Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eff8f0e9ac17e5fa47d404c2581caaab76f16cc575307a32b5574e954dfa089
+oid sha256:a1e29bc5103a8d2b4a3dc0a232f361c4de64e865cc5ad8912f33759000ff3d22
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299cdc7da3ab4bf0d30c231492f0da84220a40fdbce0bf4a02241bd3de26aa30
+oid sha256:869845ffd3167eadd5b75c2da3e160be42059c4bce0453e17a16e0829eaa94ff
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7377b9ace87e5d1348a371868e70db5975a59da41f6f7f9ecea3bfa2375b75
+oid sha256:80d158079de7efdd52b7e3840a54dca21cea7466cc7270a3d6b5a5bafc9fb7f8
 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": 1.7110700607299805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013186088676446349,
+  "best_metric": 1.6694777011871338,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.019779133014669523,
   "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": 6.784,
       "eval_steps_per_second": 3.397,
       "step": 20
+    },
+    {
+      "epoch": 0.013845393110268667,
+      "grad_norm": 12.697035789489746,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.8798,
+      "step": 21
+    },
+    {
+      "epoch": 0.01582330641173562,
+      "grad_norm": 10.777671813964844,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.7368,
+      "step": 24
+    },
+    {
+      "epoch": 0.016482610845557938,
+      "eval_loss": 1.6773645877838135,
+      "eval_runtime": 94.2167,
+      "eval_samples_per_second": 6.782,
+      "eval_steps_per_second": 3.396,
+      "step": 25
+    },
+    {
+      "epoch": 0.01780121971320257,
+      "grad_norm": 10.499444961547852,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.576,
+      "step": 27
+    },
+    {
+      "epoch": 0.019779133014669523,
+      "grad_norm": 10.993064880371094,
+      "learning_rate": 0.0,
+      "loss": 6.6867,
+      "step": 30
+    },
+    {
+      "epoch": 0.019779133014669523,
+      "eval_loss": 1.6694777011871338,
+      "eval_runtime": 94.2006,
+      "eval_samples_per_second": 6.783,
+      "eval_steps_per_second": 3.397,
+      "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": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null