Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8797eb68690e7fac56d6057b96eba21e0a331cfdd45174aee5c0ee4eea36b1cf
+oid sha256:98c964c3f4b97d7f8dc4937b7c150596ecbb65d5d84d558e394e6a057183fb47
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82363c3391b71db30a7d1992202b92ad00b4369bd85ef1a9d4b0fb6316b2d4e5
+oid sha256:83900e9a8bdb0c720e521696bb18379616e869bec8f8663a743841c3065209fd
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1022298522718ebadedfe84da1ed3a851ecc8d458aabbec70ea805199d56ba42
+oid sha256:aa9f4dcad0ce36d89bf1cf0db0ae4de33b1f8cf39473433de3f6d40fbc2ea74a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b49f2fa3a406bdd61a3e48a2439867e734b5cd9ac3b08f0221d2c0369ea6d2
+oid sha256:0051c53bcb92b7c913136d782f625b409707ede35cdcc9bbc83a63d788098e04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4602386951446533,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0326477309826967,
+  "best_metric": 1.3073418140411377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0652954619653934,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 61.116,
       "eval_steps_per_second": 15.285,
       "step": 50
+    },
+    {
+      "epoch": 0.039177277179236046,
+      "grad_norm": 0.09031832218170166,
+      "learning_rate": 0.0001964767868814516,
+      "loss": 1.2569,
+      "step": 60
+    },
+    {
+      "epoch": 0.045706823375775384,
+      "grad_norm": 0.09168185293674469,
+      "learning_rate": 0.00019493976084683813,
+      "loss": 1.2857,
+      "step": 70
+    },
+    {
+      "epoch": 0.05223636957231472,
+      "grad_norm": 0.1381785273551941,
+      "learning_rate": 0.00019313361774523385,
+      "loss": 1.3339,
+      "step": 80
+    },
+    {
+      "epoch": 0.058765915768854066,
+      "grad_norm": 0.3087773323059082,
+      "learning_rate": 0.00019106347728549135,
+      "loss": 1.3948,
+      "step": 90
+    },
+    {
+      "epoch": 0.0652954619653934,
+      "grad_norm": 0.6337625980377197,
+      "learning_rate": 0.00018873520750565718,
+      "loss": 1.3688,
+      "step": 100
+    },
+    {
+      "epoch": 0.0652954619653934,
+      "eval_loss": 1.3073418140411377,
+      "eval_runtime": 42.0855,
+      "eval_samples_per_second": 61.28,
+      "eval_steps_per_second": 15.326,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8166000449028096.0,
+  "total_flos": 1.6291971484090368e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null