Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ef27f6a93931f26d99c56faeff9bb6b958134c4dbfbd81eb30b29f0337d1b7
+oid sha256:314cf5859b97991464dd0a8bd5a4767b67035514abf19d66c856e993ce8a454b
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9314638698c4af844ad8a76f67b3a566a1b5d229d405db9d0a7fc45b4a745539
+oid sha256:1c7a4f3fd4f705d9de1e99e1250435b30e31ea7e84c6923c5ff67031e7a56783
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
+oid sha256:983baa830df615f6f61b75af5f4b0cf7a694a7d02c96696d0f4804987ec72e0d
 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": 11.060052871704102,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003526108630591637,
+  "best_metric": 11.059524536132812,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00044076357882395464,
   "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": 152.99,
       "eval_steps_per_second": 76.495,
       "step": 20
+    },
+    {
+      "epoch": 0.0003702414062121219,
+      "grad_norm": 1.2673594951629639,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.2516,
+      "step": 21
+    },
+    {
+      "epoch": 0.00038787194936508007,
+      "grad_norm": 1.0727105140686035,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.2384,
+      "step": 22
+    },
+    {
+      "epoch": 0.00040550249251803826,
+      "grad_norm": 1.2554271221160889,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.2502,
+      "step": 23
+    },
+    {
+      "epoch": 0.00042313303567099645,
+      "grad_norm": 1.1639366149902344,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.2355,
+      "step": 24
+    },
+    {
+      "epoch": 0.00044076357882395464,
+      "grad_norm": 1.2954105138778687,
+      "learning_rate": 0.0,
+      "loss": 44.2127,
+      "step": 25
+    },
+    {
+      "epoch": 0.00044076357882395464,
+      "eval_loss": 11.059524536132812,
+      "eval_runtime": 156.1425,
+      "eval_samples_per_second": 152.95,
+      "eval_steps_per_second": 76.475,
+      "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": 29884416000.0,
+  "total_flos": 37355520000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null