Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98648bf8b548910d60d5eefc29d407bc0aa482b10e8d09ca33a5657c8f9384d5
+oid sha256:64bfa39d61bc0fbb4b9917c5162978f466a15eee9e2a5be801b4cf978242d681
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fca97bc18bf56973c7bc69f4dd0ed94d43b8059fa3b5d5ce942d967750d871a
+oid sha256:e26f1a7b10bfeafc879c103d61e22eeb3f5e40fa9a1a618a5d2c1620c8e74b5f
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7e512094d815daf7351075ebf2d44b883aa6c95a75e4d1631dbb9d445a5894
+oid sha256:2de6861ab1fc1ddd50435530f2b674cd72a51a07af78567f75fec406b8ac7de3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2e6db355c807a9a2de4eb022022b555953712e4fea1aff64df401f5afec488
+oid sha256:3924273ce1dc1c5b2c847bd31095e38c7dbb110c530ea983d83283f3dbb9d68b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36fc9fdc715cb18fd4fc91e62977ee76a0d1ad9b4ea48f3af6d2c1c762e6e31
+oid sha256:3c4890b294f41536fdf5f34fdb8577292e27baf55af3e4fb68062bf3438ebcda
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1586b9c95ea9df076939542f56a6a9b1c00777f9dce7623ec823a9fac449ba8b
+oid sha256:85a8de78b90543c10bb7c58ed34e621ea640bde037da8bbbb5b8f8ec47a851c0
 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": 1.258978009223938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08130081300813008,
+  "best_metric": 1.040326714515686,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16260162601626016,
   "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": 98.491,
       "eval_steps_per_second": 25.608,
       "step": 25
+    },
+    {
+      "epoch": 0.08455284552845528,
+      "grad_norm": 4.233249187469482,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6492,
+      "step": 26
+    },
+    {
+      "epoch": 0.08780487804878048,
+      "grad_norm": 3.324646472930908,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4722,
+      "step": 27
+    },
+    {
+      "epoch": 0.0910569105691057,
+      "grad_norm": 3.379584550857544,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.4781,
+      "step": 28
+    },
+    {
+      "epoch": 0.0943089430894309,
+      "grad_norm": 2.331784963607788,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.4556,
+      "step": 29
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 2.055966377258301,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2575,
+      "step": 30
+    },
+    {
+      "epoch": 0.1008130081300813,
+      "grad_norm": 1.9917107820510864,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.29,
+      "step": 31
+    },
+    {
+      "epoch": 0.1040650406504065,
+      "grad_norm": 2.8519442081451416,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.18,
+      "step": 32
+    },
+    {
+      "epoch": 0.1073170731707317,
+      "grad_norm": 2.8271567821502686,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.054,
+      "step": 33
+    },
+    {
+      "epoch": 0.11056910569105691,
+      "grad_norm": 2.7337255477905273,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1004,
+      "step": 34
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 2.43483829498291,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9646,
+      "step": 35
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 2.1026363372802734,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9405,
+      "step": 36
+    },
+    {
+      "epoch": 0.12032520325203253,
+      "grad_norm": 1.9853432178497314,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.993,
+      "step": 37
+    },
+    {
+      "epoch": 0.12357723577235773,
+      "grad_norm": 2.1389589309692383,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2208,
+      "step": 38
+    },
+    {
+      "epoch": 0.12682926829268293,
+      "grad_norm": 2.8133692741394043,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3516,
+      "step": 39
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 2.000269651412964,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.243,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.6388593912124634,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2165,
+      "step": 41
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 1.5739003419876099,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2412,
+      "step": 42
+    },
+    {
+      "epoch": 0.13983739837398373,
+      "grad_norm": 1.612639307975769,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1447,
+      "step": 43
+    },
+    {
+      "epoch": 0.14308943089430895,
+      "grad_norm": 2.7704806327819824,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1089,
+      "step": 44
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 3.5234577655792236,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9901,
+      "step": 45
+    },
+    {
+      "epoch": 0.14959349593495935,
+      "grad_norm": 3.798884630203247,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9133,
+      "step": 46
+    },
+    {
+      "epoch": 0.15284552845528454,
+      "grad_norm": 2.6979990005493164,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.921,
+      "step": 47
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 2.207773208618164,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8548,
+      "step": 48
+    },
+    {
+      "epoch": 0.15934959349593497,
+      "grad_norm": 1.5497809648513794,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9014,
+      "step": 49
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 1.702278971672058,
+      "learning_rate": 1e-05,
+      "loss": 0.8361,
+      "step": 50
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "eval_loss": 1.040326714515686,
+      "eval_runtime": 0.5049,
+      "eval_samples_per_second": 99.028,
+      "eval_steps_per_second": 25.747,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null