Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405020d27388c9c1dd521b9aff6af42bfcfcb5963233762a035aa9d9a6432e85
+oid sha256:df524bcb3468d44b6d6e87cce65e8fc3699a2ed97a8c21aae96c0602c600628d
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b458eaf223e442a676c30eac222e1b740fc16e5177a5c47f986d7d040daa7717
+oid sha256:1dd199087f0291a07907189b5046e645a3ee8a3e04c1fdd1ae2f8ebcb9f87493
 size 36136276

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f56a010894de921f8b860be3277cb23bfe1ec64dbc824fc8257243a340a311b
+oid sha256:ee454fa67f436c945eec4d1b9fb12f953170d3e74a02865c88e86636ea98e005
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
+oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.865569591522217,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.34756703078450846,
+  "epoch": 0.3972194637537239,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,28 @@
       "eval_samples_per_second": 34.026,
       "eval_steps_per_second": 17.013,
       "step": 350
+    },
+    {
+      "epoch": 0.35749751737835156,
+      "grad_norm": 0.6154284477233887,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.883,
+      "step": 360
+    },
+    {
+      "epoch": 0.3972194637537239,
+      "grad_norm": 2.848008632659912,
+      "learning_rate": 0.0,
+      "loss": 2.9091,
+      "step": 400
+    },
+    {
+      "epoch": 0.3972194637537239,
+      "eval_loss": 2.87178373336792,
+      "eval_runtime": 24.9789,
+      "eval_samples_per_second": 33.949,
+      "eval_steps_per_second": 16.974,
+      "step": 400
     }
   ],
   "logging_steps": 40,
@@ -141,7 +163,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -150,12 +172,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7064151519657984.0,
+  "total_flos": 8083862483632128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null