Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588ca0c83e24735f73595ee82f497df45bec56ce832ced394c7c4770938e245e
+oid sha256:5027350282cb0f67eb08882ccff171f8e2bca8131922776a49cec4744ccf2159
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c61019809fca5673ba8052818cb0abcdb3db3eec75b7ad3810d1a4704ee642b
+oid sha256:9806136d05e881ff1da692efbce1b5bafc1a87606533574c8ef134fdc51a7469
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 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": 2.372363805770874,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003562078116373092,
+  "best_metric": 2.349764585494995,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0004452597645466365,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 9.116,
       "eval_steps_per_second": 4.559,
       "step": 20
+    },
+    {
+      "epoch": 0.00037401820221917467,
+      "grad_norm": 7.219645023345947,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.2832,
+      "step": 21
+    },
+    {
+      "epoch": 0.00042744937396477104,
+      "grad_norm": 5.5584635734558105,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.1534,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004452597645466365,
+      "eval_loss": 2.349764585494995,
+      "eval_runtime": 653.0315,
+      "eval_samples_per_second": 9.052,
+      "eval_steps_per_second": 4.527,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -112,12 +134,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 90119287603200.0,
+  "total_flos": 112649109504000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null