Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2ebc654f267d158508015e7ffb3cd32136f4c514a0abd25e1f3eee099968a5
+oid sha256:b5829b406724bca6942283122d73fa1e67214b60ed240bfc24c295958226688c
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b99c5ea96f70cecdc10f3f24f58842784fb36069edadc9fb335d95249e156e6b
+oid sha256:378b3acf22156f532bf652e06c7a1cd1661994b2ec030eaacd2841762eb62b2c
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8651bb89777cd6e2658de5b0d7ad93212799c8c1011ca5c2412ff04aff1cf308
+oid sha256:87cc2b55c223c49197bbdfd1940a4869f77d8832f581dbb3d5dd5035b99ec5f2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3bed0bb82dda947c213d67d8240c730849023ed745faaf2767c211811628bdf
+oid sha256:da3fce2d1db78da25f1cc95774f16123c622300551ceb9e240981c7ff9fbb3c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48365ce4b3cbc23e0d08e6c586add6d51a067badf0313992e723b91e972a97d5
+oid sha256:c665282072796092e3b66cb99313118b8e1d5236f6f03b068e0ec93546b220ce
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5730e22f63a4de662b65c139a8519e7088d58b2fbf02cc85b8acb6f62ba4f2b7
+oid sha256:94a5ba66460a1b1f694742a465d1de72ea029af2e66c1b63b7c3cb7edd7ab203
 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": 1.4621353149414062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006887823189578724,
+  "best_metric": 1.3308466672897339,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013775646379157448,
   "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": 22.1,
       "eval_steps_per_second": 5.746,
       "step": 25
+    },
+    {
+      "epoch": 0.007163336117161872,
+      "grad_norm": 1.08351731300354,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1669,
+      "step": 26
+    },
+    {
+      "epoch": 0.007438849044745021,
+      "grad_norm": 1.1508958339691162,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.796,
+      "step": 27
+    },
+    {
+      "epoch": 0.0077143619723281705,
+      "grad_norm": 1.2080681324005127,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.879,
+      "step": 28
+    },
+    {
+      "epoch": 0.00798987489991132,
+      "grad_norm": 1.3611031770706177,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.7371,
+      "step": 29
+    },
+    {
+      "epoch": 0.008265387827494468,
+      "grad_norm": 1.3392175436019897,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.6612,
+      "step": 30
+    },
+    {
+      "epoch": 0.008540900755077617,
+      "grad_norm": 1.2826539278030396,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.68,
+      "step": 31
+    },
+    {
+      "epoch": 0.008816413682660767,
+      "grad_norm": 1.4184712171554565,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.6392,
+      "step": 32
+    },
+    {
+      "epoch": 0.009091926610243915,
+      "grad_norm": 1.42243230342865,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5867,
+      "step": 33
+    },
+    {
+      "epoch": 0.009367439537827064,
+      "grad_norm": 1.5949103832244873,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4738,
+      "step": 34
+    },
+    {
+      "epoch": 0.009642952465410214,
+      "grad_norm": 1.6676265001296997,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.596,
+      "step": 35
+    },
+    {
+      "epoch": 0.009918465392993361,
+      "grad_norm": 1.4162265062332153,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5618,
+      "step": 36
+    },
+    {
+      "epoch": 0.010193978320576511,
+      "grad_norm": 1.7664705514907837,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.3765,
+      "step": 37
+    },
+    {
+      "epoch": 0.01046949124815966,
+      "grad_norm": 1.2374845743179321,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0416,
+      "step": 38
+    },
+    {
+      "epoch": 0.010745004175742808,
+      "grad_norm": 1.4492584466934204,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.9999,
+      "step": 39
+    },
+    {
+      "epoch": 0.011020517103325958,
+      "grad_norm": 1.5911473035812378,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8249,
+      "step": 40
+    },
+    {
+      "epoch": 0.011296030030909107,
+      "grad_norm": 1.7549965381622314,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7741,
+      "step": 41
+    },
+    {
+      "epoch": 0.011571542958492255,
+      "grad_norm": 1.734220027923584,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5942,
+      "step": 42
+    },
+    {
+      "epoch": 0.011847055886075404,
+      "grad_norm": 1.8675172328948975,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5419,
+      "step": 43
+    },
+    {
+      "epoch": 0.012122568813658554,
+      "grad_norm": 1.4374147653579712,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5869,
+      "step": 44
+    },
+    {
+      "epoch": 0.012398081741241702,
+      "grad_norm": 1.2492765188217163,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5914,
+      "step": 45
+    },
+    {
+      "epoch": 0.012673594668824851,
+      "grad_norm": 1.2149417400360107,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.535,
+      "step": 46
+    },
+    {
+      "epoch": 0.012949107596408,
+      "grad_norm": 1.3839102983474731,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4046,
+      "step": 47
+    },
+    {
+      "epoch": 0.013224620523991149,
+      "grad_norm": 1.3655040264129639,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5681,
+      "step": 48
+    },
+    {
+      "epoch": 0.013500133451574298,
+      "grad_norm": 1.9632959365844727,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.3139,
+      "step": 49
+    },
+    {
+      "epoch": 0.013775646379157448,
+      "grad_norm": 2.0195958614349365,
+      "learning_rate": 1e-05,
+      "loss": 1.4892,
+      "step": 50
+    },
+    {
+      "epoch": 0.013775646379157448,
+      "eval_loss": 1.3308466672897339,
+      "eval_runtime": 2.2559,
+      "eval_samples_per_second": 22.164,
+      "eval_steps_per_second": 5.763,
+      "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": 8.011890888697446e+16,
+  "total_flos": 1.601881470140416e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null