Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46538a4943201ee30cec9a6736ca3e4456e2f470da792af256421c30e129d2a0
+oid sha256:8b4f3cd011c348bfde4653d5bd1cf4a359c439009f4e6fc6e38d2ea587a804e2
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df55b9cb37a7daab0e92d60a033065e07dc7d2255f4a32d3f6393fb400b341c
+oid sha256:671d0bb4d7b653d68476cd8ce34f4654bbd5e185cba94a189face56fec70cf1a
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3326486c222c4e1bdd305fe9707b43ca73a8cd8704d44dd28187e5bbec2c7161
+oid sha256:af420570318c6445188081e63eb1f51b495f9ae66f048360d3f550f2b7610027
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df107a67dba6f043fbc86d4f2efa1e1dd74df87dfdb2bbc88160116a6a5ef332
+oid sha256:83fe8cb627e7310fa68632acb34ed7c0fe79bf65df8fb9a20488a539e1068e07
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55adb0e546bf32aaf886c27dddd7fd5b21db7479fe93f9ea52b1d348d6437d2a
+oid sha256:fe367d4efab04e6ab7022885127c242250722a760cda01887cb2bcbe729f98b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eb96885ab8ba7ed6e1f4e5b1e1770f237ec207abffc750034244bdebf5d4e7f
+oid sha256:0b9402609a31a6bea143f0d03cae1c5ee8949bb458cc894fef5b568a8a69aa35
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.720038652420044,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7532751091703056,
+  "epoch": 3.024017467248908,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 15.625,
       "eval_steps_per_second": 4.063,
       "step": 25
+    },
+    {
+      "epoch": 1.8231441048034935,
+      "grad_norm": 1.7683324813842773,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 1.8031,
+      "step": 26
+    },
+    {
+      "epoch": 1.8930131004366813,
+      "grad_norm": 1.5601824522018433,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 1.6297,
+      "step": 27
+    },
+    {
+      "epoch": 1.962882096069869,
+      "grad_norm": 2.1221816539764404,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 1.7874,
+      "step": 28
+    },
+    {
+      "epoch": 2.039301310043668,
+      "grad_norm": 2.4992384910583496,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 2.8092,
+      "step": 29
+    },
+    {
+      "epoch": 2.109170305676856,
+      "grad_norm": 1.075144648551941,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 1.371,
+      "step": 30
+    },
+    {
+      "epoch": 2.1790393013100435,
+      "grad_norm": 1.4480336904525757,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 1.4821,
+      "step": 31
+    },
+    {
+      "epoch": 2.2489082969432315,
+      "grad_norm": 0.9556394815444946,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.9686,
+      "step": 32
+    },
+    {
+      "epoch": 2.3187772925764194,
+      "grad_norm": 1.2648524045944214,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 2.0128,
+      "step": 33
+    },
+    {
+      "epoch": 2.388646288209607,
+      "grad_norm": 1.1361418962478638,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 1.3708,
+      "step": 34
+    },
+    {
+      "epoch": 2.458515283842795,
+      "grad_norm": 2.031010627746582,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 1.5572,
+      "step": 35
+    },
+    {
+      "epoch": 2.5283842794759828,
+      "grad_norm": 1.5639622211456299,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 1.4997,
+      "step": 36
+    },
+    {
+      "epoch": 2.5982532751091703,
+      "grad_norm": 0.8983284831047058,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 1.3531,
+      "step": 37
+    },
+    {
+      "epoch": 2.668122270742358,
+      "grad_norm": 1.3355714082717896,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 1.3925,
+      "step": 38
+    },
+    {
+      "epoch": 2.7379912663755457,
+      "grad_norm": 1.021559476852417,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.8967,
+      "step": 39
+    },
+    {
+      "epoch": 2.8078602620087336,
+      "grad_norm": 1.4824175834655762,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 1.9967,
+      "step": 40
+    },
+    {
+      "epoch": 2.8777292576419216,
+      "grad_norm": 1.0364881753921509,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 1.4141,
+      "step": 41
+    },
+    {
+      "epoch": 2.947598253275109,
+      "grad_norm": 1.6417279243469238,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 1.4857,
+      "step": 42
+    },
+    {
+      "epoch": 3.024017467248908,
+      "grad_norm": 2.14969801902771,
+      "learning_rate": 1e-05,
+      "loss": 2.6031,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 5.3100522362424525e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null