Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e92461c0a337d1dd2bff405603253f8264e3af53e9d34c5802a4e32340a674d
+oid sha256:7f7c95d444a18f6d4d89876ae2b4da834a6cfeaf78bcbb03128a11239100a3cf
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb4a0be311b1e98139917e61cafec146b95b94d710cbcf004fe9cd4dc0274a7
+oid sha256:8800bd0574dc25b4aba6e832e1e406ae5bfa6144fa64639eb169c977bc560fd1
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
+oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3bf1b4a06cfcf7ffbad3f6e707792c1da71ddc3c6fe8d02ca200ee95016b033
+oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03680593520402908,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-11000",
-  "epoch": 7.396449704142012,
+  "epoch": 7.889546351084813,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,32 @@
       "eval_samples_per_second": 549.469,
       "eval_steps_per_second": 2.167,
       "step": 15000
+    },
+    {
+      "epoch": 7.642998027613412,
+      "grad_norm": 0.23305435478687286,
+      "learning_rate": 1.8471696252465485e-05,
+      "loss": 0.0226,
+      "step": 15500
+    },
+    {
+      "epoch": 7.889546351084813,
+      "grad_norm": 0.5422170758247375,
+      "learning_rate": 1.8422386587771205e-05,
+      "loss": 0.0243,
+      "step": 16000
+    },
+    {
+      "epoch": 7.889546351084813,
+      "eval_accuracy": 0.9879064535278275,
+      "eval_f1": 0.6272163507729933,
+      "eval_loss": 0.0373537540435791,
+      "eval_precision": 0.7299247814596462,
+      "eval_recall": 0.5498468606431853,
+      "eval_runtime": 14.3703,
+      "eval_samples_per_second": 564.566,
+      "eval_steps_per_second": 2.227,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -420,12 +446,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 338806210140648.0,
+  "total_flos": 361390664998512.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null