Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a7284d0e11871a350ac5d939321229ab55cb211612d2ac8b32c6e70312f13c
+oid sha256:7463bcd4fd42150745138111e1d0b4b77bbe13013dbfdfb5d370fe405b6df246
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c1a5a2fbb2a08df0c1180773dcaffdf4c6db55e7afb5be462e4f0195e13ead
+oid sha256:a36c68cbcb5937fa30b72750a6b6c4e231bb3fa601c9793b4e6e8610ca907a21
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3555740ff382a0e4772feccb4023f6f5cdb024bffa07820bce3ebe4ca5b926f
+oid sha256:c6ca220e642fd937c4a5e16e89ad5ec5e42cb15c409690878d58b7f67da9c16a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a649bafa241e79f6fff150a4ecb163e9436db59059b9eca740481da71c7b3c
+oid sha256:5cbff54d28e0a79a6f03aeea36c496c3d38f6abad6a0c2e1a44325fe81da5c67
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c599c987842ce3e633969d7853cf6db5d02f7373c4fd7add216273b1fb870f8c
+oid sha256:f73a9ed48d2e7bd4d7da2edd37c167ab601afc261ff50f7577a20eeccf77797b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1cd0f454fbcce7987577ccf5a957dcba755cce4d6ee2f8d4c1229e39fd7e4a
+oid sha256:b6303f8db370731415f18bd040ba6a08fb3b7f1071b517e277ccc8d3da8c612b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6592954993247986,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9501187648456056,
+  "best_metric": 0.6442148685455322,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9002375296912115,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 15.6,
       "eval_steps_per_second": 4.056,
       "step": 25
+    },
+    {
+      "epoch": 0.9881235154394299,
+      "grad_norm": 0.38394269347190857,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7256,
+      "step": 26
+    },
+    {
+      "epoch": 1.0261282660332542,
+      "grad_norm": 0.27747994661331177,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9868,
+      "step": 27
+    },
+    {
+      "epoch": 1.0641330166270784,
+      "grad_norm": 0.12342102080583572,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4239,
+      "step": 28
+    },
+    {
+      "epoch": 1.1021377672209025,
+      "grad_norm": 0.15006037056446075,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5403,
+      "step": 29
+    },
+    {
+      "epoch": 1.1401425178147269,
+      "grad_norm": 0.16108109056949615,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4129,
+      "step": 30
+    },
+    {
+      "epoch": 1.178147268408551,
+      "grad_norm": 0.21113452315330505,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4638,
+      "step": 31
+    },
+    {
+      "epoch": 1.2161520190023754,
+      "grad_norm": 0.2221778929233551,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5473,
+      "step": 32
+    },
+    {
+      "epoch": 1.2541567695961995,
+      "grad_norm": 0.16844679415225983,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5633,
+      "step": 33
+    },
+    {
+      "epoch": 1.2921615201900236,
+      "grad_norm": 0.1440643072128296,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5656,
+      "step": 34
+    },
+    {
+      "epoch": 1.330166270783848,
+      "grad_norm": 0.133246511220932,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4032,
+      "step": 35
+    },
+    {
+      "epoch": 1.3681710213776723,
+      "grad_norm": 0.15566648542881012,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.411,
+      "step": 36
+    },
+    {
+      "epoch": 1.4061757719714965,
+      "grad_norm": 0.17614296078681946,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3639,
+      "step": 37
+    },
+    {
+      "epoch": 1.4441805225653206,
+      "grad_norm": 0.2360568791627884,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6141,
+      "step": 38
+    },
+    {
+      "epoch": 1.482185273159145,
+      "grad_norm": 0.27539122104644775,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.698,
+      "step": 39
+    },
+    {
+      "epoch": 1.520190023752969,
+      "grad_norm": 0.18563823401927948,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4828,
+      "step": 40
+    },
+    {
+      "epoch": 1.5581947743467932,
+      "grad_norm": 0.1377231478691101,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3974,
+      "step": 41
+    },
+    {
+      "epoch": 1.5961995249406176,
+      "grad_norm": 0.1511758714914322,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4339,
+      "step": 42
+    },
+    {
+      "epoch": 1.634204275534442,
+      "grad_norm": 0.16694828867912292,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.407,
+      "step": 43
+    },
+    {
+      "epoch": 1.672209026128266,
+      "grad_norm": 0.22149711847305298,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5053,
+      "step": 44
+    },
+    {
+      "epoch": 1.7102137767220902,
+      "grad_norm": 0.2526493966579437,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5899,
+      "step": 45
+    },
+    {
+      "epoch": 1.7482185273159145,
+      "grad_norm": 0.17709076404571533,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.41,
+      "step": 46
+    },
+    {
+      "epoch": 1.7862232779097387,
+      "grad_norm": 0.1758945733308792,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6798,
+      "step": 47
+    },
+    {
+      "epoch": 1.8242280285035628,
+      "grad_norm": 0.14024008810520172,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4317,
+      "step": 48
+    },
+    {
+      "epoch": 1.8622327790973872,
+      "grad_norm": 0.15684950351715088,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4303,
+      "step": 49
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "grad_norm": 0.16915641725063324,
+      "learning_rate": 1e-05,
+      "loss": 0.3758,
+      "step": 50
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "eval_loss": 0.6442148685455322,
+      "eval_runtime": 3.237,
+      "eval_samples_per_second": 15.446,
+      "eval_steps_per_second": 4.016,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null