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:f655b55469f2711bd59a7cf86377cc427ffce057be66704e0745864794777f57
+oid sha256:43e3a13de877f06b55a6c10449bdc723f733e9b49326875c4a24d2799c028ada
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55bc55916345c4db2a1c57f3c72f7a9b8172c778033f82056c736b04fc1e786a
+oid sha256:c8276c47b85b70433ce5d10239633f38bfe72858ebb6d9dbaec159c36c916c27
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49d14564eaac24cf5586f7de38ab5f99b3305fd0976438d88f8f0017718547c
+oid sha256:4fd18817582fbcbf75cbcc83bfb44274be4c3c5b4de740f13ad90a013615a094
 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": 0.20218083262443542,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0212630236019562,
+  "best_metric": 0.13084866106510162,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0425260472039124,
   "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": 13.787,
       "eval_steps_per_second": 6.907,
       "step": 25
+    },
+    {
+      "epoch": 0.022113544546034446,
+      "grad_norm": 3.286043882369995,
+      "learning_rate": 0.0001,
+      "loss": 0.2145,
+      "step": 26
+    },
+    {
+      "epoch": 0.022964065490112696,
+      "grad_norm": 1.2308350801467896,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.073,
+      "step": 27
+    },
+    {
+      "epoch": 0.023814586434190942,
+      "grad_norm": 2.7257020473480225,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0994,
+      "step": 28
+    },
+    {
+      "epoch": 0.02466510737826919,
+      "grad_norm": 4.320733547210693,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0897,
+      "step": 29
+    },
+    {
+      "epoch": 0.02551562832234744,
+      "grad_norm": 2.8672146797180176,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.1025,
+      "step": 30
+    },
+    {
+      "epoch": 0.026366149266425686,
+      "grad_norm": 5.4049530029296875,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.1706,
+      "step": 31
+    },
+    {
+      "epoch": 0.027216670210503932,
+      "grad_norm": 5.402988910675049,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.1161,
+      "step": 32
+    },
+    {
+      "epoch": 0.028067191154582182,
+      "grad_norm": 4.142680644989014,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.2015,
+      "step": 33
+    },
+    {
+      "epoch": 0.02891771209866043,
+      "grad_norm": 2.3282439708709717,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.045,
+      "step": 34
+    },
+    {
+      "epoch": 0.02976823304273868,
+      "grad_norm": 4.630530834197998,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.132,
+      "step": 35
+    },
+    {
+      "epoch": 0.030618753986816925,
+      "grad_norm": 4.213309288024902,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.2643,
+      "step": 36
+    },
+    {
+      "epoch": 0.03146927493089517,
+      "grad_norm": 2.101949691772461,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0554,
+      "step": 37
+    },
+    {
+      "epoch": 0.03231979587497342,
+      "grad_norm": 2.3443305492401123,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.1592,
+      "step": 38
+    },
+    {
+      "epoch": 0.03317031681905167,
+      "grad_norm": 1.8996334075927734,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0852,
+      "step": 39
+    },
+    {
+      "epoch": 0.03402083776312992,
+      "grad_norm": 3.1621198654174805,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.2235,
+      "step": 40
+    },
+    {
+      "epoch": 0.034871358707208165,
+      "grad_norm": 2.249910354614258,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0907,
+      "step": 41
+    },
+    {
+      "epoch": 0.03572187965128641,
+      "grad_norm": 4.59539270401001,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.2673,
+      "step": 42
+    },
+    {
+      "epoch": 0.03657240059536466,
+      "grad_norm": 2.3557896614074707,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0744,
+      "step": 43
+    },
+    {
+      "epoch": 0.03742292153944291,
+      "grad_norm": 2.4401204586029053,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.074,
+      "step": 44
+    },
+    {
+      "epoch": 0.03827344248352116,
+      "grad_norm": 3.605272054672241,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.1469,
+      "step": 45
+    },
+    {
+      "epoch": 0.039123963427599405,
+      "grad_norm": 2.9214582443237305,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0586,
+      "step": 46
+    },
+    {
+      "epoch": 0.03997448437167765,
+      "grad_norm": 4.692743301391602,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.3004,
+      "step": 47
+    },
+    {
+      "epoch": 0.0408250053157559,
+      "grad_norm": 3.563737392425537,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.2818,
+      "step": 48
+    },
+    {
+      "epoch": 0.04167552625983415,
+      "grad_norm": 5.832004070281982,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.2764,
+      "step": 49
+    },
+    {
+      "epoch": 0.0425260472039124,
+      "grad_norm": 3.295628786087036,
+      "learning_rate": 0.0,
+      "loss": 0.226,
+      "step": 50
+    },
+    {
+      "epoch": 0.0425260472039124,
+      "eval_loss": 0.13084866106510162,
+      "eval_runtime": 35.8872,
+      "eval_samples_per_second": 13.793,
+      "eval_steps_per_second": 6.911,
+      "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": 1802385752064000.0,
+  "total_flos": 3604771504128000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null