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:fc7aac25873441d6dbbb5560e72c9cd36063f53453ba0573c76ee2e77b172e3f
+oid sha256:89c59ad0c347f3da0a76bda73b466c6601c615d7978412d40d021022c7bc4c51
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741b480eead5d7dad62a4d3f29ef8fb7475bd8008eb2c7081c03f8d111940e29
+oid sha256:472eb6676c54eb9279f1e5d67db0f3a80617b0b6247e93fd0ed07ea97a73cd7d
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a61b33080e1f4b84ad2e5230243eb2da7923507fc14dd060ee26fd3dcfb4ec
+oid sha256:da23b19bfe147332d7f4cda6ddcca2a07a4601e8f77254aebaa1560512e716fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.456212043762207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008174943797261395,
+  "best_metric": 1.3194067478179932,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01634988759452279,
   "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": 25.348,
       "eval_steps_per_second": 12.698,
       "step": 10
+    },
+    {
+      "epoch": 0.009809932556713672,
+      "grad_norm": 0.7650735974311829,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.4606,
+      "step": 12
+    },
+    {
+      "epoch": 0.012262415695892091,
+      "grad_norm": 0.7929948568344116,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3442,
+      "step": 15
+    },
+    {
+      "epoch": 0.012262415695892091,
+      "eval_loss": 1.3643509149551392,
+      "eval_runtime": 20.8425,
+      "eval_samples_per_second": 24.709,
+      "eval_steps_per_second": 12.379,
+      "step": 15
+    },
+    {
+      "epoch": 0.014714898835070508,
+      "grad_norm": 0.6958890557289124,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.3561,
+      "step": 18
+    },
+    {
+      "epoch": 0.01634988759452279,
+      "eval_loss": 1.3194067478179932,
+      "eval_runtime": 21.3468,
+      "eval_samples_per_second": 24.125,
+      "eval_steps_per_second": 12.086,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 520150881140736.0,
+  "total_flos": 1040301762281472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null