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:ea72bfd8a9c45036176aaa9c262b56e6a0d58bb7612b38f2ca6b888faee01add
+oid sha256:99efeb4d2dc36984885835e9e4c9b4d84651091a391dd9e4c145978c74edab7e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2652dcdeed07bfc2b430986d62077749b821797e150423637b5937b464e3c47
+oid sha256:daf6316b7d0037b29d2e4a91aef255f160905cb29133ff2f4387fcd7c54cfda2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1724a3c3942b17ed03d901b9e96f748904200a41dbe821af0dbd68a6e622bf0f
+oid sha256:95f50234ad069ba3a8d1fc35bc85105f0fe9074110579e3a2bd7fad6d0134088
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220b2721f4116c15a435b5ddffb9041204859c8f6655f190ed62907df6234d3c
+oid sha256:891d172559e411b14fc653af92fcfebd8ab7a6e62b79ca69ff593b6f0fd2ed6b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ba008a3db65856609b259242b669a99d095ac4f6aba06a5573e9e9e0442a69
+oid sha256:ba780f551d56c882ab55ee62af3db616fd18366059c4b83a518a5cb834007883
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe29e5e0296fba01c02f12083e78d8d0ed4b736dbcfe507b3c09af1e6391c98
+oid sha256:f593cd6e57be467b971f9851a4fdcb25d7f084183184219f0a0ed6093b4aba30
 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": 3.2953968048095703,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011936379099400197,
+  "best_metric": 3.0543212890625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.023872758198800394,
   "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": 21.703,
       "eval_steps_per_second": 5.643,
       "step": 25
+    },
+    {
+      "epoch": 0.012413834263376205,
+      "grad_norm": 280.07696533203125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 57.7187,
+      "step": 26
+    },
+    {
+      "epoch": 0.012891289427352213,
+      "grad_norm": 309.6079406738281,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 62.0701,
+      "step": 27
+    },
+    {
+      "epoch": 0.013368744591328221,
+      "grad_norm": 198.18789672851562,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 60.8391,
+      "step": 28
+    },
+    {
+      "epoch": 0.013846199755304229,
+      "grad_norm": 126.65892791748047,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 56.6929,
+      "step": 29
+    },
+    {
+      "epoch": 0.014323654919280237,
+      "grad_norm": 120.12496185302734,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 56.5957,
+      "step": 30
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "grad_norm": 106.14989471435547,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 55.5069,
+      "step": 31
+    },
+    {
+      "epoch": 0.015278565247232253,
+      "grad_norm": 109.8898696899414,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 53.8022,
+      "step": 32
+    },
+    {
+      "epoch": 0.01575602041120826,
+      "grad_norm": 97.504150390625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 54.222,
+      "step": 33
+    },
+    {
+      "epoch": 0.01623347557518427,
+      "grad_norm": 99.26302337646484,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 52.5477,
+      "step": 34
+    },
+    {
+      "epoch": 0.016710930739160277,
+      "grad_norm": 96.28750610351562,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 53.3365,
+      "step": 35
+    },
+    {
+      "epoch": 0.017188385903136285,
+      "grad_norm": 77.67048645019531,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 50.728,
+      "step": 36
+    },
+    {
+      "epoch": 0.017665841067112293,
+      "grad_norm": 72.44140625,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 52.0543,
+      "step": 37
+    },
+    {
+      "epoch": 0.0181432962310883,
+      "grad_norm": 59.20539474487305,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 48.2766,
+      "step": 38
+    },
+    {
+      "epoch": 0.018620751395064306,
+      "grad_norm": 88.11383056640625,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 55.584,
+      "step": 39
+    },
+    {
+      "epoch": 0.019098206559040314,
+      "grad_norm": 88.89408111572266,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 55.1093,
+      "step": 40
+    },
+    {
+      "epoch": 0.01957566172301632,
+      "grad_norm": 102.24915313720703,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 54.6306,
+      "step": 41
+    },
+    {
+      "epoch": 0.02005311688699233,
+      "grad_norm": 82.7913589477539,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 55.5029,
+      "step": 42
+    },
+    {
+      "epoch": 0.020530572050968338,
+      "grad_norm": 64.3345947265625,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 52.6247,
+      "step": 43
+    },
+    {
+      "epoch": 0.021008027214944346,
+      "grad_norm": 43.681922912597656,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 54.5378,
+      "step": 44
+    },
+    {
+      "epoch": 0.021485482378920354,
+      "grad_norm": 35.26486587524414,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 54.1247,
+      "step": 45
+    },
+    {
+      "epoch": 0.02196293754289636,
+      "grad_norm": 38.07099151611328,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 51.6821,
+      "step": 46
+    },
+    {
+      "epoch": 0.02244039270687237,
+      "grad_norm": 36.62192916870117,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 51.4654,
+      "step": 47
+    },
+    {
+      "epoch": 0.022917847870848378,
+      "grad_norm": 42.04517364501953,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 51.8335,
+      "step": 48
+    },
+    {
+      "epoch": 0.023395303034824386,
+      "grad_norm": 58.63186264038086,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 50.0945,
+      "step": 49
+    },
+    {
+      "epoch": 0.023872758198800394,
+      "grad_norm": 88.34986877441406,
+      "learning_rate": 1e-05,
+      "loss": 50.5648,
+      "step": 50
+    },
+    {
+      "epoch": 0.023872758198800394,
+      "eval_loss": 3.0543212890625,
+      "eval_runtime": 2.3055,
+      "eval_samples_per_second": 21.688,
+      "eval_steps_per_second": 5.639,
+      "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