Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fda780a7637952628840c7dbba992f6076ff923af7f248dbe432a454bb841d6
+oid sha256:701584a4c8821d108ee6250b6193f7a3d6336ebc3e3afb02f840632477336289
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef472e571c5f43d2526766af6497ddafc52291a3253ded0a78a027003add6265
+oid sha256:038a3200aec719f87a110871bc36df39f631b3c26406ac14fd2bf6387ac87b75
 size 204773716

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c08f6915e595382d92586f3314b8028f142fd536d4135db8e1793ac4d76ed1b
+oid sha256:871e151204423fd487773204e6469f02c34a93b96468e1a264873b592654919e
 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": 3.3842179775238037,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03947887879984208,
+  "best_metric": 1.5985764265060425,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07895775759968417,
   "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": 29.917,
       "eval_steps_per_second": 3.757,
       "step": 25
+    },
+    {
+      "epoch": 0.04105803395183577,
+      "grad_norm": 94.52870178222656,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 17.9243,
+      "step": 26
+    },
+    {
+      "epoch": 0.04263718910382945,
+      "grad_norm": 128.03819274902344,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 22.7165,
+      "step": 27
+    },
+    {
+      "epoch": 0.04421634425582313,
+      "grad_norm": 111.55404663085938,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 19.1854,
+      "step": 28
+    },
+    {
+      "epoch": 0.04579549940781682,
+      "grad_norm": 50.90269088745117,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 17.1951,
+      "step": 29
+    },
+    {
+      "epoch": 0.0473746545598105,
+      "grad_norm": 89.52201080322266,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 20.8415,
+      "step": 30
+    },
+    {
+      "epoch": 0.048953809711804186,
+      "grad_norm": 56.49177169799805,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 18.926,
+      "step": 31
+    },
+    {
+      "epoch": 0.050532964863797866,
+      "grad_norm": 19.61005401611328,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 8.947,
+      "step": 32
+    },
+    {
+      "epoch": 0.05211212001579155,
+      "grad_norm": 25.89728355407715,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 13.2629,
+      "step": 33
+    },
+    {
+      "epoch": 0.053691275167785234,
+      "grad_norm": 15.740513801574707,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 7.552,
+      "step": 34
+    },
+    {
+      "epoch": 0.05527043031977892,
+      "grad_norm": 13.16495132446289,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 7.5996,
+      "step": 35
+    },
+    {
+      "epoch": 0.0568495854717726,
+      "grad_norm": 23.94729232788086,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.7504,
+      "step": 36
+    },
+    {
+      "epoch": 0.05842874062376629,
+      "grad_norm": 11.532402038574219,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 6.6911,
+      "step": 37
+    },
+    {
+      "epoch": 0.06000789577575997,
+      "grad_norm": 10.864828109741211,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.2516,
+      "step": 38
+    },
+    {
+      "epoch": 0.06158705092775365,
+      "grad_norm": 11.170804977416992,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 5.7592,
+      "step": 39
+    },
+    {
+      "epoch": 0.06316620607974734,
+      "grad_norm": 8.69717788696289,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.4448,
+      "step": 40
+    },
+    {
+      "epoch": 0.06474536123174102,
+      "grad_norm": 10.19516658782959,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.0332,
+      "step": 41
+    },
+    {
+      "epoch": 0.0663245163837347,
+      "grad_norm": 11.726682662963867,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 5.0328,
+      "step": 42
+    },
+    {
+      "epoch": 0.06790367153572839,
+      "grad_norm": 5.6751861572265625,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0514,
+      "step": 43
+    },
+    {
+      "epoch": 0.06948282668772207,
+      "grad_norm": 9.052467346191406,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.8562,
+      "step": 44
+    },
+    {
+      "epoch": 0.07106198183971575,
+      "grad_norm": 12.07613468170166,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.2497,
+      "step": 45
+    },
+    {
+      "epoch": 0.07264113699170943,
+      "grad_norm": 9.69388484954834,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1887,
+      "step": 46
+    },
+    {
+      "epoch": 0.07422029214370311,
+      "grad_norm": 9.0044584274292,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.8677,
+      "step": 47
+    },
+    {
+      "epoch": 0.0757994472956968,
+      "grad_norm": 6.885035991668701,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1339,
+      "step": 48
+    },
+    {
+      "epoch": 0.07737860244769049,
+      "grad_norm": 6.512671947479248,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.128,
+      "step": 49
+    },
+    {
+      "epoch": 0.07895775759968417,
+      "grad_norm": 5.814499855041504,
+      "learning_rate": 0.0,
+      "loss": 0.1056,
+      "step": 50
+    },
+    {
+      "epoch": 0.07895775759968417,
+      "eval_loss": 1.5985764265060425,
+      "eval_runtime": 35.7696,
+      "eval_samples_per_second": 29.83,
+      "eval_steps_per_second": 3.746,
+      "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": 1.700676023353344e+16,
+  "total_flos": 2.640276036255744e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null