Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0d1479f77d86fe6cebadc3d3fd30a998e4322a598b315657d0e268c6825e45
+oid sha256:57be2985a79988e1c43c7343385a695f1e09c0b0d3efa307e09e14dfc6eda1f5
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d97a8dffa55d0ea23c54b77a8753e8a7a991dc536e9c60836bf4b27203be07
+oid sha256:7a7cedf8f3f8737043bb42853fa18729fe005cedc2132e1e83f99da5187d7d7e
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b869bc600b7edcf2d1cd3232d0914ff69fbcd4f635d56d0a5a02fa57ed2f8add
+oid sha256:00120a95ebacce365f5d2a9e41d3513c7a534ca2652b5946ac0daac07544fc0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9712910652160645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005203252032520325,
+  "best_metric": 0.8783676028251648,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007804878048780488,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.151,
       "eval_steps_per_second": 2.077,
       "step": 20
+    },
+    {
+      "epoch": 0.005463414634146341,
+      "grad_norm": 0.5658571124076843,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.7111,
+      "step": 21
+    },
+    {
+      "epoch": 0.006243902439024391,
+      "grad_norm": 0.6791040301322937,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.8109,
+      "step": 24
+    },
+    {
+      "epoch": 0.0065040650406504065,
+      "eval_loss": 0.8912465572357178,
+      "eval_runtime": 389.6568,
+      "eval_samples_per_second": 4.155,
+      "eval_steps_per_second": 2.079,
+      "step": 25
+    },
+    {
+      "epoch": 0.007024390243902439,
+      "grad_norm": 0.6968145966529846,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.6507,
+      "step": 27
+    },
+    {
+      "epoch": 0.007804878048780488,
+      "grad_norm": 0.5855252146720886,
+      "learning_rate": 0.0,
+      "loss": 0.7571,
+      "step": 30
+    },
+    {
+      "epoch": 0.007804878048780488,
+      "eval_loss": 0.8783676028251648,
+      "eval_runtime": 389.5073,
+      "eval_samples_per_second": 4.157,
+      "eval_steps_per_second": 2.08,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.398077386653696e+16,
+  "total_flos": 2.097116079980544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null