Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3945a734ce0cb4359330ed3d6a945004d1fec439cf033a03b23d113fdc271f1d
+oid sha256:2033e2db42a36cb35b8d3ed70c0a878f8dd786e05a70110135c6fd487e281c7e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fce9c746b4058ac7d1e3cc9305e59d06be39e1ee4db3b32cc3ac09fb5fb40ef
+oid sha256:46c909521d4d433d1398dae5f1b05a10bf2e590185625bd985dfbd6e3af24d4a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99497c0bb0ccae690b5d400e178ecb75bc2e9c3473cd804f525b56764ace7bcb
+oid sha256:4ae93f9ceb4491d8b738b901af25dd83aee2a571e3ee809d3df96c157a059458
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8525367379188538,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04953560371517028,
+  "best_metric": 0.7847893238067627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07430340557275542,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 6.318,
       "eval_steps_per_second": 1.579,
       "step": 20
+    },
+    {
+      "epoch": 0.05201238390092879,
+      "grad_norm": 1.9752190113067627,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.9631,
+      "step": 21
+    },
+    {
+      "epoch": 0.05944272445820433,
+      "grad_norm": 1.472144603729248,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.8413,
+      "step": 24
+    },
+    {
+      "epoch": 0.06191950464396285,
+      "eval_loss": 0.7937929034233093,
+      "eval_runtime": 54.226,
+      "eval_samples_per_second": 6.27,
+      "eval_steps_per_second": 1.568,
+      "step": 25
+    },
+    {
+      "epoch": 0.06687306501547988,
+      "grad_norm": 1.0236313343048096,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.8092,
+      "step": 27
+    },
+    {
+      "epoch": 0.07430340557275542,
+      "grad_norm": 0.6827451586723328,
+      "learning_rate": 0.0,
+      "loss": 0.8011,
+      "step": 30
+    },
+    {
+      "epoch": 0.07430340557275542,
+      "eval_loss": 0.7847893238067627,
+      "eval_runtime": 54.1048,
+      "eval_samples_per_second": 6.284,
+      "eval_steps_per_second": 1.571,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.479651398516736e+16,
+  "total_flos": 2.219477097775104e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null