Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbe050bb03dd3e247292f5fa917523247719038cb768c2e1376a00a0239501e
+oid sha256:35174b230eb1d73d76ca43fecef393683ee08f01677800568bbb2225d1b15594
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd320be88a1b4f2bb13c95f1969c076a0091f4df50f65918746ad6318ed6a5d2
+oid sha256:6cd413933abaeda6756e233a5c02c0dd33035769b6d95080247c5315795610ff
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a45a4fedf82801e1f01bdbc49ba39d199f480f4311270c10a86b77f6f151c925
+oid sha256:376f4b6ffae13c4d334295aedab19a3a67510ca171c2f6b177538d1fcc906176
 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": 1.9506233930587769,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01422475106685633,
+  "best_metric": 1.940571904182434,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.017780938833570414,
   "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": 4.241,
       "eval_steps_per_second": 2.128,
       "step": 20
+    },
+    {
+      "epoch": 0.014935988620199146,
+      "grad_norm": 2.624873638153076,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3516,
+      "step": 21
+    },
+    {
+      "epoch": 0.015647226173541962,
+      "grad_norm": 2.866389513015747,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6004,
+      "step": 22
+    },
+    {
+      "epoch": 0.016358463726884778,
+      "grad_norm": 3.0391550064086914,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.0461,
+      "step": 23
+    },
+    {
+      "epoch": 0.017069701280227598,
+      "grad_norm": 1.268661618232727,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0511,
+      "step": 24
+    },
+    {
+      "epoch": 0.017780938833570414,
+      "grad_norm": 3.030973434448242,
+      "learning_rate": 0.0,
+      "loss": 1.9056,
+      "step": 25
+    },
+    {
+      "epoch": 0.017780938833570414,
+      "eval_loss": 1.940571904182434,
+      "eval_runtime": 67.9672,
+      "eval_samples_per_second": 4.37,
+      "eval_steps_per_second": 2.192,
+      "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": 122427475230720.0,
+  "total_flos": 149138924371968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null