Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937a6f9ed854ac5346439d75fbfa50bcf15e3e51b49c97902d90c9b3717f4cc3
+oid sha256:6535969eea98cb29614054d885bd492b50b357cd1b489a666e37ba9084ba3e05
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c7b83b7ddae2a91917233d74634eff4ace4e74fddd7b4c832c559e60ddd2f3
+oid sha256:f1d305ffc9106a64c2bdf734c3b0c827a11d9393cc1f02d5d865de875abebce8
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc92e301fbaafcc2948b746381205b7802002ef36f94213e5f939ff71a55bd8
+oid sha256:0605594bde2f8468c4639d0a7dc6c86249c33b3ad2186b79d3154bcb254910d7
 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": 0.1587245762348175,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.014202023788389846,
+  "best_metric": 0.15554063022136688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.017752529735487306,
   "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": 3.364,
       "eval_steps_per_second": 1.685,
       "step": 20
+    },
+    {
+      "epoch": 0.014912124977809338,
+      "grad_norm": 0.29156962037086487,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.1607,
+      "step": 21
+    },
+    {
+      "epoch": 0.015622226167228831,
+      "grad_norm": 0.32396185398101807,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1079,
+      "step": 22
+    },
+    {
+      "epoch": 0.016332327356648323,
+      "grad_norm": 0.23460744321346283,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1288,
+      "step": 23
+    },
+    {
+      "epoch": 0.017042428546067814,
+      "grad_norm": 0.2599011957645416,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.1264,
+      "step": 24
+    },
+    {
+      "epoch": 0.017752529735487306,
+      "grad_norm": 0.21870732307434082,
+      "learning_rate": 0.0,
+      "loss": 0.1371,
+      "step": 25
+    },
+    {
+      "epoch": 0.017752529735487306,
+      "eval_loss": 0.15554063022136688,
+      "eval_runtime": 175.7038,
+      "eval_samples_per_second": 3.375,
+      "eval_steps_per_second": 1.69,
+      "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": 7234687501074432.0,
+  "total_flos": 8876602394935296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null