Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
+base_model: ai21labs/Jamba-v0.1
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai21labs/Jamba-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "router",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "dt_proj",
+    "o_proj",
+    "out_proj",
+    "down_proj",
+    "x_proj",
+    "in_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cba8f2ae8f226ee6afed727f6475804cafaa8b945bfc8c5ab5ccdb6e387f657
+size 1062947520

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95f58cf445410920def694f59ecb751c17c2c298c04a8ff52baf824ddbbccaa
+size 534659764

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5c9071bc2f206972db0b586e770722408ed5009e49b71b1ba3d2b2ffff01d6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd121980b4f34b4940d67af5944d2f3d3e978d19b05769afcdc02492659d0642
+size 1064

tokenizer_config.json

@@ -36,7 +36,6 @@
     }
   },
   "bos_token": "<|startoftext|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9263157894736842,
+  "eval_steps": 3,
+  "global_step": 11,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3172740936279297,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9286,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.0365231037139893,
+      "eval_runtime": 24.9628,
+      "eval_samples_per_second": 0.801,
+      "eval_steps_per_second": 0.801,
+      "step": 1
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3426271378993988,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.951,
+      "step": 2
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.28614237904548645,
+      "learning_rate": 3e-06,
+      "loss": 0.9238,
+      "step": 3
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.0386725664138794,
+      "eval_runtime": 25.232,
+      "eval_samples_per_second": 0.793,
+      "eval_steps_per_second": 0.793,
+      "step": 3
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.3368183672428131,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9443,
+      "step": 4
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.37111783027648926,
+      "learning_rate": 5e-06,
+      "loss": 0.9553,
+      "step": 5
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.3505602478981018,
+      "learning_rate": 6e-06,
+      "loss": 0.9448,
+      "step": 6
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.0401721000671387,
+      "eval_runtime": 25.2324,
+      "eval_samples_per_second": 0.793,
+      "eval_steps_per_second": 0.793,
+      "step": 6
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.27382639050483704,
+      "learning_rate": 7e-06,
+      "loss": 0.9339,
+      "step": 7
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.3769858479499817,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9662,
+      "step": 8
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.3182668387889862,
+      "learning_rate": 9e-06,
+      "loss": 0.9182,
+      "step": 9
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 1.0365254878997803,
+      "eval_runtime": 25.3228,
+      "eval_samples_per_second": 0.79,
+      "eval_steps_per_second": 0.79,
+      "step": 9
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.32636308670043945,
+      "learning_rate": 1e-05,
+      "loss": 0.959,
+      "step": 10
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2772234082221985,
+      "learning_rate": 0.0,
+      "loss": 0.9204,
+      "step": 11
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 11,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.1152453558861824e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefe0f24db9bad1dba6292605914efd93d476e28217e6f88d87719b48002f940
+size 5816