,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 58.4481,
+      "step": 69
+    },
+    {
+      "epoch": 0.6026365348399246,
+      "grad_norm": 11.807805061340332,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 58.5683,
+      "step": 70
+    },
+    {
+      "epoch": 0.6112456281947808,
+      "grad_norm": 12.243427276611328,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 58.3624,
+      "step": 71
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 12.938373565673828,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 52.0863,
+      "step": 72
+    },
+    {
+      "epoch": 0.6284638149044929,
+      "grad_norm": 15.217366218566895,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 46.2949,
+      "step": 73
+    },
+    {
+      "epoch": 0.6370729082593489,
+      "grad_norm": 19.752513885498047,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 27.3293,
+      "step": 74
+    },
+    {
+      "epoch": 0.645682001614205,
+      "grad_norm": 34.682899475097656,
+      "learning_rate": 1e-05,
+      "loss": 25.5404,
+      "step": 75
+    },
+    {
+      "epoch": 0.645682001614205,
+      "eval_loss": 1.3889018297195435,
+      "eval_runtime": 0.8817,
+      "eval_samples_per_second": 56.709,
+      "eval_steps_per_second": 14.744,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.480315374030029e+16,
+  "total_flos": 3.722794729104998e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null