Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759cf38f82d02fa3cca5c27eb0dc355664f734733198e0ae1e14461845d5d15b
+oid sha256:155e7c26e998bb57a40fb21976f9a438d45daadd9fad352380b19294ba1f8cd5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4826280aa7495c73ee0e1ffdcc33a2704b7fc22871d0051ddb69836051214328
+oid sha256:6a641ee2f59702715c621712d9b3e302b7d9d6ad3e6b85b96f7869cde13db5f4
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3180a148a4f43ede07ca7a046b51928848337e1d5c6fb4b8116bc27d671f92f
+oid sha256:6f47655c9e9b15cd98bfd9f717773db5107552bfdf7eec6f02f0af66c02f8d52
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
+oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9741289615631104,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0023912385021282023,
+  "epoch": 0.003188318002837603,
   "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": 16.992,
       "eval_steps_per_second": 4.248,
       "step": 150
+    },
+    {
+      "epoch": 0.0025506544022700826,
+      "grad_norm": 0.7145971655845642,
+      "learning_rate": 0.00017451298973437308,
+      "loss": 1.7097,
+      "step": 160
+    },
+    {
+      "epoch": 0.0027100703024119624,
+      "grad_norm": 0.8129323124885559,
+      "learning_rate": 0.0001694167565454241,
+      "loss": 1.853,
+      "step": 170
+    },
+    {
+      "epoch": 0.0028694862025538427,
+      "grad_norm": 1.0721731185913086,
+      "learning_rate": 0.0001639896397455543,
+      "loss": 1.8659,
+      "step": 180
+    },
+    {
+      "epoch": 0.003028902102695723,
+      "grad_norm": 1.490907907485962,
+      "learning_rate": 0.0001582580797022808,
+      "loss": 1.9599,
+      "step": 190
+    },
+    {
+      "epoch": 0.003188318002837603,
+      "grad_norm": 5.143823623657227,
+      "learning_rate": 0.00015225,
+      "loss": 1.9821,
+      "step": 200
+    },
+    {
+      "epoch": 0.003188318002837603,
+      "eval_loss": 2.058631658554077,
+      "eval_runtime": 1553.3483,
+      "eval_samples_per_second": 17.004,
+      "eval_steps_per_second": 4.251,
+      "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": 2.772682936418304e+16,
+  "total_flos": 3.696910581891072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null