Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bdf7a12daee72631644ff26e7c9f80bbf2ff91189adeb79844f41ec3b3a0de
+oid sha256:53e52b6d2329dc025f309262138c685c2d456edec0bf62d31a7b72dcedba0776
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd720e9bd3c6b76823b903b091b8513f63bb3e34dff5623eb6c72cf14934888
+oid sha256:18bed64a2488c7a6d5c52b9cbb86e65f981cc01aeb77c06f9737f6691ab28f75
 size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912d3b1d35846784f3679bfe983446d30830056bb9c64fff6ed2d9239f2efee7
+oid sha256:2cd2165ee95963f994c4fb0318462352e4521cc9252f74bcb019a89c3a0d1bb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d1d3e656c776bd4cb00d51e16dbc3c67347908a818c2aee478de24ffb13283
+oid sha256:f6a1e3232c9dd0558d3b582345b4a537ca2d63d9ae2df7d7189cbdc92c4e384f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8344256281852722,
   "best_model_checkpoint": "miner_id_24/checkpoint-1800",
-  "epoch": 2.179176755447942,
+  "epoch": 2.4213075060532687,
   "eval_steps": 200,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 64.244,
       "eval_steps_per_second": 16.061,
       "step": 1800
+    },
+    {
+      "epoch": 2.2397094430992737,
+      "grad_norm": 0.766105592250824,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.7791,
+      "step": 1850
+    },
+    {
+      "epoch": 2.3002421307506054,
+      "grad_norm": 0.9087867140769958,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.8034,
+      "step": 1900
+    },
+    {
+      "epoch": 2.360774818401937,
+      "grad_norm": 0.7230655550956726,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8078,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4213075060532687,
+      "grad_norm": 0.8146218657493591,
+      "learning_rate": 0.0,
+      "loss": 0.7728,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4213075060532687,
+      "eval_loss": 0.8369823694229126,
+      "eval_runtime": 10.8447,
+      "eval_samples_per_second": 64.179,
+      "eval_steps_per_second": 16.045,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -353,7 +389,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -362,12 +398,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.446460309307392e+16,
+  "total_flos": 3.82940034367488e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null