Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5d157c0ea14f72bc0eb271e079a94d58ac33470f206884d96083878f383707
+oid sha256:286e90daa26e3cfdae2481a8dbd0edf0c78de5fdc0594cdf0e79a2c97f120ff8
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a798a6d2a961f0496095f4afa63c09618f7abc5905ac90da3e36af496e6c80
+oid sha256:659e3ec5958b517e55de3924286fcba74296ba808b9ed603e772a800ff84f93f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b566080560a768bd282dfb4d58666a4bbc78a891d0da9eabbc5ed4f844dc6327
+oid sha256:5e980caab9770f97cf1aac064b50e615ed2cfa77cd2dc5e07d37315000fa83d0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda6b5123d6b8b648d24ad5098e78f1851d45647d09b7d749d7a034e8273ed6a
+oid sha256:f9bf3d93efcb8d87c1d784a40b8b0af847d14159ab7c2f94c45ef9095cb4138c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be1335a5283a32118d9bf809cc7c8c6a6d841792fe466383cb389c5a95d6b9a
+oid sha256:fc632b80cfb32af6153a3d2d90acdf7a50c9797020f0844b46931aeb2f3a064c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57323ce53965765649207513cecabc1735bde0294f4b99bd3212b04c35a187f8
+oid sha256:4f97127c0b1e18517198350ea6b3e331cb72c24100723b9a80e9e713847987e9
 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": 1.6422466039657593,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0049589030906363515,
+  "best_metric": 1.0755832195281982,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009917806181272703,
   "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": 87.27,
       "eval_steps_per_second": 10.91,
       "step": 25
+    },
+    {
+      "epoch": 0.005157259214261805,
+      "grad_norm": 1.9225361347198486,
+      "learning_rate": 5e-05,
+      "loss": 1.934,
+      "step": 26
+    },
+    {
+      "epoch": 0.005355615337887259,
+      "grad_norm": 1.6286966800689697,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6607,
+      "step": 27
+    },
+    {
+      "epoch": 0.005553971461512713,
+      "grad_norm": 1.5591243505477905,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6271,
+      "step": 28
+    },
+    {
+      "epoch": 0.005752327585138168,
+      "grad_norm": 1.3496639728546143,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4905,
+      "step": 29
+    },
+    {
+      "epoch": 0.005950683708763622,
+      "grad_norm": 1.1657429933547974,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2554,
+      "step": 30
+    },
+    {
+      "epoch": 0.0061490398323890754,
+      "grad_norm": 1.1974936723709106,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1984,
+      "step": 31
+    },
+    {
+      "epoch": 0.006347395956014529,
+      "grad_norm": 1.2555491924285889,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3582,
+      "step": 32
+    },
+    {
+      "epoch": 0.006545752079639984,
+      "grad_norm": 1.268581509590149,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1061,
+      "step": 33
+    },
+    {
+      "epoch": 0.006744108203265438,
+      "grad_norm": 1.210546851158142,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2048,
+      "step": 34
+    },
+    {
+      "epoch": 0.006942464326890892,
+      "grad_norm": 1.3306183815002441,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1493,
+      "step": 35
+    },
+    {
+      "epoch": 0.0071408204505163456,
+      "grad_norm": 1.5224374532699585,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2848,
+      "step": 36
+    },
+    {
+      "epoch": 0.007339176574141799,
+      "grad_norm": 1.2854976654052734,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0915,
+      "step": 37
+    },
+    {
+      "epoch": 0.007537532697767254,
+      "grad_norm": 1.5203335285186768,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3953,
+      "step": 38
+    },
+    {
+      "epoch": 0.007735888821392708,
+      "grad_norm": 1.3025851249694824,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2828,
+      "step": 39
+    },
+    {
+      "epoch": 0.007934244945018163,
+      "grad_norm": 1.3689641952514648,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1448,
+      "step": 40
+    },
+    {
+      "epoch": 0.008132601068643617,
+      "grad_norm": 1.2690826654434204,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2001,
+      "step": 41
+    },
+    {
+      "epoch": 0.00833095719226907,
+      "grad_norm": 1.004398226737976,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0619,
+      "step": 42
+    },
+    {
+      "epoch": 0.008529313315894524,
+      "grad_norm": 1.0098557472229004,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0085,
+      "step": 43
+    },
+    {
+      "epoch": 0.008727669439519978,
+      "grad_norm": 1.0918034315109253,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0509,
+      "step": 44
+    },
+    {
+      "epoch": 0.008926025563145432,
+      "grad_norm": 1.0433894395828247,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9432,
+      "step": 45
+    },
+    {
+      "epoch": 0.009124381686770886,
+      "grad_norm": 0.8852425217628479,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8706,
+      "step": 46
+    },
+    {
+      "epoch": 0.00932273781039634,
+      "grad_norm": 0.9674733281135559,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9719,
+      "step": 47
+    },
+    {
+      "epoch": 0.009521093934021795,
+      "grad_norm": 0.9817253351211548,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9108,
+      "step": 48
+    },
+    {
+      "epoch": 0.009719450057647249,
+      "grad_norm": 1.0266602039337158,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9272,
+      "step": 49
+    },
+    {
+      "epoch": 0.009917806181272703,
+      "grad_norm": 1.561460018157959,
+      "learning_rate": 0.0,
+      "loss": 1.1452,
+      "step": 50
+    },
+    {
+      "epoch": 0.009917806181272703,
+      "eval_loss": 1.0755832195281982,
+      "eval_runtime": 383.5523,
+      "eval_samples_per_second": 88.551,
+      "eval_steps_per_second": 11.07,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null