Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58221a0143e8aebde729da2fcbaa6eb87dac9f940f124d7a4faf0a76c325f85c
+oid sha256:67f53b87a754d176f628d2679d33f097fa8f1f8e23e3bf976db37bf1df5fd5db
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b8a38914e78c69e67d0894e0570b1db318f03d1d56fc464177319a1dd30e59
+oid sha256:c8b7c2da57ccc193b5134a2fe658608a0b273693b0eb941e41daa8b253e553ea
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b634708e5784088c0b8ea7b56a28526273f52eb8d8f6121c82309bd75b906f
+oid sha256:3c2b267a9c1f060a3a4b12e9b0dd90b3e883cb4a63e0af4588507ebf2a63c41d
 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": 1.1927756071090698,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012990387113535984,
+  "best_metric": 1.1179519891738892,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.025980774227071967,
   "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": 2.838,
       "eval_steps_per_second": 1.421,
       "step": 25
+    },
+    {
+      "epoch": 0.013510002598077423,
+      "grad_norm": 1.0644140243530273,
+      "learning_rate": 0.0001,
+      "loss": 1.4075,
+      "step": 26
+    },
+    {
+      "epoch": 0.014029618082618862,
+      "grad_norm": 1.107295036315918,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.2733,
+      "step": 27
+    },
+    {
+      "epoch": 0.014549233567160301,
+      "grad_norm": 0.9191024303436279,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.3745,
+      "step": 28
+    },
+    {
+      "epoch": 0.01506884905170174,
+      "grad_norm": 1.1907384395599365,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.4105,
+      "step": 29
+    },
+    {
+      "epoch": 0.01558846453624318,
+      "grad_norm": 1.1258758306503296,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.5042,
+      "step": 30
+    },
+    {
+      "epoch": 0.01610808002078462,
+      "grad_norm": 0.9985445737838745,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.354,
+      "step": 31
+    },
+    {
+      "epoch": 0.01662769550532606,
+      "grad_norm": 1.5513899326324463,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.3469,
+      "step": 32
+    },
+    {
+      "epoch": 0.0171473109898675,
+      "grad_norm": 1.516951560974121,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.1163,
+      "step": 33
+    },
+    {
+      "epoch": 0.01766692647440894,
+      "grad_norm": 1.3848849534988403,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.1894,
+      "step": 34
+    },
+    {
+      "epoch": 0.018186541958950378,
+      "grad_norm": 1.3899662494659424,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.1942,
+      "step": 35
+    },
+    {
+      "epoch": 0.018706157443491817,
+      "grad_norm": 1.1531320810317993,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.1851,
+      "step": 36
+    },
+    {
+      "epoch": 0.019225772928033256,
+      "grad_norm": 1.802106261253357,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.4073,
+      "step": 37
+    },
+    {
+      "epoch": 0.019745388412574696,
+      "grad_norm": 2.1625168323516846,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.9136,
+      "step": 38
+    },
+    {
+      "epoch": 0.020265003897116135,
+      "grad_norm": 1.6054716110229492,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.594,
+      "step": 39
+    },
+    {
+      "epoch": 0.020784619381657574,
+      "grad_norm": 1.5181851387023926,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.3681,
+      "step": 40
+    },
+    {
+      "epoch": 0.021304234866199014,
+      "grad_norm": 2.0021746158599854,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.0049,
+      "step": 41
+    },
+    {
+      "epoch": 0.021823850350740453,
+      "grad_norm": 1.8782535791397095,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.4394,
+      "step": 42
+    },
+    {
+      "epoch": 0.022343465835281892,
+      "grad_norm": 1.5453753471374512,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.7239,
+      "step": 43
+    },
+    {
+      "epoch": 0.02286308131982333,
+      "grad_norm": 1.9624555110931396,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.8789,
+      "step": 44
+    },
+    {
+      "epoch": 0.02338269680436477,
+      "grad_norm": 1.882193684577942,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.365,
+      "step": 45
+    },
+    {
+      "epoch": 0.02390231228890621,
+      "grad_norm": 1.7306218147277832,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.1899,
+      "step": 46
+    },
+    {
+      "epoch": 0.02442192777344765,
+      "grad_norm": 2.0326011180877686,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.4146,
+      "step": 47
+    },
+    {
+      "epoch": 0.02494154325798909,
+      "grad_norm": 2.480106830596924,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.4643,
+      "step": 48
+    },
+    {
+      "epoch": 0.025461158742530528,
+      "grad_norm": 2.613811731338501,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.3891,
+      "step": 49
+    },
+    {
+      "epoch": 0.025980774227071967,
+      "grad_norm": 3.8450794219970703,
+      "learning_rate": 0.0,
+      "loss": 1.374,
+      "step": 50
+    },
+    {
+      "epoch": 0.025980774227071967,
+      "eval_loss": 1.1179519891738892,
+      "eval_runtime": 285.8158,
+      "eval_samples_per_second": 2.837,
+      "eval_steps_per_second": 1.42,
+      "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": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null