Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94f9d6666b1a9dc0e28d7b13cf83c5574ecf686f36bd31e0d0171eb47aa550d
+oid sha256:22b433288e6f4c8a585318a1780bbd9df8cfd615404e95eb9ca74a6e09187331
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba9526ab6455d8b2b40a9306ddc45df5954ef5d7b91bff76925f1d805640ab1
+oid sha256:dec91e22b6906152779015a71ae88395cfc9a88318675083944ab160e73b3cbb
 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": 0.09066470712423325,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-01/checkpoint-1000",
-  "epoch": 0.4930966469428008,
+  "best_metric": 0.07067307829856873,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-01/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": 668.329,
       "eval_steps_per_second": 2.637,
       "step": 1000
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.4004117548465729,
+      "learning_rate": 1.9852071005917162e-05,
+      "loss": 0.088,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 0.37588435411453247,
+      "learning_rate": 1.980276134122288e-05,
+      "loss": 0.0787,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_accuracy": 0.9813654208653996,
+      "eval_f1": 0.0,
+      "eval_loss": 0.07067307829856873,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 12.2547,
+      "eval_samples_per_second": 661.789,
+      "eval_steps_per_second": 2.611,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22728529355328.0,
+  "total_flos": 45294327084024.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null