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:fbb7da96b8c399ea23665b928d07773720dec486d72458f5713eaea7687fb559
+oid sha256:3653f732fff62e13e87ae36f08a8468a4c153e2db3fba944121ae389cb5e4235
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a835285cb0c2bfc01099fc0e88257d1e2aa628a256ad664929037054b7a839f6
+oid sha256:bfe69573b4f19a065beced3ad1c8eb7a33510c6015548cd8db5c8d23692bae1a
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47923f2e3140f750ef0808c894943bacc68f032253a35935a9d65725e43ff5e4
+oid sha256:a36858e62205052e6c2e38b36a6ab819aac374f0fe9ab73f7512525697488b46
 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": 0.4525754451751709,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008598452278589854,
+  "best_metric": 0.4506242275238037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.010748065348237317,
   "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": 8.834,
       "eval_steps_per_second": 4.417,
       "step": 20
+    },
+    {
+      "epoch": 0.009028374892519347,
+      "grad_norm": 0.6502081155776978,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5306,
+      "step": 21
+    },
+    {
+      "epoch": 0.009458297506448839,
+      "grad_norm": 1.0471283197402954,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5925,
+      "step": 22
+    },
+    {
+      "epoch": 0.009888220120378332,
+      "grad_norm": 1.3133803606033325,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.26,
+      "step": 23
+    },
+    {
+      "epoch": 0.010318142734307825,
+      "grad_norm": 0.8463181853294373,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.421,
+      "step": 24
+    },
+    {
+      "epoch": 0.010748065348237317,
+      "grad_norm": 1.1632798910140991,
+      "learning_rate": 0.0,
+      "loss": 2.0558,
+      "step": 25
+    },
+    {
+      "epoch": 0.010748065348237317,
+      "eval_loss": 0.4506242275238037,
+      "eval_runtime": 111.7477,
+      "eval_samples_per_second": 8.77,
+      "eval_steps_per_second": 4.385,
+      "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": 2799757802078208.0,
+  "total_flos": 3373478663159808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null