Upload folder using huggingface_hub

checkpoint-316/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-316/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-316/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfbb72d053017486fb307a2cd9cf83dcd8d915f84797c1106fdb50766696788
+size 2236892304

checkpoint-316/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ba5f9c9c1c4264f97668c459b9d743ec3e79436157a64a3d598f460ed063e6
+size 4473954638

checkpoint-316/rng_state.pth

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

checkpoint-316/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9031796aa97525ded3c7342519833c7e15ce42382c4b2d3b8c3226274a7d42d
+size 1064

checkpoint-316/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 316,
+  "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": 586014108155904.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-316/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27131aab987486cc0abf734c35f1790dbb9af39e0d4051e29646035b8e709763
+size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9370f4a70b0a63c182e280ba6cc11d8d2de19073f4b79feed1677dfabbf8f6e8
+oid sha256:adfbb72d053017486fb307a2cd9cf83dcd8d915f84797c1106fdb50766696788
 size 2236892304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943aef7a9045f9ab551b6790c00162e434f16ed88f19f903212dbc517c4cc0bf
+oid sha256:27131aab987486cc0abf734c35f1790dbb9af39e0d4051e29646035b8e709763
 size 5432