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:c06fb590e60ddd392db607b1cae3bfcee354de7b2ff782b294207479e147e8c8
+oid sha256:f3ccfe60a91a30815b38b41c0641378011d729c83583841bba42f1957fac161c
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436b868083c2e489bab3e43c205166e8d04ca13f12711ab82443ce904ad90cda
+oid sha256:5233e52e9685008c9fdc8b24ea843b5dd255b99d037afac85492d648bc481ae7
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93a77bf72a0da8ea5a4506ca638454b4ac28e53d5303cab1daedaf236a3f0fe
+oid sha256:d9730aeeef29b75de4331e597ce2d40d8ece540432feee07b302fccd35a13f97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa866c6247556e72ee35d12af31555fb90095df62cdc152eee931f34697fa4c
+oid sha256:8e468b881e731beb0aebb6525597a36327e5b1b60745f7592f34dfc383d398bf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ea58bdde309f280d4947ab1bdd9b72bc8106e0b1e7f979ac767f8fc2147843
+oid sha256:032850b1d3c846047bc068cffb5272fd1b72e9471b45f9fced423168531fb7e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3dddf2a762a59ddf5b6a561818e4c6decf9739b734b595aec8c64e02272888
+oid sha256:bef7823225137fcdfd5b738c01217ff8a8ed2300b91ff0fab1d45912bdb7d5ad
 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": 0.015500125475227833,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3929273084479371,
+  "best_metric": 0.013853449374437332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7858546168958742,
   "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": 36.074,
       "eval_steps_per_second": 9.379,
       "step": 25
+    },
+    {
+      "epoch": 0.4086444007858546,
+      "grad_norm": 0.5926785469055176,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0479,
+      "step": 26
+    },
+    {
+      "epoch": 0.4243614931237721,
+      "grad_norm": 0.6671425700187683,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0329,
+      "step": 27
+    },
+    {
+      "epoch": 0.4400785854616896,
+      "grad_norm": 0.5285760164260864,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0533,
+      "step": 28
+    },
+    {
+      "epoch": 0.45579567779960706,
+      "grad_norm": 0.3623944818973541,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0463,
+      "step": 29
+    },
+    {
+      "epoch": 0.4715127701375246,
+      "grad_norm": 0.5695236921310425,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0333,
+      "step": 30
+    },
+    {
+      "epoch": 0.48722986247544203,
+      "grad_norm": 0.2945129871368408,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0318,
+      "step": 31
+    },
+    {
+      "epoch": 0.5029469548133595,
+      "grad_norm": 0.2810068726539612,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0093,
+      "step": 32
+    },
+    {
+      "epoch": 0.518664047151277,
+      "grad_norm": 0.3693678081035614,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0228,
+      "step": 33
+    },
+    {
+      "epoch": 0.5343811394891945,
+      "grad_norm": 0.4901984632015228,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0278,
+      "step": 34
+    },
+    {
+      "epoch": 0.550098231827112,
+      "grad_norm": 0.4526285231113434,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0515,
+      "step": 35
+    },
+    {
+      "epoch": 0.5658153241650294,
+      "grad_norm": 0.16172288358211517,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0156,
+      "step": 36
+    },
+    {
+      "epoch": 0.581532416502947,
+      "grad_norm": 0.5231755375862122,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0803,
+      "step": 37
+    },
+    {
+      "epoch": 0.5972495088408645,
+      "grad_norm": 0.4872123599052429,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0544,
+      "step": 38
+    },
+    {
+      "epoch": 0.6129666011787819,
+      "grad_norm": 0.3213493525981903,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0301,
+      "step": 39
+    },
+    {
+      "epoch": 0.6286836935166994,
+      "grad_norm": 0.2550433278083801,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0187,
+      "step": 40
+    },
+    {
+      "epoch": 0.6444007858546169,
+      "grad_norm": 0.5219851732254028,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0427,
+      "step": 41
+    },
+    {
+      "epoch": 0.6601178781925344,
+      "grad_norm": 0.4075874984264374,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0446,
+      "step": 42
+    },
+    {
+      "epoch": 0.6758349705304518,
+      "grad_norm": 0.39169013500213623,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0152,
+      "step": 43
+    },
+    {
+      "epoch": 0.6915520628683693,
+      "grad_norm": 0.5663002729415894,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0167,
+      "step": 44
+    },
+    {
+      "epoch": 0.7072691552062869,
+      "grad_norm": 0.31401506066322327,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0187,
+      "step": 45
+    },
+    {
+      "epoch": 0.7229862475442044,
+      "grad_norm": 0.16422072052955627,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0208,
+      "step": 46
+    },
+    {
+      "epoch": 0.7387033398821218,
+      "grad_norm": 0.20995976030826569,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0258,
+      "step": 47
+    },
+    {
+      "epoch": 0.7544204322200393,
+      "grad_norm": 0.1727566123008728,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0247,
+      "step": 48
+    },
+    {
+      "epoch": 0.7701375245579568,
+      "grad_norm": 0.3798152804374695,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0236,
+      "step": 49
+    },
+    {
+      "epoch": 0.7858546168958742,
+      "grad_norm": 0.4489036202430725,
+      "learning_rate": 1e-05,
+      "loss": 0.0365,
+      "step": 50
+    },
+    {
+      "epoch": 0.7858546168958742,
+      "eval_loss": 0.013853449374437332,
+      "eval_runtime": 1.361,
+      "eval_samples_per_second": 36.738,
+      "eval_steps_per_second": 9.552,
+      "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": 4.168384167647642e+16,
+  "total_flos": 8.335466128054682e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null