Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539c0893f10f1179f252a4377d603db1dbda5f0cc4a1d7dc881ab0911643ea79
+oid sha256:1daf8ec6cd58f7c9c4b34fcf1a5573004b93c5659a2995c904252078eb44d1b0
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c84ff9aba276fdb8245479ac23599053ae545090b31aceca9a5b7414388973a
+oid sha256:a1a5a19301d0d099498c5854e8f00af440ca93c827912295ca035f1bfe3cf0e7
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79fdb9b9c4a6f72363c8d6df6cf235a5e296d44c10e3dceb55a0fe34ef6e42d
+oid sha256:b864c2ecdf9593d63c6f3980be9e68fc8197df96007f7686b4676c23c56c6552
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407e3e753ef51d327b388b215a1783fd368909343b8f5e6e91f976bc36a20ed9
+oid sha256:f224ebb9b2bc3cd80624193fb3a037ec57c4f819aa22308ce480dcd536bf09b2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5403283ab0b7ca82a3a5795c934fa4f51bd1c678c6a5045b88374e4eab8b1a6a
+oid sha256:630296479b10c2c55cdfc3ab317b5db56f96efad642739546a197b6f123484fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2c1b31e1375415131d40d9083cdb16472dbd440bb852b850bd67904bb6a9e8
+oid sha256:bd43c0264ae2a2e42ebd8c8ff809640485aa6fa73874baea6afdc1db49213fc4
 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": 0.2122662216424942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07437709185570844,
+  "best_metric": 0.1284322291612625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.14875418371141688,
   "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": 17.198,
       "eval_steps_per_second": 4.471,
       "step": 25
+    },
+    {
+      "epoch": 0.07735217552993678,
+      "grad_norm": 39.105255126953125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.2978,
+      "step": 26
+    },
+    {
+      "epoch": 0.08032725920416511,
+      "grad_norm": 29.777935028076172,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.3169,
+      "step": 27
+    },
+    {
+      "epoch": 0.08330234287839346,
+      "grad_norm": 34.50019454956055,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.5684,
+      "step": 28
+    },
+    {
+      "epoch": 0.08627742655262179,
+      "grad_norm": 16.251876831054688,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.9726,
+      "step": 29
+    },
+    {
+      "epoch": 0.08925251022685013,
+      "grad_norm": 35.28190994262695,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0923,
+      "step": 30
+    },
+    {
+      "epoch": 0.09222759390107847,
+      "grad_norm": 33.3674430847168,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8551,
+      "step": 31
+    },
+    {
+      "epoch": 0.0952026775753068,
+      "grad_norm": 23.594511032104492,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.7141,
+      "step": 32
+    },
+    {
+      "epoch": 0.09817776124953514,
+      "grad_norm": 22.697614669799805,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.7784,
+      "step": 33
+    },
+    {
+      "epoch": 0.10115284492376347,
+      "grad_norm": 16.394115447998047,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.4427,
+      "step": 34
+    },
+    {
+      "epoch": 0.10412792859799182,
+      "grad_norm": 14.120108604431152,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.3841,
+      "step": 35
+    },
+    {
+      "epoch": 0.10710301227222016,
+      "grad_norm": 6.709747791290283,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0642,
+      "step": 36
+    },
+    {
+      "epoch": 0.11007809594644849,
+      "grad_norm": 19.074462890625,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.2314,
+      "step": 37
+    },
+    {
+      "epoch": 0.11305317962067683,
+      "grad_norm": 18.0113525390625,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.2726,
+      "step": 38
+    },
+    {
+      "epoch": 0.11602826329490516,
+      "grad_norm": 14.895197868347168,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2632,
+      "step": 39
+    },
+    {
+      "epoch": 0.1190033469691335,
+      "grad_norm": 32.464725494384766,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.7555,
+      "step": 40
+    },
+    {
+      "epoch": 0.12197843064336185,
+      "grad_norm": 38.17766189575195,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.1778,
+      "step": 41
+    },
+    {
+      "epoch": 0.12495351431759018,
+      "grad_norm": 29.950498580932617,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.3807,
+      "step": 42
+    },
+    {
+      "epoch": 0.12792859799181852,
+      "grad_norm": 27.437570571899414,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.1036,
+      "step": 43
+    },
+    {
+      "epoch": 0.13090368166604685,
+      "grad_norm": 18.265331268310547,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.4419,
+      "step": 44
+    },
+    {
+      "epoch": 0.1338787653402752,
+      "grad_norm": 11.058792114257812,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.1983,
+      "step": 45
+    },
+    {
+      "epoch": 0.13685384901450354,
+      "grad_norm": 12.375876426696777,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.0319,
+      "step": 46
+    },
+    {
+      "epoch": 0.13982893268873187,
+      "grad_norm": 10.287103652954102,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.2049,
+      "step": 47
+    },
+    {
+      "epoch": 0.1428040163629602,
+      "grad_norm": 8.568561553955078,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8594,
+      "step": 48
+    },
+    {
+      "epoch": 0.14577910003718855,
+      "grad_norm": 10.927348136901855,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.6348,
+      "step": 49
+    },
+    {
+      "epoch": 0.14875418371141688,
+      "grad_norm": 16.63982582092285,
+      "learning_rate": 1e-05,
+      "loss": 1.8796,
+      "step": 50
+    },
+    {
+      "epoch": 0.14875418371141688,
+      "eval_loss": 0.1284322291612625,
+      "eval_runtime": 2.9278,
+      "eval_samples_per_second": 17.078,
+      "eval_steps_per_second": 4.44,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null