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:b5c8ccdd5d37f446ee3368b6b1d26e5cb2690a53f73f16a511b79f1445260ea6
+oid sha256:f5abf21cfab48dd3925d4ec5a166b7f55914349d9850978c53b268e3e112c702
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e890dbd6ac6e3de7492e1247e36948f61fcc0fe250df0718588b76dc32ece0e
+oid sha256:4252abb5398e8d90f8b250957c93777aadd7d391b06d22581496fb853312f3aa
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e9798218bd40ae36595d102983bfbf40591cdd6469830e9a8180fa1b9e34a9
+oid sha256:8a345a09bb686cac75cb2496fa891d6f1b56e65517e790e016904dc972ee23ae
 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": 0.639099657535553,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04678362573099415,
+  "best_metric": 0.4108954071998596,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0935672514619883,
   "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": 7.827,
       "eval_steps_per_second": 3.914,
       "step": 10
+    },
+    {
+      "epoch": 0.05146198830409357,
+      "grad_norm": 1.2848360538482666,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.7303,
+      "step": 11
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 1.070992350578308,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.1943,
+      "step": 12
+    },
+    {
+      "epoch": 0.0608187134502924,
+      "grad_norm": 1.0095195770263672,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8425,
+      "step": 13
+    },
+    {
+      "epoch": 0.06549707602339182,
+      "grad_norm": 1.2132809162139893,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.1708,
+      "step": 14
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 1.2868399620056152,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.1133,
+      "step": 15
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 0.47883766889572144,
+      "eval_runtime": 11.4883,
+      "eval_samples_per_second": 7.834,
+      "eval_steps_per_second": 3.917,
+      "step": 15
+    },
+    {
+      "epoch": 0.07485380116959064,
+      "grad_norm": 1.098825454711914,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5518,
+      "step": 16
+    },
+    {
+      "epoch": 0.07953216374269007,
+      "grad_norm": 1.039568305015564,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.0939,
+      "step": 17
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 1.1298397779464722,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.8204,
+      "step": 18
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.1970208883285522,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7516,
+      "step": 19
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 1.1430251598358154,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.8547,
+      "step": 20
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "eval_loss": 0.4108954071998596,
+      "eval_runtime": 11.4942,
+      "eval_samples_per_second": 7.83,
+      "eval_steps_per_second": 3.915,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1422827735482368.0,
+  "total_flos": 2845655470964736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null