Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70778af5fc726d286aaf24090ef2aad31c2726b3b21cf345026e377f598f29f5
+oid sha256:9a68a44b790d074d17d72d64c9ad63574368237921ab0e26c828878749abd3f2
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18165fa8e1aa5c02cf190d98ed30c8066a612a5ba161ccee96a3fee4f13cbe82
+oid sha256:f14d8182d7fac50478e5fb673cd58976dbc53c14d95bb5c7b19c04707ac6a2a8
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0335b1c222bfd1b57cc290d07c52fd598e48d80ea2c40960859220dad66b03
+oid sha256:1978fea88b8a880f104b72fd0829be61eb101af8c50325655e0d855cb4451775
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0fdacedfb245722e833c9574873019cadf524e122849884c005336604518c0
+oid sha256:1d50b8c296cebd239c66d96d9440fa1536e9e283b9a184391c2478c02d95278f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005144ca2d0b226ebf9ea934937f68e66e5c48080758af300c71de94e0a75832
+oid sha256:4a1d8f461d473a4a62ad763e88601cfc015a3c3bf0959993bea7d286cf24079c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f87c00708a68a175d4a30086e4a7ebd637889360caeacc6472e8024f2e80dd7
+oid sha256:cdde3682c4a825583519b9a32f50694016967abacd3f5339c832e9f20322e99e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.758246421813965,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028072145413713244,
+  "best_metric": 11.722420692443848,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05614429082742649,
   "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": 211.745,
       "eval_steps_per_second": 13.235,
       "step": 25
+    },
+    {
+      "epoch": 0.02919503123026177,
+      "grad_norm": 1.2912324666976929,
+      "learning_rate": 5e-05,
+      "loss": 11.8265,
+      "step": 26
+    },
+    {
+      "epoch": 0.030317917046810302,
+      "grad_norm": 1.2150214910507202,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.7552,
+      "step": 27
+    },
+    {
+      "epoch": 0.03144080286335883,
+      "grad_norm": 1.5897176265716553,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.7248,
+      "step": 28
+    },
+    {
+      "epoch": 0.03256368867990736,
+      "grad_norm": 1.5894674062728882,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.7212,
+      "step": 29
+    },
+    {
+      "epoch": 0.033686574496455894,
+      "grad_norm": 1.0012295246124268,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.7495,
+      "step": 30
+    },
+    {
+      "epoch": 0.03480946031300442,
+      "grad_norm": 1.0388928651809692,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.7438,
+      "step": 31
+    },
+    {
+      "epoch": 0.03593234612955295,
+      "grad_norm": 1.0270273685455322,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.7372,
+      "step": 32
+    },
+    {
+      "epoch": 0.03705523194610148,
+      "grad_norm": 0.9539456963539124,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.7432,
+      "step": 33
+    },
+    {
+      "epoch": 0.03817811776265001,
+      "grad_norm": 0.9844604134559631,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.7307,
+      "step": 34
+    },
+    {
+      "epoch": 0.03930100357919854,
+      "grad_norm": 0.9605456590652466,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.7382,
+      "step": 35
+    },
+    {
+      "epoch": 0.04042388939574707,
+      "grad_norm": 0.9321780800819397,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.7314,
+      "step": 36
+    },
+    {
+      "epoch": 0.0415467752122956,
+      "grad_norm": 0.9346773624420166,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.7312,
+      "step": 37
+    },
+    {
+      "epoch": 0.042669661028844126,
+      "grad_norm": 0.8359819650650024,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7876,
+      "step": 38
+    },
+    {
+      "epoch": 0.04379254684539266,
+      "grad_norm": 0.9656929969787598,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.7867,
+      "step": 39
+    },
+    {
+      "epoch": 0.04491543266194119,
+      "grad_norm": 1.5463958978652954,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.6946,
+      "step": 40
+    },
+    {
+      "epoch": 0.04603831847848972,
+      "grad_norm": 1.6045920848846436,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.6936,
+      "step": 41
+    },
+    {
+      "epoch": 0.04716120429503825,
+      "grad_norm": 1.1567155122756958,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.706,
+      "step": 42
+    },
+    {
+      "epoch": 0.048284090111586776,
+      "grad_norm": 0.9199723601341248,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.7236,
+      "step": 43
+    },
+    {
+      "epoch": 0.04940697592813531,
+      "grad_norm": 0.8852842450141907,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7231,
+      "step": 44
+    },
+    {
+      "epoch": 0.05052986174468384,
+      "grad_norm": 0.8971695899963379,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.7274,
+      "step": 45
+    },
+    {
+      "epoch": 0.051652747561232365,
+      "grad_norm": 0.9319720268249512,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.7129,
+      "step": 46
+    },
+    {
+      "epoch": 0.0527756333777809,
+      "grad_norm": 0.8851380944252014,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.7265,
+      "step": 47
+    },
+    {
+      "epoch": 0.053898519194329426,
+      "grad_norm": 0.9237000942230225,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.7171,
+      "step": 48
+    },
+    {
+      "epoch": 0.055021405010877954,
+      "grad_norm": 0.9351820945739746,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.7237,
+      "step": 49
+    },
+    {
+      "epoch": 0.05614429082742649,
+      "grad_norm": 0.9843584895133972,
+      "learning_rate": 0.0,
+      "loss": 11.7242,
+      "step": 50
+    },
+    {
+      "epoch": 0.05614429082742649,
+      "eval_loss": 11.722420692443848,
+      "eval_runtime": 56.3582,
+      "eval_samples_per_second": 212.906,
+      "eval_steps_per_second": 13.308,
+      "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": 550104861769728.0,
+  "total_flos": 1099948638601216.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null