Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df32a0c703458a53f9e3a07445702d09cd9239b33d681d36e0cb626aef4089e
+oid sha256:f58efa7c1a540fd84ed404062fda98c7ff7f477b90dbb1ccb8ba8687761ffe67
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c92f9082d8ee1b338ee6524d5e11143564be6d700103c961729333feacee1f
+oid sha256:c7e0a0b89f4aa4fd270b6a0c966f1e065298b0816eec0e577128355b585a50bc
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c949c6e825e9b6cc6e61770439637c62f618ab7c470350a60558b82879992b12
+oid sha256:87755beef9691a991b9cc6ce8667bce1e76fa58e779f6ff8027b45a6b913d75d
 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": 1.1749109029769897,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.020080321285140562,
+  "best_metric": 1.0417708158493042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.040160642570281124,
   "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": 2.851,
       "eval_steps_per_second": 1.425,
       "step": 10
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 1.7703816890716553,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 4.5346,
+      "step": 12
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 8.211416244506836,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.7168,
+      "step": 15
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "eval_loss": 1.092099905014038,
+      "eval_runtime": 73.6836,
+      "eval_samples_per_second": 2.85,
+      "eval_steps_per_second": 1.425,
+      "step": 15
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 1.9411234855651855,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 4.1431,
+      "step": 18
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "eval_loss": 1.0417708158493042,
+      "eval_runtime": 73.76,
+      "eval_samples_per_second": 2.847,
+      "eval_steps_per_second": 1.424,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.30129688788992e+16,
+  "total_flos": 2.57085482729472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null