Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b88d68060c8e6e99bbbcbfc2a639ae42c5e3e10dac60aade069388ad393531
+oid sha256:ad16f0b3cabccf0c5a8ddcb35949682a6e3558d4fb53e89e4b3d59bd3f498d70
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c963c7f8b85866b47c58c45f4d685192d079d01164c28530d0f36a4a15ffcec
+oid sha256:78689787ab3adabc9ddf8a51f5a736ab90f00e4cb91f7ae4343b3827dc213db1
 size 579101890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c113a434b6c4da37c61bb53ea6f9960aab6abcd777b3b576fd0b6a750ea9c29
+oid sha256:fde6f6f9e4bc0907e39cca7927282118e30eb0f0f4058ed131736ce91ee8d137
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3319cd7470c264bee54329e29b5ec91d9c9a4808c2d538532945e481104091
+oid sha256:480dd149a7e539c29c101c27ba4934fb8fdb062e60fdebf07dc67a0615db8e80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7116503119468689,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1000",
-  "epoch": 2.094240837696335,
+  "best_metric": 0.7064644694328308,
+  "best_model_checkpoint": "miner_id_24/checkpoint-2000",
+  "epoch": 2.7923211169284468,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 24.352,
       "eval_steps_per_second": 6.093,
       "step": 1500
+    },
+    {
+      "epoch": 2.164048865619546,
+      "grad_norm": 0.131423681974411,
+      "learning_rate": 2.708829915600401e-05,
+      "loss": 0.5524,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2338568935427574,
+      "grad_norm": 0.14766725897789001,
+      "learning_rate": 2.161309778686967e-05,
+      "loss": 0.5538,
+      "step": 1600
+    },
+    {
+      "epoch": 2.303664921465969,
+      "grad_norm": 0.1517447680234909,
+      "learning_rate": 1.6690435978090822e-05,
+      "loss": 0.5645,
+      "step": 1650
+    },
+    {
+      "epoch": 2.3734729493891797,
+      "grad_norm": 0.1360396295785904,
+      "learning_rate": 1.2353940501334881e-05,
+      "loss": 0.5454,
+      "step": 1700
+    },
+    {
+      "epoch": 2.4432809773123907,
+      "grad_norm": 0.14707745611667633,
+      "learning_rate": 8.633234017856605e-06,
+      "loss": 0.5348,
+      "step": 1750
+    },
+    {
+      "epoch": 2.513089005235602,
+      "grad_norm": 0.14276111125946045,
+      "learning_rate": 5.55373272568495e-06,
+      "loss": 0.536,
+      "step": 1800
+    },
+    {
+      "epoch": 2.5828970331588135,
+      "grad_norm": 0.1366841048002243,
+      "learning_rate": 3.1364727412186366e-06,
+      "loss": 0.5539,
+      "step": 1850
+    },
+    {
+      "epoch": 2.6527050610820244,
+      "grad_norm": 0.13850563764572144,
+      "learning_rate": 1.3979664012209619e-06,
+      "loss": 0.5315,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7225130890052354,
+      "grad_norm": 0.14939691126346588,
+      "learning_rate": 3.5008946681634066e-07,
+      "loss": 0.5427,
+      "step": 1950
+    },
+    {
+      "epoch": 2.7923211169284468,
+      "grad_norm": 0.1333276331424713,
+      "learning_rate": 0.0,
+      "loss": 0.5481,
+      "step": 2000
+    },
+    {
+      "epoch": 2.7923211169284468,
+      "eval_loss": 0.7064644694328308,
+      "eval_runtime": 49.5157,
+      "eval_samples_per_second": 24.376,
+      "eval_steps_per_second": 6.099,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -263,7 +341,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -272,12 +350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.1436960280582554e+17,
+  "total_flos": 6.856951542369485e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null