Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0235cfa5df35c7e0a715943b624a7fe3174cae8eb9185511a8666edefce9072a
+oid sha256:7722ff1c94dd2f10e3d5f3c0dc27508bfcb0496dac4f97002cae427b4cc5a415
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed3e5984316a5cdea499d30d0da39b3eb4bf8c3d91acded96de262eab930a97
+oid sha256:0fdd163223da3ef0d8d7395d3ba840b80907800127aa027d7d69a0b79f307491
 size 162933844

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e431db93e4826b29c1a64bf43296f45e6ad65ec8a879adf24ee1960cf0ea2bea
+oid sha256:76c249ddc96a5aac8d2f2f128f1d45cd19f0d58a9b0efb6d6b7d054c0bc52e54
 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": 1.4818726778030396,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.25341659878722056,
+  "epoch": 0.2896189700425378,
   "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": 15.157,
       "eval_steps_per_second": 7.579,
       "step": 350
+    },
+    {
+      "epoch": 0.260657073038284,
+      "grad_norm": 0.9269088506698608,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5033,
+      "step": 360
+    },
+    {
+      "epoch": 0.2896189700425378,
+      "grad_norm": 1.8110876083374023,
+      "learning_rate": 0.0,
+      "loss": 1.4524,
+      "step": 400
+    },
+    {
+      "epoch": 0.2896189700425378,
+      "eval_loss": 1.4847944974899292,
+      "eval_runtime": 76.6253,
+      "eval_samples_per_second": 15.191,
+      "eval_steps_per_second": 7.595,
+      "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": 1.242763622350848e+17,
+  "total_flos": 1.419410625527808e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null