Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369705265305bbe998d369666cfb5590cb31ee8f28326eeb447f53a798ee7b5d
+oid sha256:e23e8d10375e2207fbf1bbc471cc4dd3ff0b59d70bc93bcd2d046054c39216dc
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4f2a8732c8853443cc0698a5112b70ee28b9d8af39f2806511b56110829296
+oid sha256:d963881afd4b752e29706ffcfe4f6c5e068865979de7542440b93abe2550b792
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c655c7238c6501babc443017bf43b2162bccf0c3741390eafd9878f0a25d67c0
+oid sha256:8a724174400d58f2a149c83f19493a3a67a295ff38515085ed80a6823fcb2bf7
 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": 3.7725393772125244,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007966540529774946,
+  "best_metric": 3.7503488063812256,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.009958175662218682,
   "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": 8.132,
       "eval_steps_per_second": 4.066,
       "step": 20
+    },
+    {
+      "epoch": 0.008364867556263693,
+      "grad_norm": 35.73342514038086,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 20.6054,
+      "step": 21
+    },
+    {
+      "epoch": 0.00876319458275244,
+      "grad_norm": 39.54722595214844,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 20.2503,
+      "step": 22
+    },
+    {
+      "epoch": 0.009161521609241188,
+      "grad_norm": 34.261375427246094,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 19.7047,
+      "step": 23
+    },
+    {
+      "epoch": 0.009559848635729935,
+      "grad_norm": 32.34653854370117,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 19.2905,
+      "step": 24
+    },
+    {
+      "epoch": 0.009958175662218682,
+      "grad_norm": 38.240150451660156,
+      "learning_rate": 0.0,
+      "loss": 21.5705,
+      "step": 25
+    },
+    {
+      "epoch": 0.009958175662218682,
+      "eval_loss": 3.7503488063812256,
+      "eval_runtime": 130.6765,
+      "eval_samples_per_second": 8.096,
+      "eval_steps_per_second": 4.048,
+      "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": 1421129684090880.0,
+  "total_flos": 1776412105113600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null