Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e2e32f295b2cc30e7702976b6abace429c60fc81cf7a93b2c7b398f9c9d707
+oid sha256:ade5d1dbcbf3445406aa4f12c0e50ece4a9cc90b155498af820b15cbeae0c130
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdd16f703c816659458de2edb00b79ce72754e3aae4c9feb169d5a2ce4287e4
+oid sha256:b5571f6c42f18e635baf3c0dde0cf02d12b3942e6dc3342a534c39260c3996d2
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa13652b46ac58a7a8069b8055b99cac5fdb3015d26a3676b1286d2258da0a5b
+oid sha256:7724faffb1cb2a0ae7000fddbb109da2d9472511f9cef1e359a1949a9a2c0d9a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8adba6bf4f83d4e9982ebcbeae70e3be81f66fac1de0dc65d7a0af85fa4cead7
+oid sha256:0bde4a82cb35aeae86200126aa6746417964ef1f0dd76370ad2283c603ee599d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f133dbf980398cf41bea5ec44cb56698ae5883a6dc10ece130fdb15229ca075d
+oid sha256:4a53471b00060e3e2e08e4e7b0c96cd750bcf6a2fb13565ffb95eb06f92796cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838aa46a53704f9a8023379faee712603bbd808001c0bb2de09e23dbb357bce1
+oid sha256:ad2f33de68d8f66da4441eb2ee40ce885658d8644dcfbf454c1fa903ab162db1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cddcb24aadae81d07278497a6396e07c439ca4a7b8ebe0bf20ff2146c0295bff
+oid sha256:5cb4304039a2941ec395778b262c969aa296bcf9a2f204c43c675b3e30a23811
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6671230792999268,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.564102564102564,
+  "epoch": 3.076923076923077,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,41 @@
       "eval_samples_per_second": 33.416,
       "eval_steps_per_second": 8.688,
       "step": 25
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.176918387413025,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 0.7793,
+      "step": 26
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.5590916872024536,
+      "learning_rate": 1.252525013612346e-05,
+      "loss": 0.7132,
+      "step": 27
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 0.7971133589744568,
+      "learning_rate": 1.1128243951817937e-05,
+      "loss": 0.736,
+      "step": 28
+    },
+    {
+      "epoch": 2.9743589743589745,
+      "grad_norm": 0.9218295216560364,
+      "learning_rate": 1.0282950554804085e-05,
+      "loss": 0.8827,
+      "step": 29
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 2.245664119720459,
+      "learning_rate": 1e-05,
+      "loss": 0.8213,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.91521434075136e+16,
+  "total_flos": 4.698257208901632e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null