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:f226e3dbdbf743f7a9798c26ad198cf666b164b75596aca97f4faed0573b9204
+oid sha256:a6484038b740f7e979515957b9f0ce5c29c4e5d8228e6a01b9a72dde290f84ce
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532dbd4017681017bfc7ced8b80fc28e6acd775c6b9a1d0a1366bd4615004b31
+oid sha256:5f9dff88cefc3349ec51a1dbc9027e1b9326f52f09fdd4ba1282537ce0b84bb7
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5298b1d49e450963d59e7e0359a804e704926582819140b55484d7baa1846b49
+oid sha256:0281983e1c9a013d0af5fd8834517082f96ea1d5337a30086e8a9aa0fb18218f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7012bdf588175d484176cfa80c62725ffc4f4e4a455acde9a65300903efe602d
+oid sha256:4855ec560968347b9fbdbf12737710937d7e73e76d1157e89a5ebc5cf30e3bea
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c39bbf7c9a6576675daa854ccf567da54022429fba2b68a4e592edf6cd6059
+oid sha256:c5b6c6dbba00898a0d7e33ac9d8c92527186567f7a021c1d08758b951131c35d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b221aff718e77526f6fc99ed54c43b3c5d8a2e2edac68caa9419112c94cacbf1
+oid sha256:df3cfda5f461f989cace1b64fbf62769bf0bca8e75acb83677d07d1ae1d4a7cb
 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": 1.3890187740325928,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8849557522123894,
+  "best_metric": 1.3707951307296753,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7699115044247788,
   "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": 85.563,
       "eval_steps_per_second": 10.808,
       "step": 25
+    },
+    {
+      "epoch": 0.9203539823008849,
+      "grad_norm": 0.2022041529417038,
+      "learning_rate": 5e-05,
+      "loss": 1.385,
+      "step": 26
+    },
+    {
+      "epoch": 0.9557522123893806,
+      "grad_norm": 0.19861751794815063,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4019,
+      "step": 27
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "grad_norm": 0.2385483831167221,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3938,
+      "step": 28
+    },
+    {
+      "epoch": 1.0265486725663717,
+      "grad_norm": 0.4870010316371918,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4318,
+      "step": 29
+    },
+    {
+      "epoch": 1.0619469026548674,
+      "grad_norm": 0.3053165674209595,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3394,
+      "step": 30
+    },
+    {
+      "epoch": 1.0973451327433628,
+      "grad_norm": 0.2962687015533447,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3852,
+      "step": 31
+    },
+    {
+      "epoch": 1.1327433628318584,
+      "grad_norm": 0.3027305006980896,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3173,
+      "step": 32
+    },
+    {
+      "epoch": 1.168141592920354,
+      "grad_norm": 0.33227747678756714,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3647,
+      "step": 33
+    },
+    {
+      "epoch": 1.2035398230088497,
+      "grad_norm": 0.3296235203742981,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4011,
+      "step": 34
+    },
+    {
+      "epoch": 1.238938053097345,
+      "grad_norm": 0.39872992038726807,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4346,
+      "step": 35
+    },
+    {
+      "epoch": 1.2743362831858407,
+      "grad_norm": 0.3268812298774719,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3378,
+      "step": 36
+    },
+    {
+      "epoch": 1.3097345132743363,
+      "grad_norm": 0.3023950755596161,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3331,
+      "step": 37
+    },
+    {
+      "epoch": 1.3451327433628317,
+      "grad_norm": 0.32276710867881775,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3421,
+      "step": 38
+    },
+    {
+      "epoch": 1.3805309734513274,
+      "grad_norm": 0.31279733777046204,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3191,
+      "step": 39
+    },
+    {
+      "epoch": 1.415929203539823,
+      "grad_norm": 0.32816168665885925,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3224,
+      "step": 40
+    },
+    {
+      "epoch": 1.4513274336283186,
+      "grad_norm": 0.32745441794395447,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3618,
+      "step": 41
+    },
+    {
+      "epoch": 1.4867256637168142,
+      "grad_norm": 0.3378945291042328,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3688,
+      "step": 42
+    },
+    {
+      "epoch": 1.5221238938053099,
+      "grad_norm": 0.3114747405052185,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3884,
+      "step": 43
+    },
+    {
+      "epoch": 1.5575221238938053,
+      "grad_norm": 0.32342156767845154,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3411,
+      "step": 44
+    },
+    {
+      "epoch": 1.592920353982301,
+      "grad_norm": 0.3232678174972534,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3715,
+      "step": 45
+    },
+    {
+      "epoch": 1.6283185840707963,
+      "grad_norm": 0.3243681490421295,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3108,
+      "step": 46
+    },
+    {
+      "epoch": 1.663716814159292,
+      "grad_norm": 0.33341413736343384,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4022,
+      "step": 47
+    },
+    {
+      "epoch": 1.6991150442477876,
+      "grad_norm": 0.33767956495285034,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3355,
+      "step": 48
+    },
+    {
+      "epoch": 1.7345132743362832,
+      "grad_norm": 0.35112181305885315,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3985,
+      "step": 49
+    },
+    {
+      "epoch": 1.7699115044247788,
+      "grad_norm": 0.3286685049533844,
+      "learning_rate": 0.0,
+      "loss": 1.3658,
+      "step": 50
+    },
+    {
+      "epoch": 1.7699115044247788,
+      "eval_loss": 1.3707951307296753,
+      "eval_runtime": 2.2194,
+      "eval_samples_per_second": 85.61,
+      "eval_steps_per_second": 10.814,
+      "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