Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb179d6c448b248132cb57e6fb774b148e75841aa13a4c505f3c632b8413638a
+oid sha256:b205d7f35845d0d429aa73024ac4a0e78a6f0690b595755ca4a9b159e1694e50
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e32bcee3c48678d1c5db6c0ffdb21dd9630b8698bbf96d5f6b29d24b2e55ee
+oid sha256:ba445ab2e1edbbf4f8d111ac8e5c3669df8ae8ab180bc93dbc70439020812c2e
 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:ba9826396d1061aee6fdf7293fd789e47f8a5ac9db78d8396f43ecdcae9b12a2
+oid sha256:f11095f13a6bb8e73004d74d741982d584b499e9ac31a59ea1de9965f3fec76b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3666408658027649,
-  "best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-7500",
-  "epoch": 12.565445026178011,
+  "best_metric": 0.3662460446357727,
+  "best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_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": 32.242,
       "eval_steps_per_second": 4.034,
       "step": 7500
+    },
+    {
+      "epoch": 12.649214659685864,
+      "grad_norm": 0.8195668458938599,
+      "learning_rate": 7.566666666666667e-07,
+      "loss": 0.4032,
+      "step": 7550
+    },
+    {
+      "epoch": 12.732984293193716,
+      "grad_norm": 0.9879769086837769,
+      "learning_rate": 6.733333333333334e-07,
+      "loss": 0.4078,
+      "step": 7600
+    },
+    {
+      "epoch": 12.81675392670157,
+      "grad_norm": 2.3267557621002197,
+      "learning_rate": 5.900000000000001e-07,
+      "loss": 0.4058,
+      "step": 7650
+    },
+    {
+      "epoch": 12.900523560209423,
+      "grad_norm": 0.9204362034797668,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.4052,
+      "step": 7700
+    },
+    {
+      "epoch": 12.984293193717278,
+      "grad_norm": 1.0587321519851685,
+      "learning_rate": 4.233333333333334e-07,
+      "loss": 0.4111,
+      "step": 7750
+    },
+    {
+      "epoch": 13.06806282722513,
+      "grad_norm": 0.8546725511550903,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.4021,
+      "step": 7800
+    },
+    {
+      "epoch": 13.151832460732985,
+      "grad_norm": 0.7696201801300049,
+      "learning_rate": 2.566666666666667e-07,
+      "loss": 0.4035,
+      "step": 7850
+    },
+    {
+      "epoch": 13.235602094240837,
+      "grad_norm": 0.8487740755081177,
+      "learning_rate": 1.7333333333333335e-07,
+      "loss": 0.4077,
+      "step": 7900
+    },
+    {
+      "epoch": 13.319371727748692,
+      "grad_norm": 0.9611801505088806,
+      "learning_rate": 9e-08,
+      "loss": 0.4058,
+      "step": 7950
+    },
+    {
+      "epoch": 13.403141361256544,
+      "grad_norm": 0.7191503047943115,
+      "learning_rate": 6.666666666666667e-09,
+      "loss": 0.4044,
+      "step": 8000
+    },
+    {
+      "epoch": 13.403141361256544,
+      "eval_loss": 0.3662460446357727,
+      "eval_runtime": 261.9325,
+      "eval_samples_per_second": 32.409,
+      "eval_steps_per_second": 4.054,
+      "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