Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9298f06d8dde874659f3149406aaad4342ee36e56e6e12f4200b9462a6fd3e69
+oid sha256:6d8c947c49d4902123042f0f415accd554d88286e4871e8c9366b4a34561d8d7
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2147ac52fa5320a838eeaf35e9f06008161f0f64a0812ffa44db06ba3e4a60d3
+oid sha256:0996ccc63abde854ee0dc183fe91f1409cb68edda2a8186c2382bc175196d5cc
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1352228521ef4360b388261d13da75370d15d60b75e93641179d5e5d4df7831a
+oid sha256:3e0ce1a85378e0d50d06b0cd8040b928bd85ace147bd64f649d7101fbae762a4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5983d5de76b865a9485949c438daf2fe96f3b258d19cfd7035b2ca1bf1ea0b8
+oid sha256:76f09ddbc6e0da830a60621ff658ac405ff583e528d7b3394cc031508da933b6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ffea15b15327a7c8556ec189c8cef3d169e918642e9e079e9a1fa9012b5e778
+oid sha256:d632f71da5d1bfe3c6a940c00322d709514e7df7fa1b246caa89be7d73199457
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58d9db1c8bce5ea3e0b800e22cc306c1cbd36fe41bad7d8ab07008eeda412c1
+oid sha256:95f60f64d34863817e9b484a7cb797530084f25e09e7e5f4bd46cccc8626e799
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8348499536514282,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16913319238900634,
+  "best_metric": 0.7932476997375488,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3382663847780127,
   "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": 9.302,
       "eval_steps_per_second": 2.419,
       "step": 25
+    },
+    {
+      "epoch": 0.1758985200845666,
+      "grad_norm": 0.2902161180973053,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.9089,
+      "step": 26
+    },
+    {
+      "epoch": 0.18266384778012684,
+      "grad_norm": 0.2747015058994293,
+      "learning_rate": 7.75e-05,
+      "loss": 0.9002,
+      "step": 27
+    },
+    {
+      "epoch": 0.1894291754756871,
+      "grad_norm": 0.2739669680595398,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.8693,
+      "step": 28
+    },
+    {
+      "epoch": 0.19619450317124737,
+      "grad_norm": 0.32363882660865784,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.87,
+      "step": 29
+    },
+    {
+      "epoch": 0.2029598308668076,
+      "grad_norm": 0.22914020717144012,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.8642,
+      "step": 30
+    },
+    {
+      "epoch": 0.20972515856236787,
+      "grad_norm": 0.22579313814640045,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.8326,
+      "step": 31
+    },
+    {
+      "epoch": 0.2164904862579281,
+      "grad_norm": 0.21553149819374084,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.8511,
+      "step": 32
+    },
+    {
+      "epoch": 0.22325581395348837,
+      "grad_norm": 0.2171638011932373,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.8291,
+      "step": 33
+    },
+    {
+      "epoch": 0.23002114164904863,
+      "grad_norm": 0.23992548882961273,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.8349,
+      "step": 34
+    },
+    {
+      "epoch": 0.23678646934460887,
+      "grad_norm": 0.2586527466773987,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.8241,
+      "step": 35
+    },
+    {
+      "epoch": 0.24355179704016913,
+      "grad_norm": 0.30564969778060913,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.806,
+      "step": 36
+    },
+    {
+      "epoch": 0.25031712473572937,
+      "grad_norm": 0.31983381509780884,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.8733,
+      "step": 37
+    },
+    {
+      "epoch": 0.25708245243128963,
+      "grad_norm": 0.23221205174922943,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.8931,
+      "step": 38
+    },
+    {
+      "epoch": 0.2638477801268499,
+      "grad_norm": 0.22967343032360077,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8619,
+      "step": 39
+    },
+    {
+      "epoch": 0.27061310782241016,
+      "grad_norm": 0.21873976290225983,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.8559,
+      "step": 40
+    },
+    {
+      "epoch": 0.2773784355179704,
+      "grad_norm": 0.21719108521938324,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.8557,
+      "step": 41
+    },
+    {
+      "epoch": 0.28414376321353063,
+      "grad_norm": 0.22952087223529816,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8358,
+      "step": 42
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.20508794486522675,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.807,
+      "step": 43
+    },
+    {
+      "epoch": 0.29767441860465116,
+      "grad_norm": 0.25145912170410156,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.8144,
+      "step": 44
+    },
+    {
+      "epoch": 0.3044397463002114,
+      "grad_norm": 0.2271297127008438,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8071,
+      "step": 45
+    },
+    {
+      "epoch": 0.3112050739957717,
+      "grad_norm": 0.2127731591463089,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.7954,
+      "step": 46
+    },
+    {
+      "epoch": 0.31797040169133195,
+      "grad_norm": 0.2308739870786667,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.8334,
+      "step": 47
+    },
+    {
+      "epoch": 0.32473572938689216,
+      "grad_norm": 0.245611771941185,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8116,
+      "step": 48
+    },
+    {
+      "epoch": 0.3315010570824524,
+      "grad_norm": 0.29155588150024414,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.8337,
+      "step": 49
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 0.3584875762462616,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.8385,
+      "step": 50
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "eval_loss": 0.7932476997375488,
+      "eval_runtime": 5.3869,
+      "eval_samples_per_second": 9.282,
+      "eval_steps_per_second": 2.413,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.327074698592256e+17,
+  "total_flos": 2.654149397184512e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null