Training in progress, step 29, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec4e3550ee90df7336acfb21a3f7314aae6d42b9019ea37964bace177fefee1
+oid sha256:c499fc89305a6126ab60af3675c397a65294b885e208a948144444985ea5cb8f
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d295f29106d8bea2be7cfa211cc161f19c1e0e45a310f4e3e0108c564eb5678d
+oid sha256:8b020efdbf21752dc02a222c082800e5d15c8a1a7da713edd4a53e5cdfcc1fc3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c74f3a969e3e99a8c5ae50e05f61920bef9fcea2e1c0315750a5de6d8b69a110
+oid sha256:a5b086a9459260447ff73f60bbee60d7d63b748f4d5046667e281ece59ad58e1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97642eeb7d097f0cf4672dfbf894dd6f5fb726db54bebd0f82d8df10df4f99d7
+oid sha256:7f210bf8d8d81e47d921c65b38473b29a5fa6484e4d9ba7342dc471b813d2b45
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f33ad77e1ac17fe16159823c7daf7e8a3273275b50761ee274267967568aa01
+oid sha256:96a9ab6c518da9d9e9809ed7d3da1de2fbba16823d15c3593bd001c58cfa1da4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c358afaa27e49311ba3af0bc45fb097f71b7e94dd7d620cdb9c2ef0a37a7463
+oid sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.6315789473684212,
+  "epoch": 3.0526315789473686,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 29,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,34 @@
       "eval_samples_per_second": 38.868,
       "eval_steps_per_second": 4.858,
       "step": 25
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 1.3477564710088098e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": NaN,
+      "learning_rate": 3.380821129028489e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 29
     }
   ],
   "logging_steps": 1,
@@ -221,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 3.261953530176471e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null