Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e3d6a31f0be7063f6c6b0f7df0b81a4b51a12b8f200f873b08d736cb62ac4d
+oid sha256:ea81aa3cee4684d01dd322d60badd2ff8f94a86493c15e3b88b48b50c0708488
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288e50f3615332fcd9f487966a87221e1d4ecec6e4f422c0b5db1543d6da4da5
+oid sha256:bfe27dbe601783cf4dde2d43112f5dba71d8d1c8dc1f1f0c9c069bd75e6a0fbe
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72bb918a51629d9fa8b560a4c22e5d570c95f7624152a7f53be141edb04c494
+oid sha256:9c2fc88fe2980c4c40a0694cf1f5866a5654a05f785254dd588e11df7cf2ddf1
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4b55cf4689184a551d6783e402772f21c71cbcf3ad49144e8795a2e3edd567
+oid sha256:5d86dc09fa4fc0bc1edba1324c7d904172e964c7a227885a5b21ea4dd9be0f90
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df107024cfb32ebd141263101a68d66f3a2be132b66d0fc8d28d8bd60b6d9e6
+oid sha256:4ccc105feabbc6d14f8e812b063cc283ce486cc05baf29ad39473aeddf087247
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb14b5f99058f3b86633f8b784b0522c5c185ed400580f26f4d201904985ddfb
+oid sha256:2d73d0c65a58e9c0f86747046c9e29ac8721df48478c02e16c142b9010a5fc05
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f0477a4f52d73a0d5b42bcbbd59be121e3f32646b13d269cf4b1a335f645d7
+oid sha256:3cd3f6e9267a2b7ffad41dddfa33b74e45aa7c480b8283eebbe1a013b2da49f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8249684572219849,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2988505747126435,
+  "epoch": 3.0344827586206895,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,62 @@
       "eval_samples_per_second": 31.248,
       "eval_steps_per_second": 4.223,
       "step": 25
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 1.2132009267807007,
+      "learning_rate": 1.2062093865360458e-05,
+      "loss": 0.7836,
+      "step": 26
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 5.591070652008057,
+      "learning_rate": 8.961827939636196e-06,
+      "loss": 0.8673,
+      "step": 27
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 1.2173008918762207,
+      "learning_rate": 6.282669192770896e-06,
+      "loss": 0.7963,
+      "step": 28
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9013738036155701,
+      "learning_rate": 4.05210941898847e-06,
+      "loss": 0.7776,
+      "step": 29
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 4.316105365753174,
+      "learning_rate": 2.2930371799975594e-06,
+      "loss": 0.8378,
+      "step": 30
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.7817060351371765,
+      "learning_rate": 1.0235029373752758e-06,
+      "loss": 0.7891,
+      "step": 31
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 5.667788505554199,
+      "learning_rate": 2.5653383040524227e-07,
+      "loss": 0.8836,
+      "step": 32
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 0.7555753588676453,
+      "learning_rate": 0.0,
+      "loss": 0.8817,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -221,12 +277,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 4.075156367348859e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null