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:c5e2b6bc53fb3e6c1b383db09e0f3488f9f03aa899a5fb2e3e3bfee9c86f986a
+oid sha256:e1fb78e2584e317dcc4042ab4d2d5e5136ed96dfcb685445387bd806e1344893
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610f2bda42c4f026bb54fcf0b3029ae9fcb053d767e988a900fd20f3faac51f8
+oid sha256:d54abd1540654289ea3bbfd57233f5f34333db7fa510489eec158eb8c526b5d0
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f426393d5331fe742f260bb68b212769d993bf426df0d1e94354cd4f6646688b
+oid sha256:8accf6d9d5916a2afd0c6fdd1d79913903d339f84ec397c0a3163db55e0721db
 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": 4.319764614105225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01586671955573185,
+  "best_metric": 4.293106555938721,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02380007933359778,
   "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": 42.584,
       "eval_steps_per_second": 10.666,
       "step": 20
+    },
+    {
+      "epoch": 0.016660055533518445,
+      "grad_norm": 3.532709836959839,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 17.5431,
+      "step": 21
+    },
+    {
+      "epoch": 0.019040063466878223,
+      "grad_norm": 3.5737216472625732,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 17.8957,
+      "step": 24
+    },
+    {
+      "epoch": 0.019833399444664817,
+      "eval_loss": 4.297074317932129,
+      "eval_runtime": 24.7454,
+      "eval_samples_per_second": 42.917,
+      "eval_steps_per_second": 10.749,
+      "step": 25
+    },
+    {
+      "epoch": 0.021420071400238,
+      "grad_norm": 3.5438756942749023,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 17.4522,
+      "step": 27
+    },
+    {
+      "epoch": 0.02380007933359778,
+      "grad_norm": 3.636681318283081,
+      "learning_rate": 0.0,
+      "loss": 17.6093,
+      "step": 30
+    },
+    {
+      "epoch": 0.02380007933359778,
+      "eval_loss": 4.293106555938721,
+      "eval_runtime": 24.8587,
+      "eval_samples_per_second": 42.721,
+      "eval_steps_per_second": 10.7,
+      "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": 171959044276224.0,
+  "total_flos": 256877090832384.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null