Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd44d8567a78d72752aa4584e4fcaf3df23bae50d81082b0fb6e5a7c1a0b409d
+oid sha256:1613b2e97efa09df320040be7045f5b9200e69cae651ef1f58a828c09b130bd7
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2d3d8aedbff4d16068301f70387e84f1af5641163f3b94000f8998792c4007
+oid sha256:ed05f944ee0693777c252247175ec7b9d3f4e2be297664752dbbae188e268d9f
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8c6fc31ac199e6c243ffe062905a7862052130540b4f8afa1589a29fe97b6d
+oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.105292320251465,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008194874106246543,
+  "best_metric": 11.086691856384277,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0016389748212493086,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 133.174,
       "eval_steps_per_second": 66.587,
       "step": 10
+    },
+    {
+      "epoch": 0.0009014361516871197,
+      "grad_norm": 2.037875175476074,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 44.3682,
+      "step": 11
+    },
+    {
+      "epoch": 0.000983384892749585,
+      "grad_norm": 1.9623230695724487,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 44.3456,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010653336338120505,
+      "grad_norm": 2.0174567699432373,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.3511,
+      "step": 13
+    },
+    {
+      "epoch": 0.001147282374874516,
+      "grad_norm": 2.3729968070983887,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 44.5621,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012292311159369815,
+      "grad_norm": 2.0023834705352783,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 44.5584,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012292311159369815,
+      "eval_loss": 11.094400405883789,
+      "eval_runtime": 38.9949,
+      "eval_samples_per_second": 131.761,
+      "eval_steps_per_second": 65.88,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013111798569994469,
+      "grad_norm": 2.1765761375427246,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.4832,
+      "step": 16
+    },
+    {
+      "epoch": 0.0013931285980619123,
+      "grad_norm": 2.074971914291382,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 44.3978,
+      "step": 17
+    },
+    {
+      "epoch": 0.0014750773391243777,
+      "grad_norm": 2.2266688346862793,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 44.4469,
+      "step": 18
+    },
+    {
+      "epoch": 0.001557026080186843,
+      "grad_norm": 1.9929441213607788,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 44.3314,
+      "step": 19
+    },
+    {
+      "epoch": 0.0016389748212493086,
+      "grad_norm": 1.9637781381607056,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 44.4735,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016389748212493086,
+      "eval_loss": 11.086691856384277,
+      "eval_runtime": 38.72,
+      "eval_samples_per_second": 132.696,
+      "eval_steps_per_second": 66.348,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 96448020480.0,
+  "total_flos": 192896040960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null