Delete checkpoint-500

checkpoint-500/config.json

@@ -1,41 +0,0 @@
-{
-  "_name_or_path": "gpt2-medium",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 24,
-  "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
-  "use_cache": true,
-  "vocab_size": 50257
-}

checkpoint-500/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "transformers_version": "4.45.1"
-}

checkpoint-500/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ef04ec21c0dbb0e5b139fc8ca8f40768e3a5007cc6dabb700293b5e0c4ca919
-size 1419322880

checkpoint-500/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4cf7376cf5a360ec48ebe4de4c18e8100e9fad0f5d5b3606b82a413b51f35645
-size 2838829242

checkpoint-500/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:432de95bf48e4190f161536323973056f80bcb953554d6ffac8eaa65563057b3
-size 14244

checkpoint-500/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db4a46a26a1b390f9744d1adf3c0063293dadd0390068a13bbeebc3b177fc6b8
-size 1064

checkpoint-500/trainer_state.json

@@ -1,40 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.6496350364963503,
-  "eval_steps": 500,
-  "global_step": 500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 3.6496350364963503,
-      "grad_norm": 8.169337272644043,
-      "learning_rate": 3.175182481751825e-05,
-      "loss": 3.4139,
-      "step": 500
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 1370,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 923825015881728.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-500/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f87b340bc8350051c87f65a1906c566677b933151cba8c95319068ac9e86f65
-size 5176