Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a974b33b2ef31145e81d45c025a38c395a6c3c4541d1969f7d9f6d215512528
+oid sha256:6c8cc9a2f725c6934baa9d56c720425e0384071c22db96c2194527e1d922dbef
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec825a86988511e7dbf4537ca2dab8dc2b32517b29d61d1a8c1ff9ee520d22b
+oid sha256:68a0778a7ad31d64fe618dd6509a81ae2c6668b8e9aec7b97082b2e843f25005
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34649568145f465443beb487f2295ab3dad9e5f49f758646dd823029413e18fe
+oid sha256:69797e619b7f76fc3c65d1346887cd92f6a036b8a8ff866da9ca1a335d274133
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e136870ce715682b288c29fb4d05a0aec61f1a74b2cc393d7fb9e66e4965261
+oid sha256:de10e3ea9e9f590bd00b7f01055683747e52076430fd0eff98a7f3083d4ae0fc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.089978888630867,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-1000",
-  "epoch": 0.4930966469428008,
+  "best_metric": 0.06878085434436798,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-2000",
+  "epoch": 0.9861932938856016,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,6 +33,32 @@
       "eval_samples_per_second": 677.827,
       "eval_steps_per_second": 2.675,
       "step": 1000
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.385586678981781,
+      "learning_rate": 1.9852071005917162e-05,
+      "loss": 0.0863,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 0.3922920525074005,
+      "learning_rate": 1.980276134122288e-05,
+      "loss": 0.0769,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_accuracy": 0.9813966013294216,
+      "eval_f1": 0.0015213753232922562,
+      "eval_loss": 0.06878085434436798,
+      "eval_precision": 0.9090909090909091,
+      "eval_recall": 0.0007613247049866769,
+      "eval_runtime": 14.1244,
+      "eval_samples_per_second": 574.184,
+      "eval_steps_per_second": 2.266,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22565797728696.0,
+  "total_flos": 45150252586560.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null