Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03919594e15aa04dbb8008cf60a2a2d5b89be3490f892590197689b8410a661
+oid sha256:ffb0581c87a9b4ec4bd9bc79bf4d20868fe5ba52b951178a641df208a7d8c1f1
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e4c693ccaf9249bd98af9f184a00d5eb2f36b77cb0e433fbc26661d80daa72
+oid sha256:4348e5123797554906c7c2b1912fadc1c7517cd97cfa9d8e744ff152c29d9f62
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d880acef54d4eb61cf44bc2962e1f38bf44896cefc09a0303d9df0b77a1ae5c2
+oid sha256:012ecd1edf495661a426a7c3c4b090d5e2901f554832bf1d246a4e516cd8c109
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cdfe5ed4f14bdadfee62402701e9c3c91a7e1b8246c7c7f0be536b67574fb3
+oid sha256:797161cb36b8434a2e9b424b1551b1d663e1ac4112ca3f634c3c132aead6996b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3158954679965973,
-  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7500",
-  "epoch": 12.565445026178011,
+  "best_metric": 0.31398773193359375,
+  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-8000",
+  "epoch": 13.403141361256544,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 31.284,
       "eval_steps_per_second": 3.914,
       "step": 7500
+    },
+    {
+      "epoch": 12.649214659685864,
+      "grad_norm": 1.0162887573242188,
+      "learning_rate": 7.55e-06,
+      "loss": 0.3432,
+      "step": 7550
+    },
+    {
+      "epoch": 12.732984293193716,
+      "grad_norm": 0.977488100528717,
+      "learning_rate": 6.716666666666667e-06,
+      "loss": 0.3457,
+      "step": 7600
+    },
+    {
+      "epoch": 12.81675392670157,
+      "grad_norm": 0.8293308019638062,
+      "learning_rate": 5.8833333333333335e-06,
+      "loss": 0.3445,
+      "step": 7650
+    },
+    {
+      "epoch": 12.900523560209423,
+      "grad_norm": 0.9540147185325623,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 0.3444,
+      "step": 7700
+    },
+    {
+      "epoch": 12.984293193717278,
+      "grad_norm": 1.6243274211883545,
+      "learning_rate": 4.216666666666666e-06,
+      "loss": 0.3481,
+      "step": 7750
+    },
+    {
+      "epoch": 13.06806282722513,
+      "grad_norm": 0.8080894351005554,
+      "learning_rate": 3.3833333333333337e-06,
+      "loss": 0.3416,
+      "step": 7800
+    },
+    {
+      "epoch": 13.151832460732985,
+      "grad_norm": 0.8952440023422241,
+      "learning_rate": 2.55e-06,
+      "loss": 0.3423,
+      "step": 7850
+    },
+    {
+      "epoch": 13.235602094240837,
+      "grad_norm": 0.6296280026435852,
+      "learning_rate": 1.7166666666666668e-06,
+      "loss": 0.3454,
+      "step": 7900
+    },
+    {
+      "epoch": 13.319371727748692,
+      "grad_norm": 1.5492085218429565,
+      "learning_rate": 8.833333333333334e-07,
+      "loss": 0.344,
+      "step": 7950
+    },
+    {
+      "epoch": 13.403141361256544,
+      "grad_norm": 0.6316419839859009,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 0.3432,
+      "step": 8000
+    },
+    {
+      "epoch": 13.403141361256544,
+      "eval_loss": 0.31398773193359375,
+      "eval_runtime": 271.4112,
+      "eval_samples_per_second": 31.277,
+      "eval_steps_per_second": 3.913,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3437364892618304e+17,
+  "total_flos": 1.4332007404692806e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null