Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ad28e04697f14853133a90e86617947450e04231df6fcdeba767536df7368a
+oid sha256:a4dee134c226d4ed060b7d0b5ecd32f0f5a8ce700d7331a1c45a1684fe665953
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bdc509809155cdf7c480d70335ff7ea69867b3988a3612d75787ad8c7eb3062
+oid sha256:f8739ff899a2b924b1cf0d5127c42a479549401afd031bd60d911b5102bdabcb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8237693309783936,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.010686615014694095,
+  "best_metric": 0.8120872974395752,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.013358268768367619,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 4.599,
       "eval_steps_per_second": 2.299,
       "step": 20
+    },
+    {
+      "epoch": 0.0112209457654288,
+      "grad_norm": 4.862582206726074,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.1713,
+      "step": 21
+    },
+    {
+      "epoch": 0.011755276516163505,
+      "grad_norm": 4.579098701477051,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.1525,
+      "step": 22
+    },
+    {
+      "epoch": 0.01228960726689821,
+      "grad_norm": 4.197018146514893,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.01,
+      "step": 23
+    },
+    {
+      "epoch": 0.012823938017632914,
+      "grad_norm": 4.057913780212402,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.2771,
+      "step": 24
+    },
+    {
+      "epoch": 0.013358268768367619,
+      "grad_norm": 4.654407501220703,
+      "learning_rate": 0.0,
+      "loss": 3.787,
+      "step": 25
+    },
+    {
+      "epoch": 0.013358268768367619,
+      "eval_loss": 0.8120872974395752,
+      "eval_runtime": 170.5567,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 2.31,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6514932543651840.0,
+  "total_flos": 8143665679564800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null