Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fcd0c26e77ca64dc4c931a0bb512b8291dcb30e2f73a5c6beae64862e5da1c
+oid sha256:d590de7f58f586a410e01a95b72b3c7847a432ae56a447c23b7d77357247709d
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6f126d97a69a4fea24d075862c914bf51b76bb888427f5a3e8768fa5d6933b
+oid sha256:02c6436fa2ab683d908c820e2392344b4dacb64100e19bf529f2252848e8b70b
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a4a0024556e1b863a457f3632c7a699f1e182e747c1be3fc9aaf54cae8b54d
+oid sha256:6e70bc91a0683ac5fcfb898099615306e491eb4ab424ab7a6e6d834c1c8ccb01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9821b687b0301a05cac9bd37b28a5cb1ef278a0580c58589f7a45a55534bddb
+oid sha256:68bcbc5d331080b541bdffea9f92896fc830fbbca1b10945d8446fdc72f5b07e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5498733520507812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.6507592190889371,
+  "best_metric": 1.5005075931549072,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.8676789587852495,
   "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": 41.853,
       "eval_steps_per_second": 10.677,
       "step": 150
+    },
+    {
+      "epoch": 0.6941431670281996,
+      "grad_norm": 0.42309829592704773,
+      "learning_rate": 6.880051902916351e-05,
+      "loss": 1.5078,
+      "step": 160
+    },
+    {
+      "epoch": 0.737527114967462,
+      "grad_norm": 0.4995267391204834,
+      "learning_rate": 5.25355867597608e-05,
+      "loss": 1.4928,
+      "step": 170
+    },
+    {
+      "epoch": 0.7809110629067245,
+      "grad_norm": 0.5781512260437012,
+      "learning_rate": 3.778713645853078e-05,
+      "loss": 1.4352,
+      "step": 180
+    },
+    {
+      "epoch": 0.824295010845987,
+      "grad_norm": 0.728786289691925,
+      "learning_rate": 2.4998366758019425e-05,
+      "loss": 1.4567,
+      "step": 190
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "grad_norm": 2.4118869304656982,
+      "learning_rate": 1.4553586865461783e-05,
+      "loss": 1.8346,
+      "step": 200
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "eval_loss": 1.5005075931549072,
+      "eval_runtime": 2.4042,
+      "eval_samples_per_second": 40.762,
+      "eval_steps_per_second": 10.398,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1395241156608000.0,
+  "total_flos": 1876062724423680.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null