Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d19631c5438a5e7aa3075e5179dea2730b5c50f6fa8620281a0b02b9bf0aaf3
+oid sha256:642aeeb1c492cdf7b8debbaba0b0980ee9766d978a24a983cfa1c5da51141d9f
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c38b469d80f5ff027a232f11b9bffbbdb8059353d0ee6bd07a66015cfbdbb2
+oid sha256:1e5e4f620bb1ae0ae6634abc79ae78c373b6cb88454f5e5dbc85ce3301a65aeb
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cfec4a96624278ffb924e0c1ac518f6fbbb2400d4fdfbfa30f8f4900c7176ce
+oid sha256:1e5758089fdb8713594ae4bde11ad69715bcdfd6a1141d833070f5363243293b
 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": 5.458237648010254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04056795131845842,
+  "best_metric": 5.4380717277526855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05070993914807302,
   "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": 58.876,
       "eval_steps_per_second": 29.438,
       "step": 20
+    },
+    {
+      "epoch": 0.04259634888438134,
+      "grad_norm": 11664.0615234375,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 23.0037,
+      "step": 21
+    },
+    {
+      "epoch": 0.04462474645030426,
+      "grad_norm": 8448.078125,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 17.3446,
+      "step": 22
+    },
+    {
+      "epoch": 0.04665314401622718,
+      "grad_norm": 26231.671875,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 22.3308,
+      "step": 23
+    },
+    {
+      "epoch": 0.0486815415821501,
+      "grad_norm": 19578.056640625,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 20.9684,
+      "step": 24
+    },
+    {
+      "epoch": 0.05070993914807302,
+      "grad_norm": 14192.642578125,
+      "learning_rate": 0.0,
+      "loss": 22.2455,
+      "step": 25
+    },
+    {
+      "epoch": 0.05070993914807302,
+      "eval_loss": 5.4380717277526855,
+      "eval_runtime": 3.6333,
+      "eval_samples_per_second": 57.249,
+      "eval_steps_per_second": 28.624,
+      "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": 6599070449664.0,
+  "total_flos": 8450608201728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null