Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c7afebbfcd2272fe3ced345d78d01f67b098c7dd2d5e2ec111a0d4e8093d45
+oid sha256:4ece380abae574c7d91e11c57a0365ea75e711ef0dc765e32577c62b451d116e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344af2874827af47304d72154c92ad1fa8b3f690630a48729dc1fb804dff828f
+oid sha256:124f0e2e72bdf3ba85c611bd03eea79b5485ad5cb898ee80a8d679b277e40d69
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bd120fd086c25fbfec9308dc91d25a3b4d47ca2917fa43a04ce165b330b5c6
+oid sha256:64e784ab6ef0dd5023917a020b5529a97aad3adaa063d3022348f66a5d3bd862
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5969746112823486,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015479876160990712,
+  "best_metric": 1.593575119972229,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01934984520123839,
   "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": 4.348,
       "eval_steps_per_second": 2.178,
       "step": 20
+    },
+    {
+      "epoch": 0.016253869969040248,
+      "grad_norm": 0.923443615436554,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 7.6624,
+      "step": 21
+    },
+    {
+      "epoch": 0.017027863777089782,
+      "grad_norm": 0.8137747049331665,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.3292,
+      "step": 22
+    },
+    {
+      "epoch": 0.01780185758513932,
+      "grad_norm": 0.922442615032196,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 5.1466,
+      "step": 23
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": 0.8308588862419128,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 5.8502,
+      "step": 24
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "grad_norm": 1.1300650835037231,
+      "learning_rate": 0.0,
+      "loss": 7.9132,
+      "step": 25
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "eval_loss": 1.593575119972229,
+      "eval_runtime": 124.4941,
+      "eval_samples_per_second": 4.378,
+      "eval_steps_per_second": 2.193,
+      "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": 5904216002396160.0,
+  "total_flos": 7288652858130432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null