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:f7d89f45ed7a74588a1be035d2ea199a8be4704f9015b71bd3026c99251b02fa
+oid sha256:f250d64bb25abe4348a3143eb34ec8dd36d0a36a9512b6f04b0e9bf258f127f5
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a8bac2db7d0fa672694df4ee9566e4246e340c39abdb988b54892f0b9d4a6f
+oid sha256:729b8be3a5b12d8a399174db30d2ca3b52a2020a83cfe83284845e326562d63c
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f4d181893c9bc040ba0fad0dbbee9a3f2de880b67f739edfd1460a79f556c2
+oid sha256:a0401383a513d57a10b63649026e14d1c47bd9d80e17cfd19e806d3c044e29f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
+oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2476589679718018,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.025466893039049237,
+  "epoch": 0.03395585738539898,
   "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": 5.266,
       "eval_steps_per_second": 1.316,
       "step": 150
+    },
+    {
+      "epoch": 0.027164685908319185,
+      "grad_norm": 0.8560181856155396,
+      "learning_rate": 0.0001779516693350504,
+      "loss": 1.1788,
+      "step": 160
+    },
+    {
+      "epoch": 0.028862478777589132,
+      "grad_norm": 0.7847142815589905,
+      "learning_rate": 0.00017275501775814182,
+      "loss": 1.2282,
+      "step": 170
+    },
+    {
+      "epoch": 0.030560271646859084,
+      "grad_norm": 0.8509446382522583,
+      "learning_rate": 0.00016722096269620562,
+      "loss": 1.2029,
+      "step": 180
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 0.9557679891586304,
+      "learning_rate": 0.00016137646550922228,
+      "loss": 1.2601,
+      "step": 190
+    },
+    {
+      "epoch": 0.03395585738539898,
+      "grad_norm": 1.3051382303237915,
+      "learning_rate": 0.00015525,
+      "loss": 1.2807,
+      "step": 200
+    },
+    {
+      "epoch": 0.03395585738539898,
+      "eval_loss": 1.330949306488037,
+      "eval_runtime": 236.0189,
+      "eval_samples_per_second": 5.254,
+      "eval_steps_per_second": 1.313,
+      "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": 4.844195528520499e+16,
+  "total_flos": 6.387406029088358e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null