Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc85b58d57c78556891194f51cd0e6208e847d6918500643ee8abece7df636d
+oid sha256:e21cdd461e5bc9d4f50da8965f5ad434c55a595d047595f4f62e7336561cec25
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d128aba7f814bf530a2016047fc23e5acb76d224287872cd8a5b9b62e9cfc2d9
+oid sha256:539c312412bfbba5da3668598d9d1e7de7074b6dd84888b8efaf3bb195cc1161
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8dd46eccd2cf6a6986b75cb5b467105e129fe7f5224e3ac4e6b441948d6ee2c
+oid sha256:4c249c87c658105d1aadd71b0ab03f2b7d948a553afb9a501e72f2761aa2b5f3
 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": 1.629266619682312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010383137784238397,
+  "best_metric": 1.4880585670471191,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020766275568476794,
   "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": 3.2,
       "eval_steps_per_second": 1.6,
       "step": 25
+    },
+    {
+      "epoch": 0.010798463295607933,
+      "grad_norm": 0.24868632853031158,
+      "learning_rate": 0.0001,
+      "loss": 0.4748,
+      "step": 26
+    },
+    {
+      "epoch": 0.011213788806977468,
+      "grad_norm": 0.5774146914482117,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.7875,
+      "step": 27
+    },
+    {
+      "epoch": 0.011629114318347004,
+      "grad_norm": 0.7732341885566711,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.6975,
+      "step": 28
+    },
+    {
+      "epoch": 0.01204443982971654,
+      "grad_norm": 0.7076338529586792,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.7049,
+      "step": 29
+    },
+    {
+      "epoch": 0.012459765341086075,
+      "grad_norm": 0.7225150465965271,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.9696,
+      "step": 30
+    },
+    {
+      "epoch": 0.012875090852455612,
+      "grad_norm": 0.6315404772758484,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.7684,
+      "step": 31
+    },
+    {
+      "epoch": 0.013290416363825148,
+      "grad_norm": 0.6427789926528931,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.7576,
+      "step": 32
+    },
+    {
+      "epoch": 0.013705741875194685,
+      "grad_norm": 0.6234633922576904,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.7386,
+      "step": 33
+    },
+    {
+      "epoch": 0.01412106738656422,
+      "grad_norm": 0.6091985702514648,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.8351,
+      "step": 34
+    },
+    {
+      "epoch": 0.014536392897933756,
+      "grad_norm": 0.5979273915290833,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.7006,
+      "step": 35
+    },
+    {
+      "epoch": 0.014951718409303292,
+      "grad_norm": 0.5986985564231873,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.8208,
+      "step": 36
+    },
+    {
+      "epoch": 0.015367043920672827,
+      "grad_norm": 0.6158512234687805,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.4706,
+      "step": 37
+    },
+    {
+      "epoch": 0.015782369432042365,
+      "grad_norm": 0.6060137152671814,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.5508,
+      "step": 38
+    },
+    {
+      "epoch": 0.0161976949434119,
+      "grad_norm": 0.6137194633483887,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.5507,
+      "step": 39
+    },
+    {
+      "epoch": 0.016613020454781434,
+      "grad_norm": 0.6484068632125854,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.5866,
+      "step": 40
+    },
+    {
+      "epoch": 0.017028345966150972,
+      "grad_norm": 0.6532328128814697,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.9501,
+      "step": 41
+    },
+    {
+      "epoch": 0.017443671477520507,
+      "grad_norm": 0.6872005462646484,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.8211,
+      "step": 42
+    },
+    {
+      "epoch": 0.01785899698889004,
+      "grad_norm": 0.7130753993988037,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.7857,
+      "step": 43
+    },
+    {
+      "epoch": 0.01827432250025958,
+      "grad_norm": 0.6461330652236938,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.6955,
+      "step": 44
+    },
+    {
+      "epoch": 0.018689648011629114,
+      "grad_norm": 0.6232130527496338,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.5653,
+      "step": 45
+    },
+    {
+      "epoch": 0.01910497352299865,
+      "grad_norm": 0.7634522318840027,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.9665,
+      "step": 46
+    },
+    {
+      "epoch": 0.019520299034368187,
+      "grad_norm": 0.6845643520355225,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 3.0372,
+      "step": 47
+    },
+    {
+      "epoch": 0.01993562454573772,
+      "grad_norm": 0.633053183555603,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.7007,
+      "step": 48
+    },
+    {
+      "epoch": 0.02035095005710726,
+      "grad_norm": 0.7356605529785156,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.2683,
+      "step": 49
+    },
+    {
+      "epoch": 0.020766275568476794,
+      "grad_norm": 0.7480798363685608,
+      "learning_rate": 0.0,
+      "loss": 3.1527,
+      "step": 50
+    },
+    {
+      "epoch": 0.020766275568476794,
+      "eval_loss": 1.4880585670471191,
+      "eval_runtime": 316.8721,
+      "eval_samples_per_second": 3.2,
+      "eval_steps_per_second": 1.6,
+      "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": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null