Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359e4efeb6cde7adbac73f1f199b45366f9aa403d2ed7f5214ed473719deb84b
+oid sha256:331d94483b1de258155acfbba3192a2bcd23c97cb12debae9b1ba5c7c3e33b5f
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2619504f1ab87b13b03212c606deced14f9928264cbacfe9aa4698fdbf74a5
+oid sha256:6d66ac5bcd62023e4dfeea2c00d12238ae9866c3e5efcc4aa174343039877d7e
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888e1a2d75db1df484ef9bfa339a65ec2690ea1c03dc7252f154645447372db2
+oid sha256:276565346dbb1b1d756a912c280962e26c5fc9e1cf4aec7dbb3f45e8c3dc0bf6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300ab6a656172b6b9e0387948183d63231774d7e584b636f0fb60c8509403d87
+oid sha256:f5356ab61bac34bb4d4a97a1325d9f76010a556fe462b685962739b30cf9d2e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de4acc2331ca271ba5dbad26887edef5ae8dfadca6d309d11c4325e7184ccb0
+oid sha256:3830b85e7a404bc6026af25c9c35359028d61d8e6543787ee2770d783b64f347
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5215fc163b417483f789acc250ad5e96c57d4cbb022fbde5137018c52f5c4dee
+oid sha256:b6e4568628345f053c03b9eb0012beffa882d295cde42b3276ecd0e40515e9fc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.374171257019043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.5952143569292123,
+  "best_metric": 10.372788429260254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 2.3928215353938187,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 278.624,
       "eval_steps_per_second": 72.442,
       "step": 50
+    },
+    {
+      "epoch": 1.6271186440677967,
+      "grad_norm": 0.0471082478761673,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3914,
+      "step": 51
+    },
+    {
+      "epoch": 1.659022931206381,
+      "grad_norm": 0.03859815374016762,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 10.5452,
+      "step": 52
+    },
+    {
+      "epoch": 1.690927218344965,
+      "grad_norm": 0.043793581426143646,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 10.5909,
+      "step": 53
+    },
+    {
+      "epoch": 1.7228315054835495,
+      "grad_norm": 0.056106261909008026,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.2968,
+      "step": 54
+    },
+    {
+      "epoch": 1.7547357926221336,
+      "grad_norm": 0.09795401245355606,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 8.1943,
+      "step": 55
+    },
+    {
+      "epoch": 1.7866400797607178,
+      "grad_norm": 0.09200040251016617,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.2377,
+      "step": 56
+    },
+    {
+      "epoch": 1.8185443668993022,
+      "grad_norm": 0.06912614405155182,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3569,
+      "step": 57
+    },
+    {
+      "epoch": 1.8504486540378864,
+      "grad_norm": 0.06139494851231575,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 10.3725,
+      "step": 58
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.04969213530421257,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 10.4022,
+      "step": 59
+    },
+    {
+      "epoch": 1.914257228315055,
+      "grad_norm": 0.045224543660879135,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.6288,
+      "step": 60
+    },
+    {
+      "epoch": 1.9461615154536391,
+      "grad_norm": 0.040774866938591,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 10.4855,
+      "step": 61
+    },
+    {
+      "epoch": 1.9780658025922233,
+      "grad_norm": 0.060824956744909286,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.9078,
+      "step": 62
+    },
+    {
+      "epoch": 2.0099700897308077,
+      "grad_norm": 0.12398073822259903,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 15.4694,
+      "step": 63
+    },
+    {
+      "epoch": 2.0418743768693917,
+      "grad_norm": 0.08448352664709091,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 10.1654,
+      "step": 64
+    },
+    {
+      "epoch": 2.073778664007976,
+      "grad_norm": 0.07190793752670288,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 10.3571,
+      "step": 65
+    },
+    {
+      "epoch": 2.1056829511465605,
+      "grad_norm": 0.06088152155280113,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3712,
+      "step": 66
+    },
+    {
+      "epoch": 2.1375872382851444,
+      "grad_norm": 0.05480685457587242,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 10.4064,
+      "step": 67
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.047166239470243454,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 10.6693,
+      "step": 68
+    },
+    {
+      "epoch": 2.201395812562313,
+      "grad_norm": 0.04388361796736717,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.443,
+      "step": 69
+    },
+    {
+      "epoch": 2.233300099700897,
+      "grad_norm": 0.03891513869166374,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 9.0255,
+      "step": 70
+    },
+    {
+      "epoch": 2.2652043868394816,
+      "grad_norm": 0.12693141400814056,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.3904,
+      "step": 71
+    },
+    {
+      "epoch": 2.297108673978066,
+      "grad_norm": 0.09395328909158707,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3146,
+      "step": 72
+    },
+    {
+      "epoch": 2.32901296111665,
+      "grad_norm": 0.0779162272810936,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 10.3691,
+      "step": 73
+    },
+    {
+      "epoch": 2.3609172482552343,
+      "grad_norm": 0.06264185160398483,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 10.3792,
+      "step": 74
+    },
+    {
+      "epoch": 2.3928215353938187,
+      "grad_norm": 0.044317249208688736,
+      "learning_rate": 1e-05,
+      "loss": 10.4356,
+      "step": 75
+    },
+    {
+      "epoch": 2.3928215353938187,
+      "eval_loss": 10.372788429260254,
+      "eval_runtime": 0.1713,
+      "eval_samples_per_second": 291.857,
+      "eval_steps_per_second": 75.883,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 42768059596800.0,
+  "total_flos": 64152089395200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null