Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e1102aac4953cfe6bc9872351f27108f76fdbdbcad2bfa4066e4dafdbaff457
+oid sha256:941c4f07da1ea170ccc363b09fc82de8797e9cc5a8ad2dfd342b9a682f9fede9
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bf594a860155c376407b19b8b9f2e572b7356b73c46a6a0cb7da07cb052698
+oid sha256:c709439d065ac1da67d95461ee6538d45172539c97fe03b6d682368e1dc97b77
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0551e97453d9ae10819166b91ebf1cddf27d5fcb315c65549de5aa2ad4d60cfa
+oid sha256:ae341615e23f78ea0d9ec53f366f85dd01668aeaa6fa0024d702041da2ad7e77
 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": 2.1532111167907715,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.038204393505253106,
+  "best_metric": 2.063730001449585,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07640878701050621,
   "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": 2.522,
       "eval_steps_per_second": 0.639,
       "step": 10
+    },
+    {
+      "epoch": 0.045845272206303724,
+      "grad_norm": 0.15824028849601746,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.1492,
+      "step": 12
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "grad_norm": 0.16715355217456818,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1101,
+      "step": 15
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "eval_loss": 2.094489097595215,
+      "eval_runtime": 87.493,
+      "eval_samples_per_second": 2.526,
+      "eval_steps_per_second": 0.64,
+      "step": 15
+    },
+    {
+      "epoch": 0.06876790830945559,
+      "grad_norm": 0.14857010543346405,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.1153,
+      "step": 18
+    },
+    {
+      "epoch": 0.07640878701050621,
+      "eval_loss": 2.063730001449585,
+      "eval_runtime": 87.4237,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 0.641,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5391158788096e+16,
+  "total_flos": 5.0782317576192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null