Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1472fd3175b7ecbc2401975708851b9ad53adc2f625f3fff177700cec5b00361
+oid sha256:20265465f47ed40420d027859aeafe6a4a6e4e3e9148bc256769e270576f8336
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719d7757fcb51c761a13bbcccd311357f67f980af9041d6740cf235463842bef
+oid sha256:e0cd321e569cee7371d3bea7258f212c5e15eca62240341d944ef83ce3c8646e
 size 43123028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0a65ddb80c6261e59ab21c6d6bd531c9de851ba7b801b665eb686802ed7f21
+oid sha256:75105a7479ba58f1e99c9a19943e91bb9dadcb2ed4c28f87642caecf60cf2ef3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb61e48d266c471cccd477f025b3f7a3c0435861637d5fe39610779eedceb14
+oid sha256:fe4e625cf5525cf235a8c7e4c6984ba05d1b5436f9e969799dcec0119a3a6c2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3632562160491943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1200",
-  "epoch": 0.25929827404586336,
+  "best_metric": 1.3561660051345825,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
+  "epoch": 0.3241228425573292,
   "eval_steps": 300,
-  "global_step": 1200,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,56 @@
       "eval_samples_per_second": 14.662,
       "eval_steps_per_second": 1.833,
       "step": 1200
+    },
+    {
+      "epoch": 0.2701023687977744,
+      "grad_norm": 0.4282647669315338,
+      "learning_rate": 1.5327580077171587e-05,
+      "loss": 1.3584,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28090646354968535,
+      "grad_norm": 0.4491986930370331,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 1.3788,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2917105583015963,
+      "grad_norm": 0.7209851145744324,
+      "learning_rate": 5.611666969163243e-06,
+      "loss": 1.3648,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3025146530535073,
+      "grad_norm": 0.4760664701461792,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 1.3583,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31331874780541824,
+      "grad_norm": 0.49940499663352966,
+      "learning_rate": 6.287790106757396e-07,
+      "loss": 1.3675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3241228425573292,
+      "grad_norm": 0.4709605276584625,
+      "learning_rate": 0.0,
+      "loss": 1.3532,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3241228425573292,
+      "eval_loss": 1.3561660051345825,
+      "eval_runtime": 1061.9702,
+      "eval_samples_per_second": 14.679,
+      "eval_steps_per_second": 1.835,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -238,12 +288,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.2790924555379016e+18,
+  "total_flos": 4.100668894564319e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null