Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb00cd654211d74ac9563078a96b0f3ab7f426e93fe774c2128b4e4a0c561d65
+oid sha256:d73bdfe08379754641b2b8a3b61b4ed07636dc29013ac0f8ac0808a94e60eb48
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83603432c18aa410c78cc84810f637d978ea5dd12528e7934a46dbc0bdf9793f
+oid sha256:4e8093aa4731e885a677b2014c8730b0d671f634137cef5fc8da1145ab411fc2
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac6304c3d282c68b3b54b02e10f7ccb87b4af7f30bf7c763231322312d8a778
+oid sha256:4d1ab9a3e0897582bba709b9af425dd92bd8ad4321b5d882e5cf58b05d495cce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5134329795837402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007399186089530152,
+  "best_metric": 2.4856905937194824,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.011098779134295227,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 9.552,
       "eval_steps_per_second": 4.78,
       "step": 20
+    },
+    {
+      "epoch": 0.00776914539400666,
+      "grad_norm": 2.6072142124176025,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 10.0714,
+      "step": 21
+    },
+    {
+      "epoch": 0.008879023307436182,
+      "grad_norm": 2.119253396987915,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 9.2856,
+      "step": 24
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "eval_loss": 2.4907679557800293,
+      "eval_runtime": 119.3976,
+      "eval_samples_per_second": 9.54,
+      "eval_steps_per_second": 4.774,
+      "step": 25
+    },
+    {
+      "epoch": 0.009988901220865706,
+      "grad_norm": 2.203669548034668,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 9.7656,
+      "step": 27
+    },
+    {
+      "epoch": 0.011098779134295227,
+      "grad_norm": 2.634230136871338,
+      "learning_rate": 0.0,
+      "loss": 9.7561,
+      "step": 30
+    },
+    {
+      "epoch": 0.011098779134295227,
+      "eval_loss": 2.4856905937194824,
+      "eval_runtime": 120.34,
+      "eval_samples_per_second": 9.465,
+      "eval_steps_per_second": 4.737,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null