Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334c486ae7a9ec594d6cfbc08974813365d74f826bb2fdfaf626162f2d0159fb
+oid sha256:63d4bb6a956fb56cd0088dc28547952d24c08f2eb86d2aec9d4b21483adb9177
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b55ec3d86252fd387d6c009c1bdf36fb7f41fddcf6b88277b42c1126ff809d
+oid sha256:8bc10445b82405fb6d37d22c7fe973fefbd6d5e7a4eae5c80f3b4858a86a96da
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83137896c579d86619217aca9c0b81561f6e1913616a6fe74d20b7182e4287f
+oid sha256:d872420bc3dc74bb7836dfa2f4957583cebe65bc0ce2ca2cd3f24b22a86bb602
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
+oid sha256:f924e37bc06756f5535d9fa2079568e2b7869291abee642e58937943662c2f6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6834224462509155,
-  "best_model_checkpoint": "miner_id_24/checkpoint-30",
-  "epoch": 0.008471584892340275,
+  "best_metric": 1.6503487825393677,
+  "best_model_checkpoint": "miner_id_24/checkpoint-40",
+  "epoch": 0.011295446523120367,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 5.597,
       "eval_steps_per_second": 5.597,
       "step": 30
+    },
+    {
+      "epoch": 0.008753971055418284,
+      "grad_norm": 2.855771780014038,
+      "learning_rate": 0.00019909497617679348,
+      "loss": 2.608,
+      "step": 31
+    },
+    {
+      "epoch": 0.009036357218496294,
+      "grad_norm": 2.0999650955200195,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 1.6182,
+      "step": 32
+    },
+    {
+      "epoch": 0.009318743381574303,
+      "grad_norm": 5.745433330535889,
+      "learning_rate": 0.00019891470916809362,
+      "loss": 1.6578,
+      "step": 33
+    },
+    {
+      "epoch": 0.009601129544652313,
+      "grad_norm": 1.7802093029022217,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 1.8047,
+      "step": 34
+    },
+    {
+      "epoch": 0.009883515707730321,
+      "grad_norm": 3.094785451889038,
+      "learning_rate": 0.00019871817834144504,
+      "loss": 1.2005,
+      "step": 35
+    },
+    {
+      "epoch": 0.01016590187080833,
+      "grad_norm": 2.3366200923919678,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 2.0731,
+      "step": 36
+    },
+    {
+      "epoch": 0.01044828803388634,
+      "grad_norm": 3.872102737426758,
+      "learning_rate": 0.0001985054160109657,
+      "loss": 1.301,
+      "step": 37
+    },
+    {
+      "epoch": 0.010730674196964348,
+      "grad_norm": 1.3710724115371704,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 1.4742,
+      "step": 38
+    },
+    {
+      "epoch": 0.011013060360042359,
+      "grad_norm": 2.481275796890259,
+      "learning_rate": 0.0001982764571596004,
+      "loss": 1.5866,
+      "step": 39
+    },
+    {
+      "epoch": 0.011295446523120367,
+      "grad_norm": 1.8309324979782104,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 2.644,
+      "step": 40
+    },
+    {
+      "epoch": 0.011295446523120367,
+      "eval_loss": 1.6503487825393677,
+      "eval_runtime": 133.397,
+      "eval_samples_per_second": 5.592,
+      "eval_steps_per_second": 5.592,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -277,7 +355,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2936410755563520.0,
+  "total_flos": 3915214340751360.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null