Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7e966525cc1c832d66e1bc5aa0478d8879221ef46793d16301ad12059b8cfe
+oid sha256:49c2f9f382f586ba3e9648887a2f35d0fa0062423127404edf5a86989a19fdd8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96e3779a1770b7dce8fa74387954cab7337ca3f0a279ea02f61d864291def6c
+oid sha256:ba700d6cb80c05c4b5456855b9fd5f3341d919aa9a947ef621014a7344bece59
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4c83c657c7d48ecd59acb6a97ff190841b72a716b62dede7d34500c8317408
+oid sha256:86652856150667552ea7a8a326f68865e1c184e83be848868a259f15eeac73cc
 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": 2.38735032081604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04106776180698152,
+  "best_metric": 2.380300283432007,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.061601642710472276,
   "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": 5.566,
       "eval_steps_per_second": 1.398,
       "step": 20
+    },
+    {
+      "epoch": 0.043121149897330596,
+      "grad_norm": 0.2250877171754837,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.4157,
+      "step": 21
+    },
+    {
+      "epoch": 0.049281314168377825,
+      "grad_norm": 0.2361966371536255,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.4554,
+      "step": 24
+    },
+    {
+      "epoch": 0.0513347022587269,
+      "eval_loss": 2.381042718887329,
+      "eval_runtime": 74.6227,
+      "eval_samples_per_second": 5.494,
+      "eval_steps_per_second": 1.38,
+      "step": 25
+    },
+    {
+      "epoch": 0.055441478439425054,
+      "grad_norm": 0.24761168658733368,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.4013,
+      "step": 27
+    },
+    {
+      "epoch": 0.061601642710472276,
+      "grad_norm": 0.2639633119106293,
+      "learning_rate": 0.0,
+      "loss": 2.4621,
+      "step": 30
+    },
+    {
+      "epoch": 0.061601642710472276,
+      "eval_loss": 2.380300283432007,
+      "eval_runtime": 74.1191,
+      "eval_samples_per_second": 5.532,
+      "eval_steps_per_second": 1.39,
+      "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": 2.949001952152781e+16,
+  "total_flos": 3.690889235713229e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null