Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382cee1b564ad63a8add83af088231dfca380e2977a6e9942114e3f549648390
+oid sha256:1a7e966525cc1c832d66e1bc5aa0478d8879221ef46793d16301ad12059b8cfe
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fb6af57d864730b370094de1a3074c2d0ae1f334895e0bd11fee7d4fba6508
+oid sha256:f96e3779a1770b7dce8fa74387954cab7337ca3f0a279ea02f61d864291def6c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a269af6ca7cf5a462d4bf6222e99833c81c22e6a2a6edec4bdc43b6d749d985f
+oid sha256:2b4c83c657c7d48ecd59acb6a97ff190841b72a716b62dede7d34500c8317408
 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": 2.4324159622192383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.02053388090349076,
+  "best_metric": 2.38735032081604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04106776180698152,
   "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": 5.514,
       "eval_steps_per_second": 1.385,
       "step": 10
+    },
+    {
+      "epoch": 0.024640657084188913,
+      "grad_norm": 0.3327385187149048,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4379,
+      "step": 12
+    },
+    {
+      "epoch": 0.030800821355236138,
+      "grad_norm": 0.29605767130851746,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.4236,
+      "step": 15
+    },
+    {
+      "epoch": 0.030800821355236138,
+      "eval_loss": 2.4080677032470703,
+      "eval_runtime": 74.1284,
+      "eval_samples_per_second": 5.531,
+      "eval_steps_per_second": 1.389,
+      "step": 15
+    },
+    {
+      "epoch": 0.03696098562628337,
+      "grad_norm": 0.26171067357063293,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.3968,
+      "step": 18
+    },
+    {
+      "epoch": 0.04106776180698152,
+      "eval_loss": 2.38735032081604,
+      "eval_runtime": 73.6666,
+      "eval_samples_per_second": 5.566,
+      "eval_steps_per_second": 1.398,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.483774567120896e+16,
+  "total_flos": 2.949001952152781e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null