Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8ab0a83c340e798f7e62c92f5d1e136c3278a268c3fdb62acab74f0d0da40f
+oid sha256:e4cca5bdfb012fd0f7593bd75cdf753f944075544c69c1b80749032d30975e46
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a52a2ec9e53a8a587adf9282e7a3c07a6f690e01d2512cf2198c882029e45f
+oid sha256:0c6ee0a058beb4b6db1c17d95e2fd6cadf3d09b3a23f95df9a486b706ba0ffdf
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
+oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e10a5ec83323055cf4ec6c11bd43e47c2440d47be4e380a83e7905438399849
+oid sha256:239fa09e124e09df5505eb284e48ffb12e108ec6cdc74ac0c4570827a7cff8ee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03767974302172661,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-11000",
-  "epoch": 5.914243469689502,
+  "best_metric": 0.03750571236014366,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-13000",
+  "epoch": 6.407097092163627,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 565.503,
       "eval_steps_per_second": 2.231,
       "step": 12000
+    },
+    {
+      "epoch": 6.160670280926565,
+      "grad_norm": 0.16942404210567474,
+      "learning_rate": 1.8767964514539182e-05,
+      "loss": 0.0275,
+      "step": 12500
+    },
+    {
+      "epoch": 6.407097092163627,
+      "grad_norm": 0.3766990303993225,
+      "learning_rate": 1.8718777723016266e-05,
+      "loss": 0.0254,
+      "step": 13000
+    },
+    {
+      "epoch": 6.407097092163627,
+      "eval_accuracy": 0.9875646640305001,
+      "eval_f1": 0.6140921885995778,
+      "eval_loss": 0.03750571236014366,
+      "eval_precision": 0.7280976220275344,
+      "eval_recall": 0.5309552783693338,
+      "eval_runtime": 14.3059,
+      "eval_samples_per_second": 566.897,
+      "eval_steps_per_second": 2.237,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -347,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 272144546750178.0,
+  "total_flos": 294847422552900.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null