Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6131/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-10000/README.md

@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

checkpoint-10000/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloom-560m",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-10000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e373fe27be24eb42db1383d9d02ef59165e1f3af443dcb4920b23f34071ef8d0
+size 100734154

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1ba0d9c6cfa10de9a04b893420d0fd66f6eb88dda7422f03b3009fdc11b432
+size 201442810

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d302440082c3838f189a626575a842d5b4f3e13287c6de3e8f07f690d6a71747
+size 14244

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d201f8cd0cb533372b87ee9bb45a668e400fe99f99bc5448fb4b0b1eaec57e47
+size 1064

checkpoint-10000/special_tokens_map.json

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

checkpoint-10000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f80388e55d7d18f8caab6f55ccb39dab31d696d1726564e91fe74459b6c6f2
+size 14500653

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250680": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "trust_remove_code": true,
+  "unk_token": "<unk>"
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6309389111444095,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001095993248702382,
+      "loss": 2.4022,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.747903910575024e-05,
+      "loss": 2.0017,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 6.325609676486509e-05,
+      "loss": 1.9066,
+      "step": 3000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.47859539514937e-05,
+      "loss": 1.8683,
+      "step": 4000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.899959575500252e-05,
+      "loss": 1.819,
+      "step": 5000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.472881497382854e-05,
+      "loss": 1.7923,
+      "step": 6000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.140984967596197e-05,
+      "loss": 1.7393,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.873467559917656e-05,
+      "loss": 1.7167,
+      "step": 8000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.6518895047466676e-05,
+      "loss": 1.7016,
+      "step": 9000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.4644480772694546e-05,
+      "loss": 1.6837,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 4.319801203657114e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d07bf671b3be04c66b0eb152014c6437294127c12d6ae5e789a6a68f9a8cb3
+size 4536

checkpoint-6131/README.md

@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

checkpoint-6131/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloom-560m",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-6131/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8840ef6aae20670d2be5db6f1f0fc0b936c7584eb85b2044986482f2c1ac7e0f
+size 100734154

checkpoint-6131/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7036296f07a9f8d8fcad048b431b9260f0f0731345d71fa6cf4092b7d599393
+size 201442810

checkpoint-6131/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c34e4f2df3e9b50a7934b969333debeec0b34e3a2ab75397abd5d5bf8db84ec
+size 14244

checkpoint-6131/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d976a9c67598eccdaa2d3d2c5733e9ab247cb038585654763be550f3c13b39
+size 1064

checkpoint-6131/special_tokens_map.json

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

checkpoint-6131/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f80388e55d7d18f8caab6f55ccb39dab31d696d1726564e91fe74459b6c6f2
+size 14500653

checkpoint-6131/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250680": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "trust_remove_code": true,
+  "unk_token": "<unk>"
+}

checkpoint-6131/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999286464226375,
+  "eval_steps": 500,
+  "global_step": 6131,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001095993248702382,
+      "loss": 2.4022,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.747903910575024e-05,
+      "loss": 2.0017,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 6.325609676486509e-05,
+      "loss": 1.9066,
+      "step": 3000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.47859539514937e-05,
+      "loss": 1.8683,
+      "step": 4000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.899959575500252e-05,
+      "loss": 1.819,
+      "step": 5000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.472881497382854e-05,
+      "loss": 1.7923,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2.6444035021824e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6131/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d07bf671b3be04c66b0eb152014c6437294127c12d6ae5e789a6a68f9a8cb3
+size 4536