Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3726724bdfc1f15ccd9d7009954679040f6a5057593f0e53cb22f8de4441801e
+oid sha256:73a5f213038caea6d0f765ed163ac956e07f23817953a206db64adff8dc1c82e
 size 201353888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c731bf206b67c9dc3a3865901c094840a143ec0a7b6230d21edff62b680364
+oid sha256:d22109810585f81db587bef034fc3e7a44f4ddecd1c9d1a3b70e3597827dec2c
 size 102462970

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c3f023773a763c7752cff7a2cfe5d93061a72542e671499b251990ae933b47
+oid sha256:8e6cdc525c216b4988899877728a877ea49d5856ad047b44872ff2194edf2d63
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dda8e23eb74de37246608ecab5e9e8cf4152d083d5af11ccf1949826389d55e
+oid sha256:dfe72adb152381e7c378d620f1c9a49a58aedbeeb82de459233276badd6fa965
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269faae201d8c4599499310b72daea0f3f9d231b2503dd327095929cb1e6f65b
+oid sha256:db71312af1e5036b6f310023ab8ee1a20a8b54f3acb6f25510bb52d12ff2921b
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bd713ce0d3aa6ee4628e8a45f017ac47360a47c91b9f3e876447c02b9aa157
+oid sha256:1c8394c125a7aa571c60d2dad67062ca22f2e1c86e66337a3ce4ef278d4f6a59
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29034358b803138e7ba08457f393d394c8782b215e7dd4c2e739a328fbe36b88
+oid sha256:9d519837875d2fad360e6b123dae6fe4cca3a3863381929a43410dd1e9dc15f3
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad78d3256a679c85ec607ae3ef96ad748c4c6188b89daa9b78e6c8189f2bddbd
+oid sha256:f7b117cae206313baa43d38cad2e60f69d8976f3a9ac62686440cc343f029b12
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b4eb601c4a16da1a716244446dd8c32663c2ef695f13f81dadf39d2d03ca27
+oid sha256:806c1bdad3b16517680548407153d658b11234332f994bc7ef51b83081fc372c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c36ad1143b53df0e58c95c81b83020a040cb52a6384f8da65c6b41b04d1a221
+oid sha256:4073db78f3235682ed65df4572c0abab1f997de8322cf04c8aa786133740a37b
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb63c959df6b9e7cb6e3c4d1c60a05accf8c288a84c2d6055c2c275a02eb10d3
+oid sha256:6dda94356f651b1469f08ad6fc7af766b0d035b3f3b84ff6cdff7821e3118785
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4780738353729248,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6097560975609756,
+  "epoch": 0.8130081300813008,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 78.049,
       "eval_steps_per_second": 10.025,
       "step": 150
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 51.72230911254883,
+      "learning_rate": 0.00019999995954104554,
+      "loss": 1.9779,
+      "step": 160
+    },
+    {
+      "epoch": 0.6910569105691057,
+      "grad_norm": 69.81781005859375,
+      "learning_rate": 0.0001999997613748169,
+      "loss": 2.5513,
+      "step": 170
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 70.12183380126953,
+      "learning_rate": 0.00019999939807040424,
+      "loss": 2.5442,
+      "step": 180
+    },
+    {
+      "epoch": 0.7723577235772358,
+      "grad_norm": 49.484066009521484,
+      "learning_rate": 0.00019999886962840765,
+      "loss": 2.3451,
+      "step": 190
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 170.3453826904297,
+      "learning_rate": 0.00019999817604969975,
+      "loss": 2.3973,
+      "step": 200
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "eval_loss": 2.4376235008239746,
+      "eval_runtime": 2.7798,
+      "eval_samples_per_second": 78.423,
+      "eval_steps_per_second": 10.073,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5959498648780800.0,
+  "total_flos": 7945998198374400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null