Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81f15efc7e3ce404505af890ce245db75d3fad089f314bea69094fc866ae48f
+oid sha256:d091ae8d05dd0ffb4e38968e5fb78261e43049094a134911a5cbaea2b6bf7a5a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b74b8a270a5e136d4cb1bc947db6a88e504750e9dfb9b70537956032d32bf08
+oid sha256:c6c2c8bb4d51d0d5fbfe02927395f3fda7e44ecd66645795ccc8eaa8a13807c2
 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 sha256:6738b50414b7586ab4f34326eb323b53ebbfc9f2270aeb8382e096dd7926d61b
+oid sha256:d1898603f15858e1d30e0a114324bbe68b42a24ba79cd3917f2f7dd67be95b4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09037782996892929,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-1000",
-  "epoch": 0.4928536224741252,
+  "best_metric": 0.07024028897285461,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-2000",
+  "epoch": 0.9857072449482503,
   "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": 675.12,
       "eval_steps_per_second": 2.664,
       "step": 1000
+    },
+    {
+      "epoch": 0.7392804337111878,
+      "grad_norm": 0.3353608548641205,
+      "learning_rate": 1.9852143913257764e-05,
+      "loss": 0.0875,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9857072449482503,
+      "grad_norm": 0.3118976652622223,
+      "learning_rate": 1.980285855101035e-05,
+      "loss": 0.0778,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9857072449482503,
+      "eval_accuracy": 0.9813654208653996,
+      "eval_f1": 0.0,
+      "eval_loss": 0.07024028897285461,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 12.1524,
+      "eval_samples_per_second": 667.356,
+      "eval_steps_per_second": 2.633,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22632134187960.0,
+  "total_flos": 45379320672456.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null