Training in progress, step 31, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4509a9ea9ab61c5e32d5b0d732834dcdad3a74c27f4e999f25816b1850fc72
+oid sha256:9baa35330dfc2aaa7249aa566c7359c1f77a3da694c3eac0d917e4fc24d890a6
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78031088cbebb23c0be5ffdb745c242354778cd32c2c32b39f1baf7b6b5abc5e
+oid sha256:f6feeba1fd8d25de3dd60a36f25f505382c92d3d16336af648910c462bf73841
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e49973b2aec5204f3ee5909b8d1b7d03c735611d97c1e0a99cafc573c79dcc9b
+oid sha256:8d508902a65545022fdf098debfb58ddf14ddf5a1e11a90e53bea1f0591e051a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e30a20110a1fef47a490723af6571c46d9e158f40b1a188eda788928d343313
+oid sha256:b10d984064f694ca169cb23643ecf72a8b8597df72304e7b937cc93dd30d92a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284c02e3e9c0498d1e340bd5a39cb0bd35cfb860b2e2454a8073d7db8c853087
+oid sha256:b91e5f8f48b1050b41dd055aa10ee3a635e2fab675531c578668d834713f9f4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4eccc087876d1f07b3064f8411e225a2878c2b398b51303504448dab005adb7
+oid sha256:fafae8f1b952521a82b60164727a972e31e2ac9ab26c6cf304d66531ff0c9ee3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61914ad2881f65ba5f1666f58d28160ad68bc79e6fc6052344270b6561f306f
+oid sha256:682d2be700346346165516bd699d36bda3da310851cc5da24987008d925a3c27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.814382314682007,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.4691358024691357,
+  "epoch": 3.0617283950617282,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 31,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,48 @@
       "eval_samples_per_second": 140.979,
       "eval_steps_per_second": 18.659,
       "step": 25
+    },
+    {
+      "epoch": 2.567901234567901,
+      "grad_norm": 3.632655143737793,
+      "learning_rate": 7.157141191620548e-06,
+      "loss": 2.9517,
+      "step": 26
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 5.402245998382568,
+      "learning_rate": 4.621229016452156e-06,
+      "loss": 2.4943,
+      "step": 27
+    },
+    {
+      "epoch": 2.765432098765432,
+      "grad_norm": 2.5133705139160156,
+      "learning_rate": 2.6173414408598827e-06,
+      "loss": 2.0811,
+      "step": 28
+    },
+    {
+      "epoch": 2.8641975308641974,
+      "grad_norm": 5.495011329650879,
+      "learning_rate": 1.1689722144956671e-06,
+      "loss": 3.0137,
+      "step": 29
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 6.708992004394531,
+      "learning_rate": 2.9310214228202013e-07,
+      "loss": 2.7247,
+      "step": 30
+    },
+    {
+      "epoch": 3.0617283950617282,
+      "grad_norm": 5.700857162475586,
+      "learning_rate": 0.0,
+      "loss": 5.0588,
+      "step": 31
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.27222702669824e+16,
+  "total_flos": 1.5775615131058176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null