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:b18b92685c7a6456b3fea5967d09af30d64df626f2356a0c55575a272ab6d41b
+oid sha256:b07cb6f91e8eae90d237fb8f89f653819b51751b9f49ebe40bdc4ad48678d04b
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30e16a9469e75bd54796b458ebaf072e73452a8a91d500a3a32df02c266314b
+oid sha256:318c25e94b0ed2ef7dd6b786a31fe4138b58f5ba9d1d84e234b3ef6d1b917952
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d58d4ef710bb5bbbe3c8785ba2e5e671a4d3d656c4bf6bfe68b9e566becd2f4
+oid sha256:c04efebaa37edda3158869bd47936d07b011c8b4b72479d68c3bd1f4d044e66a
 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": 0.9107561111450195,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03547671840354767,
+  "best_metric": 0.8934311866760254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.04434589800443459,
   "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": 6.647,
       "eval_steps_per_second": 3.323,
       "step": 20
+    },
+    {
+      "epoch": 0.03725055432372506,
+      "grad_norm": 1.6538779735565186,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8503,
+      "step": 21
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 1.8892109394073486,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9907,
+      "step": 22
+    },
+    {
+      "epoch": 0.040798226164079826,
+      "grad_norm": 2.003721237182617,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7393,
+      "step": 23
+    },
+    {
+      "epoch": 0.042572062084257206,
+      "grad_norm": 1.7759606838226318,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0311,
+      "step": 24
+    },
+    {
+      "epoch": 0.04434589800443459,
+      "grad_norm": 1.840668797492981,
+      "learning_rate": 0.0,
+      "loss": 0.7071,
+      "step": 25
+    },
+    {
+      "epoch": 0.04434589800443459,
+      "eval_loss": 0.8934311866760254,
+      "eval_runtime": 32.808,
+      "eval_samples_per_second": 7.254,
+      "eval_steps_per_second": 3.627,
+      "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": 481091030876160.0,
+  "total_flos": 601363788595200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null