Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9107c0ff4e2763513ec5bf8850c4b4e538db65052ee12ccd65d557cafb1e34b8
+oid sha256:99e38e3602d41711cdbb533cb7d6b84bc03b5cfdcec09079e6e94d8e9c933c1f
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e28ceda6028390e61736b0495cead414f93a42f97c1b979bdc56131341a08c
+oid sha256:4324a138b51ccff30cd6582605837ac09263f11a633b6ebf8526d9c133d37e6a
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b7a8f09422f4c6b082af7bb144b5b0532b4a256c4619f625ac9a304c7ea0aa
+oid sha256:ddee4e1cd9c11fae1531a3888b26c6306dfc6effea2b5b4de3f934096de4907a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f334224cb0aa3586560a9532b53aefd38c1d84e10d9b30ca047caee043ff116
+oid sha256:bc650e789a99f1d69f79d9aa960ac1927e43a2cad64cee2ef28fa7a0ac21a5a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.31039854884147644,
-  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-9000",
-  "epoch": 15.078534031413612,
+  "best_metric": 0.3102165162563324,
+  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-9500",
+  "epoch": 15.916230366492147,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1411,6 +1411,84 @@
       "eval_samples_per_second": 30.275,
       "eval_steps_per_second": 3.787,
       "step": 9000
+    },
+    {
+      "epoch": 15.162303664921467,
+      "grad_norm": 1.0989015102386475,
+      "learning_rate": 2.9530000000000004e-05,
+      "loss": 0.3381,
+      "step": 9050
+    },
+    {
+      "epoch": 15.24607329842932,
+      "grad_norm": 1.1959214210510254,
+      "learning_rate": 2.903e-05,
+      "loss": 0.3381,
+      "step": 9100
+    },
+    {
+      "epoch": 15.329842931937172,
+      "grad_norm": 0.9721996188163757,
+      "learning_rate": 2.853e-05,
+      "loss": 0.3384,
+      "step": 9150
+    },
+    {
+      "epoch": 15.413612565445026,
+      "grad_norm": 1.2921016216278076,
+      "learning_rate": 2.803e-05,
+      "loss": 0.3375,
+      "step": 9200
+    },
+    {
+      "epoch": 15.497382198952879,
+      "grad_norm": 1.1854231357574463,
+      "learning_rate": 2.753e-05,
+      "loss": 0.3389,
+      "step": 9250
+    },
+    {
+      "epoch": 15.581151832460733,
+      "grad_norm": 1.571321725845337,
+      "learning_rate": 2.703e-05,
+      "loss": 0.3406,
+      "step": 9300
+    },
+    {
+      "epoch": 15.664921465968586,
+      "grad_norm": 1.2595016956329346,
+      "learning_rate": 2.6540000000000003e-05,
+      "loss": 0.3392,
+      "step": 9350
+    },
+    {
+      "epoch": 15.74869109947644,
+      "grad_norm": 1.2291969060897827,
+      "learning_rate": 2.6040000000000005e-05,
+      "loss": 0.3362,
+      "step": 9400
+    },
+    {
+      "epoch": 15.832460732984293,
+      "grad_norm": 1.0605494976043701,
+      "learning_rate": 2.5540000000000003e-05,
+      "loss": 0.3388,
+      "step": 9450
+    },
+    {
+      "epoch": 15.916230366492147,
+      "grad_norm": 0.9927255511283875,
+      "learning_rate": 2.504e-05,
+      "loss": 0.3391,
+      "step": 9500
+    },
+    {
+      "epoch": 15.916230366492147,
+      "eval_loss": 0.3102165162563324,
+      "eval_runtime": 279.552,
+      "eval_samples_per_second": 30.366,
+      "eval_steps_per_second": 3.799,
+      "step": 9500
     }
   ],
   "logging_steps": 50,
@@ -1430,7 +1508,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6124734632740026e+17,
+  "total_flos": 1.7021322045447034e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null