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-5211/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 sha256:34d5f170fa284ac43e6d83138b95f0eb448592c04b92990bd6f0b49dff28fbf2
+size 100734154

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0f7528b72d098c34885557ee5893ae888b26320250777cb09668e09f68148f
+size 201442810

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48444f7034d5cd2a774ab6dabfb862d2fbacb8da61bc2daf34905e9895ecbf3c
+size 14244

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98c0d54298f20fd24fe64f8bf745550ee8ef59a66bbdd7eb4b69edb0596a869
+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": 1.9187413057034586,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00010954451150103321,
+      "loss": 3.2729,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.745966692414834e-05,
+      "loss": 2.6883,
+      "step": 2000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 6.324555320336759e-05,
+      "loss": 2.5356,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.477225575051661e-05,
+      "loss": 2.4439,
+      "step": 4000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.898979485566356e-05,
+      "loss": 2.3769,
+      "step": 5000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.4721359549995795e-05,
+      "loss": 2.3215,
+      "step": 6000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.1406891301271574e-05,
+      "loss": 2.2594,
+      "step": 7000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.873467559917656e-05,
+      "loss": 2.2266,
+      "step": 8000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.652092449507988e-05,
+      "loss": 2.2015,
+      "step": 9000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.4646213473226916e-05,
+      "loss": 2.1844,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 4.232760154093978e+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 sha256:9505ea290a72f44c3fa1a682135f7a5d84edc36bb996a32bc9ccdcf86817ac84
+size 4536

checkpoint-5211/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-5211/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-5211/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31a75dd6a8ebf06eeddb74a78fc1b46ce50c5f75b8913b04df751911e78822f
+size 100734154

checkpoint-5211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326fd815f7a1f92c7e677ddd9995a0d6d1e997dc94f0cb015c85ba00157b96ef
+size 201442810

checkpoint-5211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83459c20b76acecdfebee7af6b9c558ee52f8a84dced3ffd07740fd02e5fa82b
+size 14244

checkpoint-5211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c5635cb6e00e62ee39de27e207a59e2e89deaa1f15092b9eec41cb14654f18
+size 1064

checkpoint-5211/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-5211/tokenizer.json

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

checkpoint-5211/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-5211/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998560944020722,
+  "eval_steps": 500,
+  "global_step": 5211,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00010954451150103321,
+      "loss": 3.2729,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.745966692414834e-05,
+      "loss": 2.6883,
+      "step": 2000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 6.324555320336759e-05,
+      "loss": 2.5356,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.477225575051661e-05,
+      "loss": 2.4439,
+      "step": 4000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.898979485566356e-05,
+      "loss": 2.3769,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2.204987132603597e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9505ea290a72f44c3fa1a682135f7a5d84edc36bb996a32bc9ccdcf86817ac84
+size 4536