Training in progress, step 110, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ac5a06868d4549d8ca809aceb34d2f9203c57f47f62226617dba3c46e929b9
+oid sha256:eeaa88bb46e23c39f7084bab91c911ab334500ac140d6c97c6230601d4b19146
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b147b7a755f582d5d04042105d6e705c48a46753db7af1c5632e3edd95f8c0
+oid sha256:8bf0396d42d68a643bb80d3f2def95c628f4ac8bdbd074e6fbcc89467a4da1b3
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ade7c6f7575905253c20fecd77ea3dd7d528c69921646b6c58b5e79233ee72
+oid sha256:f3e5a931b951401918bd8850c2797fac01ec2c7ed74710d75a14113c07f23dbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c84ec0ff3c8c6aa13b25568668096db118f67ce80a9fa015a625446606f15d
+oid sha256:398198b060b9edcfe93ff59de4a929b40cbc42323ec0afb0426f8d7b821a61c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.032732963562012,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.004519671871822106,
+  "best_metric": 11.030839920043945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-110",
+  "epoch": 0.004971639059004316,
   "eval_steps": 5,
-  "global_step": 100,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -875,6 +875,92 @@
       "eval_samples_per_second": 52.882,
       "eval_steps_per_second": 26.444,
       "step": 100
+    },
+    {
+      "epoch": 0.004564868590540326,
+      "grad_norm": 0.46195968985557556,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 44.1243,
+      "step": 101
+    },
+    {
+      "epoch": 0.004610065309258548,
+      "grad_norm": 0.4918234348297119,
+      "learning_rate": 0.00018310240965131041,
+      "loss": 44.0833,
+      "step": 102
+    },
+    {
+      "epoch": 0.004655262027976769,
+      "grad_norm": 0.39288461208343506,
+      "learning_rate": 0.00018274407791591966,
+      "loss": 44.0844,
+      "step": 103
+    },
+    {
+      "epoch": 0.00470045874669499,
+      "grad_norm": 0.7819874882698059,
+      "learning_rate": 0.00018238234489557215,
+      "loss": 44.0727,
+      "step": 104
+    },
+    {
+      "epoch": 0.004745655465413211,
+      "grad_norm": 0.4996788203716278,
+      "learning_rate": 0.0001820172254596956,
+      "loss": 44.0926,
+      "step": 105
+    },
+    {
+      "epoch": 0.004745655465413211,
+      "eval_loss": 11.03187370300293,
+      "eval_runtime": 176.1674,
+      "eval_samples_per_second": 52.887,
+      "eval_steps_per_second": 26.446,
+      "step": 105
+    },
+    {
+      "epoch": 0.004790852184131432,
+      "grad_norm": 0.4443046748638153,
+      "learning_rate": 0.00018164873461691986,
+      "loss": 44.1211,
+      "step": 106
+    },
+    {
+      "epoch": 0.0048360489028496535,
+      "grad_norm": 0.6192988753318787,
+      "learning_rate": 0.00018127688751446027,
+      "loss": 44.2023,
+      "step": 107
+    },
+    {
+      "epoch": 0.004881245621567874,
+      "grad_norm": 0.49968671798706055,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.1175,
+      "step": 108
+    },
+    {
+      "epoch": 0.004926442340286095,
+      "grad_norm": 0.5411902070045471,
+      "learning_rate": 0.0001805231858085356,
+      "loss": 44.1106,
+      "step": 109
+    },
+    {
+      "epoch": 0.004971639059004316,
+      "grad_norm": 0.7971486449241638,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 44.1488,
+      "step": 110
+    },
+    {
+      "epoch": 0.004971639059004316,
+      "eval_loss": 11.030839920043945,
+      "eval_runtime": 176.4251,
+      "eval_samples_per_second": 52.81,
+      "eval_steps_per_second": 26.408,
+      "step": 110
     }
   ],
   "logging_steps": 1,
@@ -903,7 +989,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1050673152000.0,
+  "total_flos": 1155740467200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null