Training in progress, step 89, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6885fe87420a9e61daa6887e26318ccbfd3809aa0bf5cf9c8905c8e3c287fd0
+oid sha256:c61092df7db9d6249af242ace3a690c18fe70a123aa068c31dd37e69be0b6a27
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e988350ac7aeb72302e51fc5050114611fba5173511d668ffb23f71dea022fb4
+oid sha256:367415b20d5cc3dc4c37c44568f818ad6b641407bf1415465e54f39949ef783c
 size 71077780

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ec38c92a1ffacb3f0a38ed8d4b54df9f90e56d77e8059bb98b5b1fbff8e36b
+oid sha256:2f70251008d1480d00ecfdad0f49d1166375245c9084855b063269013d1c8ca4
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2110899a5ef8c837a82b122a911b65a80a741abf25a03d446527dc4693fd41
+oid sha256:7d4b861ffcc1c43e19407a832b538630bad5376303c9174ca6aa8682e2a6f7e9
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c60ea12d3996de716a31c55ddb6ab7e0d38026befa385223b06ce8892e82cef
+oid sha256:600c83b39be0957e8f5819be8f3ffae1f72249f6198f6ae802b65455de8eacc1
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c3c8487dd0ca63e172a43843fdd7b66d43a3d801a3502c23a02e6dd4ec71a9
+oid sha256:a028e8810ac4442729d364e25156b60f8a2c8e7276b935ced95a0a8b1e750a63
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f89802dfd89ef2cac8ebd750dc9092b0e6e83c842be3c06f0e48fa24d75c66d
+oid sha256:fa0d2ce3d6468612b7b8c423c08e6d99929a5ac187833329f96e2253a8754242
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfc2979a2c7b627b806f5b54b9750f2b0abfd5e4d219b684a6e5e2c36486eda
+oid sha256:3c566e0438d21a782bb42c84ff7f457ad5984296c2dc57478af8cbf88f60c4a7
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34bc79338b4d69bd4aed584c5f5079ae3715e693f51bc1c551fb0d55e38c903
+oid sha256:6d047979362a44904895c185d8c8dc00b567703eb6f7827e1d9cb4c85f2429ec
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd985b3d5ff99f89d4d17f9ea77057ea5b20c0792e08ebf3377991f0cc0c8ba
+oid sha256:19e8c0499605d87312d99757d2e58ee14cbdc75bca0a5bb97d83baae85f5c817
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b48aef2c82921e8441da655aa35993fdaa8cc6b19a35949abde7fad9d3a218d
+oid sha256:f7d0d4bdaa823b64874e0689c50692080db68d255c97e13e0fc51d8240bbc831
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.420650452375412,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.694915254237288,
+  "epoch": 3.016949152542373,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 89,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,279 @@
       "eval_samples_per_second": 290.407,
       "eval_steps_per_second": 9.486,
       "step": 50
+    },
+    {
+      "epoch": 1.7288135593220337,
+      "grad_norm": 0.2548205256462097,
+      "learning_rate": 4.9370205928584464e-05,
+      "loss": 0.4107,
+      "step": 51
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 0.24160364270210266,
+      "learning_rate": 4.728917555732678e-05,
+      "loss": 0.4312,
+      "step": 52
+    },
+    {
+      "epoch": 1.7966101694915255,
+      "grad_norm": 0.06337052583694458,
+      "learning_rate": 4.521638457057392e-05,
+      "loss": 0.4052,
+      "step": 53
+    },
+    {
+      "epoch": 1.8305084745762712,
+      "grad_norm": 0.26108115911483765,
+      "learning_rate": 4.315511047692862e-05,
+      "loss": 0.3744,
+      "step": 54
+    },
+    {
+      "epoch": 1.8644067796610169,
+      "grad_norm": 0.18919679522514343,
+      "learning_rate": 4.11086125744183e-05,
+      "loss": 0.4286,
+      "step": 55
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": 0.24806950986385345,
+      "learning_rate": 3.908012679687508e-05,
+      "loss": 0.4354,
+      "step": 56
+    },
+    {
+      "epoch": 1.9322033898305084,
+      "grad_norm": 0.16577477753162384,
+      "learning_rate": 3.707286059725916e-05,
+      "loss": 0.4216,
+      "step": 57
+    },
+    {
+      "epoch": 1.9661016949152543,
+      "grad_norm": 0.07274139672517776,
+      "learning_rate": 3.5089987876016445e-05,
+      "loss": 0.3875,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7141322493553162,
+      "learning_rate": 3.313464396248959e-05,
+      "loss": 0.5832,
+      "step": 59
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 0.3955691158771515,
+      "learning_rate": 3.1209920657317824e-05,
+      "loss": 0.4751,
+      "step": 60
+    },
+    {
+      "epoch": 2.0677966101694913,
+      "grad_norm": 0.37002313137054443,
+      "learning_rate": 2.9318861343664646e-05,
+      "loss": 0.4308,
+      "step": 61
+    },
+    {
+      "epoch": 2.1016949152542375,
+      "grad_norm": 0.15991376340389252,
+      "learning_rate": 2.746445617500344e-05,
+      "loss": 0.4005,
+      "step": 62
+    },
+    {
+      "epoch": 2.135593220338983,
+      "grad_norm": 0.08792717754840851,
+      "learning_rate": 2.5649637347070338e-05,
+      "loss": 0.3849,
+      "step": 63
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.14280790090560913,
+      "learning_rate": 2.3877274461459966e-05,
+      "loss": 0.3955,
+      "step": 64
+    },
+    {
+      "epoch": 2.2033898305084745,
+      "grad_norm": 0.40407660603523254,
+      "learning_rate": 2.2150169988195452e-05,
+      "loss": 0.3807,
+      "step": 65
+    },
+    {
+      "epoch": 2.23728813559322,
+      "grad_norm": 0.05895840376615524,
+      "learning_rate": 2.0471054834447473e-05,
+      "loss": 0.4356,
+      "step": 66
+    },
+    {
+      "epoch": 2.2711864406779663,
+      "grad_norm": 0.20810866355895996,
+      "learning_rate": 1.884258402640846e-05,
+      "loss": 0.4502,
+      "step": 67
+    },
+    {
+      "epoch": 2.305084745762712,
+      "grad_norm": 0.10166915506124496,
+      "learning_rate": 1.7267332511150564e-05,
+      "loss": 0.4194,
+      "step": 68
+    },
+    {
+      "epoch": 2.3389830508474576,
+      "grad_norm": 0.059947896748781204,
+      "learning_rate": 1.5747791085105175e-05,
+      "loss": 0.4241,
+      "step": 69
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "grad_norm": 0.08675111830234528,
+      "learning_rate": 1.428636245560156e-05,
+      "loss": 0.4057,
+      "step": 70
+    },
+    {
+      "epoch": 2.406779661016949,
+      "grad_norm": 0.2886503040790558,
+      "learning_rate": 1.2885357441692914e-05,
+      "loss": 0.3794,
+      "step": 71
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 0.11011155694723129,
+      "learning_rate": 1.154699132027637e-05,
+      "loss": 0.4224,
+      "step": 72
+    },
+    {
+      "epoch": 2.4745762711864407,
+      "grad_norm": 0.23668210208415985,
+      "learning_rate": 1.027338032328485e-05,
+      "loss": 0.4624,
+      "step": 73
+    },
+    {
+      "epoch": 2.5084745762711864,
+      "grad_norm": 0.1450003683567047,
+      "learning_rate": 9.066538291489505e-06,
+      "loss": 0.4063,
+      "step": 74
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 0.0950573980808258,
+      "learning_rate": 7.928373490203387e-06,
+      "loss": 0.3955,
+      "step": 75
+    },
+    {
+      "epoch": 2.576271186440678,
+      "grad_norm": 0.1254480630159378,
+      "learning_rate": 6.86068559192192e-06,
+      "loss": 0.4191,
+      "step": 76
+    },
+    {
+      "epoch": 2.610169491525424,
+      "grad_norm": 0.2626599371433258,
+      "learning_rate": 5.865162830670588e-06,
+      "loss": 0.3544,
+      "step": 77
+    },
+    {
+      "epoch": 2.6440677966101696,
+      "grad_norm": 0.38685888051986694,
+      "learning_rate": 4.9433793325600285e-06,
+      "loss": 0.4176,
+      "step": 78
+    },
+    {
+      "epoch": 2.6779661016949152,
+      "grad_norm": 0.3029015362262726,
+      "learning_rate": 4.096792626769155e-06,
+      "loss": 0.42,
+      "step": 79
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 0.17327213287353516,
+      "learning_rate": 3.326741340891792e-06,
+      "loss": 0.4334,
+      "step": 80
+    },
+    {
+      "epoch": 2.7457627118644066,
+      "grad_norm": 0.10987525433301926,
+      "learning_rate": 2.6344430842914096e-06,
+      "loss": 0.4149,
+      "step": 81
+    },
+    {
+      "epoch": 2.7796610169491527,
+      "grad_norm": 0.12840408086776733,
+      "learning_rate": 2.020992522810428e-06,
+      "loss": 0.3796,
+      "step": 82
+    },
+    {
+      "epoch": 2.8135593220338984,
+      "grad_norm": 0.19848020374774933,
+      "learning_rate": 1.487359647878472e-06,
+      "loss": 0.3997,
+      "step": 83
+    },
+    {
+      "epoch": 2.847457627118644,
+      "grad_norm": 0.4496248960494995,
+      "learning_rate": 1.0343882427566057e-06,
+      "loss": 0.3558,
+      "step": 84
+    },
+    {
+      "epoch": 2.8813559322033897,
+      "grad_norm": 0.34108394384384155,
+      "learning_rate": 6.627945483424986e-07,
+      "loss": 0.4417,
+      "step": 85
+    },
+    {
+      "epoch": 2.915254237288136,
+      "grad_norm": 0.1465616226196289,
+      "learning_rate": 3.73166130646396e-07,
+      "loss": 0.4156,
+      "step": 86
+    },
+    {
+      "epoch": 2.9491525423728815,
+      "grad_norm": 0.08617256581783295,
+      "learning_rate": 1.6596095172846882e-07,
+      "loss": 0.4077,
+      "step": 87
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 0.2514786422252655,
+      "learning_rate": 4.1506645566653235e-08,
+      "loss": 0.4062,
+      "step": 88
+    },
+    {
+      "epoch": 3.016949152542373,
+      "grad_norm": 0.42695701122283936,
+      "learning_rate": 0.0,
+      "loss": 0.6505,
+      "step": 89
     }
   ],
   "logging_steps": 1,
@@ -396,12 +669,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7475518160896e+16,
+  "total_flos": 4.890642232639488e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null