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:d8a6bb7923d99eb1addaf80dd3c5f68a635e0004c3ad087e101927f681a3e8ef
+oid sha256:177a36b9aded29c575ef6d00d911b9c08de33d23a4ff58088b57f7410541fe93
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c14e484e7f9f6c436873c65eed10a21b2c5aee925b083aacae1f5a8cb3a78c
+oid sha256:7d36a76b1488aaa5c9a5dee7cfc5ec52f06306c07b4fdfaf5fb5a7b3225deaa1
 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": 2.1530466079711914,
   "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": 22.218,
       "eval_steps_per_second": 5.668,
       "step": 150
+    },
+    {
+      "epoch": 2.6147186147186146,
+      "grad_norm": 1.814753532409668,
+      "learning_rate": 4.427853541662091e-06,
+      "loss": 1.1572,
+      "step": 151
+    },
+    {
+      "epoch": 2.632034632034632,
+      "grad_norm": 2.255131959915161,
+      "learning_rate": 4.039859192235779e-06,
+      "loss": 1.3291,
+      "step": 152
+    },
+    {
+      "epoch": 2.6493506493506493,
+      "grad_norm": 2.160221576690674,
+      "learning_rate": 3.668937158903901e-06,
+      "loss": 1.3002,
+      "step": 153
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.4960460662841797,
+      "learning_rate": 3.315225224059809e-06,
+      "loss": 1.387,
+      "step": 154
+    },
+    {
+      "epoch": 2.683982683982684,
+      "grad_norm": 2.546381711959839,
+      "learning_rate": 2.9788547772478416e-06,
+      "loss": 1.3375,
+      "step": 155
+    },
+    {
+      "epoch": 2.7012987012987013,
+      "grad_norm": 2.7530722618103027,
+      "learning_rate": 2.6599507663574384e-06,
+      "loss": 1.2888,
+      "step": 156
+    },
+    {
+      "epoch": 2.7186147186147185,
+      "grad_norm": 3.3948094844818115,
+      "learning_rate": 2.3586316512101416e-06,
+      "loss": 1.0494,
+      "step": 157
+    },
+    {
+      "epoch": 2.7359307359307357,
+      "grad_norm": 2.2093355655670166,
+      "learning_rate": 2.0750093595565733e-06,
+      "loss": 0.9195,
+      "step": 158
+    },
+    {
+      "epoch": 2.7532467532467533,
+      "grad_norm": 1.2557899951934814,
+      "learning_rate": 1.8091892454998594e-06,
+      "loss": 1.3048,
+      "step": 159
+    },
+    {
+      "epoch": 2.7705627705627704,
+      "grad_norm": 1.4298012256622314,
+      "learning_rate": 1.5612700503608968e-06,
+      "loss": 1.2899,
+      "step": 160
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 1.55137300491333,
+      "learning_rate": 1.33134386599994e-06,
+      "loss": 1.3592,
+      "step": 161
+    },
+    {
+      "epoch": 2.8051948051948052,
+      "grad_norm": 1.5704561471939087,
+      "learning_rate": 1.1194961006082972e-06,
+      "loss": 1.0256,
+      "step": 162
+    },
+    {
+      "epoch": 2.8225108225108224,
+      "grad_norm": 1.9115115404129028,
+      "learning_rate": 9.258054469825972e-07,
+      "loss": 1.2241,
+      "step": 163
+    },
+    {
+      "epoch": 2.8398268398268396,
+      "grad_norm": 1.8863279819488525,
+      "learning_rate": 7.503438532937168e-07,
+      "loss": 1.2463,
+      "step": 164
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 2.0536916255950928,
+      "learning_rate": 5.931764963608866e-07,
+      "loss": 1.2806,
+      "step": 165
+    },
+    {
+      "epoch": 2.8744588744588744,
+      "grad_norm": 2.066479206085205,
+      "learning_rate": 4.543617574412184e-07,
+      "loss": 1.2572,
+      "step": 166
+    },
+    {
+      "epoch": 2.891774891774892,
+      "grad_norm": 2.4157185554504395,
+      "learning_rate": 3.339512005434309e-07,
+      "loss": 1.4229,
+      "step": 167
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 2.4809465408325195,
+      "learning_rate": 2.319895532739369e-07,
+      "loss": 1.3262,
+      "step": 168
+    },
+    {
+      "epoch": 2.9264069264069263,
+      "grad_norm": 2.556966781616211,
+      "learning_rate": 1.4851469022234e-07,
+      "loss": 1.2532,
+      "step": 169
+    },
+    {
+      "epoch": 2.9437229437229435,
+      "grad_norm": 2.8384437561035156,
+      "learning_rate": 8.355761889260461e-08,
+      "loss": 1.2835,
+      "step": 170
+    },
+    {
+      "epoch": 2.961038961038961,
+      "grad_norm": 3.8424901962280273,
+      "learning_rate": 3.7142468185014104e-08,
+      "loss": 1.2521,
+      "step": 171
+    },
+    {
+      "epoch": 2.9783549783549783,
+      "grad_norm": 2.5043461322784424,
+      "learning_rate": 9.286479433257e-09,
+      "loss": 1.1914,
+      "step": 172
+    },
+    {
+      "epoch": 2.995670995670996,
+      "grad_norm": 3.945042371749878,
+      "learning_rate": 0.0,
+      "loss": 1.3781,
+      "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