Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219f676a40b7e990c5662752eeb5696925fd78711f4f7c0826ce865ac47355c7
+oid sha256:4c7f407c22ae90bb0f2fa6b6a245a86cce4a8bc68ecf3e1c4ce95d0c961481b2
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb07025926723cf2db99ec825cf14ab94a60c229822e96e2b163cff74e6b94ca
+oid sha256:08446e11c9cc72d51281813abea3c470b4fc3a145b6e018ef0ae38a6b6df6595
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a226003836b3053b591eb46f0c65263b56bd2c76b812173045fce13770ca9942
+oid sha256:c13d070f5b77337df42e7d76c936c344d546e29db18bebee3d3b1424fe19a7fd
 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": 1.5813344717025757,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.018570102135561744,
+  "best_metric": 1.5639779567718506,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.027855153203342618,
   "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": 6.441,
       "eval_steps_per_second": 1.612,
       "step": 20
+    },
+    {
+      "epoch": 0.019498607242339833,
+      "grad_norm": 1.3178768157958984,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.1027,
+      "step": 21
+    },
+    {
+      "epoch": 0.022284122562674095,
+      "grad_norm": 1.5071885585784912,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.6605,
+      "step": 24
+    },
+    {
+      "epoch": 0.02321262766945218,
+      "eval_loss": 1.5662510395050049,
+      "eval_runtime": 140.3405,
+      "eval_samples_per_second": 6.463,
+      "eval_steps_per_second": 1.617,
+      "step": 25
+    },
+    {
+      "epoch": 0.025069637883008356,
+      "grad_norm": 1.5770764350891113,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.3939,
+      "step": 27
+    },
+    {
+      "epoch": 0.027855153203342618,
+      "grad_norm": 1.4045207500457764,
+      "learning_rate": 0.0,
+      "loss": 6.7173,
+      "step": 30
+    },
+    {
+      "epoch": 0.027855153203342618,
+      "eval_loss": 1.5639779567718506,
+      "eval_runtime": 140.0399,
+      "eval_samples_per_second": 6.477,
+      "eval_steps_per_second": 1.621,
+      "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": 2.28688285138944e+16,
+  "total_flos": 3.43032427708416e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null