Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcc03faff60c88187d193d577cb074f7b887352b1d8d0044f027b8b7434cb2b
+oid sha256:1079622f2612a95fbc448a4293eda67ec36fbd3e6fb4754f582e020e4d18564e
 size 50366280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8fe46463f94afbb7df6a2c63de8998de252334e1031f63ce36abe9e77ee7ccf
+oid sha256:277a71751ef2c8afdaacffefd9fbad45eddbf307cba61d281df97023d255956b
 size 51423589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203d8905e943b46c8e72ae2945349c735f85b24536f3be5e4997e93af1f994c2
+oid sha256:99161bb0cceb37acf26975ed4da4ae601fc9347933db90ac96946aa50c7d9117
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a7fa4a93dbd8112336bf69dd77955c95bfe5afe563e5b75d8b00190ba21fa6
+oid sha256:45e3c1568fcd4694d42878c8f9021316c81ae2099977158a4abdbd041e52fd76
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 75,
-  "best_metric": 0.4165111482143402,
-  "best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-75",
-  "epoch": 0.8016032064128257,
+  "best_global_step": 175,
+  "best_metric": 0.3314667046070099,
+  "best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-175",
+  "epoch": 0.9352037408149633,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,6 +134,27 @@
       "eval_samples_per_second": 6.602,
       "eval_steps_per_second": 0.825,
       "step": 150
+    },
+    {
+      "entropy": 0.17346227929927407,
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00011670516255021193,
+      "loss": 0.17009424209594726,
+      "mean_token_accuracy": 0.9412828385829926,
+      "num_tokens": 372951.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "eval_entropy": 0.38417646361483354,
+      "eval_loss": 0.3314667046070099,
+      "eval_mean_token_accuracy": 0.8934800239269343,
+      "eval_num_tokens": 372951.0,
+      "eval_runtime": 428.9346,
+      "eval_samples_per_second": 6.602,
+      "eval_steps_per_second": 0.825,
+      "step": 175
     }
   ],
   "logging_steps": 25,
@@ -153,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9176907730673664.0,
+  "total_flos": 1.0794539309395968e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null