Upload 13 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "tiiuae/falcon-rw-1b",
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLMSimulMT"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50258
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bf437b03c0effe9d0060e51a40a9fae5f20f03c12a5278beb01ebbfb94608d
+size 2623160918

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc0d1021e8caf207df93a564c7a1cb6ea0b705104d9b83639440be0e8d44546
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80c1b59036354cbe9a5fbd38732d33ae9231285af3651543fcf8aef5b5b8557
+size 1064

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "trust_remove_code": true,
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 10000,
+  "global_step": 7414,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.444575162494078e-05,
+      "loss": 1.6153,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.678323142825601e-05,
+      "loss": 1.0533,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.452828012447608e-05,
+      "loss": 0.9275,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4133015871047974,
+      "eval_runtime": 198.396,
+      "eval_samples_per_second": 5.056,
+      "eval_steps_per_second": 0.635,
+      "step": 3707
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.722287581247039e-05,
+      "loss": 0.7803,
+      "step": 4000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.223742416388575e-05,
+      "loss": 0.5688,
+      "step": 5000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.8557316642456684e-05,
+      "loss": 0.556,
+      "step": 6000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.56971387408811e-05,
+      "loss": 0.5531,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.454437255859375,
+      "eval_runtime": 198.5735,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 0.635,
+      "step": 7414
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 7414,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2.310114740327547e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c033703742a4b51f53ca023e6104b72c2cbdb41e8b67a1275c466bc94165c777
+size 4600