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:fe6bea76585bc8dafc667508687d2d8682d061c2829ae4caf5d99fee2263e127
+oid sha256:b6b7328f97a46109bf2a243345b24493609b643fae4ac091035a3d791b5a650c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c81339b39a15e530e10743426f260a284d658d0fdb91f720d50e46987a8314
+oid sha256:a57fa7527c2a02dadc5edbcc090d1086a05c4be264b7025a1d5b4fa781da76f4
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae0f84b72620e20dcd97ba85ffc1d2aea720cc31be13dc875099edcedaa5927
+oid sha256:819b68cbf44591e37b164b2035c03668218d35e0b3d7cb76a6adc6d3e1323063
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4660513401031494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.008908950525628082,
+  "best_metric": 1.4608114957809448,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.011878600700837441,
   "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": 12.277,
       "eval_steps_per_second": 3.071,
       "step": 150
+    },
+    {
+      "epoch": 0.009502880560669953,
+      "grad_norm": 2.0533039569854736,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 1.4115,
+      "step": 160
+    },
+    {
+      "epoch": 0.010096810595711825,
+      "grad_norm": 2.7204930782318115,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 1.4418,
+      "step": 170
+    },
+    {
+      "epoch": 0.010690740630753696,
+      "grad_norm": 3.4697649478912354,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 1.4363,
+      "step": 180
+    },
+    {
+      "epoch": 0.01128467066579557,
+      "grad_norm": 4.115236282348633,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 1.4766,
+      "step": 190
+    },
+    {
+      "epoch": 0.011878600700837441,
+      "grad_norm": 8.668231010437012,
+      "learning_rate": 0.0,
+      "loss": 1.6002,
+      "step": 200
+    },
+    {
+      "epoch": 0.011878600700837441,
+      "eval_loss": 1.4608114957809448,
+      "eval_runtime": 433.8437,
+      "eval_samples_per_second": 12.256,
+      "eval_steps_per_second": 3.066,
+      "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": 4.376125878829056e+16,
+  "total_flos": 5.834834505105408e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null