Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c019147925338f3a1871f8e9e207a46df6659cf7ba77aa4a1da77f7f4e1309
+oid sha256:1266fa533234d40ce11486e350b21e1a77bf2b58c54f55250144e1c2d6ca3d6d
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e7efd23adbb3bddbfbb46526c2752b2611736e55e2de0f5193b094a91723f
+oid sha256:242082444c92f13b0b0164288fd2287c6b4dc29f4af0ae0576515a69d647f213
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f4d181893c9bc040ba0fad0dbbee9a3f2de880b67f739edfd1460a79f556c2
+oid sha256:a0401383a513d57a10b63649026e14d1c47bd9d80e17cfd19e806d3c044e29f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2455435991287231,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.025466893039049237,
+  "epoch": 0.03395585738539898,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 5.228,
       "eval_steps_per_second": 1.307,
       "step": 150
+    },
+    {
+      "epoch": 0.027164685908319185,
+      "grad_norm": 0.8496482968330383,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 1.1761,
+      "step": 160
+    },
+    {
+      "epoch": 0.028862478777589132,
+      "grad_norm": 0.7892032861709595,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 1.2281,
+      "step": 170
+    },
+    {
+      "epoch": 0.030560271646859084,
+      "grad_norm": 0.8588133454322815,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 1.205,
+      "step": 180
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 0.9884034991264343,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 1.2602,
+      "step": 190
+    },
+    {
+      "epoch": 0.03395585738539898,
+      "grad_norm": 1.295212745666504,
+      "learning_rate": 0.0001545,
+      "loss": 1.2808,
+      "step": 200
+    },
+    {
+      "epoch": 0.03395585738539898,
+      "eval_loss": 1.3785539865493774,
+      "eval_runtime": 236.0337,
+      "eval_samples_per_second": 5.253,
+      "eval_steps_per_second": 1.313,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.844195528520499e+16,
+  "total_flos": 6.387406029088358e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null