Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5899bc1783f21949ceaf355cf78b0f0e0b0bbbb2194df6ffe261d42a743b397a
+oid sha256:9c9194b451523bb10383c464149cb790a70cbc34d0fdd522379136fcfb354c17
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff118dee4af1ef6fa194efa559bda1b5930338078daa4baf21bafb83f383b93
+oid sha256:8990914358a367b711dece82c24366af052b06a6fa9a68733dd0b5f03bcdb705
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9004a5d1cfb134c581658c7f193c7a2293f7ac4dd44f2b707e4c1f64ab2df21
+oid sha256:fc62e9646c76e2855b42dbe6fcaa7bc77293c8d322828d69d4c33b3c72352b26
 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": 0.6780943870544434,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.038834951456310676,
+  "best_metric": 0.5173833966255188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07766990291262135,
   "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": 5.747,
       "eval_steps_per_second": 1.457,
       "step": 10
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 3.01274037361145,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4687,
+      "step": 12
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 1.2839837074279785,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2457,
+      "step": 15
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "eval_loss": 0.5668467283248901,
+      "eval_runtime": 37.7843,
+      "eval_samples_per_second": 5.743,
+      "eval_steps_per_second": 1.456,
+      "step": 15
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 1.24266517162323,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.3707,
+      "step": 18
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_loss": 0.5173833966255188,
+      "eval_runtime": 37.7177,
+      "eval_samples_per_second": 5.753,
+      "eval_steps_per_second": 1.458,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.26956599246848e+16,
+  "total_flos": 2.53913198493696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null