Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5305db9dc3b35ada7e28de471d8a93c198fce0e6179c8f4843c1cad98f9ff05
+oid sha256:efa258e012b8d75321923633ffd3adc37304c7e21de6361188a7c7feb575a73d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae873e04ea15e075c791a470276bf6aed8e32e21a540007436243d921549bbb
+oid sha256:00092f073b80e6617ed19d91d817fc22c7c933aa4eacd2119ba2956a2acfa305
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d088be71b0db07e8ca0115c931279967e5eb53f1c7bedd90a04ccd028d145ff
+oid sha256:1d90ec2f6cf0a4672e81aa4266687b0f2b3f1b6f4e97f5c0361f1c6b861ef7bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4a9f0952f38c2a7352c6af4e8357c1d43055d3b068e5edda6136fb17f11371
+oid sha256:daed8632d7b3f97a5b9ece4344a465207f55e2e431b8292402e5aafb5ff0c457
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03410067781805992,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-12000",
-  "epoch": 1.6027616816668722,
+  "best_metric": 0.03322906419634819,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-14000",
+  "epoch": 1.7260510417950932,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -345,6 +345,32 @@
       "eval_samples_per_second": 308.724,
       "eval_steps_per_second": 19.298,
       "step": 13000
+    },
+    {
+      "epoch": 1.6644063617309826,
+      "grad_norm": 0.38684606552124023,
+      "learning_rate": 1.6671187276538038e-05,
+      "loss": 0.0344,
+      "step": 13500
+    },
+    {
+      "epoch": 1.7260510417950932,
+      "grad_norm": 0.26073306798934937,
+      "learning_rate": 1.6547897916409814e-05,
+      "loss": 0.0348,
+      "step": 14000
+    },
+    {
+      "epoch": 1.7260510417950932,
+      "eval_accuracy": 0.9882265746672959,
+      "eval_f1": 0.6325194621372965,
+      "eval_loss": 0.03322906419634819,
+      "eval_precision": 0.7503410641200545,
+      "eval_recall": 0.5466778805719091,
+      "eval_runtime": 26.3689,
+      "eval_samples_per_second": 307.597,
+      "eval_steps_per_second": 19.227,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -352,7 +378,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 294192868271256.0,
+  "total_flos": 316661234325408.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null