Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1259d7ebd05e08f3c3b89b1ead92396ff7d0fc5055dc419121a763f84aeea3ee
+oid sha256:32b8eada9312e28dfe04276bd8b9b7a7effa7a4756789fbf6f6382d4b09e480b
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d2228d6b2f2e2005a7c658ddf6045735a7158be5f5838aa00ee2568eae1971
+oid sha256:989cdf42d7d81c4415de6bbf3102891b617228032aed1653192415e44f262cf3
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d0af37a77f5c27d7a7b6c2e30f1f41b0153ab23109dd9c02711559ebf4c81d
+oid sha256:a138d3f3dd13599c094a8de181db049a8c4ad40cce5fb552a7b25168268ced86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6f57659ff57e9e8c8662c2d499f6f3c0fddae916869ee7e89fd9c426eda367
+oid sha256:65cc395c70978d1ffa5826990f4efb0f02f24c8cddc452cf880fdc2da2924cb2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e64010f6582a3d2e7a51d4edbefbb6ee4d395f92c80cbdf8b14bd66e7c029f
+oid sha256:2d455f46d923e3229630172efb09e19c7f5e6e2d5b9f990158b7c63d9e8a9a85
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de95672374cfd8fb1b4dd492e2c27825c5c9d5bfeac86407055976bbdb9da4b
+oid sha256:17f19e1ec7bd91a21cbfdac9bb4340b26d9f759b33807fbd0755a4d5a1205bd2
 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": 6.831989765167236,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02656042496679947,
+  "best_metric": 6.8076324462890625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05312084993359894,
   "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": 433.859,
       "eval_steps_per_second": 112.803,
       "step": 25
+    },
+    {
+      "epoch": 0.027622841965471448,
+      "grad_norm": 0.48254695534706116,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.8441,
+      "step": 26
+    },
+    {
+      "epoch": 0.028685258964143426,
+      "grad_norm": 0.4874054193496704,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.8453,
+      "step": 27
+    },
+    {
+      "epoch": 0.029747675962815405,
+      "grad_norm": 0.4814146161079407,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.8455,
+      "step": 28
+    },
+    {
+      "epoch": 0.030810092961487383,
+      "grad_norm": 0.5245039463043213,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8339,
+      "step": 29
+    },
+    {
+      "epoch": 0.03187250996015936,
+      "grad_norm": 0.4892662465572357,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8387,
+      "step": 30
+    },
+    {
+      "epoch": 0.032934926958831344,
+      "grad_norm": 0.48735734820365906,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8307,
+      "step": 31
+    },
+    {
+      "epoch": 0.03399734395750332,
+      "grad_norm": 0.5039017200469971,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.8271,
+      "step": 32
+    },
+    {
+      "epoch": 0.0350597609561753,
+      "grad_norm": 0.511929452419281,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.8286,
+      "step": 33
+    },
+    {
+      "epoch": 0.036122177954847276,
+      "grad_norm": 0.45853519439697266,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.8392,
+      "step": 34
+    },
+    {
+      "epoch": 0.03718459495351926,
+      "grad_norm": 0.5033186078071594,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.8262,
+      "step": 35
+    },
+    {
+      "epoch": 0.03824701195219123,
+      "grad_norm": 0.5333366394042969,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.8221,
+      "step": 36
+    },
+    {
+      "epoch": 0.039309428950863215,
+      "grad_norm": 0.5256316661834717,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.813,
+      "step": 37
+    },
+    {
+      "epoch": 0.04037184594953519,
+      "grad_norm": 0.49777570366859436,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.8198,
+      "step": 38
+    },
+    {
+      "epoch": 0.04143426294820717,
+      "grad_norm": 0.44153058528900146,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.8374,
+      "step": 39
+    },
+    {
+      "epoch": 0.04249667994687915,
+      "grad_norm": 0.4926466643810272,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.04355909694555113,
+      "grad_norm": 0.470235139131546,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8234,
+      "step": 41
+    },
+    {
+      "epoch": 0.04462151394422311,
+      "grad_norm": 0.47815701365470886,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.8224,
+      "step": 42
+    },
+    {
+      "epoch": 0.045683930942895086,
+      "grad_norm": 0.4792591333389282,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.82,
+      "step": 43
+    },
+    {
+      "epoch": 0.04674634794156707,
+      "grad_norm": 0.4888472855091095,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8158,
+      "step": 44
+    },
+    {
+      "epoch": 0.04780876494023904,
+      "grad_norm": 0.49055448174476624,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.8205,
+      "step": 45
+    },
+    {
+      "epoch": 0.048871181938911025,
+      "grad_norm": 0.4726165235042572,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.826,
+      "step": 46
+    },
+    {
+      "epoch": 0.049933598937583,
+      "grad_norm": 0.4675711393356323,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.8278,
+      "step": 47
+    },
+    {
+      "epoch": 0.05099601593625498,
+      "grad_norm": 0.49473482370376587,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.8164,
+      "step": 48
+    },
+    {
+      "epoch": 0.05205843293492696,
+      "grad_norm": 0.49276942014694214,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.8157,
+      "step": 49
+    },
+    {
+      "epoch": 0.05312084993359894,
+      "grad_norm": 0.5099896192550659,
+      "learning_rate": 1e-05,
+      "loss": 6.8102,
+      "step": 50
+    },
+    {
+      "epoch": 0.05312084993359894,
+      "eval_loss": 6.8076324462890625,
+      "eval_runtime": 0.1099,
+      "eval_samples_per_second": 454.851,
+      "eval_steps_per_second": 118.261,
+      "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": 2853870239744.0,
+  "total_flos": 5706848927744.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null