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:eff6883a54cbd26a7ab7afacc333c3f68a6d06374ee4a2b752db35ac2fef4824
+oid sha256:7b2cd85dcc562f8e5189683a31964ddc0a098de1f35dbf0037cc9520a1f04d3f
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb19f3315c211a5ed1a185de1826c6307ad8e26ddb9dd335338ce9213631bdb
+oid sha256:a3ef0f5dba4b14a5c58de9c1a89634be2f9038f15013c94abbbfe279c52f2a27
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38869f0abd5e8d7e0db7b37371f8fa96dc532623ec588eb787b46ae8af45f0de
+oid sha256:0793e2b8b2b5b43558736afef8027f4b28c0a8bb85c968a2626361c78dc2daae
 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": 3.4692418575286865,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007985785302162151,
+  "best_metric": 3.465536117553711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.000998223162770269,
   "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": 8.333,
       "eval_steps_per_second": 4.167,
       "step": 20
+    },
+    {
+      "epoch": 0.0008385074567270259,
+      "grad_norm": 1.018371820449829,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.1866,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008784363832378367,
+      "grad_norm": 1.0292870998382568,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.3684,
+      "step": 22
+    },
+    {
+      "epoch": 0.0009183653097486474,
+      "grad_norm": 1.2272744178771973,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.1931,
+      "step": 23
+    },
+    {
+      "epoch": 0.0009582942362594581,
+      "grad_norm": 0.924740731716156,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.3339,
+      "step": 24
+    },
+    {
+      "epoch": 0.000998223162770269,
+      "grad_norm": 0.9980890154838562,
+      "learning_rate": 0.0,
+      "loss": 3.5771,
+      "step": 25
+    },
+    {
+      "epoch": 0.000998223162770269,
+      "eval_loss": 3.465536117553711,
+      "eval_runtime": 1247.2404,
+      "eval_samples_per_second": 8.455,
+      "eval_steps_per_second": 4.228,
+      "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": 991192531599360.0,
+  "total_flos": 1235931428290560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null