Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4d2ae17a4923ca7476bf79d7aa0742fad4969cb144279f3f15d4706e444e73
+oid sha256:4a3da280c702e3fe509a111a7fc862c4db0fe83962d4d60d855ae455daeb43a0
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4875fb30a62843cc2edef5ad39db2ed35079ad397e13069707800640da9a461
+oid sha256:83b42ccc78fc9f6a5f23b89793ebcc68b3e09aded426c3afdb92755a1d0609d3
 size 507180756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97bec063427a5bc68520a7c278fee734536758732f2c4113bcc45a9d87c355c
+oid sha256:4f611f73c481744a010adf9dea97a7693cf4a6264df18bb312fb66e7779f46c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3680524826049805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14713996689350745,
+  "best_metric": 1.3588438034057617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.16553246275519587,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 10.685,
       "eval_steps_per_second": 2.678,
       "step": 400
+    },
+    {
+      "epoch": 0.15081846606584515,
+      "grad_norm": 0.5527030229568481,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 1.458,
+      "step": 410
+    },
+    {
+      "epoch": 0.15449696523818282,
+      "grad_norm": 0.5901045203208923,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 1.4088,
+      "step": 420
+    },
+    {
+      "epoch": 0.1581754644105205,
+      "grad_norm": 0.6328750848770142,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 1.3526,
+      "step": 430
+    },
+    {
+      "epoch": 0.1618539635828582,
+      "grad_norm": 0.619103193283081,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 1.3128,
+      "step": 440
+    },
+    {
+      "epoch": 0.16553246275519587,
+      "grad_norm": 0.7719127535820007,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 1.2669,
+      "step": 450
+    },
+    {
+      "epoch": 0.16553246275519587,
+      "eval_loss": 1.3588438034057617,
+      "eval_runtime": 107.2217,
+      "eval_samples_per_second": 10.679,
+      "eval_steps_per_second": 2.677,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.34067857129472e+17,
+  "total_flos": 1.50826339270656e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null