Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f132aa8374bf7795df84ded313edb6b4ad90bfe81ef96234c467b94c0e4420b2
+oid sha256:66cd672a43c71c591276ccd926c7e83289ff35c08a5099c8c1390efb58fca401
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de26bbcb96bf7379566a6120b4aaea9c6c512ccebf899e263ccf1116d7c06aa
+oid sha256:4cb4209066f478aef6866eb7fb497d9941cd8afeb8c63e717dbd4802c3614024
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d3f36f7404688de11b22d84f32e4c30f7d364fb1e74fd97db5167b06e22e57
+oid sha256:cde923dd25d49a18608ad2195296261a163ab1cd44e1c0838d6b8c98ee7e817b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2fd30f3b354b607634e22c75b4493073ee958ea49022a57afc742673e42d76
+oid sha256:cb28bb8cf2be6d829bc7d8d43fa28bbbd84fb8993a66e3e97cef2580889f0f5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3068158626556396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.018412815319462345,
+  "best_metric": 1.1203691959381104,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.03682563063892469,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 10.926,
       "eval_steps_per_second": 2.732,
       "step": 50
+    },
+    {
+      "epoch": 0.022095378383354815,
+      "grad_norm": 1.3547375202178955,
+      "learning_rate": 0.00020974422527728155,
+      "loss": 2.5193,
+      "step": 60
+    },
+    {
+      "epoch": 0.025777941447247283,
+      "grad_norm": 1.4830182790756226,
+      "learning_rate": 0.0002089781472178649,
+      "loss": 2.4821,
+      "step": 70
+    },
+    {
+      "epoch": 0.029460504511139754,
+      "grad_norm": 1.312664270401001,
+      "learning_rate": 0.0002077054980770496,
+      "loss": 2.3063,
+      "step": 80
+    },
+    {
+      "epoch": 0.03314306757503222,
+      "grad_norm": 1.2727351188659668,
+      "learning_rate": 0.00020593247807352348,
+      "loss": 2.3387,
+      "step": 90
+    },
+    {
+      "epoch": 0.03682563063892469,
+      "grad_norm": 1.5231223106384277,
+      "learning_rate": 0.00020366772518252038,
+      "loss": 2.0461,
+      "step": 100
+    },
+    {
+      "epoch": 0.03682563063892469,
+      "eval_loss": 1.1203691959381104,
+      "eval_runtime": 104.8463,
+      "eval_samples_per_second": 10.911,
+      "eval_steps_per_second": 2.728,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5300701404004352e+16,
+  "total_flos": 3.026877886444339e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null