Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720094059549fcf949f590d63d51c3664a9b27559b01b45d98a2a451b713e7c7
+oid sha256:08387f8600697465ba9a491255fc6ac96d723384a7765957397f847eb21cc26f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee37c344a1c757ece789b2532917ecab0a27d29c67268d0e475ad9e02b03d86
+oid sha256:3a90035845e92a04b624f9d8e89ea0ea156c9d13d2f83650c5d38069a9c23869
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01a5c827ffda3734ead49c3fac10a6966561dc947773d69661f4fddcf946e85
+oid sha256:2cccbbe8b3a7f210f134f20451255943ad2a2fc7b83f11c3f61d2fc33985bfd4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598e3cca82cf9c1d20ff12564edf0a2d57e8fb0ec3df8e4997e33ba16a140a35
+oid sha256:ebe0439324d17dc7b562b80e24e173a3a219afc7889095d3d6b290fa9cb1697e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3abe99e765f80e86206de8a2d4bbf9a5ff39ae7618ce3d858cc297ce4928369
+oid sha256:5f614c7b6eb2d3ec336cedccb565b4ee318fd85a0dee96e5aba91bc0f0e70173
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a80631d710555d79f1e35b0a8704cea10b2d6cc449348828a8c32eee26eeddf
+oid sha256:3bbee8346ba18531760fa9aaff3a4f6c1f08d06972b4eec1b3624257a2bd8738
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92816605af701c84337fe63ad1d8f294cf7d1f5043471d816c8da7acefc9ad8
+oid sha256:f590ad1ae5c8e7b4f203a10a7ab525a3ee9074e4623aa7b9c3bf0ec215582052
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.342057228088379,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.8181818181818183,
+  "epoch": 2.0,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,41 @@
       "eval_samples_per_second": 1953.256,
       "eval_steps_per_second": 78.13,
       "step": 50
+    },
+    {
+      "epoch": 1.8545454545454545,
+      "grad_norm": 0.16553938388824463,
+      "learning_rate": 5.810745609252165e-06,
+      "loss": 10.6196,
+      "step": 51
+    },
+    {
+      "epoch": 1.8909090909090909,
+      "grad_norm": 0.179793581366539,
+      "learning_rate": 3.2778598899291465e-06,
+      "loss": 10.0928,
+      "step": 52
+    },
+    {
+      "epoch": 1.9272727272727272,
+      "grad_norm": 0.17320050299167633,
+      "learning_rate": 1.4597896887644456e-06,
+      "loss": 10.5475,
+      "step": 53
+    },
+    {
+      "epoch": 1.9636363636363636,
+      "grad_norm": 0.2175627201795578,
+      "learning_rate": 3.653924610263703e-07,
+      "loss": 10.4599,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.26624709367752075,
+      "learning_rate": 0.0,
+      "loss": 15.3055,
+      "step": 55
     }
   ],
   "logging_steps": 1,
@@ -404,12 +439,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 22228539801600.0,
+  "total_flos": 24451393781760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null