Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bda1a1f498359227b0f7a6a52a03a8ad1b26e5c9fecf3d5d1bd9e80cb0c2f8
+oid sha256:97a44edb25c8472d6e9beeaef06b8925b3434b2af0294d9565d98474d869330b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87fbfcf08a3f85da7898752e8e4ad9b34946a36ee16be8dedab3a9a9fe1059a
+oid sha256:27bfcdfbd4fdcdbc0b393181a20731c93ff22cf64a6ab19d18fca9dc0936c93e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e167772e200bcb27a25ef7dff0022d7c666d81c4f6acaf99fd8fa8107804980a
+oid sha256:f6f8f38aa67399f23bfddb516639b4eff6ccedddab87b9ecf998a773745ea723
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278ab6d79108498938f5de31c3383559c8f6f4520b0b2ded23e081f14c01a590
+oid sha256:528d930588dd308ea98dd9cb6d701dbb631e30d2504000239e638c8d7eca90ad
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49559fe197bfe038d8a07e963002fd73c9d2b4cb94fe1ca87ed50f076fd3830e
+oid sha256:0c4d6f7fcafc41456efe50097068d2037920ec0397f4bad9686f3bae598b4d93
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735045698d407bfb9ddcd835680b295b1735a2bdced1c2a879e458dd94ddbfdd
+oid sha256:8b06c6f8edaa6e667321a1db06b9e1d756d51db713d9d1f809aabdd1d7f07265
 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": 2.190603494644165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3333333333333333,
+  "best_metric": 2.0931200981140137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6666666666666666,
   "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": 16.425,
       "eval_steps_per_second": 4.27,
       "step": 25
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2241379022598267,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3055,
+      "step": 26
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3594948053359985,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.3785,
+      "step": 27
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.2289537191390991,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.2831,
+      "step": 28
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.2282068729400635,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.2992,
+      "step": 29
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.246193289756775,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.1545,
+      "step": 30
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.2939361333847046,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1719,
+      "step": 31
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.3804665803909302,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.1569,
+      "step": 32
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.339778184890747,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9677,
+      "step": 33
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.414006233215332,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.0773,
+      "step": 34
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.5580247640609741,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.0759,
+      "step": 35
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6884983777999878,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.886,
+      "step": 36
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.781772255897522,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9403,
+      "step": 37
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.23185133934021,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.3618,
+      "step": 38
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0226683616638184,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2791,
+      "step": 39
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.0725868940353394,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.1872,
+      "step": 40
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 1.0788142681121826,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.1072,
+      "step": 41
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1302546262741089,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2024,
+      "step": 42
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.2044343948364258,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9807,
+      "step": 43
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.2247614860534668,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.1869,
+      "step": 44
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1999990940093994,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8419,
+      "step": 45
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.3661562204360962,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.1598,
+      "step": 46
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.3841426372528076,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1078,
+      "step": 47
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5462560653686523,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.0147,
+      "step": 48
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 1.6369709968566895,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.8896,
+      "step": 49
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.9499114751815796,
+      "learning_rate": 1e-05,
+      "loss": 1.7455,
+      "step": 50
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 2.0931200981140137,
+      "eval_runtime": 3.0155,
+      "eval_samples_per_second": 16.581,
+      "eval_steps_per_second": 4.311,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null