Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c608d76fde16d6f227614b951227ad24f595cfe009f342b9c1e71042f5b7da8
+oid sha256:e617eb9c2d9b984b9f3541066844a28401468a6d77bc78e2825cca67796216ba
 size 503407240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8bd9553431c5773e4542e8c59b71b11f6e950c52326131ed948519043fa9aa
+oid sha256:ac5e2d6f9b458a1cdc7f7641c17821161d453da08d510b273a6270527c0f54a4
 size 1007201074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5a7e1eaa41c25365dd936864de4029eb3496dad298f5a2799198c1c51ffbcd
+oid sha256:1d2cd7ba272fcd45961b6a8a5d441244bff4d825ea06d9dd4913abfcab32c3e4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab45b29a05ad779d262feee1475d48a21c56123180c41bc10c9cb30a417301a
+oid sha256:944c4854e3d78e987fd73f1c02c871b12015a2169190dee0b683c2ac374b8394
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16749f72543acd0ed5a31b14d4a400da18afe1cb0c5d7ada6d16d9f9a6ed503
+oid sha256:0004de867f8de4d0c409a8961e19f30339f748e8ca450702b7b583d04037e3a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34de74ce971e8bd6dae2363885a353ef2b7b0ef8c5e06706ce064afa8861b99f
+oid sha256:4ba4d2b5b422b59cc12381ade09ac7fa8dca1471e12cd4337a537557c1beac9b
 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": 0.6481190919876099,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015570260801868432,
+  "best_metric": 0.6206071972846985,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.031140521603736863,
   "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": 23.303,
       "eval_steps_per_second": 2.915,
       "step": 25
+    },
+    {
+      "epoch": 0.01619307123394317,
+      "grad_norm": 4.6942877769470215,
+      "learning_rate": 5e-05,
+      "loss": 0.7529,
+      "step": 26
+    },
+    {
+      "epoch": 0.016815881666017905,
+      "grad_norm": 2.933812379837036,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5804,
+      "step": 27
+    },
+    {
+      "epoch": 0.017438692098092644,
+      "grad_norm": 2.9494214057922363,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6122,
+      "step": 28
+    },
+    {
+      "epoch": 0.01806150253016738,
+      "grad_norm": 3.9514541625976562,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.586,
+      "step": 29
+    },
+    {
+      "epoch": 0.018684312962242117,
+      "grad_norm": 2.456082820892334,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5001,
+      "step": 30
+    },
+    {
+      "epoch": 0.019307123394316856,
+      "grad_norm": 3.063210964202881,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6416,
+      "step": 31
+    },
+    {
+      "epoch": 0.01992993382639159,
+      "grad_norm": 2.158895969390869,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4718,
+      "step": 32
+    },
+    {
+      "epoch": 0.02055274425846633,
+      "grad_norm": 3.134558916091919,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6344,
+      "step": 33
+    },
+    {
+      "epoch": 0.021175554690541068,
+      "grad_norm": 5.159844875335693,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5952,
+      "step": 34
+    },
+    {
+      "epoch": 0.021798365122615803,
+      "grad_norm": 3.6120400428771973,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7819,
+      "step": 35
+    },
+    {
+      "epoch": 0.02242117555469054,
+      "grad_norm": 3.597929000854492,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.753,
+      "step": 36
+    },
+    {
+      "epoch": 0.023043985986765277,
+      "grad_norm": 4.944601535797119,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0505,
+      "step": 37
+    },
+    {
+      "epoch": 0.023666796418840015,
+      "grad_norm": 5.831929683685303,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8816,
+      "step": 38
+    },
+    {
+      "epoch": 0.024289606850914754,
+      "grad_norm": 3.287022829055786,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.74,
+      "step": 39
+    },
+    {
+      "epoch": 0.02491241728298949,
+      "grad_norm": 2.3541550636291504,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4848,
+      "step": 40
+    },
+    {
+      "epoch": 0.025535227715064227,
+      "grad_norm": 3.2387115955352783,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6658,
+      "step": 41
+    },
+    {
+      "epoch": 0.026158038147138966,
+      "grad_norm": 2.4414989948272705,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5423,
+      "step": 42
+    },
+    {
+      "epoch": 0.0267808485792137,
+      "grad_norm": 2.677088737487793,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4431,
+      "step": 43
+    },
+    {
+      "epoch": 0.02740365901128844,
+      "grad_norm": 2.6570982933044434,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5932,
+      "step": 44
+    },
+    {
+      "epoch": 0.028026469443363178,
+      "grad_norm": 2.9952850341796875,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5313,
+      "step": 45
+    },
+    {
+      "epoch": 0.028649279875437913,
+      "grad_norm": 2.977844476699829,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5879,
+      "step": 46
+    },
+    {
+      "epoch": 0.02927209030751265,
+      "grad_norm": 2.791550397872925,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5124,
+      "step": 47
+    },
+    {
+      "epoch": 0.029894900739587386,
+      "grad_norm": 3.966216802597046,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7275,
+      "step": 48
+    },
+    {
+      "epoch": 0.030517711171662125,
+      "grad_norm": 4.126320838928223,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7949,
+      "step": 49
+    },
+    {
+      "epoch": 0.031140521603736863,
+      "grad_norm": 5.07513952255249,
+      "learning_rate": 0.0,
+      "loss": 1.1318,
+      "step": 50
+    },
+    {
+      "epoch": 0.031140521603736863,
+      "eval_loss": 0.6206071972846985,
+      "eval_runtime": 476.0766,
+      "eval_samples_per_second": 22.721,
+      "eval_steps_per_second": 2.842,
+      "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": 4.217745394630656e+17,
+  "total_flos": 8.435490789261312e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null