Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755e1b9d99f239205d1deada897e26bb86c108a099098e7fff836984404cd4b1
+oid sha256:b113f75af4e4edacfa29917f37d4572f6c7ccb0adbc816f88f9095f1cca1c610
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edf2570a661a201554401d6e9dd7887e6b241d44367774a832e763804173597
+oid sha256:cfe9f635df323949a5dfdf43f2a438a6009f6788308f45333979f8e69f4da6e3
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e067f974bd0923fc62bc7d81c2465026d4bb345af439a687601963096dea61c8
+oid sha256:a7c4c6aeb73e031b64934fbc4f87c0bedf54f8a6dbe4be586cce9651fa910fe2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820d227375038f02873567923da684b2500a67bbf69535a5b7d5b614defc8040
+oid sha256:c0a2c2d65c81d2f1a44c97f02ce25b3c742ec1ac58296e9ead6efbd6f748d93f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4705960750579834,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.01365280906546522,
+  "best_metric": 2.4184000492095947,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.02730561813093044,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 35.165,
       "eval_steps_per_second": 8.791,
       "step": 100
+    },
+    {
+      "epoch": 0.020479213598197828,
+      "grad_norm": 59.893226623535156,
+      "learning_rate": 0.00025,
+      "loss": 8.5449,
+      "step": 150
+    },
+    {
+      "epoch": 0.02730561813093044,
+      "grad_norm": 58.9417839050293,
+      "learning_rate": 0.00025,
+      "loss": 8.9737,
+      "step": 200
+    },
+    {
+      "epoch": 0.02730561813093044,
+      "eval_loss": 2.4184000492095947,
+      "eval_runtime": 175.3962,
+      "eval_samples_per_second": 35.166,
+      "eval_steps_per_second": 8.792,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -65,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.53626333642752e+16,
+  "total_flos": 7.07252667285504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null