Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494e35ab30aab16e80d348d56a8f5d2c10f13c6a9fca356c18dd27479c896f4e
+oid sha256:bd8327e35a6e61021d56c8b8e555ec4305f2ba4babdb90202cbc18f92068dc9a
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850ff3f818480b41bc2110065d24d3b4c8e0f015d9f80a849971c7eb1319f5f9
+oid sha256:abf151ef08f856e5a6a36f25de60d2e2e586f1cd0314a6e0da1c0ac8455334e8
 size 14714004

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191f7b5460613f15d5afc2e2564399c64ae3437e72470be480c0fd7b8b3ea5a7
+oid sha256:891f055740c9d9a040ad0e69d7f8a2bd96a6ac0ff9c14aea3fe159005c9fd367
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5abaa3ef0d6b5edc8213716d849c4d819788cbe0e33d2db9ca13ee66b8e1bc
+oid sha256:1e3a798ee2e655055dccb0771a74a10b580be53ed57fbd50ca80ab0f720aa4a4
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3994bc036a38f7ff76f2379696b1c10518c8ef2d67752688b2ee8e4b3af1f830
+oid sha256:ec51148e0ee915a96d17676044d6b5c688165b7b9d4a69a6a0d5a07848e19818
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7862155fdeda9b750ed84302059721a1472e34b620111b4ba8d39815a0d058
+oid sha256:7b4f813ad8f775666bba54998454f9f77424322c1727af627a89718cc62f1148
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.027291774749756,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0024644199371572917,
+  "best_metric": 2.025285482406616,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0030805249214466146,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 378.848,
       "eval_steps_per_second": 47.37,
       "step": 20
+    },
+    {
+      "epoch": 0.002587640934015156,
+      "grad_norm": 6.220272064208984,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 8.4648,
+      "step": 21
+    },
+    {
+      "epoch": 0.0027108619308730208,
+      "grad_norm": 4.325121879577637,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.125,
+      "step": 22
+    },
+    {
+      "epoch": 0.0028340829277308855,
+      "grad_norm": 4.86760950088501,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 7.9922,
+      "step": 23
+    },
+    {
+      "epoch": 0.00295730392458875,
+      "grad_norm": 6.380681991577148,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.9668,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030805249214466146,
+      "grad_norm": 5.164431095123291,
+      "learning_rate": 0.0,
+      "loss": 7.9961,
+      "step": 25
+    },
+    {
+      "epoch": 0.0030805249214466146,
+      "eval_loss": 2.025285482406616,
+      "eval_runtime": 36.1046,
+      "eval_samples_per_second": 378.567,
+      "eval_steps_per_second": 47.335,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2830804438745088.0,
+  "total_flos": 3540372839989248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null