Upload folder using huggingface_hub

checkpoint-2/config.json

@@ -31,7 +31,7 @@
       "max_length": 1000
     }
   },
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "use_cache": true,
   "vocab_size": 50257

checkpoint-2/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75daecf07ed91720ddc6b67797ffb531d15449a24ef4b9b7ca4be461e3217d63
-size 248926387
+oid sha256:d2245c47fd6ede01d43d2b61a9e51a60aa5f2b62ed7c4b3e5c29a87fa74ae47a
+size 497806003

checkpoint-2/trainer_state.json

@@ -2,17 +2,17 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [],
-  "logging_steps": 10,
-  "max_steps": 3,
+  "logging_steps": 5,
+  "max_steps": 4,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -26,8 +26,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 2612920320000.0,
-  "train_batch_size": 4,
+  "total_flos": 5225840640000.0,
+  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-2/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eabaaa0bdaccba1b86a81d17cd1c9aabd7f51bd63331449c0fc287de407316c
+oid sha256:c2d85571f50b6ee5d8da4626ce6d3a308d432ed12f04a5cdbf71aed5f844a9f7
 size 5713

checkpoint-4/chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

checkpoint-4/config.json

@@ -0,0 +1,38 @@
+{
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-4/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

checkpoint-4/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b191a3eea545f4c9475e8ce9c409f1b3a0280a4d7ee1b2c8a73100dfc382013b
+size 497806003

checkpoint-4/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-4/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 5,
+  "max_steps": 4,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 10451681280000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d85571f50b6ee5d8da4626ce6d3a308d432ed12f04a5cdbf71aed5f844a9f7
+size 5713

config.json

@@ -31,7 +31,7 @@
       "max_length": 1000
     }
   },
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "use_cache": true,
   "vocab_size": 50257

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75daecf07ed91720ddc6b67797ffb531d15449a24ef4b9b7ca4be461e3217d63
-size 248926387
+oid sha256:b191a3eea545f4c9475e8ce9c409f1b3a0280a4d7ee1b2c8a73100dfc382013b
+size 497806003

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eabaaa0bdaccba1b86a81d17cd1c9aabd7f51bd63331449c0fc287de407316c
+oid sha256:c2d85571f50b6ee5d8da4626ce6d3a308d432ed12f04a5cdbf71aed5f844a9f7
 size 5713