Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec4d16b64e97fe14851d7c0f7f504879ea3791e26a1cbb3d3f6d12fbd7550d1
+oid sha256:b74aca3abd830a4c600c43f3c25d466c4c4950992e8fcd365dd1d160b37c1169
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af2a64eeb60910f68b1401d0a2acebd1b0a3dc993d0dc4c7ea0cdd7d3ed7772
+oid sha256:84ab22c74bf6fd1ebf35ac5758b27dfee8d482a1a12653ce59b7a0296ba4f587
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a9613e0a9d0dc6ae85b4c4c50f9e62a145a6679e90b61f25acf88255527641
+oid sha256:3ae61aba6579edfb9eba13e61ab3bf344b75a00ad1c3c06a989fc733682d10cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9371713995933533,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011534025374855825,
+  "epoch": 0.02306805074971165,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 7.786,
       "eval_steps_per_second": 3.903,
       "step": 10
+    },
+    {
+      "epoch": 0.012687427912341407,
+      "grad_norm": 11.846580505371094,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 7.6904,
+      "step": 11
+    },
+    {
+      "epoch": 0.01384083044982699,
+      "grad_norm": 13.611588478088379,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 7.6595,
+      "step": 12
+    },
+    {
+      "epoch": 0.014994232987312572,
+      "grad_norm": 11.388413429260254,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.1619,
+      "step": 13
+    },
+    {
+      "epoch": 0.016147635524798153,
+      "grad_norm": 19.5468692779541,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 9.2642,
+      "step": 14
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 14.181943893432617,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.5677,
+      "step": 15
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "eval_loss": 0.9599310755729675,
+      "eval_runtime": 46.7023,
+      "eval_samples_per_second": 7.815,
+      "eval_steps_per_second": 3.918,
+      "step": 15
+    },
+    {
+      "epoch": 0.01845444059976932,
+      "grad_norm": 9.632269859313965,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.5528,
+      "step": 16
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 17.34568977355957,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.4251,
+      "step": 17
+    },
+    {
+      "epoch": 0.020761245674740483,
+      "grad_norm": 7.927713871002197,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.3126,
+      "step": 18
+    },
+    {
+      "epoch": 0.02191464821222607,
+      "grad_norm": 12.441452026367188,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.3106,
+      "step": 19
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 10.368983268737793,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.2319,
+      "step": 20
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "eval_loss": 0.9381071925163269,
+      "eval_runtime": 46.7881,
+      "eval_samples_per_second": 7.801,
+      "eval_steps_per_second": 3.911,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 888206052556800.0,
+  "total_flos": 1758647984062464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null