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:de2b80d743d84dfc95087b8d95dd2d96a45629c605263dd395bb3fe7b17d8532
+oid sha256:f6e65f05921390b3e0d2f015273d805967b04c62b25510a90660b64d1b48f669
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998c8e1f9c5c448e73afa3bb99869e1b3d3dd32426cc7a1b38fb046b0c808fc6
+oid sha256:93ceaaa3e4bd251c6e95c88be4a0bf84325c3ce4456d47dd1ce2445a375b7db6
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 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": 0.5038738250732422,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006267333093085565,
+  "best_metric": 0.48346415162086487,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0009400999639628347,
   "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": 8.727,
       "eval_steps_per_second": 4.364,
       "step": 20
+    },
+    {
+      "epoch": 0.0006580699747739844,
+      "grad_norm": 2.3658816814422607,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.1017,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007520799711702678,
+      "grad_norm": 2.807095766067505,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9288,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007834166366356955,
+      "eval_loss": 0.494514137506485,
+      "eval_runtime": 1534.5866,
+      "eval_samples_per_second": 8.756,
+      "eval_steps_per_second": 4.378,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008460899675665512,
+      "grad_norm": 2.62199068069458,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.1245,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009400999639628347,
+      "grad_norm": 1.7253998517990112,
+      "learning_rate": 0.0,
+      "loss": 1.8598,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009400999639628347,
+      "eval_loss": 0.48346415162086487,
+      "eval_runtime": 1545.4135,
+      "eval_samples_per_second": 8.695,
+      "eval_steps_per_second": 4.348,
+      "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": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null