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:e7866a6e304b10d3e47c04a8ec454021944e84301a8ee223a129d207642dbede
+oid sha256:49d74417c72b513d211aa350c50f57e08acf62dc6dcaba61a8f281c4b048ca1e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a08d0678848ef1502868d6a5fed74a90a07eeab284495a2c60baa261f772fef1
+oid sha256:70fbbc7f94322dce4268fb104aeb39c23f2a3740f9fdb38ba544ada54fe923c4
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
+oid sha256:e04d45842b4f57f7bc47c4b705d580a46ba323787f21a23ed4c2131d727599bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.3242831230163574,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00024053856584893576,
+  "best_metric": 3.3202874660491943,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0003006732073111697,
   "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": 14.785,
       "eval_steps_per_second": 7.393,
       "step": 20
+    },
+    {
+      "epoch": 0.00025256549414138255,
+      "grad_norm": 13.951614379882812,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 12.6384,
+      "step": 21
+    },
+    {
+      "epoch": 0.00026459242243382936,
+      "grad_norm": 18.604524612426758,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 15.5242,
+      "step": 22
+    },
+    {
+      "epoch": 0.0002766193507262761,
+      "grad_norm": 13.222647666931152,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 12.8506,
+      "step": 23
+    },
+    {
+      "epoch": 0.00028864627901872294,
+      "grad_norm": 20.68111801147461,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 12.2694,
+      "step": 24
+    },
+    {
+      "epoch": 0.0003006732073111697,
+      "grad_norm": 11.827173233032227,
+      "learning_rate": 0.0,
+      "loss": 13.7271,
+      "step": 25
+    },
+    {
+      "epoch": 0.0003006732073111697,
+      "eval_loss": 3.3202874660491943,
+      "eval_runtime": 2368.1373,
+      "eval_samples_per_second": 14.784,
+      "eval_steps_per_second": 7.392,
+      "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": 3257498484080640.0,
+  "total_flos": 4071873105100800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null