Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db5b072848a04a122c9741899ef6f9056f7695f897cc6e338ac67d18129d739
+oid sha256:d785c4d7c7c4401c1772ced8741c1cdfe2f614fe08759812431cf0252ab2fed6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57f6f907504e00da76d6c8a5e04d66520b9dd063cd31e7fa696007d5ff399df
+oid sha256:8265234b05f1e093f88c1d2ad91677a0c3ba42e9e131f576bff0dc1a3d604042
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb93e5ec30efb3c16f50cc48bdb65f9823b6ee27849a70639290b4a4fe9f6c8
+oid sha256:ec1e1c34e914dcb990452f4527c43a77c235e6d3fc2bd15326ae8d10b98ba213
 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": 1.7411246299743652,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019056693663649357,
+  "best_metric": 1.7318332195281982,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.028585040495474036,
   "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": 9.759,
       "eval_steps_per_second": 2.44,
       "step": 20
+    },
+    {
+      "epoch": 0.020009528346831826,
+      "grad_norm": 0.34966373443603516,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8199,
+      "step": 21
+    },
+    {
+      "epoch": 0.022868032396379228,
+      "grad_norm": 0.39327874779701233,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.7785,
+      "step": 24
+    },
+    {
+      "epoch": 0.023820867079561697,
+      "eval_loss": 1.733565330505371,
+      "eval_runtime": 90.5193,
+      "eval_samples_per_second": 9.766,
+      "eval_steps_per_second": 2.441,
+      "step": 25
+    },
+    {
+      "epoch": 0.02572653644592663,
+      "grad_norm": 0.32263967394828796,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.7819,
+      "step": 27
+    },
+    {
+      "epoch": 0.028585040495474036,
+      "grad_norm": 0.2795114517211914,
+      "learning_rate": 0.0,
+      "loss": 1.7779,
+      "step": 30
+    },
+    {
+      "epoch": 0.028585040495474036,
+      "eval_loss": 1.7318332195281982,
+      "eval_runtime": 90.187,
+      "eval_samples_per_second": 9.802,
+      "eval_steps_per_second": 2.45,
+      "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": 2.967549134241792e+16,
+  "total_flos": 4.451323701362688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null