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:e3468aaa3c4f06831d90b45994891ab3f561a49b473a31e810bdab64ba4e69e8
+oid sha256:62aad0cf15a2cc14038ccf8364687c2dcfbc6f867d254f18e8a9767aa511ca08
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5254f43289687c754de4eff0b1210430c5a27ebbbf0756f94e76a34e6b8b2b32
+oid sha256:9f4e2d9e4b2f2b376ae9998ad1969c2f208958665263edbf409fe5618cd36a8c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f02b9417fe981e207b099ec04654c97f7546c0eef770465a58dad8d62b7bfda
+oid sha256:b96d096b68aee26293531db1e4a55bf315c91c559975d9bb800d2f69cf13aebf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d0afcc7b8c03864de4aa0d8978b3cdf9371fef5c00211eabf9627b5853e8b1d
+oid sha256:b7bc3ff998d7be367ad5e8d2ffbc54079299bb8d0e1adb48c10d0908724aa238
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b43935d3fe494a3547873161e38a664157f0afabc4b59784f161ce85c7ab9af
+oid sha256:01bdae103ac39f06d23b8dece6ec7c7a7f98eeec09b0a7cdb1e0397c5718fb9e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6a4ce8cf56d8bf05a13ebbfbe9bbc0b04940a32de78a82b45ac1d260e5c7f0
+oid sha256:439334d6778ad7c39deb593049543b9db68e27a1566347d05d2a16df49bf8c16
 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": 0.6879555583000183,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17293558149589278,
+  "epoch": 0.34587116299178555,
   "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": 17.635,
       "eval_steps_per_second": 4.585,
       "step": 25
+    },
+    {
+      "epoch": 0.1798530047557285,
+      "grad_norm": 25.150753021240234,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.8376,
+      "step": 26
+    },
+    {
+      "epoch": 0.1867704280155642,
+      "grad_norm": 11.115327835083008,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.9443,
+      "step": 27
+    },
+    {
+      "epoch": 0.19368785127539992,
+      "grad_norm": 34.211116790771484,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.3249,
+      "step": 28
+    },
+    {
+      "epoch": 0.20060527453523563,
+      "grad_norm": 26.4182186126709,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.1095,
+      "step": 29
+    },
+    {
+      "epoch": 0.20752269779507135,
+      "grad_norm": 26.52771759033203,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.2013,
+      "step": 30
+    },
+    {
+      "epoch": 0.21444012105490703,
+      "grad_norm": 39.35798645019531,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.1891,
+      "step": 31
+    },
+    {
+      "epoch": 0.22135754431474275,
+      "grad_norm": 24.50100326538086,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.1125,
+      "step": 32
+    },
+    {
+      "epoch": 0.22827496757457846,
+      "grad_norm": 21.984201431274414,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.1111,
+      "step": 33
+    },
+    {
+      "epoch": 0.23519239083441418,
+      "grad_norm": 38.212711334228516,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.2054,
+      "step": 34
+    },
+    {
+      "epoch": 0.2421098140942499,
+      "grad_norm": 19.55695915222168,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.1752,
+      "step": 35
+    },
+    {
+      "epoch": 0.2490272373540856,
+      "grad_norm": 22.37201499938965,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.0952,
+      "step": 36
+    },
+    {
+      "epoch": 0.2559446606139213,
+      "grad_norm": 17.3990478515625,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.0722,
+      "step": 37
+    },
+    {
+      "epoch": 0.26286208387375704,
+      "grad_norm": 20.264245986938477,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.0233,
+      "step": 38
+    },
+    {
+      "epoch": 0.2697795071335927,
+      "grad_norm": 13.87209701538086,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.1106,
+      "step": 39
+    },
+    {
+      "epoch": 0.27669693039342846,
+      "grad_norm": 13.097599983215332,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.0787,
+      "step": 40
+    },
+    {
+      "epoch": 0.28361435365326415,
+      "grad_norm": 14.641912460327148,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.0121,
+      "step": 41
+    },
+    {
+      "epoch": 0.2905317769130999,
+      "grad_norm": 13.696270942687988,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.0541,
+      "step": 42
+    },
+    {
+      "epoch": 0.2974492001729356,
+      "grad_norm": 31.812328338623047,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.0109,
+      "step": 43
+    },
+    {
+      "epoch": 0.30436662343277127,
+      "grad_norm": 21.586620330810547,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.0635,
+      "step": 44
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 11.610532760620117,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.9459,
+      "step": 45
+    },
+    {
+      "epoch": 0.3182014699524427,
+      "grad_norm": 21.65961456298828,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.227,
+      "step": 46
+    },
+    {
+      "epoch": 0.32511889321227844,
+      "grad_norm": 15.142019271850586,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.1067,
+      "step": 47
+    },
+    {
+      "epoch": 0.3320363164721141,
+      "grad_norm": 28.59906005859375,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.1554,
+      "step": 48
+    },
+    {
+      "epoch": 0.33895373973194987,
+      "grad_norm": 14.337183952331543,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.9071,
+      "step": 49
+    },
+    {
+      "epoch": 0.34587116299178555,
+      "grad_norm": 14.704347610473633,
+      "learning_rate": 1e-05,
+      "loss": 10.9571,
+      "step": 50
+    },
+    {
+      "epoch": 0.34587116299178555,
+      "eval_loss": 0.6945770382881165,
+      "eval_runtime": 2.8248,
+      "eval_samples_per_second": 17.7,
+      "eval_steps_per_second": 4.602,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null