Training in progress, step 107, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c57c3cbfc054b67bcc71f4ca4d264b570f6013309707faa52546243b1fd30b
+oid sha256:abb01dbc490f7b8e8d75522d5a82f8a57b15100a16fabdd744770a12ac2d414e
 size 119975656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9bbacc86066af861da5976f828395efd785209a6ddc97a049e00116a1d73af
+oid sha256:d31cee0a9f7a82ece203e937776a61e9c1bd399d91418f14f297d546863d1476
 size 61297812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d478d6efa8cb8ed403991510e313f6aa1bf04e96851137a85bcb4b2764c9d53
+oid sha256:a4e60e0f7d153d8d862b9482e21c86a792560cb2b436bc698b2d47bccfa43b5b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388d25972bb1e5c37bd606304b2b7f03e402ddc476d98d532c28ffa8e9b3a17e
+oid sha256:4057dad12937a603317934bf171d567427185298a4cbff133d48047ff198bd5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.6379531621932983,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 3.7383177570093458,
+  "epoch": 4.0,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 107,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,55 @@
       "eval_samples_per_second": 32.139,
       "eval_steps_per_second": 8.213,
       "step": 100
+    },
+    {
+      "epoch": 3.7757009345794392,
+      "grad_norm": 0.7355567216873169,
+      "learning_rate": 3.366666666666667e-05,
+      "loss": 1.7526,
+      "step": 101
+    },
+    {
+      "epoch": 3.8130841121495327,
+      "grad_norm": 0.7980681657791138,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.4984,
+      "step": 102
+    },
+    {
+      "epoch": 3.850467289719626,
+      "grad_norm": 0.8555505275726318,
+      "learning_rate": 3.433333333333333e-05,
+      "loss": 1.2448,
+      "step": 103
+    },
+    {
+      "epoch": 3.8878504672897196,
+      "grad_norm": 1.4027817249298096,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 1.6987,
+      "step": 104
+    },
+    {
+      "epoch": 3.925233644859813,
+      "grad_norm": 0.5864289402961731,
+      "learning_rate": 3.5e-05,
+      "loss": 1.9383,
+      "step": 105
+    },
+    {
+      "epoch": 3.9626168224299065,
+      "grad_norm": 0.575369656085968,
+      "learning_rate": 3.5333333333333336e-05,
+      "loss": 1.6603,
+      "step": 106
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2596912384033203,
+      "learning_rate": 3.566666666666667e-05,
+      "loss": 1.8972,
+      "step": 107
     }
   ],
   "logging_steps": 1,
@@ -754,12 +803,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.294827588753818e+16,
+  "total_flos": 6.728755879870464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null