Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2c534f2f9333b0ed53f9ceedaa3005e9aec316289b0bb8c685dd50de111248
+oid sha256:20cf55fdc46f2866be663104a26121ff3fc631c9bc9d8ba48512a5acbdd0010f
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df993674050f894dab63dfb4a8acc4717450d6ae8ed8313687960a3b49af659
+oid sha256:22315d5586f04bb8428b3aa0e813b5727d68f83a3a444e407cb958c3303bc033
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22adc71b0291bf50d9a06af81163a3147a99a13484e21e37d4824565b981ee99
+oid sha256:c808dcc2e08df54dbd5d43e478314673996db5b261c45446e507b7582ff0e28e
 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": 1.4639239311218262,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0032512395350727465,
+  "best_metric": 1.445395827293396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004064049418840933,
   "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": 4.768,
       "eval_steps_per_second": 2.385,
       "step": 20
+    },
+    {
+      "epoch": 0.003413801511826384,
+      "grad_norm": 2.345309019088745,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 5.7032,
+      "step": 21
+    },
+    {
+      "epoch": 0.003576363488580021,
+      "grad_norm": 2.150189161300659,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.6857,
+      "step": 22
+    },
+    {
+      "epoch": 0.0037389254653336585,
+      "grad_norm": 2.1052958965301514,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.8889,
+      "step": 23
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 2.2360198497772217,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.5735,
+      "step": 24
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "grad_norm": 3.2359986305236816,
+      "learning_rate": 0.0,
+      "loss": 5.897,
+      "step": 25
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "eval_loss": 1.445395827293396,
+      "eval_runtime": 540.7082,
+      "eval_samples_per_second": 4.792,
+      "eval_steps_per_second": 2.397,
+      "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": 9961007292088320.0,
+  "total_flos": 1.278459991031808e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null