Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615cc2fe9f29a36b82cb33e1e1c719639ba1f1e57c30f0c685fcb6bf040b8c2f
+oid sha256:91c3bb7c41193aad216deb964f50d8f4e9e42dae2e1d3a93335ff6d02a37df5c
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5b60a6156b53e0533a651a24dac155441cb3c5b9aba2b147fa5dd5c9fa7f3a
+oid sha256:5f9f741212ed65709b23dce3a6f099bbdcaf98cacce2544decea5d1ca9daa63d
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cb781c5e4c60889ead280b02c5669391c332bc43300b75edbca8c65feb6521
+oid sha256:7ad27c620063b32151339446f8f6b2ba73508aa33db9a51cd9200bf556e5b70c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9f141f32a408f81e6b6d2a7bfb53d71f1fb147e96b315942d037f4db6da1d6
+oid sha256:68fa3bbdc30781fbbe2c509330080bae375df1d60bf72a2fdf644c549b232130
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da519449f97e62dfc80a4d9c60618a524f9d257cca53c4382ebe3f6077a53a6
+oid sha256:330ee59f39261d5473cd8aa0436e1a937606d6c65788be72c9daefa842519087
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf1863304f34c1134311c7f7c60302671b72c1e0e441c71fc77c55cd5000f72
+oid sha256:9f86d5c56f74c73c33b9fcbf58f01e45458ac96e3a158169f0b46fd88e19564a
 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": 1.7482954263687134,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4056795131845842,
+  "best_metric": 1.6689245700836182,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8113590263691683,
   "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": 38.918,
       "eval_steps_per_second": 10.119,
       "step": 25
+    },
+    {
+      "epoch": 0.42190669371196754,
+      "grad_norm": 1.2556699514389038,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6798,
+      "step": 26
+    },
+    {
+      "epoch": 0.4381338742393509,
+      "grad_norm": 1.4186452627182007,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0049,
+      "step": 27
+    },
+    {
+      "epoch": 0.4543610547667343,
+      "grad_norm": 1.4706568717956543,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.059,
+      "step": 28
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.499947190284729,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0129,
+      "step": 29
+    },
+    {
+      "epoch": 0.486815415821501,
+      "grad_norm": 1.3710793256759644,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9023,
+      "step": 30
+    },
+    {
+      "epoch": 0.5030425963488844,
+      "grad_norm": 1.329479455947876,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8568,
+      "step": 31
+    },
+    {
+      "epoch": 0.5192697768762677,
+      "grad_norm": 1.4655330181121826,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.0258,
+      "step": 32
+    },
+    {
+      "epoch": 0.5354969574036511,
+      "grad_norm": 1.617686152458191,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9157,
+      "step": 33
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 1.4850972890853882,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8218,
+      "step": 34
+    },
+    {
+      "epoch": 0.5679513184584178,
+      "grad_norm": 1.6351990699768066,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7625,
+      "step": 35
+    },
+    {
+      "epoch": 0.5841784989858012,
+      "grad_norm": 1.551815390586853,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.463,
+      "step": 36
+    },
+    {
+      "epoch": 0.6004056795131846,
+      "grad_norm": 1.770288348197937,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5631,
+      "step": 37
+    },
+    {
+      "epoch": 0.6166328600405679,
+      "grad_norm": 0.9632409811019897,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5874,
+      "step": 38
+    },
+    {
+      "epoch": 0.6328600405679513,
+      "grad_norm": 0.900738537311554,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.7267,
+      "step": 39
+    },
+    {
+      "epoch": 0.6490872210953347,
+      "grad_norm": 0.9534928798675537,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.967,
+      "step": 40
+    },
+    {
+      "epoch": 0.665314401622718,
+      "grad_norm": 1.032529354095459,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.6815415821501014,
+      "grad_norm": 1.1617575883865356,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9041,
+      "step": 42
+    },
+    {
+      "epoch": 0.6977687626774848,
+      "grad_norm": 1.1655863523483276,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.7873,
+      "step": 43
+    },
+    {
+      "epoch": 0.7139959432048681,
+      "grad_norm": 1.2248817682266235,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9275,
+      "step": 44
+    },
+    {
+      "epoch": 0.7302231237322515,
+      "grad_norm": 1.247793197631836,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.7185,
+      "step": 45
+    },
+    {
+      "epoch": 0.7464503042596349,
+      "grad_norm": 1.352537989616394,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.7711,
+      "step": 46
+    },
+    {
+      "epoch": 0.7626774847870182,
+      "grad_norm": 1.4393999576568604,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.8016,
+      "step": 47
+    },
+    {
+      "epoch": 0.7789046653144016,
+      "grad_norm": 1.519770860671997,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7282,
+      "step": 48
+    },
+    {
+      "epoch": 0.795131845841785,
+      "grad_norm": 1.366865634918213,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4245,
+      "step": 49
+    },
+    {
+      "epoch": 0.8113590263691683,
+      "grad_norm": 2.0266191959381104,
+      "learning_rate": 1e-05,
+      "loss": 1.7017,
+      "step": 50
+    },
+    {
+      "epoch": 0.8113590263691683,
+      "eval_loss": 1.6689245700836182,
+      "eval_runtime": 1.2791,
+      "eval_samples_per_second": 39.091,
+      "eval_steps_per_second": 10.164,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null