Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90f29add083e70435ccfcdb9324896e0d661ce675afea96492133329ed27409
+oid sha256:d1da9f0e1748b79b0e2ea094ecc52c3475afb89979699261200296acbbf4c5b0
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f29963d218f536f17aa1aea587ddabfad09e50c404853c0317e3fff1876cb9
+oid sha256:adfa8bf05dc665b19a9d27cdfc7aeb1f8e04a1e815cd33dacbdaff1b978c4950
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be935466c588a753f80b4b6fd059919104354d0102b7a2dca4181c83f51ce99e
+oid sha256:7211b19267643e4a4695239646f9fc645d8110b1d66e4a8494a1b44822fb5bcd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9d37d8ac9041b1174177f2abdfd03da05c909db05db7e02be2b5adefcdb593
+oid sha256:edaf981d1dfb35fd3b5ff50f9b58cbbedb093fe8427ac222964e342dc83dc071
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7082891464233398,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.08526360665056132,
+  "best_metric": 1.625133752822876,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.0994742077589882,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 9.008,
       "eval_steps_per_second": 2.261,
       "step": 300
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 1.6801893711090088,
+      "learning_rate": 7.808204475323423e-05,
+      "loss": 1.097,
+      "step": 310
+    },
+    {
+      "epoch": 0.09094784709393207,
+      "grad_norm": 1.468928575515747,
+      "learning_rate": 7.117124957938042e-05,
+      "loss": 1.6221,
+      "step": 320
+    },
+    {
+      "epoch": 0.09378996731561745,
+      "grad_norm": 2.429023027420044,
+      "learning_rate": 6.441552087816105e-05,
+      "loss": 1.7242,
+      "step": 330
+    },
+    {
+      "epoch": 0.09663208753730283,
+      "grad_norm": 2.3508596420288086,
+      "learning_rate": 5.784777188072502e-05,
+      "loss": 1.5539,
+      "step": 340
+    },
+    {
+      "epoch": 0.0994742077589882,
+      "grad_norm": 1.75046968460083,
+      "learning_rate": 5.150000000000002e-05,
+      "loss": 1.8748,
+      "step": 350
+    },
+    {
+      "epoch": 0.0994742077589882,
+      "eval_loss": 1.625133752822876,
+      "eval_runtime": 82.1926,
+      "eval_samples_per_second": 9.015,
+      "eval_steps_per_second": 2.263,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -287,7 +330,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.215556344165171e+16,
+  "total_flos": 6.106822301712384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null