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:b272dfc1af283de869b53c47122a97573473439e25cc864ec36879d322170e08
+oid sha256:8e46d0e8b89391406fa442034430f7dc7d93fc4c28793f7970cc68f42947be5b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73594681fd5a9a6fafa87226094e191d45bc1e3ff2e7c04dc2326a203b25f97
+oid sha256:93f2b0d6ada5bdeeee8bb9a0895ba3d49235866eb313c40d81776cd6d58f18fd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b50d6dfd4c67766a87d7126cc5d993e88a1ae9d35d4c78be754e5e87bc7a27f
+oid sha256:d9ee0f70e85ad28730a65a0c509883d15416174abfa1557b4e20d71328e3ef4a
 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": 2.1466376781463623,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 2.1456618309020996,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01063264221158958,
   "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": 3.207,
       "eval_steps_per_second": 1.604,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 4.635622978210449,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 8.4835,
+      "step": 21
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 5.024051189422607,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.4714,
+      "step": 22
+    },
+    {
+      "epoch": 0.009782030834662414,
+      "grad_norm": 4.305144786834717,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 8.1257,
+      "step": 23
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 3.969085693359375,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.8921,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 4.106435298919678,
+      "learning_rate": 0.0,
+      "loss": 8.6033,
+      "step": 25
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 2.1456618309020996,
+      "eval_runtime": 309.1335,
+      "eval_samples_per_second": 3.203,
+      "eval_steps_per_second": 1.601,
+      "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": 6879228909846528.0,
+  "total_flos": 8544265206497280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null