Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa258e012b8d75321923633ffd3adc37304c7e21de6361188a7c7feb575a73d
+oid sha256:d5da07f01d11e7cf1f124df9dd2f52c4e20bf0c9bf3ba44386b1292846989a5e
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00092f073b80e6617ed19d91d817fc22c7c933aa4eacd2119ba2956a2acfa305
+oid sha256:d0a32b964788782d25c5cfaf98526f2525f15670d397a29b03a398f483d05036
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d90ec2f6cf0a4672e81aa4266687b0f2b3f1b6f4e97f5c0361f1c6b861ef7bd
+oid sha256:99a9bfbfc42ab3ded4bf2d279ab34d2bb4755b1bd960316b66d8bb34b600c9e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daed8632d7b3f97a5b9ece4344a465207f55e2e431b8292402e5aafb5ff0c457
+oid sha256:13ceccea3d47e3b422f8ecdba99d0d05619c28f4d13687698def4c8f457b9cad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03322906419634819,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-14000",
-  "epoch": 1.7260510417950932,
+  "best_metric": 0.03276761621236801,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-15000",
+  "epoch": 1.849340401923314,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,6 +371,32 @@
       "eval_samples_per_second": 307.597,
       "eval_steps_per_second": 19.227,
       "step": 14000
+    },
+    {
+      "epoch": 1.7876957218592036,
+      "grad_norm": 0.46767064929008484,
+      "learning_rate": 1.6424608556281594e-05,
+      "loss": 0.035,
+      "step": 14500
+    },
+    {
+      "epoch": 1.849340401923314,
+      "grad_norm": 0.6348612308502197,
+      "learning_rate": 1.6301319196153374e-05,
+      "loss": 0.0331,
+      "step": 15000
+    },
+    {
+      "epoch": 1.849340401923314,
+      "eval_accuracy": 0.9885312552699116,
+      "eval_f1": 0.6380428462811396,
+      "eval_loss": 0.03276761621236801,
+      "eval_precision": 0.7686422413793104,
+      "eval_recall": 0.5453780870097102,
+      "eval_runtime": 26.5681,
+      "eval_samples_per_second": 305.291,
+      "eval_steps_per_second": 19.083,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -378,7 +404,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 316661234325408.0,
+  "total_flos": 339274711384200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null