Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83875137c473511da80a7e9b2c6375a0243a9fea212fbd5f1e892675f7539045
+oid sha256:15c9aa04c5d6b5a03dd2696ae36aadb2da6cac50c5a7b145084a2e002c80a44c
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8fcf922766afb18b246988432fbf2713f1487ff06e4e3d59affaa4d237b0efc
+oid sha256:aaf8689668f98f2b89523ad25888e1ab68b80fab03c31a15aec4a90c05bd3246
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d65451a88d96f0e282b793194a37648567fbfaea3cd05721c075094d356009c
+oid sha256:d81df46d5beccd06d575ff72725694bf54fb1af2308e2a38ddbdae03736b8b97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f673918b3641ca0342aa47ce45010c684a5fac2142097d110b2ca78c569b0097
+oid sha256:0711ecb8f843d07ec959077df5e61b9300d0397ab0a5cd166f54e19b46bfe705
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0107fc855788c2711a6b7df2937ef846cfde92ed61ffe1330f5c611daafdc891
+oid sha256:83481c57f9c0c7bc2334b3318b50542ee1915e3c0caf7da0b064bd7f81c0ef8d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17882ba7b494d650207cb1c356457a9baaa8dbeffea46a84a74642d81edd9f6
+oid sha256:8db908e2615b0119f98b87af3e9197021094049847059061fbd4bee6ca7d2145
 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": 0.09947963058948517,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01533918779000652,
+  "best_metric": 0.06400035321712494,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03067837558001304,
   "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": 11.346,
       "eval_steps_per_second": 2.95,
       "step": 25
+    },
+    {
+      "epoch": 0.01595275530160678,
+      "grad_norm": 0.25747811794281006,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0904,
+      "step": 26
+    },
+    {
+      "epoch": 0.01656632281320704,
+      "grad_norm": 0.23223653435707092,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.067,
+      "step": 27
+    },
+    {
+      "epoch": 0.017179890324807302,
+      "grad_norm": 0.18984195590019226,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0735,
+      "step": 28
+    },
+    {
+      "epoch": 0.017793457836407563,
+      "grad_norm": 0.2101801037788391,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0738,
+      "step": 29
+    },
+    {
+      "epoch": 0.018407025348007824,
+      "grad_norm": 0.21006661653518677,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0833,
+      "step": 30
+    },
+    {
+      "epoch": 0.019020592859608085,
+      "grad_norm": 0.1932811439037323,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0652,
+      "step": 31
+    },
+    {
+      "epoch": 0.019634160371208343,
+      "grad_norm": 0.19555415213108063,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0696,
+      "step": 32
+    },
+    {
+      "epoch": 0.020247727882808604,
+      "grad_norm": 0.24109168350696564,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0879,
+      "step": 33
+    },
+    {
+      "epoch": 0.020861295394408865,
+      "grad_norm": 0.22455033659934998,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0833,
+      "step": 34
+    },
+    {
+      "epoch": 0.021474862906009126,
+      "grad_norm": 0.25285103917121887,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0943,
+      "step": 35
+    },
+    {
+      "epoch": 0.022088430417609387,
+      "grad_norm": 0.2642708718776703,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0727,
+      "step": 36
+    },
+    {
+      "epoch": 0.022701997929209648,
+      "grad_norm": 0.29292234778404236,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0934,
+      "step": 37
+    },
+    {
+      "epoch": 0.02331556544080991,
+      "grad_norm": 0.20500828325748444,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0737,
+      "step": 38
+    },
+    {
+      "epoch": 0.02392913295241017,
+      "grad_norm": 0.14348016679286957,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.049,
+      "step": 39
+    },
+    {
+      "epoch": 0.02454270046401043,
+      "grad_norm": 0.17976398766040802,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.066,
+      "step": 40
+    },
+    {
+      "epoch": 0.025156267975610692,
+      "grad_norm": 0.1790475845336914,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0617,
+      "step": 41
+    },
+    {
+      "epoch": 0.025769835487210953,
+      "grad_norm": 0.17942076921463013,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0621,
+      "step": 42
+    },
+    {
+      "epoch": 0.026383402998811215,
+      "grad_norm": 0.15874969959259033,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0568,
+      "step": 43
+    },
+    {
+      "epoch": 0.026996970510411472,
+      "grad_norm": 0.17187748849391937,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0622,
+      "step": 44
+    },
+    {
+      "epoch": 0.027610538022011733,
+      "grad_norm": 0.18186913430690765,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.067,
+      "step": 45
+    },
+    {
+      "epoch": 0.028224105533611994,
+      "grad_norm": 0.2198343127965927,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0678,
+      "step": 46
+    },
+    {
+      "epoch": 0.028837673045212255,
+      "grad_norm": 0.22388826310634613,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0699,
+      "step": 47
+    },
+    {
+      "epoch": 0.029451240556812516,
+      "grad_norm": 0.21301940083503723,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0719,
+      "step": 48
+    },
+    {
+      "epoch": 0.030064808068412777,
+      "grad_norm": 0.2947802245616913,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0896,
+      "step": 49
+    },
+    {
+      "epoch": 0.03067837558001304,
+      "grad_norm": 0.3046525716781616,
+      "learning_rate": 1e-05,
+      "loss": 0.0936,
+      "step": 50
+    },
+    {
+      "epoch": 0.03067837558001304,
+      "eval_loss": 0.06400035321712494,
+      "eval_runtime": 4.4283,
+      "eval_samples_per_second": 11.291,
+      "eval_steps_per_second": 2.936,
+      "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": 1.327074698592256e+17,
+  "total_flos": 2.654149397184512e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null