Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8f8221b3621db010e8cd9ca10eb306fc4ac5778798ee9cc375ce1454d64e5a
+oid sha256:9e2d7d98e9db6d882fc0729152c354b12a0b9548e03440920112d79c2ad717af
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79bba6f8de4fabf1b4b8404e98471e0d567ec406689f9c97b6a748093d82a12
+oid sha256:a67f1681722d5bf17a7f62dc0720d98da35467482ae68ab3c31e8c15abd82c49
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52207afaa3b56331820c329dba5ac8fef7051bee908d9f5b26e17f92a20264c1
+oid sha256:18ce9acdb8313e659ef7715985660073295cbd4a9726b9bbfb108ee0e76c0d6e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac6c04ff8b64f39fe9f418997bf21b362a863ddf3c0a2572ade3ac8b4e8912e
+oid sha256:d18af5389097939da1f985bb07aaec8b085a13c45555e98c9161b9f3960a5ac3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf521c6cfb1a14a3470a0a47ab85f4d5c3c229ec8a96c224208ebe1227fe11ed
+oid sha256:be0ea8548e6dff5ffe6616287cbf978516c1652d031e7e200cdaf50ac841bdc6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0ff65c396e1b04902485bded4326cb6c3a521216ed3507b469405ae2dd4325
+oid sha256:fbb0ee3aaeecc60207c984e7fb86708dfb0127bbec6257c658a7b82eb8122d54
 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": 1.7822033166885376,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18382352941176472,
+  "best_metric": 1.625058650970459,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.36764705882352944,
   "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": 18.118,
       "eval_steps_per_second": 4.711,
       "step": 25
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 25.85879135131836,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 28.0197,
+      "step": 26
+    },
+    {
+      "epoch": 0.19852941176470587,
+      "grad_norm": 17.14788055419922,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 27.5581,
+      "step": 27
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 16.674339294433594,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 27.1966,
+      "step": 28
+    },
+    {
+      "epoch": 0.21323529411764705,
+      "grad_norm": 12.14965534210205,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 27.3105,
+      "step": 29
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 12.210734367370605,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 27.1443,
+      "step": 30
+    },
+    {
+      "epoch": 0.22794117647058823,
+      "grad_norm": 11.805206298828125,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 26.9579,
+      "step": 31
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 10.710463523864746,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 26.6279,
+      "step": 32
+    },
+    {
+      "epoch": 0.2426470588235294,
+      "grad_norm": 12.47972583770752,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 26.9588,
+      "step": 33
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 11.489084243774414,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 27.0147,
+      "step": 34
+    },
+    {
+      "epoch": 0.25735294117647056,
+      "grad_norm": 11.802462577819824,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 26.6679,
+      "step": 35
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 14.10996150970459,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 26.6119,
+      "step": 36
+    },
+    {
+      "epoch": 0.27205882352941174,
+      "grad_norm": 14.070399284362793,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 27.1049,
+      "step": 37
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 14.837409019470215,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 25.6963,
+      "step": 38
+    },
+    {
+      "epoch": 0.2867647058823529,
+      "grad_norm": 15.15300464630127,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 25.0391,
+      "step": 39
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 13.794343948364258,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 25.2274,
+      "step": 40
+    },
+    {
+      "epoch": 0.3014705882352941,
+      "grad_norm": 11.98012924194336,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 25.0828,
+      "step": 41
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 14.02513313293457,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 24.8935,
+      "step": 42
+    },
+    {
+      "epoch": 0.3161764705882353,
+      "grad_norm": 12.323277473449707,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 25.7782,
+      "step": 43
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 13.56668472290039,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 25.2721,
+      "step": 44
+    },
+    {
+      "epoch": 0.33088235294117646,
+      "grad_norm": 14.325328826904297,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 25.1985,
+      "step": 45
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 17.331531524658203,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 25.0337,
+      "step": 46
+    },
+    {
+      "epoch": 0.34558823529411764,
+      "grad_norm": 14.459659576416016,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 25.9566,
+      "step": 47
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 13.978584289550781,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 25.5556,
+      "step": 48
+    },
+    {
+      "epoch": 0.3602941176470588,
+      "grad_norm": 15.276152610778809,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 26.2963,
+      "step": 49
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 16.24267578125,
+      "learning_rate": 1e-05,
+      "loss": 26.876,
+      "step": 50
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "eval_loss": 1.625058650970459,
+      "eval_runtime": 2.7746,
+      "eval_samples_per_second": 18.02,
+      "eval_steps_per_second": 4.685,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null