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:f58efa7c1a540fd84ed404062fda98c7ff7f477b90dbb1ccb8ba8687761ffe67
+oid sha256:b6d03735470a40e7f75450271d1bf753079c5ad3e9872409a7b8c4caac74516a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e0a0b89f4aa4fd270b6a0c966f1e065298b0816eec0e577128355b585a50bc
+oid sha256:5d6c8760e79bc6363e79d263d0b78c04b6ffc0eb9cbce9e993226677f957e8c2
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87755beef9691a991b9cc6ce8667bce1e76fa58e779f6ff8027b45a6b913d75d
+oid sha256:9d45c6d2cee5011ec309057497889313f5227ce123689e95cf0135b0ecd3fa23
 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": 1.0417708158493042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.040160642570281124,
+  "best_metric": 1.012827754020691,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.060240963855421686,
   "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": 2.847,
       "eval_steps_per_second": 1.424,
       "step": 20
+    },
+    {
+      "epoch": 0.04216867469879518,
+      "grad_norm": 1.9102998971939087,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 4.5056,
+      "step": 21
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 3.732218027114868,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 4.1749,
+      "step": 24
+    },
+    {
+      "epoch": 0.050200803212851405,
+      "eval_loss": 1.0177347660064697,
+      "eval_runtime": 73.6595,
+      "eval_samples_per_second": 2.851,
+      "eval_steps_per_second": 1.425,
+      "step": 25
+    },
+    {
+      "epoch": 0.05421686746987952,
+      "grad_norm": 2.0057742595672607,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 3.7961,
+      "step": 27
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 3.3194940090179443,
+      "learning_rate": 0.0,
+      "loss": 4.241,
+      "step": 30
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "eval_loss": 1.012827754020691,
+      "eval_runtime": 73.608,
+      "eval_samples_per_second": 2.853,
+      "eval_steps_per_second": 1.426,
+      "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": 2.57085482729472e+16,
+  "total_flos": 3.84041276669952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null