Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33acb1d6c50fefa22243a8eef262650d8d92602708a320e06a67a922b9da403e
+oid sha256:d60bb067f969a0753513d40ed3677c14b7fc1c80e7d0fd311742234dd57fda9c
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa87a3572fdf661d7fa7e0cddba214f25e757325e93af1e6d455aeef606d3563
+oid sha256:0ea972ffb1ec6807452543ca6674465f2a3e40c618362116117e3373c1afda3d
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4599e2b662b721751b8f29197346da4bcf5ecef4f1b957d258185032c4290ecd
+oid sha256:9f50c96ff8282c5199f37410c9a08efe89e22b9f1edbe07fcb2418ce7455cd4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.222978949546814,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.10413051023950018,
+  "best_metric": 1.2226279973983765,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.11570056693277797,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 23.854,
       "eval_steps_per_second": 5.964,
       "step": 450
+    },
+    {
+      "epoch": 0.10644452157815573,
+      "grad_norm": 0.2074027806520462,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 1.2559,
+      "step": 460
+    },
+    {
+      "epoch": 0.1087585329168113,
+      "grad_norm": 0.20819057524204254,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 1.2212,
+      "step": 470
+    },
+    {
+      "epoch": 0.11107254425546685,
+      "grad_norm": 0.1963956654071808,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 1.2323,
+      "step": 480
+    },
+    {
+      "epoch": 0.11338655559412242,
+      "grad_norm": 0.1982182115316391,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 1.2442,
+      "step": 490
+    },
+    {
+      "epoch": 0.11570056693277797,
+      "grad_norm": 0.3441769778728485,
+      "learning_rate": 0.0,
+      "loss": 1.2379,
+      "step": 500
+    },
+    {
+      "epoch": 0.11570056693277797,
+      "eval_loss": 1.2226279973983765,
+      "eval_runtime": 76.5277,
+      "eval_samples_per_second": 23.782,
+      "eval_steps_per_second": 5.946,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5861722136838144e+16,
+  "total_flos": 3.987393326402765e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null