Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be8897042dd870908e2b95e92353fbf5ecafc46d10f1068c1bf13a0323783cd
+oid sha256:32f13e9607a7f62abd36347c6c4e722278e2b7a89b1f08dc1bca3cbf4441abb5
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85fdb716a1bd32a486034ac4b4c8a8427606a36e201d6602c1bbb2f032747476
+oid sha256:e2b70e4d3ee4fcb887f129bf52cff30c1884f44873679b0f2cb63c94c630ff1b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfc6b08d7a07253f82569c70a07b88d6369abc3e560999e460080e32b805808
+oid sha256:6962615f45ab4c6b6a12692e9323d5a0374b19643b57d3d267bca2752a4bea69
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f01afc4c1c0469421e4e21ea42c95c10b752818bb67f323199f58b473dcdd9
+oid sha256:56424092bcf5486245fe93f4cf87efae639af4c13d4e19ec4ed496f087d26537
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1709073f69b01ed9629c17bd7de28bc34f0a76e7ba4b412dc0e9270932cc779
+oid sha256:274967123d968155cd00c929d0afe2b07d3d9639e92a98e715ed8290bae6b634
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468d8c6a521b010c8f01047d5aaef6449ef961794c8fe632ee4454b03352ddb8
+oid sha256:00dcbeedb178549aeadbf3c75751d39b8f6a083f039bd57e88ff87b3d16be1e0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9df2a04f62b67211447d8ed44cee6691ed618e4d6af94df3c64d249c82d80c3
+oid sha256:1fe247b8abd9f098bbbafb55011dbe010f2fe145118845b911d1500aa9422fe0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.002759997732937336,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2569832402234637,
+  "epoch": 3.0726256983240225,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 23.131,
       "eval_steps_per_second": 3.084,
       "step": 25
+    },
+    {
+      "epoch": 2.346368715083799,
+      "grad_norm": 0.09329082071781158,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0015,
+      "step": 26
+    },
+    {
+      "epoch": 2.435754189944134,
+      "grad_norm": 0.08940267562866211,
+      "learning_rate": 1.134947733186315e-05,
+      "loss": 0.0012,
+      "step": 27
+    },
+    {
+      "epoch": 2.5251396648044695,
+      "grad_norm": 0.5705907940864563,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0157,
+      "step": 28
+    },
+    {
+      "epoch": 2.6145251396648046,
+      "grad_norm": 0.16675959527492523,
+      "learning_rate": 5.903936782582253e-06,
+      "loss": 0.0024,
+      "step": 29
+    },
+    {
+      "epoch": 2.7039106145251397,
+      "grad_norm": 0.04368215799331665,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0009,
+      "step": 30
+    },
+    {
+      "epoch": 2.793296089385475,
+      "grad_norm": 0.26671910285949707,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 0.0438,
+      "step": 31
+    },
+    {
+      "epoch": 2.88268156424581,
+      "grad_norm": 0.41659799218177795,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0093,
+      "step": 32
+    },
+    {
+      "epoch": 2.972067039106145,
+      "grad_norm": 0.05689646303653717,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 0.0011,
+      "step": 33
+    },
+    {
+      "epoch": 3.0726256983240225,
+      "grad_norm": 1.820482850074768,
+      "learning_rate": 0.0,
+      "loss": 0.2558,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7968812858159923e+17,
+  "total_flos": 3.7949385060909056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null