Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca22e06e41773986bf4cda69e78b19dae8d6c06562e9f7bf57bb6bc359c523cd
+oid sha256:c45df39d9c4dc5152faefbdf45711d1aa62e64d0c23e774085865f21bf591f9b
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50feb2e626b83408c0d4116c1f1ed25f6686b487bbb937489f8b52410e72e5a
+oid sha256:45efbd0d9e7c22e8c7835bae847bddd5fc3f03cc6671fcd7cf49c7ad364c0d9f
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b8d6aadceec387bdf2d000535b59c081063c48e8711fc23a19e65f0d3a3992
+oid sha256:d2a1a360bd35da073058490dcfac520d1611dcc1964a4ae6df1f2feddb4ce673
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22814798963634fbc95aa4159dff2ff1c962c3cd6bef60971d52789c5165d71
+oid sha256:331283a215653945c9f574623ef0726272c0b72361a70435936fcaea7a9b3ec5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,58 +1,34 @@
 {
-  "best_metric": 1.1206928491592407,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-800",
-  "epoch": 0.057916455512922606,
-  "eval_steps": 200,
-  "global_step": 800,
+  "best_metric": 1.0014784336090088,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
+  "epoch": 0.03619778469557663,
+  "eval_steps": 500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.014479113878230651,
-      "eval_loss": 1.4317502975463867,
-      "eval_runtime": 122.3776,
-      "eval_samples_per_second": 63.737,
-      "eval_steps_per_second": 0.498,
-      "step": 200
-    },
-    {
-      "epoch": 0.028958227756461303,
-      "eval_loss": 1.2947503328323364,
-      "eval_runtime": 122.3265,
-      "eval_samples_per_second": 63.764,
-      "eval_steps_per_second": 0.499,
-      "step": 400
-    },
     {
       "epoch": 0.03619778469557663,
-      "grad_norm": 10.083489418029785,
-      "learning_rate": 0.00019276044306088468,
-      "loss": 1.6511,
+      "grad_norm": 8.067161560058594,
+      "learning_rate": 9.638022153044234e-05,
+      "loss": 0.873,
       "step": 500
     },
     {
-      "epoch": 0.043437341634691956,
-      "eval_loss": 1.2087372541427612,
-      "eval_runtime": 122.3404,
-      "eval_samples_per_second": 63.757,
+      "epoch": 0.03619778469557663,
+      "eval_loss": 1.0014784336090088,
+      "eval_runtime": 122.228,
+      "eval_samples_per_second": 63.815,
       "eval_steps_per_second": 0.499,
-      "step": 600
-    },
-    {
-      "epoch": 0.057916455512922606,
-      "eval_loss": 1.1206928491592407,
-      "eval_runtime": 122.0821,
-      "eval_samples_per_second": 63.891,
-      "eval_steps_per_second": 0.5,
-      "step": 800
+      "step": 500
     }
   ],
   "logging_steps": 500,
   "max_steps": 13813,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 200,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -65,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6737094456115200.0,
+  "total_flos": 4210684035072000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7dc33602494f80ff9a206330dadebab61837d70a684cddb89f45ca6ed45e1c
+oid sha256:6994db69eb509e6cbee2ca91744d3ce71fc56a2d02ee0a28edcd732f1eea33bc
 size 5240