Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddba15324ccc0e9b883e810a416ea55793f38fa3ee21cd043b5b0b858b58f861
+oid sha256:42fa21bad2a8a61fd49721576708eef74f11ab8f8a4041ffd060c547f30bc555
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f57c5489d9226ea40ccdb8ef3fb83b8aa848d2c7720f43c3500fdb895e188a3
+oid sha256:4e0a6e89a4149e8a6acf9d1b011a660e793da149422d59cec20671a8f968c3e3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6d05d84134bc054dc7899f24d2f88d3ea9e2a651e736719bc9e968bca1a100
+oid sha256:0cd0f468fa70a1cf7fad818916de3bad4e117e8ec50f05116c03d5cfd88dd0a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8657696843147278,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007209805335255948,
+  "best_metric": 0.8643654584884644,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.009012256669069935,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 5.049,
       "eval_steps_per_second": 2.527,
       "step": 20
+    },
+    {
+      "epoch": 0.007570295602018745,
+      "grad_norm": 0.6700939536094666,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.5649,
+      "step": 21
+    },
+    {
+      "epoch": 0.007930785868781542,
+      "grad_norm": 0.6241040825843811,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.8753,
+      "step": 22
+    },
+    {
+      "epoch": 0.00829127613554434,
+      "grad_norm": 0.6110208034515381,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.9988,
+      "step": 23
+    },
+    {
+      "epoch": 0.008651766402307137,
+      "grad_norm": 0.7366301417350769,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.3314,
+      "step": 24
+    },
+    {
+      "epoch": 0.009012256669069935,
+      "grad_norm": 0.6382246613502502,
+      "learning_rate": 0.0,
+      "loss": 3.0501,
+      "step": 25
+    },
+    {
+      "epoch": 0.009012256669069935,
+      "eval_loss": 0.8643654584884644,
+      "eval_runtime": 231.642,
+      "eval_samples_per_second": 5.047,
+      "eval_steps_per_second": 2.525,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6474278237110272.0,
+  "total_flos": 8103027479150592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null