Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9148cbec9db2515e9c5b66de6ac37413d059ead044a45f67e8170741116132
+oid sha256:4254ea1c8d3661e51153c88d24c245d2be8acfba25923de111e778f1a7be5c42
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703b5cdc72da02040377882e2a26f2dba44fd7fa8c0c4dbdc15dd67edec99887
+oid sha256:66eb2266f0194ea4c09440fbfaa23f60222175f2c8c9acc57697bed397afff7b
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9b3c607f40ef8939d72fe5879e5487fc6a8e7ac9a16330ae80a38f6d40c9a
+oid sha256:68f6ab694e0d5c679cd10d2a75e786dbb13c82f7cd6898425533a0f79d93b8e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ce26d861c9f8d708cb45ca09fa30d799964dafb1e8ac7ad9f4d3d1492a6a48
+oid sha256:25a1664e6d2d298e9f351a4cc9f8bd572e0253d03d34b5c1a8a377dc9c209cf0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21fa86072d7c103c93cf1b982fed2cc12237e63525879fd8b606a532363254a
+oid sha256:ff000c224f3112d590e7e66e26b0f0b07a383293ac646f6ad26b89480f049c2d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15612a17638099832723b7562199e5e4f82636cbfb1a6d8b48612a9c929215b
+oid sha256:5ba02f73d82c6b939869ab974aa631db83aa6bf7dcd974dc39ddea899c72cbe5
 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": 4.555571556091309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017114495978093443,
+  "best_metric": 4.46038818359375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03422899195618689,
   "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": 154.902,
       "eval_steps_per_second": 40.274,
       "step": 25
+    },
+    {
+      "epoch": 0.017799075817217184,
+      "grad_norm": 0.652305006980896,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.8983,
+      "step": 26
+    },
+    {
+      "epoch": 0.01848365565634092,
+      "grad_norm": 0.7992231249809265,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.7073,
+      "step": 27
+    },
+    {
+      "epoch": 0.019168235495464658,
+      "grad_norm": 0.38415586948394775,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.5686,
+      "step": 28
+    },
+    {
+      "epoch": 0.019852815334588398,
+      "grad_norm": 0.38379648327827454,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4937,
+      "step": 29
+    },
+    {
+      "epoch": 0.020537395173712135,
+      "grad_norm": 0.38786450028419495,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.4419,
+      "step": 30
+    },
+    {
+      "epoch": 0.021221975012835872,
+      "grad_norm": 0.49159541726112366,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.5172,
+      "step": 31
+    },
+    {
+      "epoch": 0.02190655485195961,
+      "grad_norm": 0.5576838254928589,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.5385,
+      "step": 32
+    },
+    {
+      "epoch": 0.02259113469108335,
+      "grad_norm": 0.3310554623603821,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.5236,
+      "step": 33
+    },
+    {
+      "epoch": 0.023275714530207086,
+      "grad_norm": 0.3554631769657135,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.5445,
+      "step": 34
+    },
+    {
+      "epoch": 0.023960294369330823,
+      "grad_norm": 0.3332033157348633,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.4697,
+      "step": 35
+    },
+    {
+      "epoch": 0.02464487420845456,
+      "grad_norm": 0.4032423198223114,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.4963,
+      "step": 36
+    },
+    {
+      "epoch": 0.0253294540475783,
+      "grad_norm": 0.48033788800239563,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.5964,
+      "step": 37
+    },
+    {
+      "epoch": 0.026014033886702037,
+      "grad_norm": 0.6050848364830017,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.9098,
+      "step": 38
+    },
+    {
+      "epoch": 0.026698613725825774,
+      "grad_norm": 0.5689930319786072,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.7628,
+      "step": 39
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.35218316316604614,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.544,
+      "step": 40
+    },
+    {
+      "epoch": 0.02806777340407325,
+      "grad_norm": 0.2895558774471283,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.4886,
+      "step": 41
+    },
+    {
+      "epoch": 0.028752353243196988,
+      "grad_norm": 0.3760088384151459,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.4021,
+      "step": 42
+    },
+    {
+      "epoch": 0.029436933082320725,
+      "grad_norm": 0.2829365134239197,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.4461,
+      "step": 43
+    },
+    {
+      "epoch": 0.030121512921444462,
+      "grad_norm": 0.3910805583000183,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.4129,
+      "step": 44
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.3998270034790039,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.4577,
+      "step": 45
+    },
+    {
+      "epoch": 0.03149067259969194,
+      "grad_norm": 0.3465791344642639,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.4583,
+      "step": 46
+    },
+    {
+      "epoch": 0.03217525243881568,
+      "grad_norm": 0.31564465165138245,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.4946,
+      "step": 47
+    },
+    {
+      "epoch": 0.03285983227793941,
+      "grad_norm": 0.37373700737953186,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4635,
+      "step": 48
+    },
+    {
+      "epoch": 0.03354441211706315,
+      "grad_norm": 0.39719510078430176,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.5366,
+      "step": 49
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 0.44478699564933777,
+      "learning_rate": 1e-05,
+      "loss": 4.6088,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 4.46038818359375,
+      "eval_runtime": 0.3251,
+      "eval_samples_per_second": 153.796,
+      "eval_steps_per_second": 39.987,
+      "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": 5981868147081216.0,
+  "total_flos": 1.194596482678784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null