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:f10af26341687735ec3f2997b963ea198a9b536407ee0d81d97386dc6ecf45d8
+oid sha256:b5bd5b3c6dcde861558f7e9e44c228c4046b93a9a734d20a22f7acd1b14ec57b
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7eb7863fd01736597910e324fb487a34a120dc63292a49a07839f10d0f853b9
+oid sha256:53872f445483765bfda62260a92a16ed4b724542db1f1472592b7216d1031658
 size 9568884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf168b292b47b6378c20cda1e2df8fdddd747f289b21c643120a4043a297de6
+oid sha256:13caed2486e1da8a0948af7d72cd477768bf513db1ce28ff265331bf837f1d26
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d899ad7de26e11160375a32e0883b379b879c26902a7c976304d6dd2b3b732
+oid sha256:55777a62bf7f2ea823eb8ae44539d8fad2b3742eda9a67334d081523ea8a1fdc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d61ea2468026f4a8040e4f6bb3ee153a5f9a5febc20681330147acf05d7927
+oid sha256:d8bb503db4e06ee680e1b47429d8e2fb144d4a5001e10c8f2fd1759db8b3580b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ebe65b4e17a994b7ce17ad12085646f614e05e34eebf837d2c8d9b911c2e48
+oid sha256:72999cbe5329d0fccf9bb6ff5c1d1e79bb2e0f7db521586685b152d8f193c715
 size 15024

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": 1.0617578029632568,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006763611768684477,
+  "best_metric": 0.14818401634693146,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.013527223537368955,
   "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": 200.781,
       "eval_steps_per_second": 25.158,
       "step": 10
+    },
+    {
+      "epoch": 0.0074399729455529254,
+      "grad_norm": 6.420353412628174,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.1378,
+      "step": 11
+    },
+    {
+      "epoch": 0.008116334122421373,
+      "grad_norm": 7.892561912536621,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8164,
+      "step": 12
+    },
+    {
+      "epoch": 0.00879269529928982,
+      "grad_norm": 2.6381897926330566,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2681,
+      "step": 13
+    },
+    {
+      "epoch": 0.009469056476158269,
+      "grad_norm": 1.4537419080734253,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.38,
+      "step": 14
+    },
+    {
+      "epoch": 0.010145417653026716,
+      "grad_norm": 2.559450149536133,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2357,
+      "step": 15
+    },
+    {
+      "epoch": 0.010145417653026716,
+      "eval_loss": 0.2033427357673645,
+      "eval_runtime": 12.442,
+      "eval_samples_per_second": 200.128,
+      "eval_steps_per_second": 25.076,
+      "step": 15
+    },
+    {
+      "epoch": 0.010821778829895164,
+      "grad_norm": 2.0941014289855957,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.217,
+      "step": 16
+    },
+    {
+      "epoch": 0.011498140006763611,
+      "grad_norm": 0.9307464957237244,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0343,
+      "step": 17
+    },
+    {
+      "epoch": 0.01217450118363206,
+      "grad_norm": 3.1173644065856934,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.2368,
+      "step": 18
+    },
+    {
+      "epoch": 0.012850862360500507,
+      "grad_norm": 4.499870300292969,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.1805,
+      "step": 19
+    },
+    {
+      "epoch": 0.013527223537368955,
+      "grad_norm": 2.9719085693359375,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.2002,
+      "step": 20
+    },
+    {
+      "epoch": 0.013527223537368955,
+      "eval_loss": 0.14818401634693146,
+      "eval_runtime": 12.379,
+      "eval_samples_per_second": 201.148,
+      "eval_steps_per_second": 25.204,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 425157222989824.0,
+  "total_flos": 870348039913472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null