Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93177589457e4cd22a7fc1384d48aa23845ee9733104246f1ff99cc6716f30db
+oid sha256:0ef60ee89e2afcbf6beb7f2e499f714cf60ecb0d666abba7ceb5c48b6a143285
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f606b1ec734754375622da85fd9d6004c6628d3cd119cb24f82013b5349eb12
+oid sha256:78af5f919bf12cc938c0b43fed820ad6914576efb29081eeab4718e62e2b18e2
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe991cb283e6a17f8035de72d40279e6e574661f90a7685e2c2068bc05c490d
+oid sha256:0faad5be2742b8a1808531c613c2e6c3f65f7adddcfb7c18f41c36f36dbe5ad5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9771511245510a1ee7fbb3a9b1f6b0a9a2ab6514cde4d25095c488668267307c
+oid sha256:ed4dc15eaf5b65b89e4b5afc49e5f6254138e402d1307578a7f1c83c5037fbd2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a00fccb1b5c32c1ae5ac54650b393f9359c755fbdb34d475d86accdcf0b3643
+oid sha256:72e35ae4d003fa0ae3c8c431f72880b989f879ffce9b6b9ffb5496e631926095
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0fbb99ac754db0f38b7c598c83768d0dbba392ea4435f853aaed61f1894da08
+oid sha256:b5a0452c49e3b0ce630bbc3392315d60a2f0aa7e3e491d75b3c48c4cd394df8d
 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": 0.28254151344299316,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16339869281045752,
+  "epoch": 0.32679738562091504,
   "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": 12.492,
       "eval_steps_per_second": 3.248,
       "step": 25
+    },
+    {
+      "epoch": 0.16993464052287582,
+      "grad_norm": 1.602662205696106,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3057,
+      "step": 26
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 1.589160680770874,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.319,
+      "step": 27
+    },
+    {
+      "epoch": 0.1830065359477124,
+      "grad_norm": 2.4900217056274414,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.241,
+      "step": 28
+    },
+    {
+      "epoch": 0.1895424836601307,
+      "grad_norm": 1.270291805267334,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2711,
+      "step": 29
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 2.1127798557281494,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2638,
+      "step": 30
+    },
+    {
+      "epoch": 0.20261437908496732,
+      "grad_norm": 2.7198941707611084,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3523,
+      "step": 31
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 3.0281879901885986,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4,
+      "step": 32
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 2.0487160682678223,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3356,
+      "step": 33
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.616393804550171,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3093,
+      "step": 34
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 2.027432918548584,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2994,
+      "step": 35
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.4597184658050537,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2981,
+      "step": 36
+    },
+    {
+      "epoch": 0.24183006535947713,
+      "grad_norm": 0.7803646326065063,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3038,
+      "step": 37
+    },
+    {
+      "epoch": 0.24836601307189543,
+      "grad_norm": 1.935690999031067,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3237,
+      "step": 38
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "grad_norm": 2.474318265914917,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2763,
+      "step": 39
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 2.2222399711608887,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2458,
+      "step": 40
+    },
+    {
+      "epoch": 0.2679738562091503,
+      "grad_norm": 2.2565555572509766,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2784,
+      "step": 41
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 1.7884281873703003,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3071,
+      "step": 42
+    },
+    {
+      "epoch": 0.28104575163398693,
+      "grad_norm": 1.1541043519973755,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2965,
+      "step": 43
+    },
+    {
+      "epoch": 0.2875816993464052,
+      "grad_norm": 1.7841823101043701,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2844,
+      "step": 44
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 3.4865846633911133,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3227,
+      "step": 45
+    },
+    {
+      "epoch": 0.3006535947712418,
+      "grad_norm": 2.5097360610961914,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3135,
+      "step": 46
+    },
+    {
+      "epoch": 0.30718954248366015,
+      "grad_norm": 1.5082900524139404,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2822,
+      "step": 47
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 1.5687335729599,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3099,
+      "step": 48
+    },
+    {
+      "epoch": 0.3202614379084967,
+      "grad_norm": 0.6072501540184021,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2671,
+      "step": 49
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.7342411279678345,
+      "learning_rate": 1e-05,
+      "loss": 0.3171,
+      "step": 50
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "eval_loss": 0.29997187852859497,
+      "eval_runtime": 4.0194,
+      "eval_samples_per_second": 12.44,
+      "eval_steps_per_second": 3.234,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null