Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd039ccda2590e10924b6760c58d8d1a796922cf00f12110dac84afd4e330df
+oid sha256:5974e8f07de2f8a6c9348599cb1f69e772da151c4bcbc969e21acf1686699dd6
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10afcaff9681b4e825ed1fd77a99621ebf37f7697375e3349db6e0b302e200e5
+oid sha256:07b9663d48fed935c4bfbc41b9b2bcb7dd68d81715a1f6d2c02acbd89e8baea3
 size 61862

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.931757926940918,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 11.93172550201416,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012759170653907496,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 69.349,
       "eval_steps_per_second": 34.675,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.009563617408275604,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9308,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.01416687574237585,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9324,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 11.931729316711426,
+      "eval_runtime": 13.535,
+      "eval_samples_per_second": 73.144,
+      "eval_steps_per_second": 36.572,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 0.0107727674767375,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9328,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 0.011838309466838837,
+      "learning_rate": 0.0,
+      "loss": 11.9332,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 11.93172550201416,
+      "eval_runtime": 14.3757,
+      "eval_samples_per_second": 68.866,
+      "eval_steps_per_second": 34.433,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7588380672.0,
+  "total_flos": 11335729152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null