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:b613a20d34db6c41f47f51d13d00f843c456db9353d4414d09862ca4cb297214
+oid sha256:35295560243876b1ea17b977a61e54a375131a697eadf77a2e0b41785c194515
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fffd955c7ebdc944aa9151adc47c6aee0634d2fcf79159963b63c77f158fc34
+oid sha256:c64d14e7384e40b200cf02c2ffd56012b44aabc0cb7cbc74e2d175cdf1db4477
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.3312912583351135,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00565171317555634,
+  "best_metric": 0.32584547996520996,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.007064641469445425,
   "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": 3.306,
       "eval_steps_per_second": 1.653,
       "step": 20
+    },
+    {
+      "epoch": 0.0059342988343341575,
+      "grad_norm": 2.3116421699523926,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3819,
+      "step": 21
+    },
+    {
+      "epoch": 0.006216884493111975,
+      "grad_norm": 2.419229507446289,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3341,
+      "step": 22
+    },
+    {
+      "epoch": 0.006499470151889792,
+      "grad_norm": 2.5362722873687744,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.368,
+      "step": 23
+    },
+    {
+      "epoch": 0.006782055810667609,
+      "grad_norm": 2.0525970458984375,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.037,
+      "step": 24
+    },
+    {
+      "epoch": 0.007064641469445425,
+      "grad_norm": 2.673909902572632,
+      "learning_rate": 0.0,
+      "loss": 1.3617,
+      "step": 25
+    },
+    {
+      "epoch": 0.007064641469445425,
+      "eval_loss": 0.32584547996520996,
+      "eval_runtime": 449.8115,
+      "eval_samples_per_second": 3.312,
+      "eval_steps_per_second": 1.656,
+      "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": 7010687196856320.0,
+  "total_flos": 8763358996070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null