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:a58f383ab510d1e431e6fd8e26e97ff5eff2cb7f9a3bdb4893b86a107dfd176b
+oid sha256:87604bf6fab24fb82c3f4f15736bd1017539b1ad31a1576efb76efabe418d61f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ef1e8b6415baec7d73edb3f05c783fb443462709689d7e0b5d25e577c7629a
+oid sha256:3a70d4551c59d0bfab11349f6309815872451d119f773288ee4707cad571cd7d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fcef7bc5c614d021da10ef993563ca3f607d5b175e8fdad4ef61bfff61fbca7
+oid sha256:bd83414070aedd4505301f28e691f359fb0891cbb334dbca2c599a8921e451ba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31ea002972fa85aaeafc0dcab462c1db6aa3c4d7e61716b416884d34c5a2695
+oid sha256:a5bbaad1b18ab0c277ffa4792d6cbc7013c11522c061fed180b6003b4938c08d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb97e9b4373271833b6619228ea2f2f8cb5b2e7209166971086c5b3c85672b6e
+oid sha256:7006f8b5d9199630077a6a3f8f7758ca071b0f19816e9bb1f101734c555cbc2c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc0e8cb42810d295fa484542419432fe9f810855e9c0a70c2b8abb8f8bef9f6
+oid sha256:41fc0cd0a65be87b669652dc31550c59da8377fa7ca83713cab2fc5e567f9bfe
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98e2cafbee7e2dc6cc416b874fabce58bb4b9c5f16190e7bc77e29a2e8c950b
+oid sha256:7e838fed774f5bd6ed040d95e4aaf450503260b4fb9c07a02d9590ab9b72086d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.0446817874908447,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3114754098360657,
+  "epoch": 2.6229508196721314,
   "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": 10.538,
       "eval_steps_per_second": 2.74,
       "step": 25
+    },
+    {
+      "epoch": 1.3639344262295081,
+      "grad_norm": 15.636397361755371,
+      "learning_rate": 6.501344202803414e-05,
+      "loss": 61.7672,
+      "step": 26
+    },
+    {
+      "epoch": 1.4163934426229507,
+      "grad_norm": 15.895488739013672,
+      "learning_rate": 6.253778004871315e-05,
+      "loss": 62.7228,
+      "step": 27
+    },
+    {
+      "epoch": 1.4688524590163934,
+      "grad_norm": 19.06943702697754,
+      "learning_rate": 6.003840142464886e-05,
+      "loss": 64.0609,
+      "step": 28
+    },
+    {
+      "epoch": 1.521311475409836,
+      "grad_norm": 24.51659393310547,
+      "learning_rate": 5.752317012567363e-05,
+      "loss": 61.7292,
+      "step": 29
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 16.205303192138672,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 60.9363,
+      "step": 30
+    },
+    {
+      "epoch": 1.6262295081967213,
+      "grad_norm": 17.461999893188477,
+      "learning_rate": 5.247682987432637e-05,
+      "loss": 62.4749,
+      "step": 31
+    },
+    {
+      "epoch": 1.678688524590164,
+      "grad_norm": 17.851083755493164,
+      "learning_rate": 4.9961598575351155e-05,
+      "loss": 61.79,
+      "step": 32
+    },
+    {
+      "epoch": 1.7311475409836066,
+      "grad_norm": 20.22283172607422,
+      "learning_rate": 4.7462219951286867e-05,
+      "loss": 64.521,
+      "step": 33
+    },
+    {
+      "epoch": 1.7836065573770492,
+      "grad_norm": 28.108795166015625,
+      "learning_rate": 4.498655797196586e-05,
+      "loss": 61.2715,
+      "step": 34
+    },
+    {
+      "epoch": 1.8360655737704918,
+      "grad_norm": 18.37066078186035,
+      "learning_rate": 4.2542401985881784e-05,
+      "loss": 61.7881,
+      "step": 35
+    },
+    {
+      "epoch": 1.8885245901639345,
+      "grad_norm": 18.368694305419922,
+      "learning_rate": 4.01374422120175e-05,
+      "loss": 62.2249,
+      "step": 36
+    },
+    {
+      "epoch": 1.940983606557377,
+      "grad_norm": 18.627840042114258,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 62.6981,
+      "step": 37
+    },
+    {
+      "epoch": 1.9934426229508198,
+      "grad_norm": 22.907976150512695,
+      "learning_rate": 3.547523173970989e-05,
+      "loss": 64.4813,
+      "step": 38
+    },
+    {
+      "epoch": 2.045901639344262,
+      "grad_norm": 21.854839324951172,
+      "learning_rate": 3.323265008026421e-05,
+      "loss": 57.5238,
+      "step": 39
+    },
+    {
+      "epoch": 2.098360655737705,
+      "grad_norm": 17.733745574951172,
+      "learning_rate": 3.105855655680986e-05,
+      "loss": 59.0577,
+      "step": 40
+    },
+    {
+      "epoch": 2.1508196721311474,
+      "grad_norm": 18.677440643310547,
+      "learning_rate": 2.8959791671908742e-05,
+      "loss": 59.2771,
+      "step": 41
+    },
+    {
+      "epoch": 2.2032786885245903,
+      "grad_norm": 20.046802520751953,
+      "learning_rate": 2.6942958916356998e-05,
+      "loss": 58.3555,
+      "step": 42
+    },
+    {
+      "epoch": 2.2557377049180327,
+      "grad_norm": 26.242361068725586,
+      "learning_rate": 2.501440399215983e-05,
+      "loss": 59.7959,
+      "step": 43
+    },
+    {
+      "epoch": 2.3081967213114756,
+      "grad_norm": 17.727699279785156,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 58.5926,
+      "step": 44
+    },
+    {
+      "epoch": 2.360655737704918,
+      "grad_norm": 18.205520629882812,
+      "learning_rate": 2.144610258025755e-05,
+      "loss": 58.4511,
+      "step": 45
+    },
+    {
+      "epoch": 2.413114754098361,
+      "grad_norm": 20.044387817382812,
+      "learning_rate": 1.981758328893866e-05,
+      "loss": 57.0531,
+      "step": 46
+    },
+    {
+      "epoch": 2.4655737704918033,
+      "grad_norm": 22.331958770751953,
+      "learning_rate": 1.8299760896833295e-05,
+      "loss": 60.0991,
+      "step": 47
+    },
+    {
+      "epoch": 2.5180327868852457,
+      "grad_norm": 29.541261672973633,
+      "learning_rate": 1.6897411034727218e-05,
+      "loss": 59.2154,
+      "step": 48
+    },
+    {
+      "epoch": 2.5704918032786885,
+      "grad_norm": 20.129823684692383,
+      "learning_rate": 1.5614946014106085e-05,
+      "loss": 58.7101,
+      "step": 49
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 20.351736068725586,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 59.4648,
+      "step": 50
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "eval_loss": 2.0465781688690186,
+      "eval_runtime": 4.7768,
+      "eval_samples_per_second": 10.467,
+      "eval_steps_per_second": 2.721,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null