Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02995ccdcc012308d7250e78515a2f6bda0e58ab79b934cc98cd7442b32a44d3
+oid sha256:48a7f7dd89e18ebab61641ed2ccf9e9c54ba4f248ecbb980d4a19ce6fe9575a2
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac5bcadc12e82242e8d104c54043072eea3c8d69b856f5779e4f5ce28828e4a
+oid sha256:4b3bc66826634872063b8cb793d1f57872b974945ac2e55a53f96fce27db3d9a
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9259a5cfbb4e6f2e1e58fc827ddd08b4ba05425ee76faec52400c89c09d3a711
+oid sha256:edf29fe3862d1dc808ab7cca30de6c7c46bd888b65b2ee19da5ec8fcb1d9df36
 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": 0.8574949502944946,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.012702445220704985,
+  "best_metric": 0.5654808282852173,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02540489044140997,
   "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": 4.146,
       "eval_steps_per_second": 1.038,
       "step": 10
+    },
+    {
+      "epoch": 0.015242934264845983,
+      "grad_norm": 1.0055904388427734,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.0939,
+      "step": 12
+    },
+    {
+      "epoch": 0.01905366783105748,
+      "grad_norm": 1.397754192352295,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.0024,
+      "step": 15
+    },
+    {
+      "epoch": 0.01905366783105748,
+      "eval_loss": 0.6791817545890808,
+      "eval_runtime": 159.9577,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 1.038,
+      "step": 15
+    },
+    {
+      "epoch": 0.022864401397268974,
+      "grad_norm": 1.4741846323013306,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.5871,
+      "step": 18
+    },
+    {
+      "epoch": 0.02540489044140997,
+      "eval_loss": 0.5654808282852173,
+      "eval_runtime": 159.9867,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 1.038,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.39292061990912e+16,
+  "total_flos": 2.75186756616192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null