Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e991794fe3a2eab2baeac20cbac897f1b1cb0c6c7636ab07abdb33b16c041612
+oid sha256:2864e1aa5ca91b8ecd04ae78f381a7ade5bb89c9528ddbd45accc331363a410c
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16942443eb32174380ba4e1cb099b0649f204e6d75dbdc1279ccf562d0c49f0c
+oid sha256:b0800901bcad0fe9ba4957d26960788370e8c4cb3e651ac7db601d788690e2d2
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2d3aa11d8305e166635f9d164efdb40a0986284659eb98a6e35af65903fa1a
+oid sha256:d1206e9dfa3949a779455d628151a27d720edd203aa9163815824177a72ab093
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91993d212adf5d0c434e06b5ef6b73e078c94fb3bd99932a6c08da343c586cb8
+oid sha256:4bbe28b1b53f6d5e53efadd9130c5adc19c230139254efcc979fee21c56fada1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1906fed30565dfcf7eca605c8cb04334374eaf5525ad098d27d8ebbd3bef647
+oid sha256:992bd9027059eb4a88e12b39d7eb8fd11b196ed65b77ac233343f0f40eaff3ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e788f141d2aeb43b3c86fd0770fc1ce56af5eb6bfab67e42ca320d87c264a2e
+oid sha256:72a5c9055c68b8917023abda58f0e43f2935eacdea5c46f361b7d9551e545b77
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.14234893023967743,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.2903225806451613,
+  "best_metric": 0.12815675139427185,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.7204301075268817,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 19.763,
       "eval_steps_per_second": 1.237,
       "step": 75
+    },
+    {
+      "epoch": 1.3075268817204302,
+      "grad_norm": 1.0252635478973389,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 0.1202,
+      "step": 76
+    },
+    {
+      "epoch": 1.324731182795699,
+      "grad_norm": 2.085099458694458,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 0.1434,
+      "step": 77
+    },
+    {
+      "epoch": 1.3419354838709676,
+      "grad_norm": 1.5299032926559448,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.1217,
+      "step": 78
+    },
+    {
+      "epoch": 1.3591397849462366,
+      "grad_norm": 1.7754051685333252,
+      "learning_rate": 1.157994445715706e-05,
+      "loss": 0.1507,
+      "step": 79
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.3124242424964905,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.1144,
+      "step": 80
+    },
+    {
+      "epoch": 1.3935483870967742,
+      "grad_norm": 0.8618190884590149,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1319,
+      "step": 81
+    },
+    {
+      "epoch": 1.410752688172043,
+      "grad_norm": 0.7630754113197327,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 0.1367,
+      "step": 82
+    },
+    {
+      "epoch": 1.4279569892473118,
+      "grad_norm": 0.7989737391471863,
+      "learning_rate": 7.695237378953223e-06,
+      "loss": 0.1496,
+      "step": 83
+    },
+    {
+      "epoch": 1.4451612903225808,
+      "grad_norm": 0.6178842782974243,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.1274,
+      "step": 84
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 1.4041664600372314,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.1413,
+      "step": 85
+    },
+    {
+      "epoch": 1.4795698924731182,
+      "grad_norm": 1.104132056236267,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 0.1243,
+      "step": 86
+    },
+    {
+      "epoch": 1.4967741935483871,
+      "grad_norm": 1.1026701927185059,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.1017,
+      "step": 87
+    },
+    {
+      "epoch": 1.513978494623656,
+      "grad_norm": 1.1053061485290527,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 0.1097,
+      "step": 88
+    },
+    {
+      "epoch": 1.5311827956989248,
+      "grad_norm": 1.3247686624526978,
+      "learning_rate": 3.271776770026963e-06,
+      "loss": 0.1237,
+      "step": 89
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.4152677357196808,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.1387,
+      "step": 90
+    },
+    {
+      "epoch": 1.5655913978494622,
+      "grad_norm": 0.8789126873016357,
+      "learning_rate": 2.1982109232821178e-06,
+      "loss": 0.124,
+      "step": 91
+    },
+    {
+      "epoch": 1.5827956989247312,
+      "grad_norm": 0.5799853205680847,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 0.1238,
+      "step": 92
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6642497181892395,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.1099,
+      "step": 93
+    },
+    {
+      "epoch": 1.6172043010752688,
+      "grad_norm": 0.30784672498703003,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 0.117,
+      "step": 94
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.4279826581478119,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.1207,
+      "step": 95
+    },
+    {
+      "epoch": 1.6516129032258065,
+      "grad_norm": 0.2790074348449707,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.1456,
+      "step": 96
+    },
+    {
+      "epoch": 1.6688172043010754,
+      "grad_norm": 0.366972953081131,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 0.1131,
+      "step": 97
+    },
+    {
+      "epoch": 1.686021505376344,
+      "grad_norm": 0.548721194267273,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 0.1329,
+      "step": 98
+    },
+    {
+      "epoch": 1.7032258064516128,
+      "grad_norm": 0.7311145067214966,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.1475,
+      "step": 99
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.5288364887237549,
+      "learning_rate": 0.0,
+      "loss": 0.1075,
+      "step": 100
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "eval_loss": 0.12815675139427185,
+      "eval_runtime": 39.6008,
+      "eval_samples_per_second": 19.772,
+      "eval_steps_per_second": 1.237,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.333471006307123e+18,
+  "total_flos": 4.4446280084094976e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null