Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130622fc8d7be932e94875cc6e0f27b8df05cfdd2567a10bd496ffcdd27d5e0e
+oid sha256:b955a291eef1764a89a658a7f114e65fa02250ca0a49aaea0c1267975cc69e39
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e5daf9e2a50137176d985b2acabfb82ace1a94392a5562c83821b33c985c75
+oid sha256:91e60f334dce03007377870d899c831d43599bec9cfb0b5c7f60a794e9cb8316
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d201a5f8263e9b3b1bdcb8555c9de417731f6f752ef25786f32474077ab77f81
+oid sha256:c311df266ddd7bf83f9975354cce90596bd6bd5d3a825c530898c0deff9628cd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a924fb6e04247bf4d8941e4396455a41d67ffaaae82bbf8ee2d014eb7fa3842e
+oid sha256:94d01b396c8a9114b14015c7e331c28ab087631aa5d13e5ab087e870ce6c1ad1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354a32d2afbf31a8b461ef8214933e41795c01142ad09d1fa211e0c9885711f0
+oid sha256:215a1749c01b95b16384b63f9201e781738a43f201c5578d0ab310e84eccfd9d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bb6eb0b6483fbdf3ada30028b6e08bd71cd521663a8170f99a0a15a35ca713
+oid sha256:c93295912732a99743a52882008d47a7082f1c20d60745f404b69d00a687b436
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d490043b81d92f2523c5e5743bd899586cd05324668f1c6287fc78466d4341
+oid sha256:83bde02f2e7b736ca94b9c51f0320881be685bc5601886de1775bb4eb0e0862b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.094954013824463,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2334217506631298,
+  "epoch": 3.222811671087533,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 12.011,
       "eval_steps_per_second": 3.123,
       "step": 25
+    },
+    {
+      "epoch": 2.3183023872679045,
+      "grad_norm": 0.08489442616701126,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 2.8181,
+      "step": 26
+    },
+    {
+      "epoch": 2.4031830238726792,
+      "grad_norm": 0.08466842770576477,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 2.1872,
+      "step": 27
+    },
+    {
+      "epoch": 2.4880636604774535,
+      "grad_norm": 0.06858357042074203,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 1.7205,
+      "step": 28
+    },
+    {
+      "epoch": 2.5729442970822283,
+      "grad_norm": 0.08000484853982925,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 2.5778,
+      "step": 29
+    },
+    {
+      "epoch": 2.6578249336870026,
+      "grad_norm": 0.08722012490034103,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 2.1332,
+      "step": 30
+    },
+    {
+      "epoch": 2.7427055702917773,
+      "grad_norm": 0.0678829699754715,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 1.8788,
+      "step": 31
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.07839219272136688,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 2.4007,
+      "step": 32
+    },
+    {
+      "epoch": 2.9124668435013263,
+      "grad_norm": 0.10335433483123779,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 2.1551,
+      "step": 33
+    },
+    {
+      "epoch": 3.053050397877984,
+      "grad_norm": 0.183010995388031,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 3.9227,
+      "step": 34
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 0.07784668356180191,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 2.3547,
+      "step": 35
+    },
+    {
+      "epoch": 3.222811671087533,
+      "grad_norm": 0.07166790962219238,
+      "learning_rate": 1e-05,
+      "loss": 1.5116,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.145953126492406e+17,
+  "total_flos": 5.985801431154688e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null