Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c3c048052b26505bcbe14caa7a7564e2616aca80017766f6d9dcb5c72b0b93
+oid sha256:353845f72de90e031328485431ee0305b00c344c0639e84d481d906e5ca18f8d
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1ae9987d13850c59b919b9c6ce075f51d97eef2e00178c06cabeed9535bdeb
+oid sha256:e79fbda6aca98dab1da050e1ab89998044244132cf6eb54108a09b53f18c2000
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e97bf1fc0df7b7494795657cf00ff10f81fe5ecaafce75d405590f0e5957162
+oid sha256:593744e58d741a56890b8eb4fe62cee59c19a69f9bbfa0ddc691914a3701740e
 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": 0.2781434953212738,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016711928138709004,
+  "best_metric": 0.26856350898742676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.020889910173386254,
   "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": 11.704,
       "eval_steps_per_second": 5.852,
       "step": 20
+    },
+    {
+      "epoch": 0.017547524545644455,
+      "grad_norm": 12.404900550842285,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9451,
+      "step": 21
+    },
+    {
+      "epoch": 0.018383120952579903,
+      "grad_norm": 39.48596954345703,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9458,
+      "step": 22
+    },
+    {
+      "epoch": 0.019218717359515355,
+      "grad_norm": 13.155956268310547,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.5234,
+      "step": 23
+    },
+    {
+      "epoch": 0.020054313766450803,
+      "grad_norm": 9.780112266540527,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.1729,
+      "step": 24
+    },
+    {
+      "epoch": 0.020889910173386254,
+      "grad_norm": 4.1454315185546875,
+      "learning_rate": 0.0,
+      "loss": 0.8265,
+      "step": 25
+    },
+    {
+      "epoch": 0.020889910173386254,
+      "eval_loss": 0.26856350898742676,
+      "eval_runtime": 43.1839,
+      "eval_samples_per_second": 11.671,
+      "eval_steps_per_second": 5.836,
+      "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": 1322222380646400.0,
+  "total_flos": 1648697042534400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null