Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1abbb42592c5acca42f2058e4610f2135cefec86780cd26ce7fdc926ab5538
+oid sha256:76bb8d24673801d9f0ac03cda318ce63aa3afc09f922ed162b0afbfb8d265d0e
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74de3706848f95216743c0904d27d7cf2f764476a4e550231cf09f23ed9746ba
+oid sha256:d4675932e0350db4780394b73310645840ea97ecfd722361842541c60fbe1d1d
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af7e277fe0103e10d6cf1e1ebfff00ba2b616f2c041a959aea1b699ea34f672
+oid sha256:a5bd54eee130c17cd2a8fff7c374419f95111469057f1131bdf469dc930b821f
 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": 1.700939655303955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003440919413667332,
+  "best_metric": 1.6789900064468384,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.006881838827334664,
   "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": 113.846,
       "eval_steps_per_second": 14.234,
       "step": 25
+    },
+    {
+      "epoch": 0.003578556190214025,
+      "grad_norm": 1.8309403657913208,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5803,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037161929667607185,
+      "grad_norm": 1.8094103336334229,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4502,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038538297433074117,
+      "grad_norm": 1.837483286857605,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.587,
+      "step": 28
+    },
+    {
+      "epoch": 0.003991466519854105,
+      "grad_norm": 1.9412227869033813,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5866,
+      "step": 29
+    },
+    {
+      "epoch": 0.004129103296400798,
+      "grad_norm": 2.0173988342285156,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8093,
+      "step": 30
+    },
+    {
+      "epoch": 0.0042667400729474916,
+      "grad_norm": 2.0680758953094482,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7212,
+      "step": 31
+    },
+    {
+      "epoch": 0.004404376849494185,
+      "grad_norm": 1.93842351436615,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7122,
+      "step": 32
+    },
+    {
+      "epoch": 0.004542013626040878,
+      "grad_norm": 2.129516124725342,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7436,
+      "step": 33
+    },
+    {
+      "epoch": 0.004679650402587571,
+      "grad_norm": 1.9408643245697021,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6622,
+      "step": 34
+    },
+    {
+      "epoch": 0.004817287179134265,
+      "grad_norm": 1.9809863567352295,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6646,
+      "step": 35
+    },
+    {
+      "epoch": 0.004954923955680958,
+      "grad_norm": 2.126344919204712,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6433,
+      "step": 36
+    },
+    {
+      "epoch": 0.005092560732227651,
+      "grad_norm": 2.0364034175872803,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8124,
+      "step": 37
+    },
+    {
+      "epoch": 0.0052301975087743445,
+      "grad_norm": 2.0222976207733154,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.637,
+      "step": 38
+    },
+    {
+      "epoch": 0.005367834285321038,
+      "grad_norm": 2.119856834411621,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8401,
+      "step": 39
+    },
+    {
+      "epoch": 0.005505471061867731,
+      "grad_norm": 2.2993125915527344,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8964,
+      "step": 40
+    },
+    {
+      "epoch": 0.005643107838414424,
+      "grad_norm": 2.2917792797088623,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6729,
+      "step": 41
+    },
+    {
+      "epoch": 0.005780744614961118,
+      "grad_norm": 2.2233023643493652,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7126,
+      "step": 42
+    },
+    {
+      "epoch": 0.005918381391507811,
+      "grad_norm": 2.236922025680542,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7439,
+      "step": 43
+    },
+    {
+      "epoch": 0.006056018168054504,
+      "grad_norm": 2.325484275817871,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9329,
+      "step": 44
+    },
+    {
+      "epoch": 0.0061936549446011974,
+      "grad_norm": 2.3953254222869873,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8257,
+      "step": 45
+    },
+    {
+      "epoch": 0.006331291721147891,
+      "grad_norm": 2.677058219909668,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0218,
+      "step": 46
+    },
+    {
+      "epoch": 0.006468928497694584,
+      "grad_norm": 2.981875419616699,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0141,
+      "step": 47
+    },
+    {
+      "epoch": 0.006606565274241277,
+      "grad_norm": 3.397183895111084,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2502,
+      "step": 48
+    },
+    {
+      "epoch": 0.0067442020507879705,
+      "grad_norm": 3.8943850994110107,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3663,
+      "step": 49
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "grad_norm": 7.032155990600586,
+      "learning_rate": 0.0,
+      "loss": 3.1411,
+      "step": 50
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "eval_loss": 1.6789900064468384,
+      "eval_runtime": 107.4686,
+      "eval_samples_per_second": 113.866,
+      "eval_steps_per_second": 14.237,
+      "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": 975720907014144.0,
+  "total_flos": 1941781210988544.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null