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:e85f0bfdcd1d5e273fb1b3931c1025eef3e69909767d26904fae09438fd7029f
+oid sha256:49c984ca3dc78640172faeb08d15f07060688a6421c10c79fc7740aadeccb887
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a3a473b835245719edf06b9ae759efb27f9039587d49d5762cf25daab878d4
+oid sha256:872cb8a0be2b129caf9bec410c896821ebec450020a8a96ab705f35d5b7bb97e
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d865b58cd637f1d1f407e12e80527880e2d3aa3b8cd1673b36edcb8396e79e0
+oid sha256:0f1b654cb768b09f2447765cbe829c094ef15380fc1e40594d9f92a0a0156a3c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f896ef9ec1bf88e1f30fc9b36323d649a65a15fb8f13aacbdb60a23181b05a
+oid sha256:9530b08c1218a2d77b2c7a711131a013c1db652aaef8c8430cb02f3cbd87dd26
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbc36ecb46bafb1f82cba4d0eefa4dd81c8faddebc89b56a073163c64f0b45d
+oid sha256:0242581831c183e763ccfa45c8315bd12c761c864d8d947325419cb5ea284f3e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a61c358577e934a39f1b8901b2f1dff0c93d372fd4015b18c2156b750c9e201
+oid sha256:5af100b6dc0efc73e0c6049a00d30e732da44b09311d31a52ae6e47b893afc4c
 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": 0.9322059154510498,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4294149221685454,
+  "best_metric": 0.8873636722564697,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8588298443370908,
   "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": 24.273,
       "eval_steps_per_second": 6.311,
       "step": 25
+    },
+    {
+      "epoch": 0.44659151905528716,
+      "grad_norm": 1.0108604431152344,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9222,
+      "step": 26
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.724280834197998,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9274,
+      "step": 27
+    },
+    {
+      "epoch": 0.4809447128287708,
+      "grad_norm": 0.5844231247901917,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9069,
+      "step": 28
+    },
+    {
+      "epoch": 0.4981213097155126,
+      "grad_norm": 0.7787989974021912,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.918,
+      "step": 29
+    },
+    {
+      "epoch": 0.5152979066022544,
+      "grad_norm": 0.5017805695533752,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9007,
+      "step": 30
+    },
+    {
+      "epoch": 0.5324745034889963,
+      "grad_norm": 0.5055813193321228,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9085,
+      "step": 31
+    },
+    {
+      "epoch": 0.549651100375738,
+      "grad_norm": 0.8349924087524414,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8921,
+      "step": 32
+    },
+    {
+      "epoch": 0.5668276972624798,
+      "grad_norm": 0.6210905909538269,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9028,
+      "step": 33
+    },
+    {
+      "epoch": 0.5840042941492217,
+      "grad_norm": 0.363650381565094,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.885,
+      "step": 34
+    },
+    {
+      "epoch": 0.6011808910359635,
+      "grad_norm": 0.49789223074913025,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.88,
+      "step": 35
+    },
+    {
+      "epoch": 0.6183574879227053,
+      "grad_norm": 0.4954957067966461,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8947,
+      "step": 36
+    },
+    {
+      "epoch": 0.6355340848094472,
+      "grad_norm": 0.43311986327171326,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8592,
+      "step": 37
+    },
+    {
+      "epoch": 0.652710681696189,
+      "grad_norm": 0.46934106945991516,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.892,
+      "step": 38
+    },
+    {
+      "epoch": 0.6698872785829307,
+      "grad_norm": 0.6024031043052673,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8857,
+      "step": 39
+    },
+    {
+      "epoch": 0.6870638754696726,
+      "grad_norm": 0.711588442325592,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8997,
+      "step": 40
+    },
+    {
+      "epoch": 0.7042404723564144,
+      "grad_norm": 0.5287402868270874,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8813,
+      "step": 41
+    },
+    {
+      "epoch": 0.7214170692431562,
+      "grad_norm": 0.5963271856307983,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8864,
+      "step": 42
+    },
+    {
+      "epoch": 0.738593666129898,
+      "grad_norm": 0.8385568857192993,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8777,
+      "step": 43
+    },
+    {
+      "epoch": 0.7557702630166399,
+      "grad_norm": 0.6774641275405884,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8688,
+      "step": 44
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 0.3524174690246582,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8618,
+      "step": 45
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.3650965690612793,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8891,
+      "step": 46
+    },
+    {
+      "epoch": 0.8073000536768653,
+      "grad_norm": 0.489184707403183,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.904,
+      "step": 47
+    },
+    {
+      "epoch": 0.8244766505636071,
+      "grad_norm": 0.35907652974128723,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8735,
+      "step": 48
+    },
+    {
+      "epoch": 0.8416532474503489,
+      "grad_norm": 0.6156330704689026,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8704,
+      "step": 49
+    },
+    {
+      "epoch": 0.8588298443370908,
+      "grad_norm": 0.4536202847957611,
+      "learning_rate": 1e-05,
+      "loss": 0.8143,
+      "step": 50
+    },
+    {
+      "epoch": 0.8588298443370908,
+      "eval_loss": 0.8873636722564697,
+      "eval_runtime": 2.0378,
+      "eval_samples_per_second": 24.536,
+      "eval_steps_per_second": 6.379,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null