Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b26039d99f66309439ca1f66e8ae003bfbb31b42b752366b79a87aac969dc1
+oid sha256:47eef36ecb3b350a37dacf201791fd617126633ced4ae7c30de1da3fde0927d7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e58aff5286325899cdcfee3867f552e4cf0722f12b9c0a24dc059063cbaaa3
+oid sha256:cc1b64aa672eb1b8cc23c23be3ea8464e8d258908379f9a017a01ab21dc709b9
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432efda4eef7ba609da21098dea6308963a2ecb8fe149f3d1803352b9232832f
+oid sha256:9051584908256c7669b242e7052949f09a836d6c06b0624fe9936a3b299489f9
 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": 1.8019968271255493,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0031801558276355543,
+  "best_metric": 1.425671935081482,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006360311655271109,
   "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": 18.745,
       "eval_steps_per_second": 4.686,
       "step": 10
+    },
+    {
+      "epoch": 0.003816186993162665,
+      "grad_norm": 1.5523895025253296,
+      "learning_rate": 0.000163742398974869,
+      "loss": 6.559,
+      "step": 12
+    },
+    {
+      "epoch": 0.0047702337414533315,
+      "grad_norm": 1.4192075729370117,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.2157,
+      "step": 15
+    },
+    {
+      "epoch": 0.0047702337414533315,
+      "eval_loss": 1.5555007457733154,
+      "eval_runtime": 142.2994,
+      "eval_samples_per_second": 18.609,
+      "eval_steps_per_second": 4.652,
+      "step": 15
+    },
+    {
+      "epoch": 0.005724280489743997,
+      "grad_norm": 1.7687486410140991,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 5.7934,
+      "step": 18
+    },
+    {
+      "epoch": 0.006360311655271109,
+      "eval_loss": 1.425671935081482,
+      "eval_runtime": 141.2734,
+      "eval_samples_per_second": 18.744,
+      "eval_steps_per_second": 4.686,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4236810469244928.0,
+  "total_flos": 7920993485979648.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null