Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2bebe5e76ef5107d3ff0b01c7da56755410a477c48b21fa97f2fdd88cc1c8c
+oid sha256:f82d94706990940acaa9c506baa4904d5a08769e5b6b59ab06c7f3dbaa3cd491
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d20e7667a3124ac7080dfca2089ef25a271d60e1186587095a2ea4edc85c0a
+oid sha256:eeadbbe5ad971766a8e590e649fdf26bd738787e11ce06380762221bd3a4fa3f
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5a71f85b9114cd14ba8af960a46ef128aa17617f8a68ea324dbe570a75123f
+oid sha256:7431b5c49493e7b14b5469a1aaaf6bceb2f0f8370e90470c84f2c14a9669c9dd
 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": 0.570388674736023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.049782202862476664,
+  "best_metric": 0.5671837329864502,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06222775357809583,
   "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": 2.481,
       "eval_steps_per_second": 1.241,
       "step": 20
+    },
+    {
+      "epoch": 0.0522713130056005,
+      "grad_norm": 0.6040462255477905,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6094,
+      "step": 21
+    },
+    {
+      "epoch": 0.054760423148724334,
+      "grad_norm": 0.5361494421958923,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6016,
+      "step": 22
+    },
+    {
+      "epoch": 0.05724953329184816,
+      "grad_norm": 0.562869668006897,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5493,
+      "step": 23
+    },
+    {
+      "epoch": 0.059738643434972,
+      "grad_norm": 0.5528750419616699,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.516,
+      "step": 24
+    },
+    {
+      "epoch": 0.06222775357809583,
+      "grad_norm": 0.5297385454177856,
+      "learning_rate": 0.0,
+      "loss": 0.5296,
+      "step": 25
+    },
+    {
+      "epoch": 0.06222775357809583,
+      "eval_loss": 0.5671837329864502,
+      "eval_runtime": 72.091,
+      "eval_samples_per_second": 2.358,
+      "eval_steps_per_second": 1.179,
+      "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": 2000389322833920.0,
+  "total_flos": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null