Training in progress, step 319, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ced97375fc9ec48bb2a674469aef73a935b90722d6ed12e49d62897ab529b29
+oid sha256:2a4706895054649b391b5adf6b169cffc2d5842801826ccd096f743cfcb25a20
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67411bfab1411db605032b983a24fe1a2de14a1da4ab7addbd0fdf180c7eb30
+oid sha256:67c645173955f9f7e6c16c830b034dd0c65c91947fd04957ab4ead8fce86a35a
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f494ed238afd414043ff28eb710732ee6d09f6bd823f8c85a43c5f7febcdf3c3
+oid sha256:efca099a88de8e2d59bdb7696727755d19e1e427f95b0fce22f315d8b9a57480
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80c8dfaaac753ac73b49d0409a01e1bdc201b2ff6a123896b6b7482598e4eae
+oid sha256:048464f2b2c1c0c2f60ed7aabb6fe8e30490a5ea288e786e7ee68cb952870ef2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1487760543823242,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.9419152276295133,
+  "epoch": 1.0015698587127158,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 319,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,13 @@
       "eval_samples_per_second": 39.675,
       "eval_steps_per_second": 10.067,
       "step": 300
+    },
+    {
+      "epoch": 0.9733124018838305,
+      "grad_norm": 0.6472459435462952,
+      "learning_rate": 5.905193216585661e-07,
+      "loss": 1.201,
+      "step": 310
     }
   ],
   "logging_steps": 10,
@@ -296,12 +303,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.24089003933696e+16,
+  "total_flos": 1.3179286292791296e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null