Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402213aafbd1ed62f735e49bb02e49c80d6ef7eab1b0e0d53b76482ca55caa7c
+oid sha256:3501bb315f78f6119bd9e35e5bfd306afada61fba037f9237307eef66af009da
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f297bed4ab6f11dc349175098902ceb3f3afbea37bedc0181a4f376694942a8
+oid sha256:c00656dfb7582e6364a9643e65333baa15e8d5080d4dbb19b985296d1cce6d9b
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07afe122263cfc078eea3de35475ffdeed7ab490543f1a133fe2c7406a6f32da
+oid sha256:627ff7b56c0b2a5f76bc2af26277fa99c8f3c68f32d700ecca7ddf65824dc1a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
+oid sha256:56e06160672e234a504b2a9f8fb3d80ed8c221e80fde36a5548d37e259bd5bc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9015980362892151,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.07633587786259542,
+  "best_metric": 0.8921794295310974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.10178117048346055,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 23.62,
       "eval_steps_per_second": 5.905,
       "step": 150
+    },
+    {
+      "epoch": 0.08142493638676845,
+      "grad_norm": 9.362646102905273,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 1.1438,
+      "step": 160
+    },
+    {
+      "epoch": 0.08651399491094147,
+      "grad_norm": 14.217305183410645,
+      "learning_rate": 1.6833333333333332e-06,
+      "loss": 1.2251,
+      "step": 170
+    },
+    {
+      "epoch": 0.0916030534351145,
+      "grad_norm": 8.306926727294922,
+      "learning_rate": 1.1222222222222222e-06,
+      "loss": 0.7782,
+      "step": 180
+    },
+    {
+      "epoch": 0.09669211195928754,
+      "grad_norm": 8.390512466430664,
+      "learning_rate": 5.611111111111111e-07,
+      "loss": 0.8091,
+      "step": 190
+    },
+    {
+      "epoch": 0.10178117048346055,
+      "grad_norm": 9.584101676940918,
+      "learning_rate": 0.0,
+      "loss": 0.6583,
+      "step": 200
+    },
+    {
+      "epoch": 0.10178117048346055,
+      "eval_loss": 0.8921794295310974,
+      "eval_runtime": 35.0768,
+      "eval_samples_per_second": 23.605,
+      "eval_steps_per_second": 5.901,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.006798934881075e+16,
+  "total_flos": 5.33047358301143e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null