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:b71ee60726a41076156d3aedafa228090a72d1cac3d06b1778faec5b2f668496
+oid sha256:5411aed783493e3edc77afc49ca3ea3ae22af99e68783e5baea3cea1d880c59c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd20e47b83a408cae57678c674e8a3ed5bb41652fca9022beba9d061b17fd2c
+oid sha256:f15e73a96398b15d55d672c6c721d7a320e98d3939c472952b7ee006c295d00a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50223eb08f5fd453c6ee1745df80d7bc8d10ae0f533fcbe271b13f08b62192f0
+oid sha256:cbb14d2adca2a20917db3557028c7e3f1226dde47e7fed9b8851cfebbe463e13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.952971339225769,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005465376837732962,
+  "epoch": 0.010930753675465924,
   "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": 13.538,
       "eval_steps_per_second": 1.692,
       "step": 25
+    },
+    {
+      "epoch": 0.00568399191124228,
+      "grad_norm": 5.873587131500244,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.8957,
+      "step": 26
+    },
+    {
+      "epoch": 0.005902606984751598,
+      "grad_norm": 5.590426921844482,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.7604,
+      "step": 27
+    },
+    {
+      "epoch": 0.006121222058260917,
+      "grad_norm": 5.399012088775635,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.3861,
+      "step": 28
+    },
+    {
+      "epoch": 0.006339837131770235,
+      "grad_norm": 5.434515953063965,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.939,
+      "step": 29
+    },
+    {
+      "epoch": 0.006558452205279554,
+      "grad_norm": 5.8018999099731445,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.5712,
+      "step": 30
+    },
+    {
+      "epoch": 0.0067770672787888725,
+      "grad_norm": 5.351323127746582,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.0597,
+      "step": 31
+    },
+    {
+      "epoch": 0.006995682352298191,
+      "grad_norm": 6.120589733123779,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.3157,
+      "step": 32
+    },
+    {
+      "epoch": 0.00721429742580751,
+      "grad_norm": 6.096648216247559,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.3606,
+      "step": 33
+    },
+    {
+      "epoch": 0.007432912499316828,
+      "grad_norm": 6.251641750335693,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.1731,
+      "step": 34
+    },
+    {
+      "epoch": 0.007651527572826147,
+      "grad_norm": 9.29775619506836,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4783,
+      "step": 35
+    },
+    {
+      "epoch": 0.007870142646335464,
+      "grad_norm": 11.230655670166016,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.1192,
+      "step": 36
+    },
+    {
+      "epoch": 0.008088757719844783,
+      "grad_norm": 10.136025428771973,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0439,
+      "step": 37
+    },
+    {
+      "epoch": 0.008307372793354102,
+      "grad_norm": 9.469839096069336,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9625,
+      "step": 38
+    },
+    {
+      "epoch": 0.00852598786686342,
+      "grad_norm": 8.718362808227539,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0432,
+      "step": 39
+    },
+    {
+      "epoch": 0.008744602940372739,
+      "grad_norm": 9.521910667419434,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.9762,
+      "step": 40
+    },
+    {
+      "epoch": 0.008963218013882057,
+      "grad_norm": 9.352231979370117,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0075,
+      "step": 41
+    },
+    {
+      "epoch": 0.009181833087391376,
+      "grad_norm": 7.3484673500061035,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.955,
+      "step": 42
+    },
+    {
+      "epoch": 0.009400448160900694,
+      "grad_norm": 8.650862693786621,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0644,
+      "step": 43
+    },
+    {
+      "epoch": 0.009619063234410013,
+      "grad_norm": 10.559455871582031,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.07,
+      "step": 44
+    },
+    {
+      "epoch": 0.009837678307919331,
+      "grad_norm": 11.691309928894043,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9961,
+      "step": 45
+    },
+    {
+      "epoch": 0.01005629338142865,
+      "grad_norm": 8.233396530151367,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0817,
+      "step": 46
+    },
+    {
+      "epoch": 0.010274908454937969,
+      "grad_norm": 6.722311973571777,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8507,
+      "step": 47
+    },
+    {
+      "epoch": 0.010493523528447287,
+      "grad_norm": 6.870611190795898,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8651,
+      "step": 48
+    },
+    {
+      "epoch": 0.010712138601956606,
+      "grad_norm": 10.630144119262695,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8569,
+      "step": 49
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "grad_norm": 8.184146881103516,
+      "learning_rate": 0.0,
+      "loss": 0.8619,
+      "step": 50
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "eval_loss": 0.9873545169830322,
+      "eval_runtime": 568.3541,
+      "eval_samples_per_second": 13.555,
+      "eval_steps_per_second": 1.694,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.57749904900096e+16,
+  "total_flos": 7.11922310751191e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null