Training in progress, step 173, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed389e14f129ba8921e78796b1cfd84643f36adbb5c428d2c5b6a38ac100436e
+oid sha256:710e33d92b8562f86bfdc755807569f63221c1550408ef1b5dac8c6d70bc3716
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eeb6d7981bf24be24586c00971bdbb4cca532312be0fbc97d0b816bda618615
+oid sha256:2baa1a0cf05dbf973e1f6b079103a1c91e80941ce18902a72392bacb3a1b7aa7
 size 169157892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe33361b74b04c35e54ffd954f5a7a824246f9c920096ddc53ea563d6c62356
+oid sha256:b743a7d97e2a64156b5519aa55150606f174f9e80a6c8b836204cf2da55dfcec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb01d4f0da8d959e9ca5a4773566e24c639c6b8f18e1285757275e715c7b05f
+oid sha256:13cea8c13b7ff143621afe3809a9208b72f31395569d02b28f3b5848f77c0a7e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.152366876602173,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.5974025974025974,
+  "epoch": 2.995670995670996,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 173,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,167 @@
       "eval_samples_per_second": 22.362,
       "eval_steps_per_second": 5.704,
       "step": 150
+    },
+    {
+      "epoch": 2.6147186147186146,
+      "grad_norm": 1.8181335926055908,
+      "learning_rate": 4.427853541662091e-06,
+      "loss": 1.155,
+      "step": 151
+    },
+    {
+      "epoch": 2.632034632034632,
+      "grad_norm": 2.2399914264678955,
+      "learning_rate": 4.039859192235779e-06,
+      "loss": 1.3334,
+      "step": 152
+    },
+    {
+      "epoch": 2.6493506493506493,
+      "grad_norm": 2.19873309135437,
+      "learning_rate": 3.668937158903901e-06,
+      "loss": 1.3053,
+      "step": 153
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.5052037239074707,
+      "learning_rate": 3.315225224059809e-06,
+      "loss": 1.3906,
+      "step": 154
+    },
+    {
+      "epoch": 2.683982683982684,
+      "grad_norm": 2.5421435832977295,
+      "learning_rate": 2.9788547772478416e-06,
+      "loss": 1.3269,
+      "step": 155
+    },
+    {
+      "epoch": 2.7012987012987013,
+      "grad_norm": 2.761349678039551,
+      "learning_rate": 2.6599507663574384e-06,
+      "loss": 1.2917,
+      "step": 156
+    },
+    {
+      "epoch": 2.7186147186147185,
+      "grad_norm": 3.4365580081939697,
+      "learning_rate": 2.3586316512101416e-06,
+      "loss": 1.0455,
+      "step": 157
+    },
+    {
+      "epoch": 2.7359307359307357,
+      "grad_norm": 2.1280157566070557,
+      "learning_rate": 2.0750093595565733e-06,
+      "loss": 0.9159,
+      "step": 158
+    },
+    {
+      "epoch": 2.7532467532467533,
+      "grad_norm": 1.2609156370162964,
+      "learning_rate": 1.8091892454998594e-06,
+      "loss": 1.3023,
+      "step": 159
+    },
+    {
+      "epoch": 2.7705627705627704,
+      "grad_norm": 1.4564933776855469,
+      "learning_rate": 1.5612700503608968e-06,
+      "loss": 1.2887,
+      "step": 160
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 1.5543081760406494,
+      "learning_rate": 1.33134386599994e-06,
+      "loss": 1.3596,
+      "step": 161
+    },
+    {
+      "epoch": 2.8051948051948052,
+      "grad_norm": 1.5681473016738892,
+      "learning_rate": 1.1194961006082972e-06,
+      "loss": 1.0265,
+      "step": 162
+    },
+    {
+      "epoch": 2.8225108225108224,
+      "grad_norm": 1.7594598531723022,
+      "learning_rate": 9.258054469825972e-07,
+      "loss": 1.2222,
+      "step": 163
+    },
+    {
+      "epoch": 2.8398268398268396,
+      "grad_norm": 1.896242618560791,
+      "learning_rate": 7.503438532937168e-07,
+      "loss": 1.2466,
+      "step": 164
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.9518426656723022,
+      "learning_rate": 5.931764963608866e-07,
+      "loss": 1.2796,
+      "step": 165
+    },
+    {
+      "epoch": 2.8744588744588744,
+      "grad_norm": 2.096078634262085,
+      "learning_rate": 4.543617574412184e-07,
+      "loss": 1.263,
+      "step": 166
+    },
+    {
+      "epoch": 2.891774891774892,
+      "grad_norm": 2.4194352626800537,
+      "learning_rate": 3.339512005434309e-07,
+      "loss": 1.4151,
+      "step": 167
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 2.55708384513855,
+      "learning_rate": 2.319895532739369e-07,
+      "loss": 1.3309,
+      "step": 168
+    },
+    {
+      "epoch": 2.9264069264069263,
+      "grad_norm": 2.496046304702759,
+      "learning_rate": 1.4851469022234e-07,
+      "loss": 1.2512,
+      "step": 169
+    },
+    {
+      "epoch": 2.9437229437229435,
+      "grad_norm": 2.801349639892578,
+      "learning_rate": 8.355761889260461e-08,
+      "loss": 1.2877,
+      "step": 170
+    },
+    {
+      "epoch": 2.961038961038961,
+      "grad_norm": 4.023518085479736,
+      "learning_rate": 3.7142468185014104e-08,
+      "loss": 1.2639,
+      "step": 171
+    },
+    {
+      "epoch": 2.9783549783549783,
+      "grad_norm": 2.5057783126831055,
+      "learning_rate": 9.286479433257e-09,
+      "loss": 1.1965,
+      "step": 172
+    },
+    {
+      "epoch": 2.995670995670996,
+      "grad_norm": 3.9870026111602783,
+      "learning_rate": 0.0,
+      "loss": 1.3747,
+      "step": 173
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1273,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.202571390189568e+16,
+  "total_flos": 7.155617850143539e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null