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:e7dff8048a89e9f403825b565a6621ee31daece4fae0cf1d63c177d484aec0dc
+oid sha256:e29034eea91acc30e317255de8de7cde98f564731e38bf821143d6486da3e619
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad2d71bd9320f6abc1ef8f650c300df925fe126f671260a58d5ff54db1e232e
+oid sha256:602949b8f3787ae7539156d7d343942f9b365ef21404e969d51ec0e4d9b6d0c3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c131dbd91565c4590ffebc6de5c5bc9ac2b3ec6550c91e2c8c0f2d8d46b57d0
+oid sha256:a8080d838ff199c055d8fdfbac0b743832528f3bed5c636607beb4b966705f0e
 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": 2.4816670417785645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00030026648650677474,
+  "best_metric": 1.108259916305542,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006005329730135495,
   "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": 4.692,
       "eval_steps_per_second": 2.346,
       "step": 10
+    },
+    {
+      "epoch": 0.00033029313515745224,
+      "grad_norm": 3.4956119060516357,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.2861,
+      "step": 11
+    },
+    {
+      "epoch": 0.00036031978380812973,
+      "grad_norm": 3.3594372272491455,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5061,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003903464324588072,
+      "grad_norm": 4.1526994705200195,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.3948,
+      "step": 13
+    },
+    {
+      "epoch": 0.00042037308110948467,
+      "grad_norm": 2.729642629623413,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.487,
+      "step": 14
+    },
+    {
+      "epoch": 0.00045039972976016217,
+      "grad_norm": 2.9560699462890625,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.0658,
+      "step": 15
+    },
+    {
+      "epoch": 0.00045039972976016217,
+      "eval_loss": 1.3512855768203735,
+      "eval_runtime": 3002.1108,
+      "eval_samples_per_second": 4.671,
+      "eval_steps_per_second": 2.336,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004804263784108396,
+      "grad_norm": 3.1448676586151123,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6595,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005104530270615171,
+      "grad_norm": 7.779876708984375,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.5521,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005404796757121946,
+      "grad_norm": 3.0016863346099854,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.2587,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005705063243628721,
+      "grad_norm": 2.96671724319458,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.9777,
+      "step": 19
+    },
+    {
+      "epoch": 0.0006005329730135495,
+      "grad_norm": 2.7571752071380615,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.993,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006005329730135495,
+      "eval_loss": 1.108259916305542,
+      "eval_runtime": 3005.5794,
+      "eval_samples_per_second": 4.666,
+      "eval_steps_per_second": 2.333,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4353530737459200.0,
+  "total_flos": 8548751266283520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null