Training in progress, step 547, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba3a9c8daa4bdd1e58028a57631ab9c6677819c890282b6e771c9f4e453820e
+oid sha256:7c56401c5e3fc86419d48de1cc99bcf3059b6b2cc7c8ac93d54e779d71019847
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77f30fc7d4d2a0f3c13953f1483910cb776aeb74503dc67517e33f2a8699ffa
+oid sha256:86334b328c56e2d5a9e3f1ae6382f96c9d62d87b13ac1c2e5f6cf6724664fd79
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e085fde017ec5c64b8d00529e5946a3fdd2cc2b597c7b3cf7373c02ad0c4c8b
+oid sha256:a57af447cd6f38421f2a08b9c33ca21be0092487897eea84e8bb352a10ec5de0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2b145cc02354c01563cd3053c6b3f03d7f93c87dfd6b3852b83f2c8fa5f1fd
+oid sha256:09e993d6d0decca6557382fb23f4a5c12589ee11e4e8e3addd876b8b9972e94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.3164701461792,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.823045267489712,
+  "epoch": 1.0004572473708275,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 547,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,6 +354,69 @@
       "eval_samples_per_second": 648.792,
       "eval_steps_per_second": 162.726,
       "step": 450
+    },
+    {
+      "epoch": 0.8413351623228167,
+      "grad_norm": 0.06713691353797913,
+      "learning_rate": 7.3721207795187876e-06,
+      "loss": 10.3323,
+      "step": 460
+    },
+    {
+      "epoch": 0.8596250571559213,
+      "grad_norm": 0.06836876273155212,
+      "learning_rate": 5.806543362721945e-06,
+      "loss": 10.3244,
+      "step": 470
+    },
+    {
+      "epoch": 0.877914951989026,
+      "grad_norm": 0.0769273117184639,
+      "learning_rate": 4.417488550807386e-06,
+      "loss": 10.3197,
+      "step": 480
+    },
+    {
+      "epoch": 0.8962048468221308,
+      "grad_norm": 0.08537283539772034,
+      "learning_rate": 3.210504666816133e-06,
+      "loss": 10.3179,
+      "step": 490
+    },
+    {
+      "epoch": 0.9144947416552355,
+      "grad_norm": 0.20503534376621246,
+      "learning_rate": 2.1904127850760457e-06,
+      "loss": 10.314,
+      "step": 500
+    },
+    {
+      "epoch": 0.9327846364883402,
+      "grad_norm": 0.07405146211385727,
+      "learning_rate": 1.3612874743103189e-06,
+      "loss": 10.3337,
+      "step": 510
+    },
+    {
+      "epoch": 0.9510745313214449,
+      "grad_norm": 0.07247216254472733,
+      "learning_rate": 7.264405225248294e-07,
+      "loss": 10.3237,
+      "step": 520
+    },
+    {
+      "epoch": 0.9693644261545497,
+      "grad_norm": 0.08077077567577362,
+      "learning_rate": 2.8840770868230894e-07,
+      "loss": 10.3192,
+      "step": 530
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.12774144113063812,
+      "learning_rate": 4.89386740013198e-08,
+      "loss": 10.3162,
+      "step": 540
     }
   ],
   "logging_steps": 10,
@@ -377,12 +440,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 26019191586816.0,
+  "total_flos": 31629841219584.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null