Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e2a3fa46cd966ca0a2d03c02f0d3ee14e24b17711aeb2bc5844e0538f06611
+oid sha256:9294ed142a03823d3740ec17eb902a49bef63d5bc8f8ece32c33a0601ef53e4e
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2f4eeb7be5ab17b69e7a1c8d81dcca6af848c23da2f6e5aa62fac354e745b9
+oid sha256:54873ad9a5c352ffd5b562d5f75fbaf0723f5af468aae64ef008839b6d38ddc4
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed6425c84b12a66a4a948fa766ed8b32ee8ebbbcbf40a048a0a7e4935ce99a6a
+oid sha256:24e0f85f9b5b3d8cae412cb7a9da540bb0735334c77e4e9b3b840ac6b14dc7e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0118319988250732,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013748066678123389,
+  "best_metric": 0.9577704668045044,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.020622100017185084,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.361,
       "eval_steps_per_second": 1.342,
       "step": 20
+    },
+    {
+      "epoch": 0.014435470012029558,
+      "grad_norm": 0.9361578822135925,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.867,
+      "step": 21
+    },
+    {
+      "epoch": 0.016497680013748066,
+      "grad_norm": 0.9102057814598083,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.9175,
+      "step": 24
+    },
+    {
+      "epoch": 0.017185083347654236,
+      "eval_loss": 0.9690696001052856,
+      "eval_runtime": 228.6776,
+      "eval_samples_per_second": 5.361,
+      "eval_steps_per_second": 1.343,
+      "step": 25
+    },
+    {
+      "epoch": 0.018559890015466575,
+      "grad_norm": 1.1423685550689697,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.9455,
+      "step": 27
+    },
+    {
+      "epoch": 0.020622100017185084,
+      "grad_norm": 1.8876031637191772,
+      "learning_rate": 0.0,
+      "loss": 1.0372,
+      "step": 30
+    },
+    {
+      "epoch": 0.020622100017185084,
+      "eval_loss": 0.9577704668045044,
+      "eval_runtime": 228.8671,
+      "eval_samples_per_second": 5.357,
+      "eval_steps_per_second": 1.341,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.647225084051456e+16,
+  "total_flos": 2.470837626077184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null