Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a7488bed7d21b9d657acf5d802f757403baaf63574695009d71fae3ac47f67
+oid sha256:11865c358c291dac86ad735d2f7fd6af498765fee0e0c8d8af77fea4c92d553f
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2607522a98a6903a037ba433898c5e6d87958fa03ff6b99f53dfb04c2ca554
+oid sha256:8a2446bdd553d6e87bb5e148cc8c035cb0dbb3c5c706ab879520da8f84e90137
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d80b79a69e4f894c197c0b1defc7caf9fab30548c188de1b8721ebe81256e1
+oid sha256:6f3aed9227eb5675bbeae15066ad3be786e895f17e73f557c12d5171190ed5f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc78139ebcfada68990564fb6a028a79c77713a52b6e3d0b599cebfd1682acb
+oid sha256:c39a5eb5a9b85db1e545d7fe966a0dbc20c74269a76ea5b66d44f5c7e74d1aa6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7471781403358312,
   "best_model_checkpoint": "training_dir/checkpoint-6000",
-  "epoch": 0.9536929108826958,
+  "epoch": 1.0596587898696619,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -178,6 +178,25 @@
       "eval_samples_per_second": 50.687,
       "eval_steps_per_second": 6.336,
       "step": 9000
+    },
+    {
+      "epoch": 1.0596587898696619,
+      "grad_norm": 0.9228487610816956,
+      "learning_rate": 8.987962075210399e-06,
+      "loss": 0.4301,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0596587898696619,
+      "eval_accuracy": 0.7543706293706294,
+      "eval_f1": 0.7467502305507533,
+      "eval_loss": 0.9882783889770508,
+      "eval_precision": 0.7520962568093716,
+      "eval_recall": 0.7543706293706294,
+      "eval_runtime": 45.8296,
+      "eval_samples_per_second": 49.924,
+      "eval_steps_per_second": 6.241,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -197,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7917341296849568e+16,
+  "total_flos": 1.990786624703705e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null