Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fcb0b12d80922acf2ee11edfa317445b89d6ea898d7004e49308eab044ae29f
+oid sha256:2b5e3d074c6d233b824116477cd45caa5f2af53ea01b79852be89a501cbc11a6
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bef9e44e257616711808e8eccedc362b9ac2a971c10fdc4ca87f4f7d96f3c34
+oid sha256:16ee9cc242df46373729458c2a333a599ef680eeded9e36d27a47f326299a9bf
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651d1232597f5c3e9197278fb6bc58c260307b3b5a878a7a3eef0561cd79931c
+oid sha256:b03b85e31744d00cc2d94c7c6e3fa2c80dfeeb8c31f749966344ce5e50d86f7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed05c2781030d49f708235d0b4004a9dd014c1dad90b888053a7b20bddc62e8a
+oid sha256:552768df724b19ebb0b14b82f95a15767c10a28d5a12e1405c76a16dc8363389
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.038920916616916656,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-9000",
-  "epoch": 70.86614173228347,
+  "best_metric": 0.03880663216114044,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-10000",
+  "epoch": 78.74015748031496,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,32 @@
       "eval_samples_per_second": 573.016,
       "eval_steps_per_second": 2.261,
       "step": 9000
+    },
+    {
+      "epoch": 74.80314960629921,
+      "grad_norm": 0.1340780407190323,
+      "learning_rate": 2.66240157480315e-06,
+      "loss": 0.0279,
+      "step": 9500
+    },
+    {
+      "epoch": 78.74015748031496,
+      "grad_norm": 0.15667644143104553,
+      "learning_rate": 2.5393700787401576e-06,
+      "loss": 0.0269,
+      "step": 10000
+    },
+    {
+      "epoch": 78.74015748031496,
+      "eval_accuracy": 0.9875037203962753,
+      "eval_f1": 0.598039662639617,
+      "eval_loss": 0.03880663216114044,
+      "eval_precision": 0.7453409090909091,
+      "eval_recall": 0.49935287400076134,
+      "eval_runtime": 14.1798,
+      "eval_samples_per_second": 571.941,
+      "eval_steps_per_second": 2.257,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -260,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4045469369052420.0,
+  "total_flos": 4494270757217364.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null