Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5913e52e684eef321b3fcf38e3e7386d96729c038e722e7b3b9a7ded0384a4f3
+oid sha256:a25d49f19bf2dc996e269538d282b896cf684992a9dc8259b01b3bd6512c4b31
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817dea761a44bbd12a54ca57b9e171d7d98314838ae80bd56d75f6b514afa505
+oid sha256:53f4ac7c02130ae2529da47a414b5905148f315fdec6a594db1676ee46d862f2
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a203f78def4a971b2e61ff58bd189487b3bedb6e6f11df5f6bf99bbf0bb120aa
+oid sha256:e4eeaec583b8e88d41d4feb1c13c00f1e2fa981140a3d611124b0c6b30258d95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
+oid sha256:200a199971193d5b4ec602093f689606117a65db31ca244b618fc0f0cd969846
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.27697739005088806,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16051364365971107,
+  "best_metric": 0.27326497435569763,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.17834849295523453,
   "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": 9.338,
       "eval_steps_per_second": 2.34,
       "step": 450
+    },
+    {
+      "epoch": 0.16408061351881575,
+      "grad_norm": 0.767898678779602,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 0.4768,
+      "step": 460
+    },
+    {
+      "epoch": 0.16764758337792046,
+      "grad_norm": 0.8965118527412415,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 0.3135,
+      "step": 470
+    },
+    {
+      "epoch": 0.17121455323702514,
+      "grad_norm": 0.7519134283065796,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 0.2856,
+      "step": 480
+    },
+    {
+      "epoch": 0.17478152309612985,
+      "grad_norm": 0.5825276374816895,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 0.2907,
+      "step": 490
+    },
+    {
+      "epoch": 0.17834849295523453,
+      "grad_norm": 0.5771666169166565,
+      "learning_rate": 0.0,
+      "loss": 0.1991,
+      "step": 500
+    },
+    {
+      "epoch": 0.17834849295523453,
+      "eval_loss": 0.27326497435569763,
+      "eval_runtime": 126.8529,
+      "eval_samples_per_second": 9.31,
+      "eval_steps_per_second": 2.333,
+      "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": 1.619766455178363e+17,
+  "total_flos": 1.7989024426544333e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null