Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3a80806a563a9e8decbbcba13c4dfef6743516d003ae87ee1fb55ab4ca7037
+oid sha256:30166798f0b89cbcd554b9765e4626732cce8f4fc037268b839bb4c4f6485e4a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c12b4e07d1f0aa4a58f09f73747e4e80f37b3d945241a5bd270008977415f1
+oid sha256:2e7c78eb7a7e769688e8ff1b10be5e82b9ed52e9ad57d1017024dc64e5982a59
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf28eade6cb6d7d7731158c0de04222d71e1eb7eda652ae1faf10ca8fe267a2
+oid sha256:24940c124cae98ef6d559351f02c9609cbfadbed064153f376724b067b976a1b
 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": 1.0627840757369995,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012292562999385371,
+  "best_metric": 1.053037166595459,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.015365703749231715,
   "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": 5.799,
       "eval_steps_per_second": 2.904,
       "step": 20
+    },
+    {
+      "epoch": 0.01290719114935464,
+      "grad_norm": 0.6228127479553223,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3138,
+      "step": 21
+    },
+    {
+      "epoch": 0.013521819299323909,
+      "grad_norm": 0.8131234049797058,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.1545,
+      "step": 22
+    },
+    {
+      "epoch": 0.014136447449293177,
+      "grad_norm": 0.6289592981338501,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.9514,
+      "step": 23
+    },
+    {
+      "epoch": 0.014751075599262446,
+      "grad_norm": 0.542924702167511,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0524,
+      "step": 24
+    },
+    {
+      "epoch": 0.015365703749231715,
+      "grad_norm": 0.6711887717247009,
+      "learning_rate": 0.0,
+      "loss": 0.8151,
+      "step": 25
+    },
+    {
+      "epoch": 0.015365703749231715,
+      "eval_loss": 1.053037166595459,
+      "eval_runtime": 117.9389,
+      "eval_samples_per_second": 5.808,
+      "eval_steps_per_second": 2.908,
+      "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": 5733649169252352.0,
+  "total_flos": 7352017886380032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null