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:ace3e1d916938495d70b4901a38da48e429f19511c96e14765d597a7b189cd08
+oid sha256:ac0982dbb965825b51d54d7f56d28eb2d6528e73e8170192d2e5fe70f0c4ee36
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67fb9d9167abef4e28034544bc99917878853549ea2b914e5d47f9955d5fe52
+oid sha256:ad448e42a0e160df00298388a48c72154d4a6fdf2fe926f069ddeded6e864f55
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 0.810635507106781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01677500524218914,
+  "best_metric": 0.798811137676239,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.020968756552736424,
   "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": 6.82,
       "eval_steps_per_second": 3.41,
       "step": 20
+    },
+    {
+      "epoch": 0.017613755504298594,
+      "grad_norm": 1.9000037908554077,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7495,
+      "step": 21
+    },
+    {
+      "epoch": 0.018452505766408053,
+      "grad_norm": 0.6952345967292786,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8508,
+      "step": 22
+    },
+    {
+      "epoch": 0.019291256028517507,
+      "grad_norm": 0.6956720352172852,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7993,
+      "step": 23
+    },
+    {
+      "epoch": 0.020130006290626966,
+      "grad_norm": 0.6497891545295715,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8036,
+      "step": 24
+    },
+    {
+      "epoch": 0.020968756552736424,
+      "grad_norm": 0.7134623527526855,
+      "learning_rate": 0.0,
+      "loss": 0.7515,
+      "step": 25
+    },
+    {
+      "epoch": 0.020968756552736424,
+      "eval_loss": 0.798811137676239,
+      "eval_runtime": 74.0655,
+      "eval_samples_per_second": 6.778,
+      "eval_steps_per_second": 3.389,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null