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:b771ae53dff710dbe25c683ac292bec3ebfdf971730a8052a6ee4d3946c5c5f8
+oid sha256:791b6db9e18e8054ce9baa0a5429a8e86ab753b403e93a9c0cd4aae9868a07e7
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ae71ba79298a0575253aa2fb78164745eefb06636f6da7103f9b48ca34ab7e
+oid sha256:ae8c0af5f1743e8bacb3cb169a9c1ba0f0fd4fecb5bf402fddea9cc07bbbfce4
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbf023379a103c9911e2849bd2387b4916a963da88c06d2106f4d6248852f6d
+oid sha256:0557c6e88eaf5789b34ed48faaff0749e7e72b0558e6d0639830b6bd558ba5da
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6535354476ba8c75e7c7ac3cf365065561df080abaaa0a3cc592bf4aa9173101
+oid sha256:afdaaa9b30d248302c68b9eed5e4f267f633b70e559accc356535ee7c6ea9302
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1414d73e6be6b676157616a82478ac1573616f5f4724b8f1995aa4f83ea53245
+oid sha256:be385af65c0d45daabdc555634dfd512cb014eee97b17e185c5afadeafca2884
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b8cffdd2eaa9157204c3a146f1b100eee667f103b91f37a84959b50ab927c1
+oid sha256:02ab37cd24b6beb713cbf5b8410eeb9bf0fc8153a7bd88377ab0e026003f1b11
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6876567602157593,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.062315002336812586,
+  "best_metric": 1.5878689289093018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12463000467362517,
   "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": 14.011,
       "eval_steps_per_second": 3.643,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 5.439934253692627,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 19.7855,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 4.207176685333252,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 20.4741,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 3.8984763622283936,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 20.3979,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 5.220901012420654,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 20.7536,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 5.235278129577637,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 20.9558,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 3.8804500102996826,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 22.0987,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 4.0022406578063965,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 21.0463,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 4.649126052856445,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 21.102,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 4.967099666595459,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 22.072,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 5.563882827758789,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 22.531,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 7.969014644622803,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 23.6819,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 10.51347541809082,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 25.2001,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 12.85457706451416,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 24.4643,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 3.841174602508545,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 18.7518,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 3.515620231628418,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 19.236,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 3.0310733318328857,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 19.8089,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 2.838557720184326,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 20.2579,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 3.141146659851074,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 20.6255,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 3.739708185195923,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 20.5905,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 4.207951068878174,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 21.4834,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 5.091900825500488,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 20.8686,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 5.662145137786865,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 22.0861,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 6.919090270996094,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 22.5946,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 8.793493270874023,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 23.2693,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 14.914314270019531,
+      "learning_rate": 1e-05,
+      "loss": 26.3377,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 1.5878689289093018,
+      "eval_runtime": 3.7543,
+      "eval_samples_per_second": 13.318,
+      "eval_steps_per_second": 3.463,
+      "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": 2.78568205121749e+17,
+  "total_flos": 5.5762945316172595e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null