Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67349a662c4807251911040be49be280ef7f429b79689f7fda56c9c34fba0cb7
+oid sha256:0bf45d1879addfef1c3cf2199757c441941206dd68f70e6ddab31b608f05a4c8
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335a4056bc11095232d4898c51a70d8b859b9d239ea1ba9b58e4f16f4b0a0554
+oid sha256:3eefc1c9b2c0de5b00cba06245aeb5744b3a3129e4389d8b563587fe58d0037f
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0cc465a75681ba50afdecee660968bcd8503a20558be1104c59586aa9b9c2e7
+oid sha256:d1af2d1ad71d0a525efd297d63ece1800652033d73e1aabfc1096f4a3269303a
 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": 11.928520202636719,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014449301015063397,
+  "best_metric": 11.9270601272583,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0021673951522595096,
   "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": 50.564,
       "eval_steps_per_second": 25.286,
       "step": 20
+    },
+    {
+      "epoch": 0.0015171766065816567,
+      "grad_norm": 0.12181365489959717,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9291,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017339161218076075,
+      "grad_norm": 0.18912532925605774,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9264,
+      "step": 24
+    },
+    {
+      "epoch": 0.0018061626268829245,
+      "eval_loss": 11.927303314208984,
+      "eval_runtime": 115.1498,
+      "eval_samples_per_second": 50.621,
+      "eval_steps_per_second": 25.315,
+      "step": 25
+    },
+    {
+      "epoch": 0.0019506556370335584,
+      "grad_norm": 0.1745712161064148,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9232,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021673951522595096,
+      "grad_norm": 0.17553108930587769,
+      "learning_rate": 0.0,
+      "loss": 11.9241,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021673951522595096,
+      "eval_loss": 11.9270601272583,
+      "eval_runtime": 115.0491,
+      "eval_samples_per_second": 50.665,
+      "eval_steps_per_second": 25.337,
+      "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": 5078054338560.0,
+  "total_flos": 7617081507840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null