Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88f375c58d8ecf6070a3a48664a302ed8dbf0dad2ffd826a2ad6db509b872e9
+oid sha256:c08c279901858aee025dc9a01eaaf3e63e8e74ad64705510b55da3cc4bb13f92
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904aabd09e5ab2d4842541ff4a64ea0652371fcb9abb5ec68b195bb9f350b357
+oid sha256:2c4047bf30ee81dddc69b9bef4cd7dcad91c50c20b3f88f85ae682e07be9e180
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d252aa4fd4abcdd6921ac9bca5da24468d71664fb81e0357f080da3a33cfddad
+oid sha256:2a4e08f4bd2e13338aa886519af02f9f55dcd6d189e44d6214fbeb6f35dbe5b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,48 +1,24 @@
 {
-  "best_metric": 0.5371374487876892,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-172",
-  "epoch": 4.0,
+  "best_metric": 0.550789475440979,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-85",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 172,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5563850402832031,
-      "eval_runtime": 16.8934,
-      "eval_samples_per_second": 17.758,
-      "eval_steps_per_second": 4.44,
-      "step": 43
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.5786572694778442,
-      "eval_runtime": 16.9078,
-      "eval_samples_per_second": 17.743,
-      "eval_steps_per_second": 4.436,
-      "step": 86
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.5410714745521545,
-      "eval_runtime": 16.9111,
-      "eval_samples_per_second": 17.74,
-      "eval_steps_per_second": 4.435,
-      "step": 129
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.5371374487876892,
-      "eval_runtime": 16.8955,
-      "eval_samples_per_second": 17.756,
-      "eval_steps_per_second": 4.439,
-      "step": 172
+      "eval_loss": 0.550789475440979,
+      "eval_runtime": 28.7861,
+      "eval_samples_per_second": 10.422,
+      "eval_steps_per_second": 2.605,
+      "step": 85
     }
   ],
   "logging_steps": 500,
-  "max_steps": 840,
+  "max_steps": 1680,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -58,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 7872761701094400.0,
-  "train_batch_size": 8,
+  "total_flos": 3280317375456000.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79588ef006b4c033f0fd3d59d0987acd4668042b7cfd96edaf0a29cb13b029d
+oid sha256:398e7e7a79c7e812a6a1020ffa15321ac036a12ab5f062eb1380c17bb0b3f7bc
 size 5368