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:bb7e1bc70a70ebd5d8327cf2fc19d5542c491c1415cc357a24a45c1f22cb03af
+oid sha256:4f19c0209adf85e51c88ccfe69de41ca345598c3b30099a717c388d0e71bddb8
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff33fe2a5db300f9403b01b2a25bdc9abe99cb6c3daedf23952da4cdd80d377
+oid sha256:bc7235cbd47d156793ee982a3a481a3fbc2ddfcaf1d0208e641a517e25699c5f
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:39ccd5622448d5b4793f7c0320456317dd3c53025e79a98eaa0b1029556f2441
 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": 4.511049270629883,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006026819346090101,
+  "best_metric": 4.010801315307617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.012053638692180202,
   "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": 9.296,
       "eval_steps_per_second": 4.654,
       "step": 10
+    },
+    {
+      "epoch": 0.006629501280699111,
+      "grad_norm": 3.848144054412842,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.5971,
+      "step": 11
+    },
+    {
+      "epoch": 0.007232183215308121,
+      "grad_norm": 4.838451862335205,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.4905,
+      "step": 12
+    },
+    {
+      "epoch": 0.00783486514991713,
+      "grad_norm": 3.418919563293457,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.0452,
+      "step": 13
+    },
+    {
+      "epoch": 0.008437547084526141,
+      "grad_norm": 5.053792953491211,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.8261,
+      "step": 14
+    },
+    {
+      "epoch": 0.009040229019135152,
+      "grad_norm": 5.080602645874023,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.8139,
+      "step": 15
+    },
+    {
+      "epoch": 0.009040229019135152,
+      "eval_loss": 4.185687065124512,
+      "eval_runtime": 75.4289,
+      "eval_samples_per_second": 9.267,
+      "eval_steps_per_second": 4.64,
+      "step": 15
+    },
+    {
+      "epoch": 0.009642910953744161,
+      "grad_norm": 3.5324654579162598,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.7614,
+      "step": 16
+    },
+    {
+      "epoch": 0.010245592888353172,
+      "grad_norm": 4.834116458892822,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.6882,
+      "step": 17
+    },
+    {
+      "epoch": 0.010848274822962183,
+      "grad_norm": 3.57612943649292,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.3122,
+      "step": 18
+    },
+    {
+      "epoch": 0.011450956757571192,
+      "grad_norm": 3.308840751647949,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.7553,
+      "step": 19
+    },
+    {
+      "epoch": 0.012053638692180202,
+      "grad_norm": 3.328306198120117,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.1738,
+      "step": 20
+    },
+    {
+      "epoch": 0.012053638692180202,
+      "eval_loss": 4.010801315307617,
+      "eval_runtime": 81.4236,
+      "eval_samples_per_second": 8.585,
+      "eval_steps_per_second": 4.299,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89038163804160.0,
+  "total_flos": 180302281703424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null