Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134ca07422e66ab8512510bc55e2bc05b843a25b32ca074888175e686ad0b8b4
+oid sha256:b6dff0c3460c96ccb39cd490620b4e23d871507f3dd0a2714fc206fd1b9efe7c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab1b773b06bacf741ad44f7e0cdaa1927108b70cbdf5935f8f302e214a27a0a
+oid sha256:d22e5562eb5deae8c3a575d50482a17275c7254cdd7ab61a8516476dc0e90d2d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2440aab99aaea8f12309d43fda04fcacfe47d5b3400cf510393e1fcf0e5535
+oid sha256:a01350bb3744c03ac1a7da9e0f79a68dee354459aa6ccb638382fc2706d63001
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3951972424983978,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.018656716417910446,
+  "best_metric": 0.3907972276210785,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02332089552238806,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 2.113,
       "eval_steps_per_second": 1.056,
       "step": 20
+    },
+    {
+      "epoch": 0.01958955223880597,
+      "grad_norm": 0.19263756275177002,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.3699,
+      "step": 21
+    },
+    {
+      "epoch": 0.020522388059701493,
+      "grad_norm": 0.2069644331932068,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4451,
+      "step": 22
+    },
+    {
+      "epoch": 0.021455223880597014,
+      "grad_norm": 0.18779270350933075,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4153,
+      "step": 23
+    },
+    {
+      "epoch": 0.022388059701492536,
+      "grad_norm": 0.20380006730556488,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4172,
+      "step": 24
+    },
+    {
+      "epoch": 0.02332089552238806,
+      "grad_norm": 0.1967461258172989,
+      "learning_rate": 0.0,
+      "loss": 0.4723,
+      "step": 25
+    },
+    {
+      "epoch": 0.02332089552238806,
+      "eval_loss": 0.3907972276210785,
+      "eval_runtime": 212.4073,
+      "eval_samples_per_second": 2.128,
+      "eval_steps_per_second": 1.064,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26648166907904e+16,
+  "total_flos": 1.5831020863488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null