Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2718d6a10fd95fd7b30d8862a5bb74ff4891cf882c125a95eadaa99beefbbaf4
+oid sha256:4d7c7fcd544052ca81e15fb027b86dda4e9aa454ce9f20e55d5642fa52824b77
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2b455b14d850bb613bdc95b567c88cd2f5f2b558aba6c22e58191f12dd3269
+oid sha256:22962fcc4931f3a7c98097437b53c3da1f2d2a7df24bd805cb07ba4c2b3e337e
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
+oid sha256:116d3c88be1e3818f36b37bfa7af6291c955e2a5a7ecf577ddc54dd045f02ed6
 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": 1.362160563468933,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04230565838180857,
+  "best_metric": 1.3393476009368896,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06345848757271286,
   "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": 33.068,
       "eval_steps_per_second": 16.617,
       "step": 20
+    },
+    {
+      "epoch": 0.044420941300899,
+      "grad_norm": 0.9378082752227783,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4346,
+      "step": 21
+    },
+    {
+      "epoch": 0.05076679005817028,
+      "grad_norm": 0.7110140919685364,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.3119,
+      "step": 24
+    },
+    {
+      "epoch": 0.05288207297726071,
+      "eval_loss": 1.342877984046936,
+      "eval_runtime": 6.1249,
+      "eval_samples_per_second": 32.49,
+      "eval_steps_per_second": 16.327,
+      "step": 25
+    },
+    {
+      "epoch": 0.05711263881544157,
+      "grad_norm": 0.762420654296875,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2939,
+      "step": 27
+    },
+    {
+      "epoch": 0.06345848757271286,
+      "grad_norm": 0.6510502696037292,
+      "learning_rate": 0.0,
+      "loss": 1.3413,
+      "step": 30
+    },
+    {
+      "epoch": 0.06345848757271286,
+      "eval_loss": 1.3393476009368896,
+      "eval_runtime": 6.2084,
+      "eval_samples_per_second": 32.053,
+      "eval_steps_per_second": 16.107,
+      "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": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null