Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9194b451523bb10383c464149cb790a70cbc34d0fdd522379136fcfb354c17
+oid sha256:f4310db881d19f6d5cc755cab87e8507bfd607571ab24b20dd864bc94b884b87
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8990914358a367b711dece82c24366af052b06a6fa9a68733dd0b5f03bcdb705
+oid sha256:f3ba007c6af5563def96a51799914e83f3804e110edc2dc3e3e9cdc5166959bd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc62e9646c76e2855b42dbe6fcaa7bc77293c8d322828d69d4c33b3c72352b26
+oid sha256:110bb0a07b65ef0ba3f7307fd47628fd55a214320bb7f200381813ecfd336e89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5173833966255188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07766990291262135,
+  "best_metric": 0.49480313062667847,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11650485436893204,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.753,
       "eval_steps_per_second": 1.458,
       "step": 20
+    },
+    {
+      "epoch": 0.08155339805825243,
+      "grad_norm": 0.9959689378738403,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8811,
+      "step": 21
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.9961031675338745,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.0414,
+      "step": 24
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "eval_loss": 0.4978864789009094,
+      "eval_runtime": 37.7461,
+      "eval_samples_per_second": 5.749,
+      "eval_steps_per_second": 1.457,
+      "step": 25
+    },
+    {
+      "epoch": 0.10485436893203884,
+      "grad_norm": 1.0980758666992188,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.0524,
+      "step": 27
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 1.2487680912017822,
+      "learning_rate": 0.0,
+      "loss": 1.8476,
+      "step": 30
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "eval_loss": 0.49480313062667847,
+      "eval_runtime": 37.7726,
+      "eval_samples_per_second": 5.745,
+      "eval_steps_per_second": 1.456,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.53913198493696e+16,
+  "total_flos": 3.80869797740544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null