Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c363a1a59fc93c3321875d7f58013a2f10c3aab12f3af0076dff096e82ffb9c
+oid sha256:c1c8f434ea18d3b22fd15254827178bbe3ed96c6503f495dffba91cdd8f6000a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f24ddbe795a6b5a789b92a1ca3088daece7124054a836e4ca83341f355e4ec
+oid sha256:6bfe40ca2e2f7716947536cdec78ff3399a93f458d287f2974b9aa308cf568d4
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32a2a6418efcb48342a1dc67d0b88b496c3ab628f281d571af1360b4d0af05a5
+oid sha256:f7ddd132ae0c177184ed8a4f1a9ac2f3b51a04d85a111aa5717d5124f81bcd9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189a7468f8c95c103f6fc6f9a588f85a4d6a2cdd577f74ddb50948dbca31a23b
+oid sha256:9de1891a9bbbac025ea7d704b1888c3c146080478050b5c9e6f8305f0eea645f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.035977210849523544,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-18000",
-  "epoch": 8.875739644970414,
+  "best_metric": 0.035947080701589584,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-19000",
+  "epoch": 9.368836291913215,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,32 @@
       "eval_samples_per_second": 306.709,
       "eval_steps_per_second": 19.174,
       "step": 18000
+    },
+    {
+      "epoch": 9.122287968441814,
+      "grad_norm": 0.3517369031906128,
+      "learning_rate": 1.755424063116371e-06,
+      "loss": 0.0238,
+      "step": 18500
+    },
+    {
+      "epoch": 9.368836291913215,
+      "grad_norm": 0.5258517265319824,
+      "learning_rate": 1.2623274161735703e-06,
+      "loss": 0.0236,
+      "step": 19000
+    },
+    {
+      "epoch": 9.368836291913215,
+      "eval_accuracy": 0.9880196153464574,
+      "eval_f1": 0.6215357062905753,
+      "eval_loss": 0.035947080701589584,
+      "eval_precision": 0.7497299632750054,
+      "eval_recall": 0.5307792307104076,
+      "eval_runtime": 26.2793,
+      "eval_samples_per_second": 308.608,
+      "eval_steps_per_second": 19.293,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -494,7 +520,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 407138463972036.0,
+  "total_flos": 429748313255712.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null