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:a24d466fc7008e6fd947b0a9f285a4bd103a0702f08740c3c57bf34569b9ad79
+oid sha256:a15c361c2eb02bf2cd170d14f83a658d331924b4d40f0da8f26c272844cf5976
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634bd72cec9d73784cd8d4999627ec2174648a683bcc60c1dbedae6d31c3f46e
+oid sha256:ff9a94949ae3238965f3446523ac619e378532bd943eb1eb86fb9415be004749
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba85cacb3618987e96506b86a4d6be73c05fa84bea46cdc90d160ec4a92148e
+oid sha256:1084009eb122d9e4c09a692cbac2291f8318a96f7fadc957232e5d4c4713c4ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39eac5fd8779395e014946b93a7b0bfaa19b182a4bbf95f3bc4cdc5caf338699
+oid sha256:2a8cf07dd7fc6a4cf3acbc97242f179193b6d955129e9ed6d413c15f80738aa4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afeb6f78c8153568c2f0ba0284ba4c48624da3b3fa6f452a346e7bf1a88491ca
+oid sha256:85216c53dd669a2220385363f9b5ed621f1f0513455505ff5ea251ceac579192
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901c3ef0ca04367333a6f236f7b9e02011fbb797c9442bc77dc8a9400b435c52
+oid sha256:b87ef3bd4709bd6f62bc85016a9c4ed233299db4ca6a1c798a8760eaf33d6679
 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": 11.924481391906738,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2222222222222223,
+  "epoch": 3.022222222222222,
   "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": 234.279,
       "eval_steps_per_second": 30.826,
       "step": 25
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 0.04880596697330475,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 13.1801,
+      "step": 26
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.060412779450416565,
+      "learning_rate": 1.134947733186315e-05,
+      "loss": 10.955,
+      "step": 27
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 0.07174395024776459,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.4168,
+      "step": 28
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 0.04970638453960419,
+      "learning_rate": 5.903936782582253e-06,
+      "loss": 14.1483,
+      "step": 29
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.05909634754061699,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.6889,
+      "step": 30
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 0.07133551687002182,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 11.3121,
+      "step": 31
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.05919625237584114,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.2727,
+      "step": 32
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.050839297473430634,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 12.6717,
+      "step": 33
+    },
+    {
+      "epoch": 3.022222222222222,
+      "grad_norm": 0.10524462908506393,
+      "learning_rate": 0.0,
+      "loss": 19.9286,
+      "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": 521247129600.0,
+  "total_flos": 708896096256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null