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:a2909979e9faad9ee03baf014804815ef1335d4e1aca990f4f5d21fe09b77577
+oid sha256:e57ffce39ef627cfe4cae7613a59ca678e7de0461218a561b6d0caa375f3b1c4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952d9a073ae7f45ae1eb0ce9493f09b9c1e4264c1be9ce53434cb8a0ebd6c03e
+oid sha256:535ff122d5358adf0a3469d6e2892463598aafe35b8c15d075c6821f4886de89
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180310b640506faf41b71a75e1250a78b73eba492592ab7d74e5959e95609bf4
+oid sha256:32425b888a312319e7383b8d70e433a197e400224e856df2f82780d0e6fb29aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2043137550354004,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0038218994840435697,
+  "best_metric": 2.195990800857544,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005732849226065355,
   "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": 6.69,
       "eval_steps_per_second": 3.345,
       "step": 20
+    },
+    {
+      "epoch": 0.004012994458245748,
+      "grad_norm": 0.6142160892486572,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.176,
+      "step": 21
+    },
+    {
+      "epoch": 0.004586279380852283,
+      "grad_norm": 0.7290622591972351,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0933,
+      "step": 24
+    },
+    {
+      "epoch": 0.004777374355054462,
+      "eval_loss": 2.197537660598755,
+      "eval_runtime": 329.6748,
+      "eval_samples_per_second": 6.685,
+      "eval_steps_per_second": 3.343,
+      "step": 25
+    },
+    {
+      "epoch": 0.005159564303458819,
+      "grad_norm": 0.5822762250900269,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0678,
+      "step": 27
+    },
+    {
+      "epoch": 0.005732849226065355,
+      "grad_norm": 0.703194260597229,
+      "learning_rate": 0.0,
+      "loss": 2.2373,
+      "step": 30
+    },
+    {
+      "epoch": 0.005732849226065355,
+      "eval_loss": 2.195990800857544,
+      "eval_runtime": 330.0284,
+      "eval_samples_per_second": 6.678,
+      "eval_steps_per_second": 3.339,
+      "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": 8346231940055040.0,
+  "total_flos": 1.2612083820527616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null