Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d252fbf566eb957c0cfbc8448aac38fb6da5b709aacfbe542ef85cd0802cf6
+oid sha256:c42ba18b8bf26e3fbee9ba5e431f62c5ec5ae10b489c35d9a04c13e18f9c76b4
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b144cc08cdac9d9b14c65ec884314bc9ca020b4e75e264424cf870173312581
+oid sha256:af971a1ca735a146ae16d5eef1d14cc677906d2afd01b2072fa012961f0cfe12
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f04b5302900676e06009047ea5dcb675723c0ce0ae6bfd57e68b40f6a199cc
+oid sha256:c0aaa8092d42f737d0d24b5de179d4c5bd61d260ed091186851f7bc6acf50199
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1654425412416458,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04106776180698152,
+  "best_metric": 0.16326583921909332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0513347022587269,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 3.261,
       "eval_steps_per_second": 1.639,
       "step": 20
+    },
+    {
+      "epoch": 0.043121149897330596,
+      "grad_norm": 0.48649734258651733,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6026,
+      "step": 21
+    },
+    {
+      "epoch": 0.045174537987679675,
+      "grad_norm": 0.47328346967697144,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6899,
+      "step": 22
+    },
+    {
+      "epoch": 0.04722792607802875,
+      "grad_norm": 0.4465431869029999,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7068,
+      "step": 23
+    },
+    {
+      "epoch": 0.049281314168377825,
+      "grad_norm": 0.44562870264053345,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7001,
+      "step": 24
+    },
+    {
+      "epoch": 0.0513347022587269,
+      "grad_norm": 0.5656099319458008,
+      "learning_rate": 0.0,
+      "loss": 0.8205,
+      "step": 25
+    },
+    {
+      "epoch": 0.0513347022587269,
+      "eval_loss": 0.16326583921909332,
+      "eval_runtime": 62.8094,
+      "eval_samples_per_second": 3.264,
+      "eval_steps_per_second": 1.64,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.211080796798976e+16,
+  "total_flos": 1.519787666571264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null