Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18faf378cc83306823012fe8b50a3846b2466dfc2ac837b3ec050873f82c43fa
+oid sha256:08465380d656b23cc532862eeedc599907b02de4275641059448bcc89e5d69d8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ec3b24a3dca01594a2d4f6be6e85d0f2e69f9d5d0e2cd5548fd0822f1aeb37
+oid sha256:50a8af042cdaefd5aee0b1e5b03bae311e71676a9fdcdddc7a589e8a794557e9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6c8c8005f761597275404d272c3e4a41cab724899a67a64511d3b2eee6db9b
+oid sha256:f65862cc6ebe07d18b57855ee8d7f6d5a1b504eb519a516d2f1dd289fbac5545
 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": 3.67405366897583,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003108003108003108,
+  "best_metric": 3.628095865249634,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.003885003885003885,
   "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": 5.738,
       "eval_steps_per_second": 2.869,
       "step": 20
+    },
+    {
+      "epoch": 0.0032634032634032634,
+      "grad_norm": 5.634303092956543,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.7469,
+      "step": 21
+    },
+    {
+      "epoch": 0.003418803418803419,
+      "grad_norm": 5.808221817016602,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.8198,
+      "step": 22
+    },
+    {
+      "epoch": 0.003574203574203574,
+      "grad_norm": 5.099615097045898,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.4756,
+      "step": 23
+    },
+    {
+      "epoch": 0.0037296037296037296,
+      "grad_norm": 4.355826377868652,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.568,
+      "step": 24
+    },
+    {
+      "epoch": 0.003885003885003885,
+      "grad_norm": 4.638548851013184,
+      "learning_rate": 0.0,
+      "loss": 3.7543,
+      "step": 25
+    },
+    {
+      "epoch": 0.003885003885003885,
+      "eval_loss": 3.628095865249634,
+      "eval_runtime": 480.1391,
+      "eval_samples_per_second": 5.644,
+      "eval_steps_per_second": 2.822,
+      "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": 5456214532030464.0,
+  "total_flos": 6889626824343552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null