Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a410a7d4292bfc4825106d85a2eb048e37d3bbc867398fac60084aca6202ba
+oid sha256:5e9217c4e7493723781205fbbb36c7630f31a446af44d93fd157564aa65b452c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee8035221d8ba5da3b08dd396abb96d53b0005ea5ae8b8fce3eb2eb1153be72
+oid sha256:99c380babf18db499e31d669d07ecb01758a05de5a7dc7bb0e190868eeb46347
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddda6bad744e38a967a5f5660089d67b61f472e72abc86193f2b3f610298e7d
+oid sha256:c0e4a4e1df670242b46e9d7aa0e1b2d2fe23a87169fd32d093899196d63f9049
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e293ca78b3b18d0aa4ad930c10c9c041458484d77dcf4b19cb0316cb4774abdb
+oid sha256:c5f7878a94bc314bf35d9091cb34ec228fac1158c22f59bcd3f048b3ca1e98f3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139b65b769c348ec60a94fddc0a021a837de318b3dbbaaa9daa5e0ba8792b614
+oid sha256:07b74483d155db113a90f2552caf45a8dd69bb51cd0e676605b36d946e32e793
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2355ee2417a6f93c5c3fa97608cd4b094d1fa0a3aadba1fb858b6a7ce9cdc9
+oid sha256:54adfa0f1506732f1899acbe81527440a3d680a98d806e1eaab77ceb5159fd33
 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": 1.1263799667358398,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009666855975929528,
+  "best_metric": 1.079894781112671,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.019333711951859057,
   "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": 11.223,
       "eval_steps_per_second": 2.918,
       "step": 25
+    },
+    {
+      "epoch": 0.010053530214966709,
+      "grad_norm": 0.6278276443481445,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0529,
+      "step": 26
+    },
+    {
+      "epoch": 0.010440204454003892,
+      "grad_norm": 0.7694540619850159,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1474,
+      "step": 27
+    },
+    {
+      "epoch": 0.010826878693041072,
+      "grad_norm": 0.8079923987388611,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2902,
+      "step": 28
+    },
+    {
+      "epoch": 0.011213552932078253,
+      "grad_norm": 0.7759771943092346,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3836,
+      "step": 29
+    },
+    {
+      "epoch": 0.011600227171115434,
+      "grad_norm": 0.8336804509162903,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3003,
+      "step": 30
+    },
+    {
+      "epoch": 0.011986901410152616,
+      "grad_norm": 0.8377479910850525,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.139,
+      "step": 31
+    },
+    {
+      "epoch": 0.012373575649189797,
+      "grad_norm": 0.9176948666572571,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.1629,
+      "step": 32
+    },
+    {
+      "epoch": 0.012760249888226978,
+      "grad_norm": 1.0604687929153442,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1758,
+      "step": 33
+    },
+    {
+      "epoch": 0.013146924127264158,
+      "grad_norm": 1.2144715785980225,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2301,
+      "step": 34
+    },
+    {
+      "epoch": 0.01353359836630134,
+      "grad_norm": 1.3745107650756836,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2456,
+      "step": 35
+    },
+    {
+      "epoch": 0.013920272605338522,
+      "grad_norm": 1.600318193435669,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3851,
+      "step": 36
+    },
+    {
+      "epoch": 0.014306946844375702,
+      "grad_norm": 2.159118175506592,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2168,
+      "step": 37
+    },
+    {
+      "epoch": 0.014693621083412883,
+      "grad_norm": 0.42829155921936035,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0154,
+      "step": 38
+    },
+    {
+      "epoch": 0.015080295322450065,
+      "grad_norm": 0.47999152541160583,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.0847,
+      "step": 39
+    },
+    {
+      "epoch": 0.015466969561487246,
+      "grad_norm": 0.5711833238601685,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.168,
+      "step": 40
+    },
+    {
+      "epoch": 0.01585364380052443,
+      "grad_norm": 0.6433935761451721,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3372,
+      "step": 41
+    },
+    {
+      "epoch": 0.016240318039561608,
+      "grad_norm": 1.0092722177505493,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2755,
+      "step": 42
+    },
+    {
+      "epoch": 0.01662699227859879,
+      "grad_norm": 0.7510892748832703,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.187,
+      "step": 43
+    },
+    {
+      "epoch": 0.01701366651763597,
+      "grad_norm": 0.8415061831474304,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.224,
+      "step": 44
+    },
+    {
+      "epoch": 0.01740034075667315,
+      "grad_norm": 0.9812833070755005,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2346,
+      "step": 45
+    },
+    {
+      "epoch": 0.017787014995710334,
+      "grad_norm": 0.9822847247123718,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0966,
+      "step": 46
+    },
+    {
+      "epoch": 0.018173689234747513,
+      "grad_norm": 1.2030738592147827,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1899,
+      "step": 47
+    },
+    {
+      "epoch": 0.018560363473784695,
+      "grad_norm": 1.260042667388916,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1596,
+      "step": 48
+    },
+    {
+      "epoch": 0.018947037712821878,
+      "grad_norm": 2.2965540885925293,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.199,
+      "step": 49
+    },
+    {
+      "epoch": 0.019333711951859057,
+      "grad_norm": 2.204000473022461,
+      "learning_rate": 1e-05,
+      "loss": 1.2124,
+      "step": 50
+    },
+    {
+      "epoch": 0.019333711951859057,
+      "eval_loss": 1.079894781112671,
+      "eval_runtime": 4.4734,
+      "eval_samples_per_second": 11.177,
+      "eval_steps_per_second": 2.906,
+      "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": 2.984974321220321e+17,
+  "total_flos": 5.969016129878753e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null