Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c3cfbc71baa360ea503a04599efc9dfe299a54d04c47b2f646367599cbac9d
+oid sha256:999f076b8f5f2d9d9faefe07d63f0a355fc27c5beef3d916a5727556d9cbc800
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af020e95108d540c6d446acbaabbd2498107f9d85933dc962f0469dddc9c4a38
+oid sha256:3fdf4c8fc9c4532475e85c7b5d525faceeb854e0f5252e1fb3c98d5ec1bd5485
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49768a88e541f702eb75d71268964d7cc79b72046465ea5ab4d2f7b2684f932
+oid sha256:f27e6ce44b63159e5afa22f0fea678bb8d77bbcda6ef64c9b02895897e534fdb
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e3a6f19e06c36f6182caeab45c4d6cf1899bf44ba738453d442d66c7fa692
+oid sha256:136936543dc8c1c85d2dabe8b804440676128344b22e8d997ffe3bd503facb6c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedb05ed73814bd7342db7ab5d4bec7aa9950516a77a467f7cfda9f6dec31cc9
+oid sha256:5080f711d3aa0a0b66148b31e234a97245bd7d82a63fe15d54b7de9dc1ce4a27
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c8d3317a9d670385f3523e97d1d1073e2b084502a4c464fcf0832f7fe80c1c6
+oid sha256:0028d968992a8c63eab1e9f7d07956a002eade85d427bedc709b096cd233480d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370cee31176b8bff781da8f054b9870dc93c63a8623674218a84718aa7abd3af
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.021306684240698814,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.05740940078937926,
+  "best_metric": 0.01876358687877655,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.07654586771917235,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 47.938,
       "eval_steps_per_second": 12.464,
       "step": 75
+    },
+    {
+      "epoch": 0.058174859466570986,
+      "grad_norm": 0.18385003507137299,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.17,
+      "step": 76
+    },
+    {
+      "epoch": 0.05894031814376271,
+      "grad_norm": 0.40027400851249695,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 0.1423,
+      "step": 77
+    },
+    {
+      "epoch": 0.05970577682095443,
+      "grad_norm": 0.142598494887352,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0031,
+      "step": 78
+    },
+    {
+      "epoch": 0.060471235498146154,
+      "grad_norm": 0.06515596807003021,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.0014,
+      "step": 79
+    },
+    {
+      "epoch": 0.06123669417533788,
+      "grad_norm": 0.05153204873204231,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0014,
+      "step": 80
+    },
+    {
+      "epoch": 0.0620021528525296,
+      "grad_norm": 0.014992534182965755,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 0.0005,
+      "step": 81
+    },
+    {
+      "epoch": 0.06276761152972132,
+      "grad_norm": 0.013885805383324623,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0004,
+      "step": 82
+    },
+    {
+      "epoch": 0.06353307020691305,
+      "grad_norm": 0.010251723229885101,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 0.0003,
+      "step": 83
+    },
+    {
+      "epoch": 0.06429852888410477,
+      "grad_norm": 0.0075831301510334015,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0003,
+      "step": 84
+    },
+    {
+      "epoch": 0.0650639875612965,
+      "grad_norm": 0.0066162901930511,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.0003,
+      "step": 85
+    },
+    {
+      "epoch": 0.06582944623848822,
+      "grad_norm": 0.006637216545641422,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0002,
+      "step": 86
+    },
+    {
+      "epoch": 0.06659490491567994,
+      "grad_norm": 0.011600018478929996,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 0.0003,
+      "step": 87
+    },
+    {
+      "epoch": 0.06736036359287166,
+      "grad_norm": 0.14439114928245544,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1791,
+      "step": 88
+    },
+    {
+      "epoch": 0.06812582227006339,
+      "grad_norm": 0.1987999677658081,
+      "learning_rate": 1.2884233295920353e-05,
+      "loss": 0.1352,
+      "step": 89
+    },
+    {
+      "epoch": 0.0688912809472551,
+      "grad_norm": 0.19108176231384277,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.066,
+      "step": 90
+    },
+    {
+      "epoch": 0.06965673962444684,
+      "grad_norm": 0.07157070934772491,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.0013,
+      "step": 91
+    },
+    {
+      "epoch": 0.07042219830163857,
+      "grad_norm": 0.04157419875264168,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0009,
+      "step": 92
+    },
+    {
+      "epoch": 0.07118765697883028,
+      "grad_norm": 0.02740364894270897,
+      "learning_rate": 1.1175535932519987e-05,
+      "loss": 0.0007,
+      "step": 93
+    },
+    {
+      "epoch": 0.07195311565602201,
+      "grad_norm": 0.013225646689534187,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0004,
+      "step": 94
+    },
+    {
+      "epoch": 0.07271857433321373,
+      "grad_norm": 0.00674827815964818,
+      "learning_rate": 1.0601050056180447e-05,
+      "loss": 0.0002,
+      "step": 95
+    },
+    {
+      "epoch": 0.07348403301040546,
+      "grad_norm": 0.005964465904980898,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0002,
+      "step": 96
+    },
+    {
+      "epoch": 0.07424949168759717,
+      "grad_norm": 0.005700402893126011,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.0002,
+      "step": 97
+    },
+    {
+      "epoch": 0.0750149503647889,
+      "grad_norm": 0.005580263212323189,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0002,
+      "step": 98
+    },
+    {
+      "epoch": 0.07578040904198062,
+      "grad_norm": 0.009917444549500942,
+      "learning_rate": 1.0024093563563546e-05,
+      "loss": 0.0002,
+      "step": 99
+    },
+    {
+      "epoch": 0.07654586771917235,
+      "grad_norm": 0.0060340710915625095,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 100
+    },
+    {
+      "epoch": 0.07654586771917235,
+      "eval_loss": 0.01876358687877655,
+      "eval_runtime": 1.0439,
+      "eval_samples_per_second": 47.897,
+      "eval_steps_per_second": 12.453,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.482214844275098e+16,
+  "total_flos": 5.965949609128755e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null