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:bb7450912ab10dd6c67decbd6ebdef80b441b915bbda269892a5697b6258c0fe
+oid sha256:2b1fababf23a30af94a377bceb1cb0d3b985ad4d5549fdc505b41e33bdb33357
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739c0d4e85f0ea4401ea3c379facba1b5cebb38bb8fa614d8d5b84fc6fd8f7c0
+oid sha256:34447ebb8f9577b52b9ce2ac27c08d2db3ae8c49c946ef5625b36d0e64abce94
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccff9edabac8d200b678ea6c220447aa10f4aecda57fd9d1cd5a0f67ac45157
+oid sha256:68f3bb0128cb90659cdd9a65eeb20441b2ab990e3a63d301ccd14ae9930f2a13
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a65c8e3c7a587d3118769d21b059c24ec878aaa7205a88de1f2b316d8aa8721
+oid sha256:c8db1134bb50f9bd2954c27b73e466359531d133e283db14a90ecb7a70acf467
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801cce6786c43ddf13583ee846186e01edab5b7b3c92cd8568634d974a3221ac
+oid sha256:4e635529dcd85e3ac871eb07e11ff0ca810efa568be8ae0d8943ab6b109c25f2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bece9f43aa67239a73929054d2ac95960981f126445941b29be6872d908a98
+oid sha256:b78d4cdc19942896d2a8c699c0677e71c0ed8d5fa92da246f3a2d756504a80a6
 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": 1.8924641609191895,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0036452779980133236,
+  "best_metric": 1.8648408651351929,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007290555996026647,
   "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": 10.526,
       "eval_steps_per_second": 2.737,
       "step": 25
+    },
+    {
+      "epoch": 0.0037910891179338563,
+      "grad_norm": 26.175640106201172,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 26.2252,
+      "step": 26
+    },
+    {
+      "epoch": 0.003936900237854389,
+      "grad_norm": 15.854564666748047,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 25.0846,
+      "step": 27
+    },
+    {
+      "epoch": 0.004082711357774923,
+      "grad_norm": 10.27354621887207,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 24.7296,
+      "step": 28
+    },
+    {
+      "epoch": 0.004228522477695455,
+      "grad_norm": 7.37852668762207,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 26.9477,
+      "step": 29
+    },
+    {
+      "epoch": 0.004374333597615988,
+      "grad_norm": 8.127168655395508,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 26.5466,
+      "step": 30
+    },
+    {
+      "epoch": 0.004520144717536521,
+      "grad_norm": 8.220149040222168,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 27.5078,
+      "step": 31
+    },
+    {
+      "epoch": 0.0046659558374570545,
+      "grad_norm": 9.664246559143066,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 29.0629,
+      "step": 32
+    },
+    {
+      "epoch": 0.004811766957377587,
+      "grad_norm": 15.414687156677246,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 30.4415,
+      "step": 33
+    },
+    {
+      "epoch": 0.00495757807729812,
+      "grad_norm": 12.483214378356934,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 31.7473,
+      "step": 34
+    },
+    {
+      "epoch": 0.005103389197218653,
+      "grad_norm": 12.741660118103027,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 31.6221,
+      "step": 35
+    },
+    {
+      "epoch": 0.0052492003171391854,
+      "grad_norm": 16.10197639465332,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 38.1968,
+      "step": 36
+    },
+    {
+      "epoch": 0.005395011437059719,
+      "grad_norm": 18.518325805664062,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 41.1575,
+      "step": 37
+    },
+    {
+      "epoch": 0.005540822556980252,
+      "grad_norm": 17.992542266845703,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 36.9056,
+      "step": 38
+    },
+    {
+      "epoch": 0.0056866336769007845,
+      "grad_norm": 8.159541130065918,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 26.2108,
+      "step": 39
+    },
+    {
+      "epoch": 0.005832444796821317,
+      "grad_norm": 7.749679088592529,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 24.0422,
+      "step": 40
+    },
+    {
+      "epoch": 0.005978255916741851,
+      "grad_norm": 8.064474105834961,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 26.6737,
+      "step": 41
+    },
+    {
+      "epoch": 0.006124067036662384,
+      "grad_norm": 8.049077033996582,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 28.3026,
+      "step": 42
+    },
+    {
+      "epoch": 0.006269878156582916,
+      "grad_norm": 8.30419921875,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 27.3363,
+      "step": 43
+    },
+    {
+      "epoch": 0.006415689276503449,
+      "grad_norm": 8.461013793945312,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 29.2888,
+      "step": 44
+    },
+    {
+      "epoch": 0.006561500396423983,
+      "grad_norm": 8.340715408325195,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 28.1052,
+      "step": 45
+    },
+    {
+      "epoch": 0.006707311516344515,
+      "grad_norm": 8.852931022644043,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 31.5895,
+      "step": 46
+    },
+    {
+      "epoch": 0.006853122636265048,
+      "grad_norm": 10.949113845825195,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 32.1618,
+      "step": 47
+    },
+    {
+      "epoch": 0.006998933756185581,
+      "grad_norm": 13.277790069580078,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 35.7908,
+      "step": 48
+    },
+    {
+      "epoch": 0.007144744876106114,
+      "grad_norm": 16.61524772644043,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 39.5844,
+      "step": 49
+    },
+    {
+      "epoch": 0.007290555996026647,
+      "grad_norm": 24.676464080810547,
+      "learning_rate": 1e-05,
+      "loss": 44.0687,
+      "step": 50
+    },
+    {
+      "epoch": 0.007290555996026647,
+      "eval_loss": 1.8648408651351929,
+      "eval_runtime": 4.7569,
+      "eval_samples_per_second": 10.511,
+      "eval_steps_per_second": 2.733,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null