Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c017c3e7399d8ead08a3bb745bd56b594f68fb299a8ceb054c0df350e753f7
+oid sha256:75af2c56b5da59a4d6c99559eef7f4536c44a45fbb6f55daea2e88115d9fee2e
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5372e90507d313aee5726f45d4ac32a57ac726dcc7db535da7c2c7c2a1aa8c
+oid sha256:d917f7ac83950a454d50ceaa18445bc6ec934e9fa7a59cf941eab779d0d5bcf9
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973cb9c31f34267369ffd901bd9098fd8f4cb03b37083277b617aa82784f0094
+oid sha256:ab30765be6f3fc06f48afc18afbac7a60f85012715b51fd034866fd7d34a3e1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baec16f1d3203641053b140012c961fd8b8e1dac231c353313afb13a49c1d1fe
+oid sha256:d9d4e004ca157e9e2e51f06820328f72b00d1e93f5fe5770010a13d46b658813
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.7592430114746094,
   "best_model_checkpoint": "miner_id_24/checkpoint-1350",
-  "epoch": 0.026067563262114176,
+  "epoch": 0.028963959180126862,
   "eval_steps": 150,
-  "global_step": 1350,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1032,6 +1032,119 @@
       "eval_samples_per_second": 133.451,
       "eval_steps_per_second": 33.363,
       "step": 1350
+    },
+    {
+      "epoch": 0.02626065632331502,
+      "grad_norm": 10.175602912902832,
+      "learning_rate": 0.0001,
+      "loss": 10.0645,
+      "step": 1360
+    },
+    {
+      "epoch": 0.026453749384515866,
+      "grad_norm": 13.354422569274902,
+      "learning_rate": 0.0001,
+      "loss": 9.9626,
+      "step": 1370
+    },
+    {
+      "epoch": 0.026646842445716714,
+      "grad_norm": 14.017874717712402,
+      "learning_rate": 0.0001,
+      "loss": 10.6526,
+      "step": 1380
+    },
+    {
+      "epoch": 0.02683993550691756,
+      "grad_norm": 15.533336639404297,
+      "learning_rate": 0.0001,
+      "loss": 11.3396,
+      "step": 1390
+    },
+    {
+      "epoch": 0.027033028568118404,
+      "grad_norm": 21.672401428222656,
+      "learning_rate": 0.0001,
+      "loss": 13.0943,
+      "step": 1400
+    },
+    {
+      "epoch": 0.027226121629319252,
+      "grad_norm": 11.563956260681152,
+      "learning_rate": 0.0001,
+      "loss": 10.1492,
+      "step": 1410
+    },
+    {
+      "epoch": 0.027419214690520097,
+      "grad_norm": 9.616212844848633,
+      "learning_rate": 0.0001,
+      "loss": 10.1169,
+      "step": 1420
+    },
+    {
+      "epoch": 0.02761230775172094,
+      "grad_norm": 14.188048362731934,
+      "learning_rate": 0.0001,
+      "loss": 10.3995,
+      "step": 1430
+    },
+    {
+      "epoch": 0.027805400812921786,
+      "grad_norm": 13.804783821105957,
+      "learning_rate": 0.0001,
+      "loss": 11.1481,
+      "step": 1440
+    },
+    {
+      "epoch": 0.027998493874122635,
+      "grad_norm": 23.23021125793457,
+      "learning_rate": 0.0001,
+      "loss": 13.1522,
+      "step": 1450
+    },
+    {
+      "epoch": 0.02819158693532348,
+      "grad_norm": 7.562139511108398,
+      "learning_rate": 0.0001,
+      "loss": 10.1138,
+      "step": 1460
+    },
+    {
+      "epoch": 0.028384679996524324,
+      "grad_norm": 26.057680130004883,
+      "learning_rate": 0.0001,
+      "loss": 9.7856,
+      "step": 1470
+    },
+    {
+      "epoch": 0.02857777305772517,
+      "grad_norm": 12.248312950134277,
+      "learning_rate": 0.0001,
+      "loss": 10.4052,
+      "step": 1480
+    },
+    {
+      "epoch": 0.028770866118926017,
+      "grad_norm": 14.60325813293457,
+      "learning_rate": 0.0001,
+      "loss": 11.6516,
+      "step": 1490
+    },
+    {
+      "epoch": 0.028963959180126862,
+      "grad_norm": 52.02046585083008,
+      "learning_rate": 0.0001,
+      "loss": 13.2193,
+      "step": 1500
+    },
+    {
+      "epoch": 0.028963959180126862,
+      "eval_loss": 2.770695209503174,
+      "eval_runtime": 330.0972,
+      "eval_samples_per_second": 132.119,
+      "eval_steps_per_second": 33.03,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -1046,7 +1159,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1055,12 +1168,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.785147236856627e+16,
+  "total_flos": 3.0944605381853184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null