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:f1ad8e69be5a5a660039eea766c7a04e8646d0ee51149cdc4e468ac8f562c90e
+oid sha256:dbf3483eda57b30652a76ebf48ffd13c86facaef0fe4b04464b576f9e93e6868
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea05d37ccc4d412c8177a4be29fd89613a8a3687ebb80a3fb8747d5b6e53e89c
+oid sha256:1faf480b1986137072d06483c87a6aec0ab1f50bcf4421ec5fef5fcec7f115e9
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6833ab40493f834f95371ad686495a27d1254dd413f048f1377119b9154e484c
+oid sha256:6f9f7ef70996e84f7dc6811ec752eea202da535749f2ac49923b4322384b4a8b
 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": 4.148122310638428,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016808135137406505,
+  "best_metric": 3.8484609127044678,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003361627027481301,
   "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": 11.827,
       "eval_steps_per_second": 5.916,
       "step": 10
+    },
+    {
+      "epoch": 0.0018488948651147156,
+      "grad_norm": 0.9299777150154114,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.4881,
+      "step": 11
+    },
+    {
+      "epoch": 0.0020169762164887806,
+      "grad_norm": 1.18503999710083,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.0163,
+      "step": 12
+    },
+    {
+      "epoch": 0.0021850575678628455,
+      "grad_norm": 1.2439167499542236,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.0226,
+      "step": 13
+    },
+    {
+      "epoch": 0.002353138919236911,
+      "grad_norm": 0.9216750264167786,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.3341,
+      "step": 14
+    },
+    {
+      "epoch": 0.0025212202706109757,
+      "grad_norm": 0.8185566663742065,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.4702,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025212202706109757,
+      "eval_loss": 3.90740704536438,
+      "eval_runtime": 211.8663,
+      "eval_samples_per_second": 11.823,
+      "eval_steps_per_second": 5.914,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026893016219850406,
+      "grad_norm": 0.7571693658828735,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.0438,
+      "step": 16
+    },
+    {
+      "epoch": 0.002857382973359106,
+      "grad_norm": 1.0295147895812988,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.6677,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030254643247331708,
+      "grad_norm": 0.9374280571937561,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.2293,
+      "step": 18
+    },
+    {
+      "epoch": 0.003193545676107236,
+      "grad_norm": 0.9331271648406982,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.5881,
+      "step": 19
+    },
+    {
+      "epoch": 0.003361627027481301,
+      "grad_norm": 0.8545352816581726,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.211,
+      "step": 20
+    },
+    {
+      "epoch": 0.003361627027481301,
+      "eval_loss": 3.8484609127044678,
+      "eval_runtime": 209.7391,
+      "eval_samples_per_second": 11.943,
+      "eval_steps_per_second": 5.974,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 255791978250240.0,
+  "total_flos": 511583956500480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null