Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2c001f237ffca1cd839278a313f657af631af3ec6a76bc8b2eac4e50e3a25a
+oid sha256:892c6e2e6435c73463c3134fd84a37b5f246ee300223faba464a5be9a30532b4
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369f651983a45750392de2801cfc00489afdeea1f73debf56bd876311854ee9c
+oid sha256:c7fb74db006dd44b6e502d7da881da69cec15dd4690ca116f9dd1533ecbde16a
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3111302d79787eb2b7e881e82d970f10e7ab48daddfbf3a91d39b7ad609669ba
+oid sha256:7faf92e9d1cf9db27d7d53e0f09be3f79b4c8736a000208b6975d432c5fe0a63
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317ba05605195c1d4e2040522f74e7ab98f17d7a309d9ff3aaeabe58a301e214
+oid sha256:c9abf3b00130ebbc35657fb7788755e92886d9a53e2a5677dea2a31074b05473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.39147135615348816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.1631321370309951,
+  "best_metric": 0.3247433006763458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.21750951604132682,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 17.021,
       "eval_steps_per_second": 4.255,
       "step": 150
+    },
+    {
+      "epoch": 0.17400761283306146,
+      "grad_norm": 0.6848308444023132,
+      "learning_rate": 0.00018053067903555837,
+      "loss": 0.2406,
+      "step": 160
+    },
+    {
+      "epoch": 0.18488308863512778,
+      "grad_norm": 1.072629451751709,
+      "learning_rate": 0.00017525871366768012,
+      "loss": 0.1456,
+      "step": 170
+    },
+    {
+      "epoch": 0.19575856443719414,
+      "grad_norm": 1.8140205144882202,
+      "learning_rate": 0.00016964445490919413,
+      "loss": 0.1917,
+      "step": 180
+    },
+    {
+      "epoch": 0.20663404023926046,
+      "grad_norm": 2.534623861312866,
+      "learning_rate": 0.00016371525486442843,
+      "loss": 0.2614,
+      "step": 190
+    },
+    {
+      "epoch": 0.21750951604132682,
+      "grad_norm": 3.094886302947998,
+      "learning_rate": 0.0001575,
+      "loss": 0.2873,
+      "step": 200
+    },
+    {
+      "epoch": 0.21750951604132682,
+      "eval_loss": 0.3247433006763458,
+      "eval_runtime": 22.7847,
+      "eval_samples_per_second": 17.029,
+      "eval_steps_per_second": 4.257,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.701588502151168e+16,
+  "total_flos": 3.59915573477376e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null