Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14cbefeed138a27b1d9b6bedc5026d1f94da87f0db988ac8fe7bf84078c88cac
+oid sha256:59a8c762beea5f11fc906b8c27b6da658bea429d10e2c430a29c66287f832874
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cd9c9134822c9785c8f33cab9dd121d6187ec405c6fc044112d2339b56bf64
+oid sha256:a6baf6fbf4679ead67304ae886c3cc0932671616540d354e418e12f69f74e55b
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7a0c0065d0ba26cff148c5e2439d8a0be77fdb41de603f36271afbf412e7d0
+oid sha256:86af0e95432181f76f3d78ccaddb184cec979175c0b8dfc59cd979bf4fc08eb3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c69a1167701b9a8aaa97baf49dd131a191a28e1688c247e9caa0eaedec4ec78
+oid sha256:aabfdebb38d9223e529ababf11d0767b798decb34d12acbd49e0715ea736a210
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd4ed9aef1c06deae187945d2bba19d3ec9693ab84566a66362a0c1434567d0
+oid sha256:89e4165e2dd494e8aa6811534a828345ba37847e19df0b03845cec243dbfa153
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5462e810bece3a5e672018cff4c6ffc18ac6ae32be907f3d8dc2b7ab3cc36423
+oid sha256:1f4ec9174bd4610eb13f705d29ae58de97c7f6ca24963c30b8e572c816be49b7
 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": 3.2968196868896484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004914004914004914,
+  "best_metric": 3.1323347091674805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009828009828009828,
   "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": 33.341,
       "eval_steps_per_second": 8.669,
       "step": 25
+    },
+    {
+      "epoch": 0.005110565110565111,
+      "grad_norm": 2.572341203689575,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.3732,
+      "step": 26
+    },
+    {
+      "epoch": 0.005307125307125307,
+      "grad_norm": 3.403599977493286,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.5602,
+      "step": 27
+    },
+    {
+      "epoch": 0.005503685503685503,
+      "grad_norm": 3.0410282611846924,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.6618,
+      "step": 28
+    },
+    {
+      "epoch": 0.0057002457002457005,
+      "grad_norm": 2.961358070373535,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.6719,
+      "step": 29
+    },
+    {
+      "epoch": 0.005896805896805897,
+      "grad_norm": 2.4283437728881836,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.6161,
+      "step": 30
+    },
+    {
+      "epoch": 0.006093366093366094,
+      "grad_norm": 1.9574626684188843,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.5441,
+      "step": 31
+    },
+    {
+      "epoch": 0.00628992628992629,
+      "grad_norm": 1.8170067071914673,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.5679,
+      "step": 32
+    },
+    {
+      "epoch": 0.006486486486486486,
+      "grad_norm": 1.8830921649932861,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.5489,
+      "step": 33
+    },
+    {
+      "epoch": 0.006683046683046683,
+      "grad_norm": 1.862863540649414,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.4594,
+      "step": 34
+    },
+    {
+      "epoch": 0.0068796068796068794,
+      "grad_norm": 1.9999181032180786,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.3772,
+      "step": 35
+    },
+    {
+      "epoch": 0.0070761670761670765,
+      "grad_norm": 2.3578336238861084,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.3478,
+      "step": 36
+    },
+    {
+      "epoch": 0.007272727272727273,
+      "grad_norm": 2.8680801391601562,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.2627,
+      "step": 37
+    },
+    {
+      "epoch": 0.007469287469287469,
+      "grad_norm": 1.4693502187728882,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.0606,
+      "step": 38
+    },
+    {
+      "epoch": 0.007665847665847666,
+      "grad_norm": 1.6032438278198242,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.4613,
+      "step": 39
+    },
+    {
+      "epoch": 0.007862407862407862,
+      "grad_norm": 1.457249641418457,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.5225,
+      "step": 40
+    },
+    {
+      "epoch": 0.00805896805896806,
+      "grad_norm": 1.222512125968933,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.5046,
+      "step": 41
+    },
+    {
+      "epoch": 0.008255528255528256,
+      "grad_norm": 1.281494140625,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.5168,
+      "step": 42
+    },
+    {
+      "epoch": 0.008452088452088452,
+      "grad_norm": 1.415714144706726,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.6238,
+      "step": 43
+    },
+    {
+      "epoch": 0.008648648648648649,
+      "grad_norm": 1.6013180017471313,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.4776,
+      "step": 44
+    },
+    {
+      "epoch": 0.008845208845208846,
+      "grad_norm": 1.7021321058273315,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.5909,
+      "step": 45
+    },
+    {
+      "epoch": 0.009041769041769041,
+      "grad_norm": 1.7219823598861694,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.4036,
+      "step": 46
+    },
+    {
+      "epoch": 0.009238329238329238,
+      "grad_norm": 1.8510271310806274,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.4587,
+      "step": 47
+    },
+    {
+      "epoch": 0.009434889434889435,
+      "grad_norm": 2.234412431716919,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.5253,
+      "step": 48
+    },
+    {
+      "epoch": 0.00963144963144963,
+      "grad_norm": 2.6374800205230713,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.4089,
+      "step": 49
+    },
+    {
+      "epoch": 0.009828009828009828,
+      "grad_norm": 3.493394136428833,
+      "learning_rate": 1e-05,
+      "loss": 3.0774,
+      "step": 50
+    },
+    {
+      "epoch": 0.009828009828009828,
+      "eval_loss": 3.1323347091674805,
+      "eval_runtime": 1.5396,
+      "eval_samples_per_second": 32.476,
+      "eval_steps_per_second": 8.444,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null