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:dceaadd3cb4635a5d9ad20f0f5603655b5d5293c157ede9c8c70a91c6f3c0d04
+oid sha256:fd94f60dcb41e1f6070a83888d11c52cfddc191245737cde12e73cd6727c9837
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf4ea63412ba4c1b4edc0e55318f75a1dcc65264952a892632405abbb0ef9ec
+oid sha256:09cc486aace91239e7341f1900f8dd0aca1d0d22ffc4b3e020e572ac3389f6ce
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbb9550bb79cf5c2c5113cd33018c72667dd17516224dda2d4060d0662bf731
+oid sha256:4a92b72791c1f7c05319fe043b1fba83957f96bc746c107d2f565f8038057032
 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": 0.4381260871887207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.029607698001480384,
+  "best_metric": 0.43646159768104553,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.037009622501850484,
   "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": 18.83,
       "eval_steps_per_second": 9.448,
       "step": 20
+    },
+    {
+      "epoch": 0.031088082901554404,
+      "grad_norm": 0.6623015403747559,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8741,
+      "step": 21
+    },
+    {
+      "epoch": 0.03256846780162842,
+      "grad_norm": 0.729452908039093,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.148,
+      "step": 22
+    },
+    {
+      "epoch": 0.034048852701702444,
+      "grad_norm": 0.7802658081054688,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.0453,
+      "step": 23
+    },
+    {
+      "epoch": 0.03552923760177646,
+      "grad_norm": 0.8557211756706238,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.3438,
+      "step": 24
+    },
+    {
+      "epoch": 0.037009622501850484,
+      "grad_norm": 1.1988826990127563,
+      "learning_rate": 0.0,
+      "loss": 3.0318,
+      "step": 25
+    },
+    {
+      "epoch": 0.037009622501850484,
+      "eval_loss": 0.43646159768104553,
+      "eval_runtime": 16.721,
+      "eval_samples_per_second": 17.044,
+      "eval_steps_per_second": 8.552,
+      "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": 897469655285760.0,
+  "total_flos": 1121837069107200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null