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:c7e763e5d1b71defade0ea5776003586d13247cc6a27db65b8ca02c25e05f1d5
+oid sha256:881590cb83796e8f9e7f613dd55c636d14e43244b025b57e1cf3e34f447bab71
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fed4d8e7b56ee058401ace3640f3912a648971d005be1dc940c66e4b8919ad
+oid sha256:7181fe967e2884bf861d20ea8ec6a780fa5220b5bbb32b8261e69083e421f167
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af542938e45c3a5fd140809f8275a5b870a3c7a84d42c3bef4ff2e349cb4a3a3
+oid sha256:a36b74e20e30062a5bc3571617676f6ebd5d9a256ec1f65d71d16e56ee83721d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d2ac6f436212d7cc15fe192c8ad1576d2baee0013a7ccf6774dfb1b4eb9ffe
+oid sha256:a812b94aba6cc6589dea9e5e425ac894cfa71f94e7dbd4a0d4aa863303cacc08
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9313b9d7033efa524638e5bb969e6eebaeaea091dd808aad2abf668ebb927596
+oid sha256:5e19edfcde514f1c7463f8f27a41ae012b7a9c41f175834ac87cfb743cbc49ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228988f29b6513a6cba720dd5196c43d86228196e04d890129202b046bd951b8
+oid sha256:b5fedee966240f0b8ef690fbf31d82870be89cc55bc591f498d1eabbc85c6685
 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": 0.09560767561197281,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0278481012658227,
+  "best_metric": 0.09009819477796555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.0556962025316454,
   "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": 33.909,
       "eval_steps_per_second": 4.264,
       "step": 25
+    },
+    {
+      "epoch": 1.0683544303797468,
+      "grad_norm": 0.20028449594974518,
+      "learning_rate": 5e-05,
+      "loss": 0.0578,
+      "step": 26
+    },
+    {
+      "epoch": 1.1088607594936708,
+      "grad_norm": 0.17910338938236237,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0266,
+      "step": 27
+    },
+    {
+      "epoch": 1.1493670886075948,
+      "grad_norm": 0.6377457976341248,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0856,
+      "step": 28
+    },
+    {
+      "epoch": 1.189873417721519,
+      "grad_norm": 0.6066492795944214,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0464,
+      "step": 29
+    },
+    {
+      "epoch": 1.230379746835443,
+      "grad_norm": 0.09580016881227493,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0327,
+      "step": 30
+    },
+    {
+      "epoch": 1.2708860759493672,
+      "grad_norm": 0.6638514995574951,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0382,
+      "step": 31
+    },
+    {
+      "epoch": 1.311392405063291,
+      "grad_norm": 0.2734617292881012,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0544,
+      "step": 32
+    },
+    {
+      "epoch": 1.3518987341772153,
+      "grad_norm": 0.5110018253326416,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1043,
+      "step": 33
+    },
+    {
+      "epoch": 1.3924050632911391,
+      "grad_norm": 0.5602982640266418,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0719,
+      "step": 34
+    },
+    {
+      "epoch": 1.4329113924050634,
+      "grad_norm": 0.3711053431034088,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0676,
+      "step": 35
+    },
+    {
+      "epoch": 1.4734177215189874,
+      "grad_norm": 0.16281400620937347,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0146,
+      "step": 36
+    },
+    {
+      "epoch": 1.5139240506329115,
+      "grad_norm": 0.15146973729133606,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0525,
+      "step": 37
+    },
+    {
+      "epoch": 1.5544303797468353,
+      "grad_norm": 0.46896079182624817,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0544,
+      "step": 38
+    },
+    {
+      "epoch": 1.5949367088607596,
+      "grad_norm": 0.8656461834907532,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0566,
+      "step": 39
+    },
+    {
+      "epoch": 1.6354430379746834,
+      "grad_norm": 0.6313591003417969,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.084,
+      "step": 40
+    },
+    {
+      "epoch": 1.6759493670886076,
+      "grad_norm": 1.0002316236495972,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1236,
+      "step": 41
+    },
+    {
+      "epoch": 1.7164556962025317,
+      "grad_norm": 0.25096988677978516,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0603,
+      "step": 42
+    },
+    {
+      "epoch": 1.7569620253164557,
+      "grad_norm": 0.6598709225654602,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0335,
+      "step": 43
+    },
+    {
+      "epoch": 1.7974683544303798,
+      "grad_norm": 0.2084610015153885,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0304,
+      "step": 44
+    },
+    {
+      "epoch": 1.8379746835443038,
+      "grad_norm": 0.3605667054653168,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0538,
+      "step": 45
+    },
+    {
+      "epoch": 1.8784810126582279,
+      "grad_norm": 0.5047392249107361,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0532,
+      "step": 46
+    },
+    {
+      "epoch": 1.918987341772152,
+      "grad_norm": 0.1747433990240097,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0328,
+      "step": 47
+    },
+    {
+      "epoch": 1.959493670886076,
+      "grad_norm": 0.3657343089580536,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.065,
+      "step": 48
+    },
+    {
+      "epoch": 2.0151898734177216,
+      "grad_norm": 0.3927527666091919,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0802,
+      "step": 49
+    },
+    {
+      "epoch": 2.0556962025316454,
+      "grad_norm": 0.4265093505382538,
+      "learning_rate": 0.0,
+      "loss": 0.0281,
+      "step": 50
+    },
+    {
+      "epoch": 2.0556962025316454,
+      "eval_loss": 0.09009819477796555,
+      "eval_runtime": 4.9245,
+      "eval_samples_per_second": 33.912,
+      "eval_steps_per_second": 4.264,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null