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:b4a3eb33b6c545a2c8ee8e31124d70dd2a85b5cade585d995a98f6c9543ac0d3
+oid sha256:b6f2ae1b4d6e7c20b896636adb0d796edfb5363220de16add3e866ec34bbee66
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d119db7fe68c2111e323bdd9727c03997723417484d826efb14af272caf3be
+oid sha256:d0ac9417a4d98e6df8e6bb1e47b4270bf21b4d928c5e90f503069f9dbe126897
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180b125b0a44cbead9ec7f5c2de948b4228fa28bd6237b21a55ce349eba3617b
+oid sha256:872aa889ce39c7463de2cf24340fe24dabdcd01071e057a53936c463613623a5
 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": 2.018906354904175,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 2.0030875205993652,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 95.387,
       "eval_steps_per_second": 47.693,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 3.4456512928009033,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.9461,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 3.77186918258667,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.3606,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 2.0057647228240967,
+      "eval_runtime": 5.2572,
+      "eval_samples_per_second": 93.205,
+      "eval_steps_per_second": 46.602,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 3.1643145084381104,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.425,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 3.8465747833251953,
+      "learning_rate": 0.0,
+      "loss": 8.1357,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 2.0030875205993652,
+      "eval_runtime": 5.1722,
+      "eval_samples_per_second": 94.738,
+      "eval_steps_per_second": 47.369,
+      "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": 92689341087744.0,
+  "total_flos": 137956228595712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null