Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea04c62f86354903725e778768a676c9e8755773730a2112c47696a6dbdae13
+oid sha256:9215d8b78658375c795fed778633ad91d45671ba02c04c18a9eb5c8be5b061f6
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e44db9ba9879524905b188daaee170f5b56ecf9052494cda70cb5c944f9ae0
+oid sha256:0f792a3acbcee0554775d1cb5b49a21def1a0697ba696e5f71232258efae550a
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca669e357aa0e15c87e40a1da0e0ab9476977a64e76ef375c8f5d113bdeafa4
+oid sha256:5f0ea74a9a227ee08098d7ff3550c975c32a198c9f884426b3e881fa54ff49c7
 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": 1.9039485454559326,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004110574452779776,
+  "best_metric": 1.8126800060272217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0051382180659747196,
   "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": 8.505,
       "eval_steps_per_second": 4.254,
       "step": 20
+    },
+    {
+      "epoch": 0.0043161031754187645,
+      "grad_norm": 17.467388153076172,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.9072,
+      "step": 21
+    },
+    {
+      "epoch": 0.004521631898057754,
+      "grad_norm": 19.71384048461914,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.7993,
+      "step": 22
+    },
+    {
+      "epoch": 0.0047271606206967425,
+      "grad_norm": 18.68255043029785,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 8.0685,
+      "step": 23
+    },
+    {
+      "epoch": 0.004932689343335731,
+      "grad_norm": 15.721320152282715,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 6.9365,
+      "step": 24
+    },
+    {
+      "epoch": 0.0051382180659747196,
+      "grad_norm": 16.148300170898438,
+      "learning_rate": 0.0,
+      "loss": 7.5588,
+      "step": 25
+    },
+    {
+      "epoch": 0.0051382180659747196,
+      "eval_loss": 1.8126800060272217,
+      "eval_runtime": 240.9238,
+      "eval_samples_per_second": 8.505,
+      "eval_steps_per_second": 4.254,
+      "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": 2611797295104000.0,
+  "total_flos": 3264746618880000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null