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:d2755206480b20ccbf9621d4fdf1cf320addd280a17bd0a36797dd85a747316b
+oid sha256:43b305ea4cd030409b1233aea75237b015379c5f75cced4c3a63ab4f7e0b76e7
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1f1e3038ce708da4bfa15cd54ea8a54f2fad7acd70490e91384a9a25ec7777
+oid sha256:0e8c06bb0e6c5c0db6ec28a95236e942f90d87f26fc4355aaff4f3695e93341e
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d38c3e9dc7f2884a7a8241183aa548d7962ae3933facbb8e2b3a2861b7f1d0
+oid sha256:d29443ed9c7ce389702d78569e9f0ca9c50fd16be83842525d94727cfc623778
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.543307304382324,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 2.537973165512085,
+  "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": 28.627,
       "eval_steps_per_second": 14.313,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 2.0592212677001953,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.1342,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 4.000472545623779,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.318,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 2.5389299392700195,
+      "eval_runtime": 17.125,
+      "eval_samples_per_second": 28.613,
+      "eval_steps_per_second": 14.307,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 3.650594472885132,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.5925,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 2.5528719425201416,
+      "learning_rate": 0.0,
+      "loss": 10.5036,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 2.537973165512085,
+      "eval_runtime": 17.1349,
+      "eval_samples_per_second": 28.597,
+      "eval_steps_per_second": 14.298,
+      "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": 1893182157619200.0,
+  "total_flos": 2839773236428800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null