Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c332525c35f61940a1e128655b324ece399295419063d829ecaa07de07d6efe2
+oid sha256:d96951b6225f68e8d6c1f7b9f819d643f134d0a455f57e6323551035b02d06ab
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159aef76cdd40ac3b209a14ebacb9eb0f4a1fbdd459cb8ff9c7a9c10168a9b5c
+oid sha256:c7ca6235505bbad8b8fb46fa330893140a4cc5eb270810cb32c605e2f29a6f98
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3217664bac745ab2e2496875001a288721c377bbe507431b9347caf7eed8657
+oid sha256:6e3d9bb444895910fb97d5f21d06ae3b869598b0c429a5659a5efbedaa39a536
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6813758015632629,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01921229586935639,
+  "best_metric": 0.6621928215026855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03842459173871278,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.838,
       "eval_steps_per_second": 1.419,
       "step": 25
+    },
+    {
+      "epoch": 0.019980787704130643,
+      "grad_norm": 2.3865928649902344,
+      "learning_rate": 0.0001,
+      "loss": 0.5742,
+      "step": 26
+    },
+    {
+      "epoch": 0.0207492795389049,
+      "grad_norm": 2.167008399963379,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.7711,
+      "step": 27
+    },
+    {
+      "epoch": 0.021517771373679155,
+      "grad_norm": 2.8643157482147217,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.7881,
+      "step": 28
+    },
+    {
+      "epoch": 0.02228626320845341,
+      "grad_norm": 2.675781011581421,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.8584,
+      "step": 29
+    },
+    {
+      "epoch": 0.023054755043227664,
+      "grad_norm": 5.553785800933838,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.7431,
+      "step": 30
+    },
+    {
+      "epoch": 0.02382324687800192,
+      "grad_norm": 2.85943341255188,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.8504,
+      "step": 31
+    },
+    {
+      "epoch": 0.024591738712776177,
+      "grad_norm": 2.1145620346069336,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4937,
+      "step": 32
+    },
+    {
+      "epoch": 0.025360230547550433,
+      "grad_norm": 2.0370304584503174,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.8028,
+      "step": 33
+    },
+    {
+      "epoch": 0.02612872238232469,
+      "grad_norm": 2.053551197052002,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7418,
+      "step": 34
+    },
+    {
+      "epoch": 0.026897214217098942,
+      "grad_norm": 1.7939903736114502,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.5822,
+      "step": 35
+    },
+    {
+      "epoch": 0.0276657060518732,
+      "grad_norm": 2.718136787414551,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.8955,
+      "step": 36
+    },
+    {
+      "epoch": 0.028434197886647455,
+      "grad_norm": 2.0340025424957275,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.49,
+      "step": 37
+    },
+    {
+      "epoch": 0.02920268972142171,
+      "grad_norm": 2.521495819091797,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.7506,
+      "step": 38
+    },
+    {
+      "epoch": 0.029971181556195964,
+      "grad_norm": 1.7781364917755127,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.5979,
+      "step": 39
+    },
+    {
+      "epoch": 0.03073967339097022,
+      "grad_norm": 2.1692018508911133,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.654,
+      "step": 40
+    },
+    {
+      "epoch": 0.031508165225744476,
+      "grad_norm": 3.2491769790649414,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.8937,
+      "step": 41
+    },
+    {
+      "epoch": 0.03227665706051873,
+      "grad_norm": 2.3188233375549316,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7068,
+      "step": 42
+    },
+    {
+      "epoch": 0.03304514889529299,
+      "grad_norm": 3.3548412322998047,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.9072,
+      "step": 43
+    },
+    {
+      "epoch": 0.03381364073006724,
+      "grad_norm": 3.1296138763427734,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.9079,
+      "step": 44
+    },
+    {
+      "epoch": 0.0345821325648415,
+      "grad_norm": 2.4776840209960938,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.5561,
+      "step": 45
+    },
+    {
+      "epoch": 0.035350624399615754,
+      "grad_norm": 3.5687758922576904,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.7228,
+      "step": 46
+    },
+    {
+      "epoch": 0.03611911623439001,
+      "grad_norm": 5.37619686126709,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.8427,
+      "step": 47
+    },
+    {
+      "epoch": 0.03688760806916427,
+      "grad_norm": 5.639602184295654,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.1088,
+      "step": 48
+    },
+    {
+      "epoch": 0.03765609990393852,
+      "grad_norm": 3.618199110031128,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.8533,
+      "step": 49
+    },
+    {
+      "epoch": 0.03842459173871278,
+      "grad_norm": 5.885342597961426,
+      "learning_rate": 0.0,
+      "loss": 0.5561,
+      "step": 50
+    },
+    {
+      "epoch": 0.03842459173871278,
+      "eval_loss": 0.6621928215026855,
+      "eval_runtime": 193.1089,
+      "eval_samples_per_second": 2.838,
+      "eval_steps_per_second": 1.419,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null