Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc84affc9bf28bacff9231b52926c4fbed2c91209561afd86b5e7f3d393b653
+oid sha256:75adf59f57d1cbc0b1831e468ec8cef83e60f7b6a73be3d8c364b6d44632e687
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f708b429b358c6bfbf1d83e6d54b835dfd13e96ecad9f8e5eeac1b7dcb7159
+oid sha256:a5c8e8f2d5a246a505a5531f95903a2ac72e44deaeee72a2c5ec1f5b2a252829
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a70e65e71d2d226bcd8496ef924cd74beb303b0077fdc9276737c33661d28c
+oid sha256:f72b1fd640b6a4dbb86104f971b8930ca1ff52402426d8d3d9c00ede391c7292
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ccfbaa2500a5822dbbaf812b9327685a2d94cee1383ace8059d3608332c9298
+oid sha256:be32f1f2c9153d09859bef425b8466013b77316cbe36552f35b7a9f79c83cbc3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b27ade6e4810d5c7bf2cdf0c4119ceb72963096c536e9ef2dd8e374fb6372a
+oid sha256:bd56690602987894d5674f73f6494ae9498f857accb2aef1e4b08fec8feb52cc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00225f917f23e8692c7696bc71a2c15fb0cf05d0d72f1286d839c97db64cdd59
+oid sha256:8cb2d4995605c938c90dbf6b59b0bf5141d8c29a635793488238b050283cebab
 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": 0.6260367035865784,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5333333333333333,
+  "best_metric": 0.5262271165847778,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0706666666666667,
   "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": 33.84,
       "eval_steps_per_second": 8.798,
       "step": 25
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 9.099970817565918,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5431,
+      "step": 26
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 8.249467849731445,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.625,
+      "step": 27
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 1.556484341621399,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5582,
+      "step": 28
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 2.128772020339966,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5032,
+      "step": 29
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.6905689239501953,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5859,
+      "step": 30
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 0.8498053550720215,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5389,
+      "step": 31
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 1.1759029626846313,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5202,
+      "step": 32
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.9058291912078857,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5411,
+      "step": 33
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 1.376121163368225,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5221,
+      "step": 34
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 2.186556577682495,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4881,
+      "step": 35
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.8152661323547363,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4973,
+      "step": 36
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 0.7359256744384766,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.5243,
+      "step": 37
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.7243295907974243,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4645,
+      "step": 38
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 3.939314126968384,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4964,
+      "step": 39
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 4.687667369842529,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5477,
+      "step": 40
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 5.146167278289795,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5801,
+      "step": 41
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 3.052762746810913,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5013,
+      "step": 42
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 2.1193552017211914,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.533,
+      "step": 43
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 1.4770478010177612,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5794,
+      "step": 44
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.062102317810059,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4997,
+      "step": 45
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 4.741394996643066,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5361,
+      "step": 46
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 5.473133087158203,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.664,
+      "step": 47
+    },
+    {
+      "epoch": 1.028,
+      "grad_norm": 3.7654004096984863,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4983,
+      "step": 48
+    },
+    {
+      "epoch": 1.0493333333333332,
+      "grad_norm": 4.608935832977295,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5102,
+      "step": 49
+    },
+    {
+      "epoch": 1.0706666666666667,
+      "grad_norm": 3.692960262298584,
+      "learning_rate": 1e-05,
+      "loss": 0.5325,
+      "step": 50
+    },
+    {
+      "epoch": 1.0706666666666667,
+      "eval_loss": 0.5262271165847778,
+      "eval_runtime": 1.4748,
+      "eval_samples_per_second": 33.904,
+      "eval_steps_per_second": 8.815,
+      "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": 8.061561648604774e+16,
+  "total_flos": 1.6063518385320755e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null