Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0ab1ac9e51b05d52203571ae4f695beec7862b870c2fd729ed3156a764407d
+oid sha256:d9ac58a0f8c8d5e8d20630153039d6e18a1d82ef9ec86f21946eceb591127ca5
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9ca385708dee42ed1978c001cf0947b06d3e70238c7703fc9b4c0dfe6b850a
+oid sha256:5f79c999348abc4d033904783646869cdecd9f5fbf8950ee3e8c54d9d5527c29
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 11.082746505737305,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006195786864931847,
+  "best_metric": 11.0792875289917,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.012391573729863693,
   "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": 83.501,
       "eval_steps_per_second": 41.75,
       "step": 10
+    },
+    {
+      "epoch": 0.006815365551425031,
+      "grad_norm": 0.44168758392333984,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 22.1878,
+      "step": 11
+    },
+    {
+      "epoch": 0.007434944237918215,
+      "grad_norm": 0.6517569422721863,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 22.1982,
+      "step": 12
+    },
+    {
+      "epoch": 0.0080545229244114,
+      "grad_norm": 0.4158121347427368,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 22.1605,
+      "step": 13
+    },
+    {
+      "epoch": 0.008674101610904586,
+      "grad_norm": 0.4672068655490875,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 22.161,
+      "step": 14
+    },
+    {
+      "epoch": 0.00929368029739777,
+      "grad_norm": 0.4878174662590027,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 22.1602,
+      "step": 15
+    },
+    {
+      "epoch": 0.00929368029739777,
+      "eval_loss": 11.080683708190918,
+      "eval_runtime": 4.2563,
+      "eval_samples_per_second": 79.882,
+      "eval_steps_per_second": 39.941,
+      "step": 15
+    },
+    {
+      "epoch": 0.009913258983890954,
+      "grad_norm": 0.49828019738197327,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 22.1889,
+      "step": 16
+    },
+    {
+      "epoch": 0.010532837670384139,
+      "grad_norm": 0.37732353806495667,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 22.1754,
+      "step": 17
+    },
+    {
+      "epoch": 0.011152416356877323,
+      "grad_norm": 0.4671807289123535,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 22.2014,
+      "step": 18
+    },
+    {
+      "epoch": 0.011771995043370507,
+      "grad_norm": 0.45731818675994873,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 22.1428,
+      "step": 19
+    },
+    {
+      "epoch": 0.012391573729863693,
+      "grad_norm": 0.5330766439437866,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 22.1427,
+      "step": 20
+    },
+    {
+      "epoch": 0.012391573729863693,
+      "eval_loss": 11.0792875289917,
+      "eval_runtime": 3.9761,
+      "eval_samples_per_second": 85.512,
+      "eval_steps_per_second": 42.756,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3735552000.0,
+  "total_flos": 7471104000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null