Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e523e2b3c2733268038bc407e3d125f2050d580d63ce79dbeac81e1b717495
+oid sha256:485ad83f60464cbe387bc71a5ba70f7a1d09613e4939092d7a7dee0a40e1c5f1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e90b505153016f8c265003aabec726ff17e25de6b1fa2382b651b181724dc11
+oid sha256:a8919cbe2832526ee9632a24b195da452f6e80f188178b4a38bcfb0e983ec1c5
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff7c17184a2a63ce890f39f18b74b58a2c3e8f57792117daa2c4fdb0f733653
+oid sha256:4211050507b57dc2ac7b7cafe32e1b2f7aae53225dcddfb60e261ffaaffe9d51
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a053b7de268396c428a47bf54fac9f28dadfa78484e33dbec2baebe336d6f433
+oid sha256:8926f288f20d72cd9a6d1763235af942d4f86c92a42f2873d652d1c6769a3afc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35a17d6e6faf28c2f73548ca0c57714999731e978643c0b1d98bbb5db6a2f79
+oid sha256:d43f47c0228ac0277a685add1666dcff595a7067dbb4424f831582c78bcfd39e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4336eb2c776ad1c2f74fb07721aeed5d99ea1b3a141f9dd6f619fc342d37b4c1
+oid sha256:53b458359efd7953f1953937f4e6de1d77ada83b566d6c409c3085f210e67f88
 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": 0.6890727877616882,
   "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": 10.616,
       "eval_steps_per_second": 2.76,
       "step": 25
+    },
+    {
+      "epoch": 0.1798530047557285,
+      "grad_norm": 31.32541275024414,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.9615,
+      "step": 26
+    },
+    {
+      "epoch": 0.1867704280155642,
+      "grad_norm": 11.566988945007324,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.8916,
+      "step": 27
+    },
+    {
+      "epoch": 0.19368785127539992,
+      "grad_norm": 26.623291015625,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.2515,
+      "step": 28
+    },
+    {
+      "epoch": 0.20060527453523563,
+      "grad_norm": 12.670833587646484,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.0147,
+      "step": 29
+    },
+    {
+      "epoch": 0.20752269779507135,
+      "grad_norm": 18.8542423248291,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.2094,
+      "step": 30
+    },
+    {
+      "epoch": 0.21444012105490703,
+      "grad_norm": 22.972414016723633,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.0838,
+      "step": 31
+    },
+    {
+      "epoch": 0.22135754431474275,
+      "grad_norm": 18.56379508972168,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.187,
+      "step": 32
+    },
+    {
+      "epoch": 0.22827496757457846,
+      "grad_norm": 20.60142707824707,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.1898,
+      "step": 33
+    },
+    {
+      "epoch": 0.23519239083441418,
+      "grad_norm": 27.812822341918945,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.2153,
+      "step": 34
+    },
+    {
+      "epoch": 0.2421098140942499,
+      "grad_norm": 9.875837326049805,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.1487,
+      "step": 35
+    },
+    {
+      "epoch": 0.2490272373540856,
+      "grad_norm": 13.512711524963379,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.0882,
+      "step": 36
+    },
+    {
+      "epoch": 0.2559446606139213,
+      "grad_norm": 11.75142765045166,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.0221,
+      "step": 37
+    },
+    {
+      "epoch": 0.26286208387375704,
+      "grad_norm": 11.987626075744629,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.0416,
+      "step": 38
+    },
+    {
+      "epoch": 0.2697795071335927,
+      "grad_norm": 10.277228355407715,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.1801,
+      "step": 39
+    },
+    {
+      "epoch": 0.27669693039342846,
+      "grad_norm": 11.25522518157959,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.1051,
+      "step": 40
+    },
+    {
+      "epoch": 0.28361435365326415,
+      "grad_norm": 12.054732322692871,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.0765,
+      "step": 41
+    },
+    {
+      "epoch": 0.2905317769130999,
+      "grad_norm": 7.122025489807129,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.0064,
+      "step": 42
+    },
+    {
+      "epoch": 0.2974492001729356,
+      "grad_norm": 16.80191993713379,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.9657,
+      "step": 43
+    },
+    {
+      "epoch": 0.30436662343277127,
+      "grad_norm": 10.954202651977539,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.0736,
+      "step": 44
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 7.031284332275391,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.9168,
+      "step": 45
+    },
+    {
+      "epoch": 0.3182014699524427,
+      "grad_norm": 13.944522857666016,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.2041,
+      "step": 46
+    },
+    {
+      "epoch": 0.32511889321227844,
+      "grad_norm": 8.850104331970215,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.1053,
+      "step": 47
+    },
+    {
+      "epoch": 0.3320363164721141,
+      "grad_norm": 19.365779876708984,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.1555,
+      "step": 48
+    },
+    {
+      "epoch": 0.33895373973194987,
+      "grad_norm": 9.599617004394531,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.9737,
+      "step": 49
+    },
+    {
+      "epoch": 0.34587116299178555,
+      "grad_norm": 8.487637519836426,
+      "learning_rate": 1e-05,
+      "loss": 10.9277,
+      "step": 50
+    },
+    {
+      "epoch": 0.34587116299178555,
+      "eval_loss": 0.693572998046875,
+      "eval_runtime": 4.7237,
+      "eval_samples_per_second": 10.585,
+      "eval_steps_per_second": 2.752,
+      "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