Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0dd0aec9ab4aa86523a5e5b6f12d34b888fd67eb2662f1d5ca4b03b554f3e3
+oid sha256:3d5e2b911cfe1d1b0d4aebaf27be27e11d91fcdd68c5b73dcea55abba11890af
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6248c87d832c72c24b75298445123514c73181249158e4ccf4e811644724eb
+oid sha256:232b4dbc9c8e67e1654845f1e26aa0ec30399f98d1c5e4ad60ee9071b336eed0
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9efb22ba3f290c82f0a1fb62fd1857ef198195a3c42701c1156d5ef2bad165
+oid sha256:63fd6d5aed6c2215216221f703e2ad1a8bf83f72765db48a8fdf2404047d83dd
 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": 1.2121158838272095,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.4831751509922347,
+  "best_metric": 1.2065986394882202,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.5522001725625539,
   "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": 32.894,
       "eval_steps_per_second": 16.447,
       "step": 350
+    },
+    {
+      "epoch": 0.4969801553062985,
+      "grad_norm": 5.483723163604736,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 9.9872,
+      "step": 360
+    },
+    {
+      "epoch": 0.5522001725625539,
+      "grad_norm": 14.02880573272705,
+      "learning_rate": 0.0,
+      "loss": 10.3119,
+      "step": 400
+    },
+    {
+      "epoch": 0.5522001725625539,
+      "eval_loss": 1.2065986394882202,
+      "eval_runtime": 18.6134,
+      "eval_samples_per_second": 32.772,
+      "eval_steps_per_second": 16.386,
+      "step": 400
     }
   ],
   "logging_steps": 40,
@@ -150,12 +172,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.432509716253901e+16,
+  "total_flos": 2.7834763721048064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null