Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97881ccf005eff38f04028afe96d790d18e48ad5f7c9a3deb643e5ec5ee08084
+oid sha256:e46ae41d379db0382564b4beb34e7b076e640571000a8842bb820d1027aeaeed
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48c3b825c7d7e8d1e07c0fa1418153891b109926b4cccdce740607530e24515
+oid sha256:bc809b2cad30aaf35a99ea8496e8ef0356b4abd433698bb682d6e9fd997622c8
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9234ffd516e0fef6b0c85c553e05b9026dd8a7bbd4e80ac8c1ac989037e3a250
+oid sha256:158381598da2d53aaee4a30e450cc62cd811df38fd77d57dca435f190ea91e24
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4bc6418e4739d72e411fec51f1a947bb329d5bdabd9a7b6ade8fa6147e52b5
+oid sha256:d6427453b748ce6701b542a8a48643deb77634b95e37527e8c3fe2994d0cb8c3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c44fadbdb6649c9a9b986fe70c2e4db1a18de188d9404b521310f0e7c35003b
+oid sha256:848dd7c00885fde429d26fb6a8856118dfca955fac1b7b5de8168310cf1b4bd8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12dd54c5d2e235d25c07e5f8cacd2e1561c2cde59926ac2efba8075650b2bec
+oid sha256:8ce475520683489e8f27e52451e91fa461bf2a5b59c0838246bb92464bc4606f
 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": 10.382533073425293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.062315002336812586,
+  "best_metric": 10.170746803283691,
+  "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": 326.548,
       "eval_steps_per_second": 84.903,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 58.24401092529297,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 331.0769,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 57.016700744628906,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 330.4106,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 55.45833206176758,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 329.9051,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 53.81894302368164,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 329.6223,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 52.6780891418457,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 329.1109,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 51.28841781616211,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 328.8589,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 49.68301010131836,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 328.7733,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 48.246246337890625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 328.7826,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 47.71107864379883,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 328.3093,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 44.84560775756836,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 329.2457,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 43.82417678833008,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 329.2555,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 41.64598083496094,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 330.7998,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 39.73112869262695,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 343.9659,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 45.642311096191406,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 325.8868,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 45.110870361328125,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 325.7518,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 44.50864028930664,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 325.5027,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 44.23891830444336,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 325.328,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 43.78203582763672,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 325.3905,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 42.987205505371094,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 325.5956,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 42.830806732177734,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 325.7647,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 42.426273345947266,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 325.6996,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 42.392818450927734,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 325.4753,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 39.53705978393555,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 327.3095,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 38.0192985534668,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 328.2975,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 36.17513656616211,
+      "learning_rate": 1e-05,
+      "loss": 334.8141,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 10.170746803283691,
+      "eval_runtime": 0.1497,
+      "eval_samples_per_second": 334.014,
+      "eval_steps_per_second": 86.844,
+      "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": 19841603862528.0,
+  "total_flos": 39843989028864.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null