Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce19c672be0d8e93a7fa34f22da21019af73a72b352a65bdfa8a3d06b1c6a9e
+oid sha256:27bb833041adfed42b6a3ef2a35959c1b1b7ec6fac87c9be3548d8be65091b43
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f1fa73ea7a5820ec872caa2a1dcbe4434a262fc31339d2a61a280dcaae0398
+oid sha256:769c965d71315065d6a2bf11b3587d15c515c2ddccef1e3c359b7c3985c89ed3
 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": 0.0910971537232399,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-1000",
-  "epoch": 0.4930966469428008,
+  "best_metric": 0.07068673521280289,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/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": 669.294,
       "eval_steps_per_second": 2.641,
       "step": 1000
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.33391374349594116,
+      "learning_rate": 1.9852071005917162e-05,
+      "loss": 0.0874,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 0.3162483870983124,
+      "learning_rate": 1.980276134122288e-05,
+      "loss": 0.0785,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_accuracy": 0.981383845685049,
+      "eval_f1": 0.0,
+      "eval_loss": 0.07068673521280289,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 12.2907,
+      "eval_samples_per_second": 659.85,
+      "eval_steps_per_second": 2.604,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22568907250224.0,
+  "total_flos": 45292254069672.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null