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:d437d85eeed7ef15375ba27a257c871986318122fbd22a95623cde03f9cd6195
+oid sha256:b39f6942fe1d6ce196683e9244f5cef329de1a463c9c5c5cb6a9736c1ee5ef49
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2d720ffe871f50a4df18e865ba5c60f677cc437d167ce06fc83b28c25dfa9b
+oid sha256:4cbafdec0eb4c791da81efa7ffd4ca3fad8aa3786812e9108ce4a1266cbc7209
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55a89c4a8dac8600dbdf7db5fb05fbd448c7e58c9f0906de94cf1cd7faf8fb6
+oid sha256:d622ab5cd5b2e759faeaea3c801e782e4027157d5931d0ebc0bc0dcaa81089f4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9245866997d65476c8df1633c0d85b635c5896fa0efd78be102687dd6c902ffb
+oid sha256:a1057cc960fefdfe6ec0e329fe4fd862e3679c96923a3b7696891aa62b272cb4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0218b546befe675ace34090cd9eaaf436e1624ae5449f8ce025903a5e8183504
+oid sha256:08e2c0ac6c8f20a063fc9ad0d5130c6fa48d88fd1cfce52a3723c03f902feb19
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc24d86716505fd2936908463954c72bf0627b6edf4ac979aebde0d3468f8e6
+oid sha256:8bfa488aad91bb75bfefa11338f2d3ae8f06352e91b05b5abe6e5057420b0299
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.40562108159065247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7905138339920948,
+  "best_metric": 0.29548346996307373,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5810276679841897,
   "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": 32.494,
       "eval_steps_per_second": 4.119,
       "step": 25
+    },
+    {
+      "epoch": 0.8221343873517787,
+      "grad_norm": 3.445368528366089,
+      "learning_rate": 5e-05,
+      "loss": 0.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.8537549407114624,
+      "grad_norm": 2.0446903705596924,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3686,
+      "step": 27
+    },
+    {
+      "epoch": 0.8853754940711462,
+      "grad_norm": 2.180802822113037,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3829,
+      "step": 28
+    },
+    {
+      "epoch": 0.9169960474308301,
+      "grad_norm": 2.177382469177246,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3715,
+      "step": 29
+    },
+    {
+      "epoch": 0.9486166007905138,
+      "grad_norm": 1.3226820230484009,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3066,
+      "step": 30
+    },
+    {
+      "epoch": 0.9802371541501976,
+      "grad_norm": 2.0610783100128174,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2111,
+      "step": 31
+    },
+    {
+      "epoch": 1.0118577075098814,
+      "grad_norm": 4.565697193145752,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5298,
+      "step": 32
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 2.319690704345703,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4085,
+      "step": 33
+    },
+    {
+      "epoch": 1.075098814229249,
+      "grad_norm": 1.3422417640686035,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2987,
+      "step": 34
+    },
+    {
+      "epoch": 1.1067193675889329,
+      "grad_norm": 2.624420404434204,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2566,
+      "step": 35
+    },
+    {
+      "epoch": 1.1383399209486167,
+      "grad_norm": 1.8034946918487549,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.281,
+      "step": 36
+    },
+    {
+      "epoch": 1.1699604743083003,
+      "grad_norm": 4.372071266174316,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3521,
+      "step": 37
+    },
+    {
+      "epoch": 1.2015810276679841,
+      "grad_norm": 3.8450584411621094,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2495,
+      "step": 38
+    },
+    {
+      "epoch": 1.233201581027668,
+      "grad_norm": 1.1193829774856567,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1677,
+      "step": 39
+    },
+    {
+      "epoch": 1.2648221343873518,
+      "grad_norm": 2.4760582447052,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3147,
+      "step": 40
+    },
+    {
+      "epoch": 1.2964426877470356,
+      "grad_norm": 1.6052770614624023,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.307,
+      "step": 41
+    },
+    {
+      "epoch": 1.3280632411067192,
+      "grad_norm": 1.8670191764831543,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3078,
+      "step": 42
+    },
+    {
+      "epoch": 1.359683794466403,
+      "grad_norm": 2.709547281265259,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2934,
+      "step": 43
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 3.421477794647217,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.252,
+      "step": 44
+    },
+    {
+      "epoch": 1.4229249011857708,
+      "grad_norm": 3.747044324874878,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3245,
+      "step": 45
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.8317062854766846,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2493,
+      "step": 46
+    },
+    {
+      "epoch": 1.4861660079051384,
+      "grad_norm": 1.9713412523269653,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.212,
+      "step": 47
+    },
+    {
+      "epoch": 1.5177865612648223,
+      "grad_norm": 1.5141923427581787,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2669,
+      "step": 48
+    },
+    {
+      "epoch": 1.5494071146245059,
+      "grad_norm": 1.7601076364517212,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3634,
+      "step": 49
+    },
+    {
+      "epoch": 1.5810276679841897,
+      "grad_norm": 2.3023111820220947,
+      "learning_rate": 0.0,
+      "loss": 0.3262,
+      "step": 50
+    },
+    {
+      "epoch": 1.5810276679841897,
+      "eval_loss": 0.29548346996307373,
+      "eval_runtime": 6.5505,
+      "eval_samples_per_second": 32.517,
+      "eval_steps_per_second": 4.122,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null