Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e259bb1688c91af2031fff6919ac7ed22c01dc3631e3fd8bd3275f7a4e893a4f
+oid sha256:a892ebdec680c09d105e8029acbc8b4560c0a1fe39d88aba0689e63e862f905f
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca1895ae6627efdbe36fc664464dff826e965b73854845308dfecb3247f15f3
+oid sha256:aca20ff500f98b01ecc9ef99309a7fef52bd015d8890be43686f12059c06e874
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0830ad979b92ab5e6b0523b453c96e606c05cc95e3833a22590e2b5d9a82d88d
+oid sha256:95c4c885defb2b2a37d4fd46a3766cafed0a9db06956c731219eeac9f43af737
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932af9a44378c6c77c419c49b734fac231c4373e33895451da24b59309ac75a3
+oid sha256:3fb5dbad467fa48c40ce13c5c5af7cdb92a75edc4b024b24fa3fbd02983cb705
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303c79fafa0a21570b9895f5e64700d1e2b4756b50037edf093a169bb2cffe62
+oid sha256:dd8d2f37a03e1c45363bd4c58ebc77aff300c3578388309066b3e8000539bf3a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bcdd9a02327ce29b0e35fe84d8c555e6ecbbfbae63311850e948136cf19f42
+oid sha256:4aec87f226887687543ab738fe031644a9f3e9858b9842bd14ecd5ddc40f81eb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e23a2d1e485599a7b5fae1501ffcbc43db47e90bf1e1f6de6ac821e4368041
+oid sha256:eff6fb7d68f4fba752f9a34c10ead544a122d6bff4d10f27de692e046608ac1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.179546356201172,
-  "best_model_checkpoint": "miner_id_24/checkpoint-125",
-  "epoch": 0.311284046692607,
+  "best_metric": 6.170444488525391,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.3735408560311284,
   "eval_steps": 25,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -930,6 +930,189 @@
       "eval_samples_per_second": 106.458,
       "eval_steps_per_second": 27.679,
       "step": 125
+    },
+    {
+      "epoch": 0.31377431906614783,
+      "grad_norm": 0.9346608519554138,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.5225,
+      "step": 126
+    },
+    {
+      "epoch": 0.3162645914396887,
+      "grad_norm": 0.6118949055671692,
+      "learning_rate": 1.5547295993162156e-05,
+      "loss": 6.4428,
+      "step": 127
+    },
+    {
+      "epoch": 0.3187548638132296,
+      "grad_norm": 0.6192405819892883,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 6.4609,
+      "step": 128
+    },
+    {
+      "epoch": 0.3212451361867704,
+      "grad_norm": 0.588732123374939,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.5698,
+      "step": 129
+    },
+    {
+      "epoch": 0.3237354085603113,
+      "grad_norm": 0.5688731074333191,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 6.5966,
+      "step": 130
+    },
+    {
+      "epoch": 0.3262256809338521,
+      "grad_norm": 0.6245626211166382,
+      "learning_rate": 1.3810983439624881e-05,
+      "loss": 6.6626,
+      "step": 131
+    },
+    {
+      "epoch": 0.328715953307393,
+      "grad_norm": 0.632944643497467,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.5214,
+      "step": 132
+    },
+    {
+      "epoch": 0.33120622568093383,
+      "grad_norm": 0.657809853553772,
+      "learning_rate": 1.305964588227407e-05,
+      "loss": 6.4713,
+      "step": 133
+    },
+    {
+      "epoch": 0.3336964980544747,
+      "grad_norm": 0.895321249961853,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 6.3877,
+      "step": 134
+    },
+    {
+      "epoch": 0.3361867704280156,
+      "grad_norm": 1.1434446573257446,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.1312,
+      "step": 135
+    },
+    {
+      "epoch": 0.3386770428015564,
+      "grad_norm": 1.5215338468551636,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 6.0709,
+      "step": 136
+    },
+    {
+      "epoch": 0.3411673151750973,
+      "grad_norm": 1.9847782850265503,
+      "learning_rate": 1.1797756552633215e-05,
+      "loss": 6.0749,
+      "step": 137
+    },
+    {
+      "epoch": 0.3436575875486381,
+      "grad_norm": 1.5506428480148315,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.3161,
+      "step": 138
+    },
+    {
+      "epoch": 0.346147859922179,
+      "grad_norm": 0.6647637486457825,
+      "learning_rate": 1.1289606858403237e-05,
+      "loss": 6.2913,
+      "step": 139
+    },
+    {
+      "epoch": 0.3486381322957198,
+      "grad_norm": 0.5917825102806091,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 6.4274,
+      "step": 140
+    },
+    {
+      "epoch": 0.3511284046692607,
+      "grad_norm": 0.6158031225204468,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.5412,
+      "step": 141
+    },
+    {
+      "epoch": 0.35361867704280153,
+      "grad_norm": 0.5898491144180298,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 6.4685,
+      "step": 142
+    },
+    {
+      "epoch": 0.3561089494163424,
+      "grad_norm": 0.6009002923965454,
+      "learning_rate": 1.0523732028950771e-05,
+      "loss": 6.5796,
+      "step": 143
+    },
+    {
+      "epoch": 0.3585992217898833,
+      "grad_norm": 0.6442568302154541,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.4879,
+      "step": 144
+    },
+    {
+      "epoch": 0.3610894941634241,
+      "grad_norm": 0.7317888140678406,
+      "learning_rate": 1.0267464779995617e-05,
+      "loss": 6.5173,
+      "step": 145
+    },
+    {
+      "epoch": 0.363579766536965,
+      "grad_norm": 0.7633945345878601,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 6.4973,
+      "step": 146
+    },
+    {
+      "epoch": 0.3660700389105058,
+      "grad_norm": 0.9598979353904724,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.2805,
+      "step": 147
+    },
+    {
+      "epoch": 0.3685603112840467,
+      "grad_norm": 1.2085940837860107,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 6.2707,
+      "step": 148
+    },
+    {
+      "epoch": 0.37105058365758753,
+      "grad_norm": 1.805843472480774,
+      "learning_rate": 1.001070878140409e-05,
+      "loss": 6.3792,
+      "step": 149
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "grad_norm": 2.4956977367401123,
+      "learning_rate": 1e-05,
+      "loss": 6.4434,
+      "step": 150
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "eval_loss": 6.170444488525391,
+      "eval_runtime": 0.4749,
+      "eval_samples_per_second": 105.283,
+      "eval_steps_per_second": 27.374,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -953,12 +1136,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 580106999300096.0,
+  "total_flos": 696113898192896.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null