Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a202f269b1e830fb54975c16a2229693f52db828e1d1db25e6309dcf8cf8e21
+oid sha256:0fc14ee668b05f777fc43e5822f8c8b4387dc68095d21531403dccad48389f4b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792a41c6e999323e230ff19a983b018e5cff0200ff9294ff0033ed69d098559d
+oid sha256:67ff48ec11635322b09696f30c79f2550bb7416fbadb431561ddd7445882d38b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee095a33f22670901fd859567f3431503ef42cfa2b0900449c762f9652e5814
+oid sha256:85cfa40c93403006475c5ac2afb377af6a1a9a344a0c133802861991b343f26f
 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": 10.361103057861328,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01903855306996668,
+  "best_metric": 10.359004020690918,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.028557829604950024,
   "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": 455.442,
       "eval_steps_per_second": 114.246,
       "step": 20
+    },
+    {
+      "epoch": 0.019990480723465015,
+      "grad_norm": 0.2671791613101959,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3624,
+      "step": 21
+    },
+    {
+      "epoch": 0.02284626368396002,
+      "grad_norm": 0.279178649187088,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3612,
+      "step": 24
+    },
+    {
+      "epoch": 0.023798191337458353,
+      "eval_loss": 10.359330177307129,
+      "eval_runtime": 1.9488,
+      "eval_samples_per_second": 454.12,
+      "eval_steps_per_second": 113.915,
+      "step": 25
+    },
+    {
+      "epoch": 0.02570204664445502,
+      "grad_norm": 0.2777588367462158,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.3575,
+      "step": 27
+    },
+    {
+      "epoch": 0.028557829604950024,
+      "grad_norm": 0.28034502267837524,
+      "learning_rate": 0.0,
+      "loss": 10.3584,
+      "step": 30
+    },
+    {
+      "epoch": 0.028557829604950024,
+      "eval_loss": 10.359004020690918,
+      "eval_runtime": 1.9773,
+      "eval_samples_per_second": 447.578,
+      "eval_steps_per_second": 112.274,
+      "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": 1046048931840.0,
+  "total_flos": 1569073397760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null