Training in progress, step 113, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b787b9f89d02f7dc3b19bedf8767e6c4968a519b508b2c87dad6d80083b1ca
+oid sha256:5692f34c97b1100d6c75723da71e2b0f079d9b91e8a95fe6f494f4b63f6a10d6
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8fbc5adea491f72a0015774548c8af88a7276041f77ca09132f6b0b1933ebf
+oid sha256:e04b29f4c1c43c72a522148668f8ef9c6f68d772079c07760733a8fe27f5b10e
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b42a00279b6c46adb4b97489b480522f7ffc839a33b02d2036504646d2a860f
+oid sha256:b367c1d9dc53d9831965356fc9a49bb755995d4a290a4eb8463184b6c0ce43d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c90fedf08c2ca11af554a410bf047de63425ab96dca555f6c49020443d209ed
+oid sha256:45b74f08c885c76380c4ac1d181f205527fac73fc64a3e940746e9c93cee703f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.01180648803711,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.8859357696566998,
+  "epoch": 1.0066445182724253,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 113,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -723,6 +723,97 @@
       "eval_samples_per_second": 279.069,
       "eval_steps_per_second": 70.502,
       "step": 100
+    },
+    {
+      "epoch": 0.8947951273532669,
+      "grad_norm": 1.4452682733535767,
+      "learning_rate": 6.623751839046455e-06,
+      "loss": 88.1532,
+      "step": 101
+    },
+    {
+      "epoch": 0.9036544850498339,
+      "grad_norm": 1.3395559787750244,
+      "learning_rate": 5.575745090030138e-06,
+      "loss": 88.1788,
+      "step": 102
+    },
+    {
+      "epoch": 0.9125138427464009,
+      "grad_norm": 1.4853826761245728,
+      "learning_rate": 4.61557487563673e-06,
+      "loss": 88.1785,
+      "step": 103
+    },
+    {
+      "epoch": 0.9213732004429679,
+      "grad_norm": 1.385549545288086,
+      "learning_rate": 3.7441343776484117e-06,
+      "loss": 88.1602,
+      "step": 104
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.4303137063980103,
+      "learning_rate": 2.9622342385589254e-06,
+      "loss": 88.0615,
+      "step": 105
+    },
+    {
+      "epoch": 0.9390919158361019,
+      "grad_norm": 1.3606700897216797,
+      "learning_rate": 2.2706018074875045e-06,
+      "loss": 88.1822,
+      "step": 106
+    },
+    {
+      "epoch": 0.9479512735326688,
+      "grad_norm": 1.3698482513427734,
+      "learning_rate": 1.6698804635747579e-06,
+      "loss": 88.1556,
+      "step": 107
+    },
+    {
+      "epoch": 0.9568106312292359,
+      "grad_norm": 1.4697903394699097,
+      "learning_rate": 1.160629017490389e-06,
+      "loss": 88.1125,
+      "step": 108
+    },
+    {
+      "epoch": 0.9656699889258029,
+      "grad_norm": 1.2570511102676392,
+      "learning_rate": 7.433211916092142e-07,
+      "loss": 88.0736,
+      "step": 109
+    },
+    {
+      "epoch": 0.9745293466223699,
+      "grad_norm": 1.4869191646575928,
+      "learning_rate": 4.1834517933907467e-07,
+      "loss": 88.137,
+      "step": 110
+    },
+    {
+      "epoch": 0.9833887043189369,
+      "grad_norm": 1.265148401260376,
+      "learning_rate": 1.8600328401061629e-07,
+      "loss": 88.1054,
+      "step": 111
+    },
+    {
+      "epoch": 0.9922480620155039,
+      "grad_norm": 1.3339345455169678,
+      "learning_rate": 4.651163766484779e-08,
+      "loss": 88.0929,
+      "step": 112
+    },
+    {
+      "epoch": 1.0066445182724253,
+      "grad_norm": 1.3491634130477905,
+      "learning_rate": 0.0,
+      "loss": 88.1079,
+      "step": 113
     }
   ],
   "logging_steps": 1,
@@ -746,12 +837,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1497366528000.0,
+  "total_flos": 1692024176640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null