Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ff7b103fbf2a62cf83285c3d35e79764b0a6a100bfaf21cabf82c433c20f97
+oid sha256:0852cab315c00547006239006588df8ba649fa679a9f31fe039cd2e80d6a69c4
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0619521c92c9ef74bb584e95fe7eca487ab7a87e7fd26dcc19406232c50629
+oid sha256:4359ffee27fd15e7697af1b3881f7d9b531e6b6caf3e157bab3a7a0da95f93a7
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c155d1a1c1f969e878956dc759e2e9d11e367ab138a5f1443b6590f5e33f4be7
+oid sha256:f84d32a2e168a7189b8452898662edf5271122e9691f0a9121d95cd3b94bc525
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf4d0d730ccc9e2c8ddc5f19d724b476847a4fd05d50494d967b231b2616759
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.04533863067627,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.003146694986921549,
+  "best_metric": 11.043575286865234,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0039333687336519365,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,92 @@
       "eval_samples_per_second": 211.837,
       "eval_steps_per_second": 52.974,
       "step": 40
+    },
+    {
+      "epoch": 0.003225362361594588,
+      "grad_norm": 1.1779751777648926,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 44.1988,
+      "step": 41
+    },
+    {
+      "epoch": 0.0033040297362676263,
+      "grad_norm": 1.303176999092102,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 44.1614,
+      "step": 42
+    },
+    {
+      "epoch": 0.003382697110940665,
+      "grad_norm": 1.3195992708206177,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 44.1673,
+      "step": 43
+    },
+    {
+      "epoch": 0.003461364485613704,
+      "grad_norm": 1.385149598121643,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 44.1786,
+      "step": 44
+    },
+    {
+      "epoch": 0.003540031860286743,
+      "grad_norm": 1.317044734954834,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 44.1559,
+      "step": 45
+    },
+    {
+      "epoch": 0.003540031860286743,
+      "eval_loss": 11.04379653930664,
+      "eval_runtime": 53.7626,
+      "eval_samples_per_second": 199.116,
+      "eval_steps_per_second": 49.793,
+      "step": 45
+    },
+    {
+      "epoch": 0.003618699234959781,
+      "grad_norm": 1.2045557498931885,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 44.1879,
+      "step": 46
+    },
+    {
+      "epoch": 0.00369736660963282,
+      "grad_norm": 1.2000638246536255,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 44.1948,
+      "step": 47
+    },
+    {
+      "epoch": 0.003776033984305859,
+      "grad_norm": 1.237587809562683,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 44.1867,
+      "step": 48
+    },
+    {
+      "epoch": 0.0038547013589788973,
+      "grad_norm": 1.2065627574920654,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 44.1953,
+      "step": 49
+    },
+    {
+      "epoch": 0.0039333687336519365,
+      "grad_norm": 1.2785414457321167,
+      "learning_rate": 0.0,
+      "loss": 44.1624,
+      "step": 50
+    },
+    {
+      "epoch": 0.0039333687336519365,
+      "eval_loss": 11.043575286865234,
+      "eval_runtime": 51.5531,
+      "eval_samples_per_second": 207.65,
+      "eval_steps_per_second": 51.927,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -382,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 149736652800.0,
+  "total_flos": 187170816000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null