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:e325d3c36812be85e615c64aa5c90d643f566fa2e023170752c9a536860a2200
+oid sha256:e8a7715ee1464a05c54192107b6a20498bbc6c526942acd386f9dc094474fcf9
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6570816d264b02759ab94203a65b15331bca1d6c51ddae59dc642f04f11228
+oid sha256:28612f723fa0224b56a0d820855bd945fc3e42ad309679300f520b4abe9c2815
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:705deedf796b313cb76cd6c14cb7b94da899d809f9d9c1109db82fbb592f3b6c
 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": 2.6460254192352295,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03368421052631579,
+  "best_metric": 2.6249186992645264,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.05052631578947368,
   "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": 65.686,
       "eval_steps_per_second": 32.843,
       "step": 20
+    },
+    {
+      "epoch": 0.03536842105263158,
+      "grad_norm": 45.487239837646484,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.2749,
+      "step": 21
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "grad_norm": 51.95940017700195,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.3656,
+      "step": 24
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 2.626051425933838,
+      "eval_runtime": 3.8337,
+      "eval_samples_per_second": 65.211,
+      "eval_steps_per_second": 32.606,
+      "step": 25
+    },
+    {
+      "epoch": 0.04547368421052632,
+      "grad_norm": 39.46547317504883,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.9621,
+      "step": 27
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 38.4549674987793,
+      "learning_rate": 0.0,
+      "loss": 9.9003,
+      "step": 30
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "eval_loss": 2.6249186992645264,
+      "eval_runtime": 3.842,
+      "eval_samples_per_second": 65.07,
+      "eval_steps_per_second": 32.535,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null