Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b194acf948b5e269d7768921a842c9bd9ff3f276e1b2ac08b1ea73ecef35235
+oid sha256:d8c961af73dffb1f4ebebbbd4303aca980ec230176555788e095290ae9c0e8d8
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2295e16e4ac6e303a1cc68b08b32384502fa266abd7b948c233efa1291d9db62
+oid sha256:ea002b327f6f2b14f0351b5345e45fa072a1f4c815b3ed21d1f207a06ddc2316
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026cd28a0a1a57594b37b8060ae84ab05aa73bcf694b398c75f9a329bec2ca9c
+oid sha256:5432b820300d282a8444374d08d8e4807bad06cdbd4da7480a14a6aa7dcb1284
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1645d5960cffb716058498f15a18dead45abc30cdbe88bcf0f6d3a17de954548
+oid sha256:98f920e12d11147a20f040642d9542844d9ecd269825a9052fb669ae55b94f84
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3778539896011353,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05129081894340913,
+  "best_metric": 1.3041934967041016,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.06838775859121217,
   "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": 6.77,
       "eval_steps_per_second": 1.693,
       "step": 150
+    },
+    {
+      "epoch": 0.054710206872969736,
+      "grad_norm": 0.3281489610671997,
+      "learning_rate": 0.00017365331983420376,
+      "loss": 0.8043,
+      "step": 160
+    },
+    {
+      "epoch": 0.05812959480253035,
+      "grad_norm": 0.2923721969127655,
+      "learning_rate": 0.0001685821912422447,
+      "loss": 0.7794,
+      "step": 170
+    },
+    {
+      "epoch": 0.06154898273209095,
+      "grad_norm": 6.542027950286865,
+      "learning_rate": 0.00016318180900789148,
+      "loss": 2.2373,
+      "step": 180
+    },
+    {
+      "epoch": 0.06496837066165156,
+      "grad_norm": 0.3875706195831299,
+      "learning_rate": 0.00015747848325054544,
+      "loss": 1.3301,
+      "step": 190
+    },
+    {
+      "epoch": 0.06838775859121217,
+      "grad_norm": 0.8955979943275452,
+      "learning_rate": 0.0001515,
+      "loss": 0.8364,
+      "step": 200
+    },
+    {
+      "epoch": 0.06838775859121217,
+      "eval_loss": 1.3041934967041016,
+      "eval_runtime": 182.0023,
+      "eval_samples_per_second": 6.769,
+      "eval_steps_per_second": 1.692,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.998218189144064e+16,
+  "total_flos": 1.0648421438324736e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null