Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67566a2e698128d578a6d379dfdbcf9f55ef745aaa392d32ae476522321bddb2
+oid sha256:5a3a86b4c889ea262753f7eb40998eca2ece239c88bf803ae3251a4c564e771e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c221acfbf0c436aeaed3520283fc568fe9ceb782ce8d26eaafa6795c8f40d272
+oid sha256:9d8d88e577a885c5fd429efcb5a71a09956c7bd5248e1e12c562719ccdd24f30
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86229f6975fa4e5972602ba6cd5b5d2de9c4fb42728492fea685c848f2780344
+oid sha256:b41ebb28fd31b00de937ba31a6b215df7b28381cc173f98348689e6431ef27cb
 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": 0.49102675914764404,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005825935608846683,
+  "best_metric": 0.4814574122428894,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0007282419511058354,
   "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": 5.866,
       "eval_steps_per_second": 2.933,
       "step": 20
+    },
+    {
+      "epoch": 0.0006117232389289017,
+      "grad_norm": 1.1783339977264404,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8808,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006408529169731351,
+      "grad_norm": 1.586045742034912,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.7825,
+      "step": 22
+    },
+    {
+      "epoch": 0.0006699825950173686,
+      "grad_norm": 2.2189619541168213,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.8943,
+      "step": 23
+    },
+    {
+      "epoch": 0.000699112273061602,
+      "grad_norm": 1.2450097799301147,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5824,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007282419511058354,
+      "grad_norm": 1.3376847505569458,
+      "learning_rate": 0.0,
+      "loss": 0.6038,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007282419511058354,
+      "eval_loss": 0.4814574122428894,
+      "eval_runtime": 2432.3948,
+      "eval_samples_per_second": 5.943,
+      "eval_steps_per_second": 2.972,
+      "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": 5040062576197632.0,
+  "total_flos": 6380996656103424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null