Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f7d1cab1f1c1f94445cd22369257aaa21529875106c6c56c58b5307c1bc477
+oid sha256:8e1cf37faf9885b6cb74c0c4ef4e2c2d7e9e4aab0773875932068d778e74f6f5
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7b7ae7c5bb58cdf42f58142b085e62f4e7a4f192e231d24d38bd4992f8be42
+oid sha256:00e3c513aa284f4a659f6163efed2ca9c3075b3ed338078bb8fc52b80c446eec
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf47f03b057010c0300b7a3c8bdc5b1074d0d042fbd2a7295866ded90ee1395
+oid sha256:eb63af91c38df442748945f1270836c41afb394cb114946f4943111c086f7fbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b80d146b8b37f82a1962ba385b8329fd6c2c35ba5116c53e131bb661ab681b
+oid sha256:ed29baad6d6611c736eccf18bdd7afdc5d6f3612cde61e7bfa83472d3e2068d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1519354581832886,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-60",
-  "epoch": 1.263157894736842,
+  "epoch": 1.6842105263157894,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,6 +459,154 @@
       "eval_samples_per_second": 48.71,
       "eval_steps_per_second": 4.871,
       "step": 60
+    },
+    {
+      "epoch": 1.2842105263157895,
+      "grad_norm": 0.4118487238883972,
+      "learning_rate": 0.00014135585049665207,
+      "loss": 0.9891,
+      "step": 61
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 0.32802432775497437,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 0.9878,
+      "step": 62
+    },
+    {
+      "epoch": 1.3263157894736843,
+      "grad_norm": 0.41467538475990295,
+      "learning_rate": 0.00013722936584019453,
+      "loss": 1.0542,
+      "step": 63
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 0.39795804023742676,
+      "learning_rate": 0.0001351374824081343,
+      "loss": 1.1358,
+      "step": 64
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.3385366201400757,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 1.1107,
+      "step": 65
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 0.4300186336040497,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0554,
+      "step": 66
+    },
+    {
+      "epoch": 1.4105263157894736,
+      "grad_norm": 0.4523608982563019,
+      "learning_rate": 0.00012875993274320173,
+      "loss": 1.1442,
+      "step": 67
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 0.48153308033943176,
+      "learning_rate": 0.00012660368455666752,
+      "loss": 1.1677,
+      "step": 68
+    },
+    {
+      "epoch": 1.4526315789473685,
+      "grad_norm": 0.46898069977760315,
+      "learning_rate": 0.0001244340406137894,
+      "loss": 1.1212,
+      "step": 69
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.3733386695384979,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.9843,
+      "step": 70
+    },
+    {
+      "epoch": 1.4947368421052631,
+      "grad_norm": 0.4410829544067383,
+      "learning_rate": 0.00012005894157832729,
+      "loss": 1.1679,
+      "step": 71
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 0.46537336707115173,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 1.0453,
+      "step": 72
+    },
+    {
+      "epoch": 1.5368421052631578,
+      "grad_norm": 0.39270663261413574,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.1019,
+      "step": 73
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 0.3547813296318054,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 0.9807,
+      "step": 74
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.33064335584640503,
+      "learning_rate": 0.00011119644761033078,
+      "loss": 0.9903,
+      "step": 75
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.41019386053085327,
+      "learning_rate": 0.00010896393089034336,
+      "loss": 0.9956,
+      "step": 76
+    },
+    {
+      "epoch": 1.6210526315789475,
+      "grad_norm": 0.43731600046157837,
+      "learning_rate": 0.00010672690056120399,
+      "loss": 0.9657,
+      "step": 77
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 0.38457056879997253,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 1.1255,
+      "step": 78
+    },
+    {
+      "epoch": 1.663157894736842,
+      "grad_norm": 0.4372155964374542,
+      "learning_rate": 0.00010224380642958052,
+      "loss": 1.105,
+      "step": 79
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.4701666533946991,
+      "learning_rate": 0.0001,
+      "loss": 1.0658,
+      "step": 80
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_loss": 1.152337908744812,
+      "eval_runtime": 2.0462,
+      "eval_samples_per_second": 48.871,
+      "eval_steps_per_second": 4.887,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -473,7 +621,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -487,7 +635,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6036925560913920.0,
+  "total_flos": 8119797185249280.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null