Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb8aa408391aaf66dc233779a24e2cc10c3d1b6b42c9c732aed82d867962a2f
+oid sha256:ddf9dea434cdc338e3a9b4d548a10cede018c09a8bfb89a578267a8ecfb561d3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0896735137ddcab1158cf8713d502baaa1c7ac803c106117d8e474ef6cde51a
+oid sha256:e1128ca729591379699cd452f272cfe04fd2eb90c5eff42728fedd688c8023d0
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147a294f9a33d16934a9eb60b9f9bedc7178384ab62a9efc5e72db5352813f0b
+oid sha256:a88628f8133847b1cbc77f6708fc959720431b7fc77b41b61cda1b94710b0d63
 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": 1.0417572259902954,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0011861340924591525,
+  "best_metric": 1.031199336051941,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0014826676155739406,
   "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": 4.949,
       "eval_steps_per_second": 2.474,
       "step": 20
+    },
+    {
+      "epoch": 0.0012454407970821102,
+      "grad_norm": 5.03507661819458,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.1459,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013047475017050677,
+      "grad_norm": 5.1348419189453125,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.7684,
+      "step": 22
+    },
+    {
+      "epoch": 0.0013640542063280254,
+      "grad_norm": 5.261707782745361,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.0605,
+      "step": 23
+    },
+    {
+      "epoch": 0.001423360910950983,
+      "grad_norm": 6.641138076782227,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.1477,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014826676155739406,
+      "grad_norm": 5.031643867492676,
+      "learning_rate": 0.0,
+      "loss": 3.6754,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014826676155739406,
+      "eval_loss": 1.031199336051941,
+      "eval_runtime": 1426.5631,
+      "eval_samples_per_second": 4.977,
+      "eval_steps_per_second": 2.488,
+      "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": 5782002632491008.0,
+  "total_flos": 7084989141221376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null