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:f19914fcc03a09be5bb0aa60a215a69a61210290787d1afb11948b062027f8bb
+oid sha256:64bd4392a710f5f930f33044488ddfaa2f9920b8107aa99dfc9973744a41e618
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e70b739757098f9c0b2b7f02be609f9870d79e4d9512b614475bd0a419d48d
+oid sha256:45dc4589d8e01c685e0c1195589af12a4649dbdb9dbfda7f99a026d20d8f7d85
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10519610009c540670d3642510b46a0f6a5f528db3cc7a9cdbb98825023d8a4
+oid sha256:90f2543b5d365b5b767b58d2e68fc7e0c2cae1ff5a01ec9b26a8a8d43c476af6
 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": 0.7788602709770203,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0035234529839242457,
+  "best_metric": 0.7341243028640747,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005285179475886369,
   "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": 3.061,
       "eval_steps_per_second": 1.531,
       "step": 20
+    },
+    {
+      "epoch": 0.003699625633120458,
+      "grad_norm": 1.5902005434036255,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.9492,
+      "step": 21
+    },
+    {
+      "epoch": 0.004228143580709095,
+      "grad_norm": 1.705464243888855,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 3.3754,
+      "step": 24
+    },
+    {
+      "epoch": 0.004404316229905308,
+      "eval_loss": 0.7406635880470276,
+      "eval_runtime": 780.7439,
+      "eval_samples_per_second": 3.062,
+      "eval_steps_per_second": 1.532,
+      "step": 25
+    },
+    {
+      "epoch": 0.004756661528297732,
+      "grad_norm": 1.763797402381897,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 3.1869,
+      "step": 27
+    },
+    {
+      "epoch": 0.005285179475886369,
+      "grad_norm": 1.737493872642517,
+      "learning_rate": 0.0,
+      "loss": 3.0219,
+      "step": 30
+    },
+    {
+      "epoch": 0.005285179475886369,
+      "eval_loss": 0.7341243028640747,
+      "eval_runtime": 779.2463,
+      "eval_samples_per_second": 3.068,
+      "eval_steps_per_second": 1.535,
+      "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": 2.28688285138944e+16,
+  "total_flos": 3.43032427708416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null