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:c5d440db78f5822de3cb666a768393fa3e7ba4f09c52484b37b7f60c1a2ef529
+oid sha256:638bb7a9e33217559e75f1456274d2de5e03fa2d7311a4f7803c8b884f2f4879
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b2f13e9fa30d42bdd39b98930a9468fd242e413392f51246e52e9962d20b9f
+oid sha256:c1105b0abe493aa9a8b80233db53b08837f1342577758f4c38f10307a8a59c65
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e43ee91deb5777851016850dee9dcc3fd2d91510bbf98de07d7de49243532b
+oid sha256:4a1f88010b3fb92b81a6bf3208d0ba0fbf8e03ccced365995d4ca15b18643cb4
 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": 1.918581485748291,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006501527859046876,
+  "best_metric": 1.8941960334777832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013003055718093752,
   "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": 25.384,
       "eval_steps_per_second": 3.174,
       "step": 25
+    },
+    {
+      "epoch": 0.006761588973408751,
+      "grad_norm": 1.1087353229522705,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.855,
+      "step": 26
+    },
+    {
+      "epoch": 0.007021650087770626,
+      "grad_norm": 1.423514485359192,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.9699,
+      "step": 27
+    },
+    {
+      "epoch": 0.0072817112021325014,
+      "grad_norm": 1.0818465948104858,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.834,
+      "step": 28
+    },
+    {
+      "epoch": 0.007541772316494376,
+      "grad_norm": 1.0367424488067627,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.8464,
+      "step": 29
+    },
+    {
+      "epoch": 0.007801833430856251,
+      "grad_norm": 1.0133615732192993,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8544,
+      "step": 30
+    },
+    {
+      "epoch": 0.008061894545218126,
+      "grad_norm": 1.3788729906082153,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7787,
+      "step": 31
+    },
+    {
+      "epoch": 0.00832195565958,
+      "grad_norm": 1.0124037265777588,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.8585,
+      "step": 32
+    },
+    {
+      "epoch": 0.008582016773941877,
+      "grad_norm": 2.421003818511963,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.8256,
+      "step": 33
+    },
+    {
+      "epoch": 0.008842077888303752,
+      "grad_norm": 1.1224663257598877,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9481,
+      "step": 34
+    },
+    {
+      "epoch": 0.009102139002665627,
+      "grad_norm": 1.1296459436416626,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0793,
+      "step": 35
+    },
+    {
+      "epoch": 0.009362200117027502,
+      "grad_norm": 1.1591365337371826,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1769,
+      "step": 36
+    },
+    {
+      "epoch": 0.009622261231389376,
+      "grad_norm": 0.9858690500259399,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.735,
+      "step": 37
+    },
+    {
+      "epoch": 0.009882322345751251,
+      "grad_norm": 0.973463237285614,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9322,
+      "step": 38
+    },
+    {
+      "epoch": 0.010142383460113126,
+      "grad_norm": 1.051450490951538,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.008,
+      "step": 39
+    },
+    {
+      "epoch": 0.010402444574475,
+      "grad_norm": 1.0749822854995728,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7987,
+      "step": 40
+    },
+    {
+      "epoch": 0.010662505688836877,
+      "grad_norm": 1.1620749235153198,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.96,
+      "step": 41
+    },
+    {
+      "epoch": 0.010922566803198752,
+      "grad_norm": 1.0434108972549438,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.9113,
+      "step": 42
+    },
+    {
+      "epoch": 0.011182627917560627,
+      "grad_norm": 1.1357665061950684,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.9717,
+      "step": 43
+    },
+    {
+      "epoch": 0.011442689031922502,
+      "grad_norm": 1.258142352104187,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9138,
+      "step": 44
+    },
+    {
+      "epoch": 0.011702750146284377,
+      "grad_norm": 0.9736027121543884,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8724,
+      "step": 45
+    },
+    {
+      "epoch": 0.011962811260646251,
+      "grad_norm": 1.0701547861099243,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.733,
+      "step": 46
+    },
+    {
+      "epoch": 0.012222872375008126,
+      "grad_norm": 1.0976836681365967,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.8591,
+      "step": 47
+    },
+    {
+      "epoch": 0.012482933489370003,
+      "grad_norm": 1.0743271112442017,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.8,
+      "step": 48
+    },
+    {
+      "epoch": 0.012742994603731878,
+      "grad_norm": 1.1132044792175293,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.9799,
+      "step": 49
+    },
+    {
+      "epoch": 0.013003055718093752,
+      "grad_norm": 1.1801347732543945,
+      "learning_rate": 0.0,
+      "loss": 2.2087,
+      "step": 50
+    },
+    {
+      "epoch": 0.013003055718093752,
+      "eval_loss": 1.8941960334777832,
+      "eval_runtime": 254.6608,
+      "eval_samples_per_second": 25.434,
+      "eval_steps_per_second": 3.181,
+      "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": 1.9422112326352896e+16,
+  "total_flos": 3.82785320606761e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null