Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189beaf6681e6d167f21a3a98f0dc7706adcbfe55b9863e00513984df19635d9
+oid sha256:42bdf7a12daee72631644ff26e7c9f80bbf2ff91189adeb79844f41ec3b3a0de
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1746a0d8cbd16bd3e6cbf655cff4dd390682cb0ea8605c3478fee85a7e0e94
+oid sha256:1dd720e9bd3c6b76823b903b091b8513f63bb3e34dff5623eb6c72cf14934888
 size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf841e914f4af7cd797b78cf530260f06ddfcee84a29b6949d8e836b74c7ebd
+oid sha256:912d3b1d35846784f3679bfe983446d30830056bb9c64fff6ed2d9239f2efee7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd47ab20420ef0e1aa00f2819f474325b5901ebc7d45e94590bc3f5c403b9641
+oid sha256:f2d1d3e656c776bd4cb00d51e16dbc3c67347908a818c2aee478de24ffb13283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.838295578956604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1600",
-  "epoch": 1.937046004842615,
+  "best_metric": 0.8344256281852722,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1800",
+  "epoch": 2.179176755447942,
   "eval_steps": 200,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,42 @@
       "eval_samples_per_second": 64.248,
       "eval_steps_per_second": 16.062,
       "step": 1600
+    },
+    {
+      "epoch": 1.9975786924939467,
+      "grad_norm": 0.8213570713996887,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.691,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0581113801452786,
+      "grad_norm": 0.8155060410499573,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.803,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1186440677966103,
+      "grad_norm": 0.870134711265564,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.8079,
+      "step": 1750
+    },
+    {
+      "epoch": 2.179176755447942,
+      "grad_norm": 0.7964152097702026,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.8172,
+      "step": 1800
+    },
+    {
+      "epoch": 2.179176755447942,
+      "eval_loss": 0.8344256281852722,
+      "eval_runtime": 10.8338,
+      "eval_samples_per_second": 64.244,
+      "eval_steps_per_second": 16.061,
+      "step": 1800
     }
   ],
   "logging_steps": 50,
@@ -331,7 +367,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.06845728210944e+16,
+  "total_flos": 3.446460309307392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null