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:d2e0847bfeba50611d58cb06a549c7220c36f50d2e189f002a1506ec84dc9577
+oid sha256:245f8bb132e3acc13cd825ae2067e1dafa3f6edc5c9029640952148759a17f63
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2292ecca69d99de4be552ad46729fe3bd5d089fe54cba7608a69f9a585dbcf
+oid sha256:bffa4b8350ad8632cd131be2623a5bf8692231982b9499f9ab61dae5ec0470ba
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1145b8f97fc5aa288dbced0858b2e3a89f8223130b2f24ae70f7b6014547dca4
+oid sha256:ddc73d70bf4c77204e2b51cd54a33381be8c386e6258639ef1bfa347b23ca7cc
 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": 0.6332871913909912,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09950248756218906,
+  "best_metric": 0.6260796785354614,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.14925373134328357,
   "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": 28.185,
       "eval_steps_per_second": 7.129,
       "step": 20
+    },
+    {
+      "epoch": 0.1044776119402985,
+      "grad_norm": 0.4247596859931946,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.6587,
+      "step": 21
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 0.4106825590133667,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.6146,
+      "step": 24
+    },
+    {
+      "epoch": 0.12437810945273632,
+      "eval_loss": 0.6272332668304443,
+      "eval_runtime": 6.0465,
+      "eval_samples_per_second": 28.116,
+      "eval_steps_per_second": 7.112,
+      "step": 25
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 0.4225139617919922,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.6011,
+      "step": 27
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 0.43210238218307495,
+      "learning_rate": 0.0,
+      "loss": 0.6208,
+      "step": 30
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "eval_loss": 0.6260796785354614,
+      "eval_runtime": 6.0498,
+      "eval_samples_per_second": 28.1,
+      "eval_steps_per_second": 7.108,
+      "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": 4071458076622848.0,
+  "total_flos": 6082054657671168.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null