Training in progress, step 184, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e05557815278a51311d45226ab11c4cc422ca229d2e952d19949937572de49
+oid sha256:0d258a9b335f90563aa9a487dbf4277e3ead5ca2a46cfb09a0754628ae593ddf
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd70f35c4435388e8de300b6b9f919239af487dab526e60bfc9f6104f78495c4
+oid sha256:ec5a31b8cbd05bcf27a25c7ae39d16adf03ac5ea318289a0ba689a8ac6f8af43
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52629c0968912ff569f2629fd2d5fa3372027877212d052a5768eca54b1b4687
+oid sha256:8b2c2c220277ba59be432484feabd81ecd9bcc271782118e743a7adae5e31dd0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90386d2b9346b46992a3b3ef316fcc7403d4fcb482e738f4aecb1e41902efa87
+oid sha256:99a1adfb5925aadf0a7b934202364342c13942aa8a01689a2949df92e571d865
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.338530540466309,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.4489795918367347,
+  "epoch": 3.0040816326530613,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 184,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,244 @@
       "eval_samples_per_second": 423.02,
       "eval_steps_per_second": 106.782,
       "step": 150
+    },
+    {
+      "epoch": 2.4653061224489794,
+      "grad_norm": 0.0756654441356659,
+      "learning_rate": 8.615550092155478e-06,
+      "loss": 10.5522,
+      "step": 151
+    },
+    {
+      "epoch": 2.4816326530612245,
+      "grad_norm": 0.09580621123313904,
+      "learning_rate": 8.115707568501768e-06,
+      "loss": 10.7689,
+      "step": 152
+    },
+    {
+      "epoch": 2.497959183673469,
+      "grad_norm": 0.06406902521848679,
+      "learning_rate": 7.629518439195671e-06,
+      "loss": 10.0105,
+      "step": 153
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.08935669809579849,
+      "learning_rate": 7.157141191620548e-06,
+      "loss": 9.9995,
+      "step": 154
+    },
+    {
+      "epoch": 2.5306122448979593,
+      "grad_norm": 0.05751555413007736,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.5834,
+      "step": 155
+    },
+    {
+      "epoch": 2.546938775510204,
+      "grad_norm": 0.07112957537174225,
+      "learning_rate": 6.2544337290925185e-06,
+      "loss": 10.0825,
+      "step": 156
+    },
+    {
+      "epoch": 2.563265306122449,
+      "grad_norm": 0.05463530868291855,
+      "learning_rate": 5.824397777698859e-06,
+      "loss": 11.154,
+      "step": 157
+    },
+    {
+      "epoch": 2.5795918367346937,
+      "grad_norm": 0.06352207809686661,
+      "learning_rate": 5.408762139230888e-06,
+      "loss": 9.9031,
+      "step": 158
+    },
+    {
+      "epoch": 2.595918367346939,
+      "grad_norm": 0.08281508833169937,
+      "learning_rate": 5.007662302124672e-06,
+      "loss": 10.6062,
+      "step": 159
+    },
+    {
+      "epoch": 2.612244897959184,
+      "grad_norm": 0.0804663822054863,
+      "learning_rate": 4.621229016452156e-06,
+      "loss": 9.8127,
+      "step": 160
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 0.06747894734144211,
+      "learning_rate": 4.249588251299391e-06,
+      "loss": 10.2959,
+      "step": 161
+    },
+    {
+      "epoch": 2.644897959183673,
+      "grad_norm": 0.0881141647696495,
+      "learning_rate": 3.892861153703342e-06,
+      "loss": 10.3972,
+      "step": 162
+    },
+    {
+      "epoch": 2.6612244897959183,
+      "grad_norm": 0.06336997449398041,
+      "learning_rate": 3.551164009160429e-06,
+      "loss": 10.1351,
+      "step": 163
+    },
+    {
+      "epoch": 2.6775510204081634,
+      "grad_norm": 0.0677282065153122,
+      "learning_rate": 3.2246082037199532e-06,
+      "loss": 10.3315,
+      "step": 164
+    },
+    {
+      "epoch": 2.693877551020408,
+      "grad_norm": 0.06688407808542252,
+      "learning_rate": 2.9133001876746004e-06,
+      "loss": 10.778,
+      "step": 165
+    },
+    {
+      "epoch": 2.710204081632653,
+      "grad_norm": 0.055454302579164505,
+      "learning_rate": 2.6173414408598827e-06,
+      "loss": 10.0015,
+      "step": 166
+    },
+    {
+      "epoch": 2.726530612244898,
+      "grad_norm": 0.12665700912475586,
+      "learning_rate": 2.3368284395738684e-06,
+      "loss": 10.5561,
+      "step": 167
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 0.07574506103992462,
+      "learning_rate": 2.0718526251279346e-06,
+      "loss": 10.6876,
+      "step": 168
+    },
+    {
+      "epoch": 2.759183673469388,
+      "grad_norm": 0.06783638894557953,
+      "learning_rate": 1.8225003740388547e-06,
+      "loss": 9.6811,
+      "step": 169
+    },
+    {
+      "epoch": 2.7755102040816326,
+      "grad_norm": 0.0635710060596466,
+      "learning_rate": 1.5888529698718346e-06,
+      "loss": 10.4183,
+      "step": 170
+    },
+    {
+      "epoch": 2.7918367346938773,
+      "grad_norm": 0.09244585782289505,
+      "learning_rate": 1.3709865767438435e-06,
+      "loss": 10.5344,
+      "step": 171
+    },
+    {
+      "epoch": 2.8081632653061224,
+      "grad_norm": 0.06933451443910599,
+      "learning_rate": 1.1689722144956671e-06,
+      "loss": 10.0331,
+      "step": 172
+    },
+    {
+      "epoch": 2.8244897959183675,
+      "grad_norm": 0.0735977292060852,
+      "learning_rate": 9.82875735540989e-07,
+      "loss": 11.0642,
+      "step": 173
+    },
+    {
+      "epoch": 2.840816326530612,
+      "grad_norm": 0.05742630735039711,
+      "learning_rate": 8.127578033998662e-07,
+      "loss": 10.0735,
+      "step": 174
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.0781678631901741,
+      "learning_rate": 6.58673872923693e-07,
+      "loss": 10.236,
+      "step": 175
+    },
+    {
+      "epoch": 2.873469387755102,
+      "grad_norm": 0.06694554537534714,
+      "learning_rate": 5.206741722181386e-07,
+      "loss": 10.4922,
+      "step": 176
+    },
+    {
+      "epoch": 2.889795918367347,
+      "grad_norm": 0.06435613334178925,
+      "learning_rate": 3.9880368626978304e-07,
+      "loss": 10.0171,
+      "step": 177
+    },
+    {
+      "epoch": 2.906122448979592,
+      "grad_norm": 0.06160068139433861,
+      "learning_rate": 2.9310214228202013e-07,
+      "loss": 9.9337,
+      "step": 178
+    },
+    {
+      "epoch": 2.9224489795918367,
+      "grad_norm": 0.07912050932645798,
+      "learning_rate": 2.0360399672478824e-07,
+      "loss": 11.0737,
+      "step": 179
+    },
+    {
+      "epoch": 2.938775510204082,
+      "grad_norm": 0.07679970562458038,
+      "learning_rate": 1.3033842410251075e-07,
+      "loss": 10.182,
+      "step": 180
+    },
+    {
+      "epoch": 2.9551020408163264,
+      "grad_norm": 0.06117856130003929,
+      "learning_rate": 7.332930744380906e-08,
+      "loss": 10.4093,
+      "step": 181
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 0.06400584429502487,
+      "learning_rate": 3.259523051615254e-08,
+      "loss": 10.8033,
+      "step": 182
+    },
+    {
+      "epoch": 2.987755102040816,
+      "grad_norm": 0.07549428939819336,
+      "learning_rate": 8.149471767937567e-09,
+      "loss": 9.6617,
+      "step": 183
+    },
+    {
+      "epoch": 3.0040816326530613,
+      "grad_norm": 0.18150553107261658,
+      "learning_rate": 0.0,
+      "loss": 18.2373,
+      "step": 184
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 16711683342336.0,
+  "total_flos": 20493947928576.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null