Training in progress, step 196, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c634efe3d1804e3b94e93fb78dca72ed6d5adcfe6297c43904c8344c2e6e902
+oid sha256:28da115c0b8bb2fb5445ea5db891e5db489ccea02711510fdb8e081770446046
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15067758cd3886f04b9f1b91099dac6112e70b680f2f370478fd13429d2457fc
+oid sha256:6444f097ab3c1d05335c0a0726cb0cdcc676b78771d2a6d9a2ddaa136973f170
 size 40131268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58628ee66213497cf18b06c72edfd1038519f93f56f392aeb3f3e972a9a53a95
+oid sha256:c0b1e86b9929c8ff8d0a6759088c34f4c1cc5c1c4ddc923d3cf9a24b37857fff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3438010991b5747ebbb97eb340c57138172fd649c5fe8532f1b3d4802c9ffa30
+oid sha256:e22ca0a50bab80d00c8b8910bffb983a348f8762b7cf025e6f8e64a05a938289
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4868355989456177,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.7682458386683739,
+  "epoch": 1.0038412291933418,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 196,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,34 @@
       "eval_samples_per_second": 51.988,
       "eval_steps_per_second": 13.116,
       "step": 150
+    },
+    {
+      "epoch": 0.8194622279129321,
+      "grad_norm": 2.048182487487793,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 0.2675,
+      "step": 160
+    },
+    {
+      "epoch": 0.8706786171574904,
+      "grad_norm": 1.122640609741211,
+      "learning_rate": 9.488549274967872e-06,
+      "loss": 0.1,
+      "step": 170
+    },
+    {
+      "epoch": 0.9218950064020487,
+      "grad_norm": 2.5161125659942627,
+      "learning_rate": 3.6294356110059157e-06,
+      "loss": 0.1207,
+      "step": 180
+    },
+    {
+      "epoch": 0.9731113956466069,
+      "grad_norm": 6.927064895629883,
+      "learning_rate": 5.130676608104845e-07,
+      "loss": 1.1711,
+      "step": 190
     }
   ],
   "logging_steps": 10,
@@ -167,12 +195,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.95132603613184e+16,
+  "total_flos": 3.853325055924634e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null