Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207a048a38876070aa53dbad27e69a8474c9620c8fd75fea6e4a106b7a399c33
+oid sha256:ac63a2411bc381033b3a691f0d3b3790721fdde162fc5785a0d355651b92ef7d
 size 249439848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41eff9f2d39685ef6ea621cc0c4b5dcbe2da2df747bd1ef1f85bed9f1301a0aa
+oid sha256:ef85e0b49544ba9e6f781a010214932f899e7da48dac80a2cd6cdf1a7a33a8bb
 size 499202402

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49984bb1acbeaf71cf255dc3c268cdc658d49a0e97d60a0ed1515654fc6e54ac
+oid sha256:ce753e99cc64abefd05744d3440dca147e5dda91b0d870b547007fd98836720d
 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": 1.8435406684875488,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004231684739486909,
+  "best_metric": 1.800808310508728,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.006347527109230362,
   "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": 4.022,
       "eval_steps_per_second": 2.011,
       "step": 20
+    },
+    {
+      "epoch": 0.004443268976461253,
+      "grad_norm": 0.5833864808082581,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8511,
+      "step": 21
+    },
+    {
+      "epoch": 0.0050780216873842895,
+      "grad_norm": 0.6056792736053467,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9373,
+      "step": 24
+    },
+    {
+      "epoch": 0.005289605924358635,
+      "eval_loss": 1.808415174484253,
+      "eval_runtime": 494.8926,
+      "eval_samples_per_second": 4.021,
+      "eval_steps_per_second": 2.011,
+      "step": 25
+    },
+    {
+      "epoch": 0.005712774398307326,
+      "grad_norm": 0.7835950255393982,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8092,
+      "step": 27
+    },
+    {
+      "epoch": 0.006347527109230362,
+      "grad_norm": 0.5311419367790222,
+      "learning_rate": 0.0,
+      "loss": 1.8405,
+      "step": 30
+    },
+    {
+      "epoch": 0.006347527109230362,
+      "eval_loss": 1.800808310508728,
+      "eval_runtime": 494.8249,
+      "eval_samples_per_second": 4.022,
+      "eval_steps_per_second": 2.011,
+      "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": 2.380128168443904e+16,
+  "total_flos": 3.63630692401152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null