Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502759a44c5a70ef0bc3ca930aff5a021d7a05770fc9c2a1a4a4c679b84bb50a
+oid sha256:f1369d4af1d8525c2b70a81313906591883f3a2892f6fb69a5fd3b689afd6c47
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad73c807726fcbfa80a967e9abcbda7482ec409646155d3a97117b6f061a798
+oid sha256:63e851d770e0c4cfad8242303b70225568fe1c9aee3b8f021e2023762a8b1aad
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e45da6603c2b1efb7a93833de191a847c194fcf0ee449429292953d0f2c503d
+oid sha256:b272366be3c5f163b7e801b6c66a633efb6cfc65a21c68050706eccec73e5531
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2f9ac20a212bbf913ce1945bff4bc88a4b24a7e6b52ad4bed8dd86fd0b8013
+oid sha256:4e9abccd9316094728a8143c00fc1bb097d09e95067932619f11dea259f30b22
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a81e74d5ea1383544d35ce060de33081a6673bc57761e9fc4f2236d88ecf82a
+oid sha256:5829d6dccfd9549776c0c94b5415b4d73f05fa1eb17d5fc71eb12eb621b65a9b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faea6f2f6ed424c2817315be28339aeed96b2a549f37a45ba7fec70f11f1464d
+oid sha256:a7fec904e607408a7cf753752d121d65cfe10971a844f2a62eaa427e022af76c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5398735404014587,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7575757575757576,
+  "best_metric": 0.348781555891037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5151515151515151,
   "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": 28.65,
       "eval_steps_per_second": 7.449,
       "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 8.93183422088623,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 7.1282,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 7.6780195236206055,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 7.2661,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 7.696419715881348,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 7.2112,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 7.388005256652832,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.579,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.553566932678223,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.682,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 9.785886764526367,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 7.1062,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 14.416071891784668,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 8.1055,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.140599250793457,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.4307,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 11.224316596984863,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 5.541,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 7.196849822998047,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.2257,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 6.592137336730957,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.2948,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 6.121169567108154,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.4573,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 7.207998752593994,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.3519,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 6.918445110321045,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 5.0212,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 7.768368721008301,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 5.1239,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 11.915384292602539,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 5.7944,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 6.817359924316406,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.724,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 7.651495933532715,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.8022,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 5.93342399597168,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.7365,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 6.173413276672363,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.7833,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 7.115561485290527,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.987,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 6.725718975067139,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.6219,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 8.670489311218262,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.9975,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 13.76158618927002,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.3094,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 5.179720878601074,
+      "learning_rate": 1e-05,
+      "loss": 4.1417,
+      "step": 50
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 0.348781555891037,
+      "eval_runtime": 1.7648,
+      "eval_samples_per_second": 28.332,
+      "eval_steps_per_second": 7.366,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null