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:e6b281a001d697e83e03126cb45e7934d40bd435f43ba97ec17741bdc7df8ea7
+oid sha256:1f847ff396795e2b1eaebf1da5e3bca69f639c09b11ed8c9dbacadd0357cb2b6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4944cb9d7184381d6fb83cb7a9b948ecb857a9d20ae71c8714e3625decc0d3
+oid sha256:b9c55dbc3e9688451e955a2f1a964b948e9bcfd3c1283941a5fab8872bcad0a4
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eaa896fd95a61ed8c30eed7dbb62c65a8ca1fd80550d35ac9127e458a83ffe1
+oid sha256:9c7223db00e5df7bc27489ac3455dd6cca47006f9e81ae72d49a40c5505f5267
 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": 0.8091033101081848,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0032512395350727465,
+  "best_metric": 0.8036689162254333,
+  "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": 7.04,
       "eval_steps_per_second": 3.521,
       "step": 20
+    },
+    {
+      "epoch": 0.003413801511826384,
+      "grad_norm": 2.1230952739715576,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.4785,
+      "step": 21
+    },
+    {
+      "epoch": 0.003576363488580021,
+      "grad_norm": 2.285691976547241,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.4729,
+      "step": 22
+    },
+    {
+      "epoch": 0.0037389254653336585,
+      "grad_norm": 1.9919122457504272,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.3723,
+      "step": 23
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 1.6255426406860352,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.4557,
+      "step": 24
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "grad_norm": 2.079230308532715,
+      "learning_rate": 0.0,
+      "loss": 3.5221,
+      "step": 25
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "eval_loss": 0.8036689162254333,
+      "eval_runtime": 374.3428,
+      "eval_samples_per_second": 6.921,
+      "eval_steps_per_second": 3.462,
+      "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": 3338902928621568.0,
+  "total_flos": 4153269496578048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null