Training in progress, step 29, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d90cc40175d8289a5ae4f39c776076a74f98543163b5b147403f83c30e1bd00
+oid sha256:3ad97a39f38b55a1ed74ad3f85d6d56a8fa0e4c3c2f684578716c80cc7d447ab
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9631a574a06f3a212450c98b320ac9b46ee6b08b37d63926bb289500c0a3577a
+oid sha256:14252288a031bed3440fb69a5ffd7fead8346af2a866e0c133dac701e45cdc91
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a7d00d30a817148495065781e02ca66d94ec178482af375f3a5b50f755da69
+oid sha256:77d8b6497afbe8e271412b48b3c91dff27ffc551eacd17a57d75fd4af1fb0dd7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8317de8b3963c550fd5d2a202543f07767ab3b16fd32f0997314bc9e2edcbc8b
+oid sha256:d4f19d5e5d3234b86eb113a1ee531eaff10824d08ec4828171d7dc21ff2ab4bd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414601f007e868d48902915dbdb7636814f987b437b622aa4f8011e4e86eca61
+oid sha256:1e8e7f451d852df161156fdd46bb4df8184f8b69fec15c77fb656add209e0270
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078bb04a71659901d8dc28ea1b91fe00665d4896646f1cef495b79e8ba493297
+oid sha256:be58ec648eeef96a0ee08d13bf5090959b5f08295fb24ae9aa67b330d2451779
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c358afaa27e49311ba3af0bc45fb097f71b7e94dd7d620cdb9c2ef0a37a7463
+oid sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7155137062072754,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.709677419354839,
+  "epoch": 3.1870967741935483,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 29,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,34 @@
       "eval_samples_per_second": 47.165,
       "eval_steps_per_second": 6.531,
       "step": 25
+    },
+    {
+      "epoch": 2.8129032258064517,
+      "grad_norm": 1.4053550958633423,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8174,
+      "step": 26
+    },
+    {
+      "epoch": 2.9161290322580644,
+      "grad_norm": 2.1084353923797607,
+      "learning_rate": 1.3477564710088098e-06,
+      "loss": 0.7691,
+      "step": 27
+    },
+    {
+      "epoch": 3.0838709677419356,
+      "grad_norm": 5.000555515289307,
+      "learning_rate": 3.380821129028489e-07,
+      "loss": 1.2892,
+      "step": 28
+    },
+    {
+      "epoch": 3.1870967741935483,
+      "grad_norm": 2.501575469970703,
+      "learning_rate": 0.0,
+      "loss": 0.8028,
+      "step": 29
     }
   ],
   "logging_steps": 1,
@@ -221,12 +249,12 @@
         "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": 4.541648635271578e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null