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:dfa62b5a9aa3664fba57f5b73fa2f1944af28c6703a685d0077f2e3d50f6be03
+oid sha256:576f53319f01b2bce43f374455d21447020f2335044acf9c5c59e62ca65c8c3c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2389e8c0022667e48613b4619f62a4b93c9278424194077d6e1bbb3986f9628
+oid sha256:ec94c06ffd745c58f442418c01cbe7ec891213f590e278bbfa757856d0cb2b7f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8956c690f48a3865e6e5662196cdfbe2f756d60d95368e580ee80049f7f84a28
+oid sha256:bab76dcd72c1eb009f5930484673f0871d0c7533e23586dee98d4f043dce204d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf8bfacf51aaee0b7ae52034cf01bae98e38c288d1b5d8b807d4db3bee7543d
+oid sha256:52fe1e90eb753d352f1bda09a6e365ed98d2533ae7bbf9661970454988bd82f3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e112d3fab7945c9a1be0bdd0289438697f2bd24b929f370dcffcc822d7be1b2
+oid sha256:3da318435df057fa2bb51551adf96d3cd83d63cd726a89518cf882bd94fbee76
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92648d496110d1217d40562a091d9453457cccf10e9eb2b4a3231e137ac94c7d
+oid sha256:f65938b4c4d7f15d474c51a4364287866b5846a6824937fd58bc709f011ae329
 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": 0.8574177622795105,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0389610389610389,
+  "best_metric": 0.8472527861595154,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.0779220779220777,
   "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": 27.294,
       "eval_steps_per_second": 3.516,
       "step": 25
+    },
+    {
+      "epoch": 1.0805194805194804,
+      "grad_norm": 7.461629390716553,
+      "learning_rate": 5e-05,
+      "loss": 0.7891,
+      "step": 26
+    },
+    {
+      "epoch": 1.122077922077922,
+      "grad_norm": 8.457158088684082,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.746,
+      "step": 27
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 9.096592903137207,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7679,
+      "step": 28
+    },
+    {
+      "epoch": 1.2051948051948052,
+      "grad_norm": 11.256149291992188,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7985,
+      "step": 29
+    },
+    {
+      "epoch": 1.2467532467532467,
+      "grad_norm": 19.310684204101562,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8611,
+      "step": 30
+    },
+    {
+      "epoch": 1.2883116883116883,
+      "grad_norm": 8.05862808227539,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7934,
+      "step": 31
+    },
+    {
+      "epoch": 1.3298701298701299,
+      "grad_norm": 8.173073768615723,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7804,
+      "step": 32
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 8.027366638183594,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7394,
+      "step": 33
+    },
+    {
+      "epoch": 1.412987012987013,
+      "grad_norm": 10.47994613647461,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7495,
+      "step": 34
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 12.401349067687988,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7311,
+      "step": 35
+    },
+    {
+      "epoch": 1.4961038961038962,
+      "grad_norm": 20.069787979125977,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8611,
+      "step": 36
+    },
+    {
+      "epoch": 1.5376623376623377,
+      "grad_norm": 8.742693901062012,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7572,
+      "step": 37
+    },
+    {
+      "epoch": 1.5792207792207793,
+      "grad_norm": 8.219439506530762,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7444,
+      "step": 38
+    },
+    {
+      "epoch": 1.6207792207792209,
+      "grad_norm": 9.581369400024414,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7499,
+      "step": 39
+    },
+    {
+      "epoch": 1.6623376623376624,
+      "grad_norm": 9.756193161010742,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.695,
+      "step": 40
+    },
+    {
+      "epoch": 1.703896103896104,
+      "grad_norm": 12.657617568969727,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7158,
+      "step": 41
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 18.518951416015625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7977,
+      "step": 42
+    },
+    {
+      "epoch": 1.7870129870129872,
+      "grad_norm": 8.128936767578125,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7749,
+      "step": 43
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 8.058290481567383,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7658,
+      "step": 44
+    },
+    {
+      "epoch": 1.87012987012987,
+      "grad_norm": 8.940549850463867,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.774,
+      "step": 45
+    },
+    {
+      "epoch": 1.9116883116883117,
+      "grad_norm": 10.234519958496094,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7182,
+      "step": 46
+    },
+    {
+      "epoch": 1.9532467532467532,
+      "grad_norm": 12.169855117797852,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.698,
+      "step": 47
+    },
+    {
+      "epoch": 1.9948051948051948,
+      "grad_norm": 21.937511444091797,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8068,
+      "step": 48
+    },
+    {
+      "epoch": 2.036363636363636,
+      "grad_norm": 8.143593788146973,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7351,
+      "step": 49
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 7.586548328399658,
+      "learning_rate": 0.0,
+      "loss": 0.7503,
+      "step": 50
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "eval_loss": 0.8472527861595154,
+      "eval_runtime": 6.2447,
+      "eval_samples_per_second": 26.102,
+      "eval_steps_per_second": 3.363,
+      "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": 2.8620878873257574e+17,
+  "total_flos": 5.7188690633844326e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null