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:fe39c2c5b91956cc00896fad7a991d736d889684c098240bb4813e7b25d5b142
+oid sha256:580d7b109cdad78279cb7aaa127f83fa660289a7e21046cbdf9d3ceb0b19a07a
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f65b53fca0a1eeafb76bb41c7f4afecf9363e8563acdc3a8de218eec7266ad
+oid sha256:9241d95b4b5f3892a587b548c89faf2278cd45aaaca86e15fce4b15e66fd967d
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef84085d70e061641ac0decc1ac0ac0e88548f873f7a104fb45e0627fe2e7e5
+oid sha256:c4eafea06aa6a46dd54e4d8c532c5647de04350057e36ea11cef2ba10c4e7dd6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.6557891368865967,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009936653831822134,
+  "best_metric": 3.5841777324676514,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.014904980747733202,
   "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": 10.962,
       "eval_steps_per_second": 5.481,
       "step": 20
+    },
+    {
+      "epoch": 0.01043348652341324,
+      "grad_norm": 11.381671905517578,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 14.3006,
+      "step": 21
+    },
+    {
+      "epoch": 0.011923984598186561,
+      "grad_norm": 12.137283325195312,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 14.4807,
+      "step": 24
+    },
+    {
+      "epoch": 0.012420817289777668,
+      "eval_loss": 3.590764284133911,
+      "eval_runtime": 77.337,
+      "eval_samples_per_second": 10.965,
+      "eval_steps_per_second": 5.482,
+      "step": 25
+    },
+    {
+      "epoch": 0.01341448267295988,
+      "grad_norm": 12.388276100158691,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 14.1514,
+      "step": 27
+    },
+    {
+      "epoch": 0.014904980747733202,
+      "grad_norm": 13.344575881958008,
+      "learning_rate": 0.0,
+      "loss": 15.1692,
+      "step": 30
+    },
+    {
+      "epoch": 0.014904980747733202,
+      "eval_loss": 3.5841777324676514,
+      "eval_runtime": 77.5415,
+      "eval_samples_per_second": 10.936,
+      "eval_steps_per_second": 5.468,
+      "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": 606741976842240.0,
+  "total_flos": 910112965263360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null