Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45d5f483bd316cb53ec5927dc41eec1c071f2ae13894887acb76c41c211bc20
+oid sha256:b6a57cfb26d94713f1271c173c1d103208fea6048d229594e679c614f345484c
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1e8bfe580b15a5252867c9aab6445be33cd092bc857612dcd0c2314d81b6e0
+oid sha256:e76a837259c6294a0bee49d7f0970d4241c758189734256e38737a371798f7bc
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea700645d5d847c0004a54d122e57717513cffc5f5cad95acb6fbff114711511
+oid sha256:035bec1b373bbb80e6880f74ff1d0891458dc64ff836d08504054861a735cb46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.8334808349609375,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.11825572801182557,
+  "epoch": 0.17738359201773837,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 244.912,
       "eval_steps_per_second": 61.357,
       "step": 50
+    },
+    {
+      "epoch": 0.12062084257206208,
+      "grad_norm": 0.2359568029642105,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 6.8327,
+      "step": 51
+    },
+    {
+      "epoch": 0.1229859571322986,
+      "grad_norm": 0.23612986505031586,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 6.832,
+      "step": 52
+    },
+    {
+      "epoch": 0.12535107169253512,
+      "grad_norm": 0.2312479317188263,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.8325,
+      "step": 53
+    },
+    {
+      "epoch": 0.12771618625277162,
+      "grad_norm": 0.22688338160514832,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 6.8332,
+      "step": 54
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.2325437366962433,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 6.8307,
+      "step": 55
+    },
+    {
+      "epoch": 0.13244641537324464,
+      "grad_norm": 0.22511352598667145,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 6.8324,
+      "step": 56
+    },
+    {
+      "epoch": 0.13481152993348117,
+      "grad_norm": 0.23657694458961487,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 6.8284,
+      "step": 57
+    },
+    {
+      "epoch": 0.13717664449371766,
+      "grad_norm": 0.23125885426998138,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 6.8301,
+      "step": 58
+    },
+    {
+      "epoch": 0.1395417590539542,
+      "grad_norm": 0.223617821931839,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 6.8289,
+      "step": 59
+    },
+    {
+      "epoch": 0.1419068736141907,
+      "grad_norm": 0.2352152019739151,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 6.8294,
+      "step": 60
+    },
+    {
+      "epoch": 0.1442719881744272,
+      "grad_norm": 0.2208397537469864,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 6.8318,
+      "step": 61
+    },
+    {
+      "epoch": 0.1466371027346637,
+      "grad_norm": 0.2222435176372528,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 6.8241,
+      "step": 62
+    },
+    {
+      "epoch": 0.14900221729490024,
+      "grad_norm": 0.21461376547813416,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 6.8299,
+      "step": 63
+    },
+    {
+      "epoch": 0.15136733185513673,
+      "grad_norm": 0.21560494601726532,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.833,
+      "step": 64
+    },
+    {
+      "epoch": 0.15373244641537326,
+      "grad_norm": 0.2203921377658844,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 6.828,
+      "step": 65
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 0.219926655292511,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 6.8277,
+      "step": 66
+    },
+    {
+      "epoch": 0.15846267553584628,
+      "grad_norm": 0.22064423561096191,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 6.8305,
+      "step": 67
+    },
+    {
+      "epoch": 0.16082779009608278,
+      "grad_norm": 0.21617873013019562,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 6.8269,
+      "step": 68
+    },
+    {
+      "epoch": 0.1631929046563193,
+      "grad_norm": 0.22675487399101257,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 6.8228,
+      "step": 69
+    },
+    {
+      "epoch": 0.1655580192165558,
+      "grad_norm": 0.22574570775032043,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 6.8249,
+      "step": 70
+    },
+    {
+      "epoch": 0.16792313377679233,
+      "grad_norm": 0.22798891365528107,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 6.8268,
+      "step": 71
+    },
+    {
+      "epoch": 0.17028824833702882,
+      "grad_norm": 0.21950149536132812,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 6.824,
+      "step": 72
+    },
+    {
+      "epoch": 0.17265336289726535,
+      "grad_norm": 0.22483089566230774,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 6.8232,
+      "step": 73
+    },
+    {
+      "epoch": 0.17501847745750185,
+      "grad_norm": 0.2169935554265976,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 6.8269,
+      "step": 74
+    },
+    {
+      "epoch": 0.17738359201773837,
+      "grad_norm": 0.21611732244491577,
+      "learning_rate": 0.0,
+      "loss": 6.8257,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7689024307200.0,
+  "total_flos": 11533536460800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null