Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326ed99b57907c5f65c7c06f3fc16de25dcd005c9d620a0b4446c5795bcfaa83
+oid sha256:a118422d33fe15d02e9d7e4ce2449da6198ec3044a65dc26b6074afdd9a335fe
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792a8e328f9e6b8e20f4f54f3196234f58dd7b894c9928b2c50a4e70cd132bf2
+oid sha256:73af39ed3acb754209c6c89517eb777fd280f8e0323ca842149fde447f100ae0
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd49b2786a8d17d85af9560f2cd9de9251cf5702655d12dcdc5f065b5824a9a
+oid sha256:2121bfcbe20e74b4a5a32d184ffc1e3f833f8c83133d5f0245f218b945dfaa0d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6e8fec18c2271856cddf0281a0c965a0e45162b0519b7f9b70ae54f16f51ec
+oid sha256:495bfe98333f9899bd98bc05c2de24205c14cbad444e8859f9483ec77ac87106
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c2b06f6a967859f488bbf9c84d634ebb05a033abec58d22578439735d8a2c5
+oid sha256:6a3d421dfc24c1454c0a39195d46f9465e2aa03c8dc5a73cd7b4ce836c882236
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e1d1116d20eb9db85e9e3d6f8cc99d866fddc9a2cdf1abffdd7880c7ec7423
+oid sha256:b28ce94121a82115bf6a40739d72531a8e7cd839a9dd0548b09a37a498aa8f2e
 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": 2.707570791244507,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.062315002336812586,
+  "best_metric": 2.6504759788513184,
+  "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": 69.159,
       "eval_steps_per_second": 17.981,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 0.45077604055404663,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.5811,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 0.3960801959037781,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.6605,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 0.40392717719078064,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.6883,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 0.4010487496852875,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.6943,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 0.44553473591804504,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.7217,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 0.47251877188682556,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.6897,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 0.483795166015625,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.5993,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 0.5359827876091003,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.6468,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 0.7356964349746704,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.6997,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 0.931477427482605,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.6975,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 1.087597131729126,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.6616,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 1.4653799533843994,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.6927,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 0.4064444601535797,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.5191,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 0.33260494470596313,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6045,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 0.32690829038619995,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.5739,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 0.3391484320163727,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.6839,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 0.34284722805023193,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.6149,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 0.38321492075920105,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.7208,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 0.4366220235824585,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.7701,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 0.5214863419532776,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.5239,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 0.6461559534072876,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.6886,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 0.8496044874191284,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.6529,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 1.0152771472930908,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.5445,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 1.2712960243225098,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.4558,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 1.9823209047317505,
+      "learning_rate": 1e-05,
+      "loss": 2.7049,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 2.6504759788513184,
+      "eval_runtime": 0.7137,
+      "eval_samples_per_second": 70.058,
+      "eval_steps_per_second": 18.215,
+      "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": 1.27222702669824e+16,
+  "total_flos": 2.54445405339648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null