Upload folder using huggingface_hub

checkpoint-1/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "MisterAI/bigscience_bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

checkpoint-1/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.49.0"
+}

checkpoint-1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9370f4a70b0a63c182e280ba6cc11d8d2de19073f4b79feed1677dfabbf8f6e8
+size 2236892304

checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974d8e2eb5dea815f1dc835d65e4f100dcd576acd3a6f8e6375e59bdabb72c3a
+size 4473954638

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4864c89835cbf79e96fc0a2d2de7044506fea9c48cfcbba91fdab915a1eb9808
+size 13990

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde8705bb323f5fe23427d88f7466e6183420613d541a4cbb3a30eb1a9de7c0c
+size 1064

checkpoint-1/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 928706985984.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943aef7a9045f9ab551b6790c00162e434f16ed88f19f903212dbc517c4cc0bf
+size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d6a4e21de45183e66e64f21d7b23a4c9c5a9eaa4a96d3218508febf0f36c22
+oid sha256:9370f4a70b0a63c182e280ba6cc11d8d2de19073f4b79feed1677dfabbf8f6e8
 size 2236892304

tokenizer_config.json

@@ -38,11 +38,17 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
+  "max_length": 512,
   "merges_file": null,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
+  "stride": 0,
   "tokenizer_class": "BloomTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "vocab_file": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41940dd9c9d8d44bbd60d5a3b1f83593e41741b8ef22fc21d087a365cb41d1e
+oid sha256:943aef7a9045f9ab551b6790c00162e434f16ed88f19f903212dbc517c4cc0bf
 size 5432