Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948ce3df8de5f88bedf7a0d9c134994839cd943fc6c974c4b0a7866cbcc61a5d
+oid sha256:eb0d654ae1994400f8086b840dfcc8e484eb3002e89d6a3418c3c8f0407a9c09
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf48eec840e36521100fdb0611fe1e64bde2bbc3a990f25ee67d320b312b849
+oid sha256:8c167292d730170c6990b552caef9aa07241fce814a6dbd869bb5ee77a20ed9b
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb471a00377648163edcebbc32112eb1f202af215f062520c97ce9d8c504ad0
+oid sha256:1188d1b65b79c9433a115016b6160888d1d7b5d49732c2ea8159722fa4c81776
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4817118644714355,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 1.4780610799789429,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01063264221158958,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 16.169,
       "eval_steps_per_second": 8.085,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 18.555313110351562,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.0527,
+      "step": 21
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 19.77273941040039,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.6609,
+      "step": 22
+    },
+    {
+      "epoch": 0.009782030834662414,
+      "grad_norm": 19.876432418823242,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.8107,
+      "step": 23
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 16.81047821044922,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.8589,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 15.21854019165039,
+      "learning_rate": 0.0,
+      "loss": 5.6738,
+      "step": 25
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 1.4780610799789429,
+      "eval_runtime": 60.261,
+      "eval_samples_per_second": 16.429,
+      "eval_steps_per_second": 8.214,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 320209265098752.0,
+  "total_flos": 399164974301184.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null