Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191485769db511e2d03518326bc4aad5e5ba6bd9cb6dd525349577d6b7346d7b
+oid sha256:3dcaefdc18640997eeca15e9952a1e590618dd74bf3106579b85b7b1e706bf06
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d5f7cadf903b7cd25cc888a5a24759b018f20952f97fdc7d5af0f265ec7300
+oid sha256:0729761e2be19d3c6838c7f5f0f378a7f07ac877805c9f7ab3151216f72a9170
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03730fc10f9461c04974b9d8cd2c7da3024fffee67d8ea7e1ae031f9229042c
+oid sha256:5121dc2e2ef6c98bf0f8ee6bc71f1273cca40449466010f399173a3a0c9d6c31
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2615bc5002f66094203b3e57b1ad2bd8475d057eeffafba3d6f33c68c21dba32
+oid sha256:1572e47d51979a342631144ad9588005719a26ee885694d1a7485467fe1daf3a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b968082b68d7828ca11b326e25ebfcdf13504c4fa5266b1539816e57dcdb64
+oid sha256:6b580ee43dbeca36deaf736e147b19961f6506422fccdcd2f92baffc5f2f8fa1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d75de72583b180d80c9641550a1c9538593dbda8492def752849dcb62f87ae
+oid sha256:2acc882d0e7505daf9325401f166d9baa71830e8598eea2d1124f60d5e246563
 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": 9.246109962463379,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11782032400589101,
+  "best_metric": 8.976583480834961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.23564064801178203,
   "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": 178.563,
       "eval_steps_per_second": 46.426,
       "step": 25
+    },
+    {
+      "epoch": 0.12253313696612665,
+      "grad_norm": 2.965689182281494,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 9.37,
+      "step": 26
+    },
+    {
+      "epoch": 0.1272459499263623,
+      "grad_norm": 2.868656873703003,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 9.3271,
+      "step": 27
+    },
+    {
+      "epoch": 0.13195876288659794,
+      "grad_norm": 2.586918592453003,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.2831,
+      "step": 28
+    },
+    {
+      "epoch": 0.13667157584683357,
+      "grad_norm": 2.540886402130127,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 9.2554,
+      "step": 29
+    },
+    {
+      "epoch": 0.14138438880706922,
+      "grad_norm": 2.4895763397216797,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 9.2658,
+      "step": 30
+    },
+    {
+      "epoch": 0.14609720176730487,
+      "grad_norm": 2.181830406188965,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 9.2177,
+      "step": 31
+    },
+    {
+      "epoch": 0.1508100147275405,
+      "grad_norm": 2.153486967086792,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.2031,
+      "step": 32
+    },
+    {
+      "epoch": 0.15552282768777614,
+      "grad_norm": 2.118992805480957,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.194,
+      "step": 33
+    },
+    {
+      "epoch": 0.1602356406480118,
+      "grad_norm": 2.1694352626800537,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.1453,
+      "step": 34
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 2.3047266006469727,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.12,
+      "step": 35
+    },
+    {
+      "epoch": 0.16966126656848307,
+      "grad_norm": 2.5099029541015625,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.1125,
+      "step": 36
+    },
+    {
+      "epoch": 0.1743740795287187,
+      "grad_norm": 2.925784111022949,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 9.078,
+      "step": 37
+    },
+    {
+      "epoch": 0.17908689248895435,
+      "grad_norm": 2.911679267883301,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 9.1566,
+      "step": 38
+    },
+    {
+      "epoch": 0.18379970544919,
+      "grad_norm": 2.5921273231506348,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 9.1378,
+      "step": 39
+    },
+    {
+      "epoch": 0.18851251840942562,
+      "grad_norm": 2.3401689529418945,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 9.1303,
+      "step": 40
+    },
+    {
+      "epoch": 0.19322533136966127,
+      "grad_norm": 2.2154057025909424,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 9.1271,
+      "step": 41
+    },
+    {
+      "epoch": 0.1979381443298969,
+      "grad_norm": 2.124439001083374,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.1033,
+      "step": 42
+    },
+    {
+      "epoch": 0.20265095729013255,
+      "grad_norm": 1.984527349472046,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.1068,
+      "step": 43
+    },
+    {
+      "epoch": 0.2073637702503682,
+      "grad_norm": 1.848252773284912,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.0778,
+      "step": 44
+    },
+    {
+      "epoch": 0.21207658321060383,
+      "grad_norm": 1.807987093925476,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.0737,
+      "step": 45
+    },
+    {
+      "epoch": 0.21678939617083948,
+      "grad_norm": 1.8763501644134521,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.0675,
+      "step": 46
+    },
+    {
+      "epoch": 0.2215022091310751,
+      "grad_norm": 2.026942729949951,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.0569,
+      "step": 47
+    },
+    {
+      "epoch": 0.22621502209131075,
+      "grad_norm": 2.279087543487549,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 9.0495,
+      "step": 48
+    },
+    {
+      "epoch": 0.2309278350515464,
+      "grad_norm": 2.5268728733062744,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 8.9968,
+      "step": 49
+    },
+    {
+      "epoch": 0.23564064801178203,
+      "grad_norm": 4.308773517608643,
+      "learning_rate": 1e-05,
+      "loss": 8.9847,
+      "step": 50
+    },
+    {
+      "epoch": 0.23564064801178203,
+      "eval_loss": 8.976583480834961,
+      "eval_runtime": 0.2765,
+      "eval_samples_per_second": 180.809,
+      "eval_steps_per_second": 47.01,
+      "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": 116224411828224.0,
+  "total_flos": 232376319344640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null