Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21816532de9a26e452c4286b95b406c625e38c3748821740e8c6f75b7eb7cdec
+oid sha256:ae28b514d923c802135c52be5c5aca22468acb76b2479bca3277d03aa1f72fd7
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0faa662a4500b16a03d528ff2a9fef1e60939f44f18326592e0cc2fd306ad83
+oid sha256:e228cbd870ff9f975c4f5615ddfc0d8019fa8e0276147daf16e8350a0c5d340a
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b954aa125cb706989c93eb8b8a07d1f671c59f16b1a580fbfb54e4277378b1
+oid sha256:f730d25ca7055812680848b28a7f272d6c688ebe371af523184e3e32b4a5c53b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e5fa9b5dd6a1e93b49fb54b88fcd17f280fec5b8ecd677a0fd769432d6af9a
+oid sha256:e184f69d00141178850739df7430ff513af0727be2f561e148f54a68dd89a4d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebe216a68903ec3b1ec0fd787b455a9025050298e1faacd6a6dfd0e3c4c3cd3
+oid sha256:afbf69036d9a73903827785037cdde400907c7e61c3874bffeddbb41adcc82b1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489c6810aa00bdabb22946e4ee8163eee88c18ee07387d934dbaae647cbc97c4
+oid sha256:6e878db44b907ff1c4121e7918493401b760e4740646221db7d716b8d9cf7f22
 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": 4.227850437164307,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4351687388987566,
+  "best_metric": 4.055038928985596,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8703374777975132,
   "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": 76.093,
       "eval_steps_per_second": 19.784,
       "step": 25
+    },
+    {
+      "epoch": 1.492007104795737,
+      "grad_norm": 0.514370858669281,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.031,
+      "step": 26
+    },
+    {
+      "epoch": 1.5488454706927177,
+      "grad_norm": 1.1798518896102905,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.6368,
+      "step": 27
+    },
+    {
+      "epoch": 1.605683836589698,
+      "grad_norm": 0.7508013844490051,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.8476,
+      "step": 28
+    },
+    {
+      "epoch": 1.6625222024866786,
+      "grad_norm": 0.7122344374656677,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.1605,
+      "step": 29
+    },
+    {
+      "epoch": 1.7193605683836588,
+      "grad_norm": 0.45820507407188416,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2039,
+      "step": 30
+    },
+    {
+      "epoch": 1.7761989342806395,
+      "grad_norm": 1.2526981830596924,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.6394,
+      "step": 31
+    },
+    {
+      "epoch": 1.83303730017762,
+      "grad_norm": 0.5841005444526672,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.823,
+      "step": 32
+    },
+    {
+      "epoch": 1.8898756660746003,
+      "grad_norm": 0.6095443367958069,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.0752,
+      "step": 33
+    },
+    {
+      "epoch": 1.9467140319715808,
+      "grad_norm": 1.193407654762268,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.4321,
+      "step": 34
+    },
+    {
+      "epoch": 2.0177619893428065,
+      "grad_norm": 1.1657941341400146,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.658,
+      "step": 35
+    },
+    {
+      "epoch": 2.0746003552397867,
+      "grad_norm": 0.54337477684021,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.3645,
+      "step": 36
+    },
+    {
+      "epoch": 2.1314387211367674,
+      "grad_norm": 0.5608218908309937,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8492,
+      "step": 37
+    },
+    {
+      "epoch": 2.1882770870337476,
+      "grad_norm": 0.7258840203285217,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.1457,
+      "step": 38
+    },
+    {
+      "epoch": 2.2451154529307282,
+      "grad_norm": 0.7750731110572815,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.4016,
+      "step": 39
+    },
+    {
+      "epoch": 2.301953818827709,
+      "grad_norm": 0.67059725522995,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.313,
+      "step": 40
+    },
+    {
+      "epoch": 2.358792184724689,
+      "grad_norm": 0.5662630796432495,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.813,
+      "step": 41
+    },
+    {
+      "epoch": 2.4156305506216698,
+      "grad_norm": 0.6992785334587097,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.0543,
+      "step": 42
+    },
+    {
+      "epoch": 2.47246891651865,
+      "grad_norm": 0.6731230616569519,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8761,
+      "step": 43
+    },
+    {
+      "epoch": 2.5293072824156306,
+      "grad_norm": 0.8138448596000671,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.7918,
+      "step": 44
+    },
+    {
+      "epoch": 2.586145648312611,
+      "grad_norm": 0.5428887009620667,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.7575,
+      "step": 45
+    },
+    {
+      "epoch": 2.6429840142095915,
+      "grad_norm": 0.6178069710731506,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0502,
+      "step": 46
+    },
+    {
+      "epoch": 2.699822380106572,
+      "grad_norm": 0.6623405814170837,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.0481,
+      "step": 47
+    },
+    {
+      "epoch": 2.7566607460035524,
+      "grad_norm": 0.7139769196510315,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.5405,
+      "step": 48
+    },
+    {
+      "epoch": 2.8134991119005326,
+      "grad_norm": 0.7384081482887268,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6188,
+      "step": 49
+    },
+    {
+      "epoch": 2.8703374777975132,
+      "grad_norm": 0.5655322074890137,
+      "learning_rate": 1e-05,
+      "loss": 3.9295,
+      "step": 50
+    },
+    {
+      "epoch": 2.8703374777975132,
+      "eval_loss": 4.055038928985596,
+      "eval_runtime": 0.6379,
+      "eval_samples_per_second": 78.385,
+      "eval_steps_per_second": 20.38,
+      "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": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null