Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919d48391fed840ad8672a525e11d3bc76c4c5a4ec764c71cd4a54501ede306d
+oid sha256:545a04e9df3284fbdb667405b41943b312504d3dbee9cbcfd0e52fe0a66f2c9b
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fd45871c6f4e8dba3677acee539835bde0dd3500881ad08433b9627ee66c9d
+oid sha256:e6aca25c636dd48dd894e38f353ade9a31f62907a721efb9ea69241bda3a7ed5
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bd5b58e5e84ac4c2b56f9128f64021729566b6b5ae932fe03473b24f49f906
+oid sha256:88089b75d6b623f34c98becff8927336b43ddcda017bf8dd6cdbc2ddbbe5dcbc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9185737371444702,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.024891101431238332,
+  "best_metric": 0.8677180409431458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.049782202862476664,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 6.284,
       "eval_steps_per_second": 3.142,
       "step": 10
+    },
+    {
+      "epoch": 0.029869321717486,
+      "grad_norm": 1.371448278427124,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.636,
+      "step": 12
+    },
+    {
+      "epoch": 0.037336652146857496,
+      "grad_norm": 1.3308101892471313,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.5174,
+      "step": 15
+    },
+    {
+      "epoch": 0.037336652146857496,
+      "eval_loss": 0.8843600749969482,
+      "eval_runtime": 27.1081,
+      "eval_samples_per_second": 6.271,
+      "eval_steps_per_second": 3.136,
+      "step": 15
+    },
+    {
+      "epoch": 0.044803982576229,
+      "grad_norm": 1.197558045387268,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.4537,
+      "step": 18
+    },
+    {
+      "epoch": 0.049782202862476664,
+      "eval_loss": 0.8677180409431458,
+      "eval_runtime": 26.9775,
+      "eval_samples_per_second": 6.302,
+      "eval_steps_per_second": 3.151,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5717207128473600.0,
+  "total_flos": 1.14344142569472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null