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:c4ae46111f25900606231672cf402245efca0e9b4093b985143d26b5bca9c5e2
+oid sha256:8cca12517617dd6ff1f2e3d2b403901885eec92e3d18fc0ebafa8473a00b8a1b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980bc17486b9c932821a4567bbaaa0d174ebf5ed4b824ec174814c48b08665b6
+oid sha256:bcc47bc08930597edf93a50b4fd53eab2ef9f57d6e672d7082900db70d7f1431
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca1f53ba0dd38aa3dffdca6ceb9cf6d0cb74b2c743225a3ed71b2ef636ce7ad
+oid sha256:f65862cc6ebe07d18b57855ee8d7f6d5a1b504eb519a516d2f1dd289fbac5545
 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": 0.46810051798820496,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007979413114165454,
+  "best_metric": 0.34694528579711914,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0009974266392706816,
   "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": 5.874,
       "eval_steps_per_second": 2.937,
       "step": 20
+    },
+    {
+      "epoch": 0.0008378383769873726,
+      "grad_norm": 26.54975128173828,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7679,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008777354425581999,
+      "grad_norm": 4.3329691886901855,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.2106,
+      "step": 22
+    },
+    {
+      "epoch": 0.0009176325081290271,
+      "grad_norm": 0.4202094078063965,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0065,
+      "step": 23
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "grad_norm": 12.792423248291016,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7221,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009974266392706816,
+      "grad_norm": 12.721324920654297,
+      "learning_rate": 0.0,
+      "loss": 0.635,
+      "step": 25
+    },
+    {
+      "epoch": 0.0009974266392706816,
+      "eval_loss": 0.34694528579711914,
+      "eval_runtime": 1795.7899,
+      "eval_samples_per_second": 5.877,
+      "eval_steps_per_second": 2.939,
+      "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": 5594931850641408.0,
+  "total_flos": 6889626824343552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null