Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1613b2e97efa09df320040be7045f5b9200e69cae651ef1f58a828c09b130bd7
+oid sha256:6a49a8951566a3eaaaed0c065dd596236d9d3bd6ba9a1c7efc56e75ba44e1a77
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed05f944ee0693777c252247175ec7b9d3f4e2be297664752dbbae188e268d9f
+oid sha256:4f86e1c92409d913fe76ccd17e2130bb79fdaa03282e9d0fff5888a9f02e5b45
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
+oid sha256:983baa830df615f6f61b75af5f4b0cf7a694a7d02c96696d0f4804987ec72e0d
 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": 11.086691856384277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016389748212493086,
+  "best_metric": 11.0850830078125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0020487185265616356,
   "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": 132.696,
       "eval_steps_per_second": 66.348,
       "step": 20
+    },
+    {
+      "epoch": 0.001720923562311774,
+      "grad_norm": 2.490718126296997,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.379,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018028723033742394,
+      "grad_norm": 2.075052499771118,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.2296,
+      "step": 22
+    },
+    {
+      "epoch": 0.0018848210444367048,
+      "grad_norm": 1.9929821491241455,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.3492,
+      "step": 23
+    },
+    {
+      "epoch": 0.00196676978549917,
+      "grad_norm": 2.7142038345336914,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.2775,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020487185265616356,
+      "grad_norm": 2.383056879043579,
+      "learning_rate": 0.0,
+      "loss": 44.1968,
+      "step": 25
+    },
+    {
+      "epoch": 0.0020487185265616356,
+      "eval_loss": 11.0850830078125,
+      "eval_runtime": 39.0523,
+      "eval_samples_per_second": 131.567,
+      "eval_steps_per_second": 65.784,
+      "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": 192896040960.0,
+  "total_flos": 241120051200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null