Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4048df42b0edbd9da090c8c014a7d4b251e358d7a9d32eb021f26dcc9ff5c37f
+oid sha256:93ac256aed23bee437ec9fe18e7a3bd9781451f26bc8c41021d62a036e87081f
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777919d2370e3423725dcf405283182c643b494622ae665c493c9d3b6622dc7c
+oid sha256:504edc3a7f6533bd46f7f52a19c55352264aa3ff65f9962413f8848e6a7fcfc6
 size 25279290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9ab7db431e6cea4f6f67f645378c70ef004171a9209f8ce85124ff5172a3ca
+oid sha256:19c3a950b1db5e5a53ee1807fed513e1459650c81b28057a7dd9e7f6eb2c4dc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.755293130874634,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007355713090410909,
+  "best_metric": 3.7517294883728027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0009194641363013636,
   "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": 15.485,
       "eval_steps_per_second": 7.743,
       "step": 20
+    },
+    {
+      "epoch": 0.0007723498744931454,
+      "grad_norm": 4.634418487548828,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 15.9765,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008091284399452,
+      "grad_norm": 3.4980578422546387,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 15.835,
+      "step": 22
+    },
+    {
+      "epoch": 0.0008459070053972545,
+      "grad_norm": 3.5311439037323,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 15.0439,
+      "step": 23
+    },
+    {
+      "epoch": 0.000882685570849309,
+      "grad_norm": 3.130390167236328,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 14.4918,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009194641363013636,
+      "grad_norm": 2.921156644821167,
+      "learning_rate": 0.0,
+      "loss": 15.3883,
+      "step": 25
+    },
+    {
+      "epoch": 0.0009194641363013636,
+      "eval_loss": 3.7517294883728027,
+      "eval_runtime": 745.0938,
+      "eval_samples_per_second": 15.366,
+      "eval_steps_per_second": 7.684,
+      "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": 300278611968000.0,
+  "total_flos": 375348264960000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null