Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a20a7ed0bce9a46a1aadbe93e9c26a53ffcfb6678a2ba2740c0fce8cd7eed9
+oid sha256:c4ae46111f25900606231672cf402245efca0e9b4093b985143d26b5bca9c5e2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc88b986dbc5dd55447f6ed00b265aebf736ef29a955075cf0c092aa6412f776
+oid sha256:980bc17486b9c932821a4567bbaaa0d174ebf5ed4b824ec174814c48b08665b6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a13813b119121d652898d31d0955f6df4e3ecbfb5b46b3366a5ca49b8ffb35c
+oid sha256:7ca1f53ba0dd38aa3dffdca6ceb9cf6d0cb74b2c743225a3ed71b2ef636ce7ad
 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": 2.9394724369049072,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003989706557082727,
+  "best_metric": 0.46810051798820496,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0007979413114165454,
   "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": 5.929,
       "eval_steps_per_second": 2.964,
       "step": 10
+    },
+    {
+      "epoch": 0.00043886772127909993,
+      "grad_norm": 15.616610527038574,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.1589,
+      "step": 11
+    },
+    {
+      "epoch": 0.0004787647868499272,
+      "grad_norm": 14.602272987365723,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.2852,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005186618524207544,
+      "grad_norm": 50.422203063964844,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.3434,
+      "step": 13
+    },
+    {
+      "epoch": 0.0005585589179915817,
+      "grad_norm": 4.45857572555542,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0479,
+      "step": 14
+    },
+    {
+      "epoch": 0.0005984559835624089,
+      "grad_norm": 19.128103256225586,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7122,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005984559835624089,
+      "eval_loss": 1.144124984741211,
+      "eval_runtime": 1799.5762,
+      "eval_samples_per_second": 5.865,
+      "eval_steps_per_second": 2.932,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006383530491332362,
+      "grad_norm": 23.54120445251465,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.604,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006782501147040636,
+      "grad_norm": 6.584514617919922,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.788,
+      "step": 17
+    },
+    {
+      "epoch": 0.0007181471802748908,
+      "grad_norm": 1.4092001914978027,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0147,
+      "step": 18
+    },
+    {
+      "epoch": 0.0007580442458457181,
+      "grad_norm": 11.170414924621582,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5299,
+      "step": 19
+    },
+    {
+      "epoch": 0.0007979413114165454,
+      "grad_norm": 7.714025020599365,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.0699,
+      "step": 20
+    },
+    {
+      "epoch": 0.0007979413114165454,
+      "eval_loss": 0.46810051798820496,
+      "eval_runtime": 1796.8416,
+      "eval_samples_per_second": 5.874,
+      "eval_steps_per_second": 2.937,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2774346372218880.0,
+  "total_flos": 5594931850641408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null