Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2d442e705a8a4ced55fc52cc592a8896d779e3c89a3c29dbc55eb8931e86c8
+oid sha256:b4bd09422d0b7c8fdc05ed63dd6b8493b020643b78cc39e4976e0a4106fb2c8f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e93903215ac814e19d289e9743c4d33ebe36034e3eee390cd5e82fac9242ba
+oid sha256:a737277efd53be2b08084ad09925b57e5ecf8596dc26bca3cf7ea00720d0b72e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09ed8f3813d419cdd237f1c086b98663614daa503511765ffb887c799052057
+oid sha256:788ce74773dc097a02db174c1b76a451d4de773159aa59d9363addfc5e09e076
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8386927247047424,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016858786588835268,
+  "best_metric": 0.8302116394042969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00252881798832529,
   "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": 17.557,
       "eval_steps_per_second": 4.39,
       "step": 20
+    },
+    {
+      "epoch": 0.0017701725918277031,
+      "grad_norm": 0.3175795376300812,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 0.8545,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020230543906602323,
+      "grad_norm": 0.3080345094203949,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 0.8205,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021073483236044087,
+      "eval_loss": 0.8314608335494995,
+      "eval_runtime": 569.5242,
+      "eval_samples_per_second": 17.541,
+      "eval_steps_per_second": 4.386,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022759361894927614,
+      "grad_norm": 0.2943112552165985,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 0.8416,
+      "step": 27
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "grad_norm": 0.32156476378440857,
+      "learning_rate": 0.0,
+      "loss": 0.8636,
+      "step": 30
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "eval_loss": 0.8302116394042969,
+      "eval_runtime": 568.427,
+      "eval_samples_per_second": 17.575,
+      "eval_steps_per_second": 4.395,
+      "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": 1.6276165383684096e+16,
+  "total_flos": 2.3674422376267776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null