Model save

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- orpo
+- generated_from_trainer
+model-index:
+- name: mistral-7b-orpo-alignment-handbook
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mistral-7b-orpo-alignment-handbook
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8562
+- Rewards/chosen: -0.0394
+- Rewards/rejected: -0.0485
+- Rewards/accuracies: 0.6615
+- Rewards/margins: 0.0091
+- Logps/rejected: -0.9709
+- Logps/chosen: -0.7880
+- Logits/rejected: -2.9507
+- Logits/chosen: -2.9399
+- Nll Loss: 0.8317
+- Log Odds Ratio: -0.6238
+- Log Odds Chosen: 0.3606
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
+| 0.9081        | 0.95  | 100  | 0.8756          | -0.0406        | -0.0483          | 0.625              | 0.0077          | -0.9657        | -0.8116      | -3.0351         | -3.0266       | 0.8517   | -0.6438        | 0.3078          |
+| 0.8743        | 1.9   | 200  | 0.8544          | -0.0391        | -0.0474          | 0.6458             | 0.0083          | -0.9474        | -0.7823      | -2.9519         | -2.9423       | 0.8308   | -0.6319        | 0.3327          |
+| 0.7952        | 2.84  | 300  | 0.8562          | -0.0394        | -0.0485          | 0.6615             | 0.0091          | -0.9709        | -0.7880      | -2.9507         | -2.9399       | 0.8317   | -0.6238        | 0.3606          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.8898289559379456,
+    "train_runtime": 3406.8155,
+    "train_samples": 6750,
+    "train_samples_per_second": 5.944,
+    "train_steps_per_second": 0.092
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 32000,
+  "eos_token_id": 32001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 32001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32000,
+  "eos_token_id": 32001,
+  "pad_token_id": 32001,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a341df9a54a42f1c330f1a3793a3e7096e098e4206381d159ee25cfb6b3b6f8c
+size 4943178720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf782ccdca3632bd96289ee50cd23d33e868ab33109c3bdaaee7be0a1f67f773
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881edc1af6374c03e83b1a88dce2b1565f7871394a84e6b21986a4c48e364881
+size 4540532728

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483496960
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/Mar27_08-37-28_alvarobartt-sharp-bobcat-1-0/events.out.tfevents.1711543163.alvarobartt-sharp-bobcat-1-0.498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f80999120033b8aacb35fb4a2c843ee51b3d05244c38f32775cb061e276b57
+size 34630

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% 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": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.8898289559379456,
+    "train_runtime": 3406.8155,
+    "train_samples": 6750,
+    "train_samples_per_second": 5.944,
+    "train_steps_per_second": 0.092
+}

trainer_state.json

@@ -0,0 +1,645 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.985781990521327,
+  "eval_steps": 100,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "grad_norm": 77.33639458677236,
+      "learning_rate": 5e-08,
+      "log_odds_chosen": 0.2618955969810486,
+      "log_odds_ratio": -0.777361273765564,
+      "logits/chosen": -2.8855865001678467,
+      "logits/rejected": -2.892557144165039,
+      "logps/chosen": -1.5272881984710693,
+      "logps/rejected": -1.7787439823150635,
+      "loss": 1.2832,
+      "nll_loss": 1.2394630908966064,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.0763644129037857,
+      "rewards/margins": 0.012572775594890118,
+      "rewards/rejected": -0.0889371931552887,
+      "step": 10
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 54.38141225395272,
+      "learning_rate": 1e-07,
+      "log_odds_chosen": -0.03225521370768547,
+      "log_odds_ratio": -0.8774896860122681,
+      "logits/chosen": -2.933506727218628,
+      "logits/rejected": -2.9356539249420166,
+      "logps/chosen": -1.5450432300567627,
+      "logps/rejected": -1.4802385568618774,
+      "loss": 1.2241,
+      "nll_loss": 1.1661609411239624,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -0.07725216448307037,
+      "rewards/margins": -0.0032402321230620146,
+      "rewards/rejected": -0.07401192933320999,
+      "step": 20
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 23.013934951529215,
+      "learning_rate": 1.5e-07,
+      "log_odds_chosen": 0.3505951762199402,
+      "log_odds_ratio": -0.6906026601791382,
+      "logits/chosen": -2.9268429279327393,
+      "logits/rejected": -2.9279420375823975,
+      "logps/chosen": -1.233396291732788,
+      "logps/rejected": -1.5268161296844482,
+      "loss": 1.1005,
+      "nll_loss": 1.0289665460586548,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.06166981905698776,
+      "rewards/margins": 0.014670980162918568,
+      "rewards/rejected": -0.07634080946445465,
+      "step": 30
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 19.881755252038474,
+      "learning_rate": 2e-07,
+      "log_odds_chosen": 0.05373505502939224,
+      "log_odds_ratio": -0.755977988243103,
+      "logits/chosen": -3.021728277206421,
+      "logits/rejected": -3.0213043689727783,
+      "logps/chosen": -1.0615440607070923,
+      "logps/rejected": -1.1156013011932373,
+      "loss": 1.0027,
+      "nll_loss": 0.9945588111877441,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.053077198565006256,
+      "rewards/margins": 0.0027028678450733423,
+      "rewards/rejected": -0.0557800717651844,
+      "step": 40
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 17.85460584897372,
+      "learning_rate": 2.5e-07,
+      "log_odds_chosen": 0.2669735252857208,
+      "log_odds_ratio": -0.6554110050201416,
+      "logits/chosen": -2.984776735305786,
+      "logits/rejected": -2.98599910736084,
+      "logps/chosen": -0.9630029797554016,
+      "logps/rejected": -1.140073299407959,
+      "loss": 0.9808,
+      "nll_loss": 0.9621084332466125,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.04815014451742172,
+      "rewards/margins": 0.008853518404066563,
+      "rewards/rejected": -0.05700366571545601,
+      "step": 50
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 10.727306830796762,
+      "learning_rate": 3e-07,
+      "log_odds_chosen": 0.24170732498168945,
+      "log_odds_ratio": -0.6548684239387512,
+      "logits/chosen": -2.933190107345581,
+      "logits/rejected": -2.919651746749878,
+      "logps/chosen": -0.8642565011978149,
+      "logps/rejected": -1.0084782838821411,
+      "loss": 0.9582,
+      "nll_loss": 0.8713911175727844,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -0.04321281984448433,
+      "rewards/margins": 0.00721109751611948,
+      "rewards/rejected": -0.05042392015457153,
+      "step": 60
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 7.901492264358037,
+      "learning_rate": 3.5e-07,
+      "log_odds_chosen": 0.2393842190504074,
+      "log_odds_ratio": -0.6571385264396667,
+      "logits/chosen": -2.9068989753723145,
+      "logits/rejected": -2.9116122722625732,
+      "logps/chosen": -0.8636172413825989,
+      "logps/rejected": -1.0111676454544067,
+      "loss": 0.9439,
+      "nll_loss": 0.8679887652397156,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.043180860579013824,
+      "rewards/margins": 0.0073775192722678185,
+      "rewards/rejected": -0.05055838078260422,
+      "step": 70
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 9.286628580140562,
+      "learning_rate": 4e-07,
+      "log_odds_chosen": 0.3271833658218384,
+      "log_odds_ratio": -0.6348003149032593,
+      "logits/chosen": -2.9881081581115723,
+      "logits/rejected": -2.9824562072753906,
+      "logps/chosen": -0.8416474461555481,
+      "logps/rejected": -1.044790267944336,
+      "loss": 0.891,
+      "nll_loss": 0.8611804842948914,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.042082373052835464,
+      "rewards/margins": 0.010157138109207153,
+      "rewards/rejected": -0.05223950743675232,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 14.185856511216093,
+      "learning_rate": 4.5e-07,
+      "log_odds_chosen": 0.09227167814970016,
+      "log_odds_ratio": -0.7197006344795227,
+      "logits/chosen": -3.0093541145324707,
+      "logits/rejected": -3.0240068435668945,
+      "logps/chosen": -0.8808207511901855,
+      "logps/rejected": -0.944561779499054,
+      "loss": 0.8948,
+      "nll_loss": 0.8881239891052246,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.04404103755950928,
+      "rewards/margins": 0.003187048714607954,
+      "rewards/rejected": -0.04722809046506882,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 7.623951794451487,
+      "learning_rate": 5e-07,
+      "log_odds_chosen": 0.1973893940448761,
+      "log_odds_ratio": -0.6770023703575134,
+      "logits/chosen": -3.0369744300842285,
+      "logits/rejected": -3.0375945568084717,
+      "logps/chosen": -0.8410383462905884,
+      "logps/rejected": -0.9645870327949524,
+      "loss": 0.9081,
+      "nll_loss": 0.8671768307685852,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -0.04205191880464554,
+      "rewards/margins": 0.0061774346977472305,
+      "rewards/rejected": -0.04822935536503792,
+      "step": 100
+    },
+    {
+      "epoch": 0.95,
+      "eval_log_odds_chosen": 0.30781975388526917,
+      "eval_log_odds_ratio": -0.6437683701515198,
+      "eval_logits/chosen": -3.026639223098755,
+      "eval_logits/rejected": -3.035104990005493,
+      "eval_logps/chosen": -0.8116251826286316,
+      "eval_logps/rejected": -0.9657273888587952,
+      "eval_loss": 0.8755595684051514,
+      "eval_nll_loss": 0.8516923785209656,
+      "eval_rewards/accuracies": 0.625,
+      "eval_rewards/chosen": -0.04058125242590904,
+      "eval_rewards/margins": 0.007705114781856537,
+      "eval_rewards/rejected": -0.048286378383636475,
+      "eval_runtime": 32.7393,
+      "eval_samples_per_second": 22.908,
+      "eval_steps_per_second": 0.733,
+      "step": 100
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 8.31992434723541,
+      "learning_rate": 4.973358420187775e-07,
+      "log_odds_chosen": 0.2791669964790344,
+      "log_odds_ratio": -0.6692678332328796,
+      "logits/chosen": -3.0303468704223633,
+      "logits/rejected": -3.025372266769409,
+      "logps/chosen": -0.8586570620536804,
+      "logps/rejected": -1.0267794132232666,
+      "loss": 0.9228,
+      "nll_loss": 0.9038568735122681,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.04293284937739372,
+      "rewards/margins": 0.008406125009059906,
+      "rewards/rejected": -0.05133897811174393,
+      "step": 110
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 7.967670280486583,
+      "learning_rate": 4.894001499771015e-07,
+      "log_odds_chosen": 0.38782748579978943,
+      "log_odds_ratio": -0.6013778448104858,
+      "logits/chosen": -3.0236096382141113,
+      "logits/rejected": -3.0155141353607178,
+      "logps/chosen": -0.8168986439704895,
+      "logps/rejected": -1.0334148406982422,
+      "loss": 0.8715,
+      "nll_loss": 0.8525303602218628,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.040844932198524475,
+      "rewards/margins": 0.010825812816619873,
+      "rewards/rejected": -0.05167074874043465,
+      "step": 120
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 8.352441708638352,
+      "learning_rate": 4.7636205937328664e-07,
+      "log_odds_chosen": 0.2141951024532318,
+      "log_odds_ratio": -0.6885079145431519,
+      "logits/chosen": -2.985905647277832,
+      "logits/rejected": -2.982698440551758,
+      "logps/chosen": -0.7959944605827332,
+      "logps/rejected": -0.9118129014968872,
+      "loss": 0.9124,
+      "nll_loss": 0.8475678563117981,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.03979972377419472,
+      "rewards/margins": 0.005790921859443188,
+      "rewards/rejected": -0.04559064656496048,
+      "step": 130
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.671580837241858,
+      "learning_rate": 4.584994544724695e-07,
+      "log_odds_chosen": 0.2413184642791748,
+      "log_odds_ratio": -0.6780685782432556,
+      "logits/chosen": -2.9718122482299805,
+      "logits/rejected": -2.9794762134552,
+      "logps/chosen": -0.7854965925216675,
+      "logps/rejected": -0.9058204889297485,
+      "loss": 0.8615,
+      "nll_loss": 0.8538535237312317,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.039274830371141434,
+      "rewards/margins": 0.006016193423420191,
+      "rewards/rejected": -0.045291025191545486,
+      "step": 140
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 7.772020240967411,
+      "learning_rate": 4.3619304568594546e-07,
+      "log_odds_chosen": 0.35438692569732666,
+      "log_odds_ratio": -0.6226890683174133,
+      "logits/chosen": -2.9541661739349365,
+      "logits/rejected": -2.975813388824463,
+      "logps/chosen": -0.77320796251297,
+      "logps/rejected": -0.9510070085525513,
+      "loss": 0.8533,
+      "nll_loss": 0.8167142868041992,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.03866039589047432,
+      "rewards/margins": 0.008889952674508095,
+      "rewards/rejected": -0.047550346702337265,
+      "step": 150
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 7.766336059303151,
+      "learning_rate": 4.099182553897228e-07,
+      "log_odds_chosen": 0.41911888122558594,
+      "log_odds_ratio": -0.5898452997207642,
+      "logits/chosen": -2.93475079536438,
+      "logits/rejected": -2.9203600883483887,
+      "logps/chosen": -0.7571161389350891,
+      "logps/rejected": -1.0282914638519287,
+      "loss": 0.8498,
+      "nll_loss": 0.7975727915763855,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.03785580396652222,
+      "rewards/margins": 0.013558770529925823,
+      "rewards/rejected": -0.05141457915306091,
+      "step": 160
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 6.962214901131027,
+      "learning_rate": 3.8023508512198257e-07,
+      "log_odds_chosen": 0.343596875667572,
+      "log_odds_ratio": -0.6280649900436401,
+      "logits/chosen": -2.953634262084961,
+      "logits/rejected": -2.9548466205596924,
+      "logps/chosen": -0.7480501532554626,
+      "logps/rejected": -0.9306358098983765,
+      "loss": 0.8487,
+      "nll_loss": 0.7963918447494507,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.037402503192424774,
+      "rewards/margins": 0.009129286743700504,
+      "rewards/rejected": -0.046531792730093,
+      "step": 170
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 7.684687327116239,
+      "learning_rate": 3.4777618012253895e-07,
+      "log_odds_chosen": 0.21630027890205383,
+      "log_odds_ratio": -0.6737483739852905,
+      "logits/chosen": -2.919468879699707,
+      "logits/rejected": -2.9328620433807373,
+      "logps/chosen": -0.8119864463806152,
+      "logps/rejected": -0.9226973652839661,
+      "loss": 0.8625,
+      "nll_loss": 0.8666168451309204,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.04059932753443718,
+      "rewards/margins": 0.0055355411022901535,
+      "rewards/rejected": -0.046134866774082184,
+      "step": 180
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 7.394125467411221,
+      "learning_rate": 3.1323334559792015e-07,
+      "log_odds_chosen": 0.24404248595237732,
+      "log_odds_ratio": -0.6521191000938416,
+      "logits/chosen": -2.9319450855255127,
+      "logits/rejected": -2.9281563758850098,
+      "logps/chosen": -0.764248251914978,
+      "logps/rejected": -0.9116944074630737,
+      "loss": 0.8487,
+      "nll_loss": 0.7953720688819885,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.03821241110563278,
+      "rewards/margins": 0.007372308522462845,
+      "rewards/rejected": -0.045584727078676224,
+      "step": 190
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 7.078165164064633,
+      "learning_rate": 2.7734280209446865e-07,
+      "log_odds_chosen": 0.27770525217056274,
+      "log_odds_ratio": -0.6487261056900024,
+      "logits/chosen": -2.9408035278320312,
+      "logits/rejected": -2.9414825439453125,
+      "logps/chosen": -0.8372436761856079,
+      "logps/rejected": -0.9893075227737427,
+      "loss": 0.8743,
+      "nll_loss": 0.8854878544807434,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.041862182319164276,
+      "rewards/margins": 0.007603197358548641,
+      "rewards/rejected": -0.04946538433432579,
+      "step": 200
+    },
+    {
+      "epoch": 1.9,
+      "eval_log_odds_chosen": 0.3327343761920929,
+      "eval_log_odds_ratio": -0.6319172978401184,
+      "eval_logits/chosen": -2.942302942276001,
+      "eval_logits/rejected": -2.951889991760254,
+      "eval_logps/chosen": -0.7823134064674377,
+      "eval_logps/rejected": -0.9474297165870667,
+      "eval_loss": 0.8543919920921326,
+      "eval_nll_loss": 0.8307900428771973,
+      "eval_rewards/accuracies": 0.6458333134651184,
+      "eval_rewards/chosen": -0.03911567106842995,
+      "eval_rewards/margins": 0.008255816996097565,
+      "eval_rewards/rejected": -0.04737148806452751,
+      "eval_runtime": 32.7039,
+      "eval_samples_per_second": 22.933,
+      "eval_steps_per_second": 0.734,
+      "step": 200
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 8.396601904639242,
+      "learning_rate": 2.4086949423558525e-07,
+      "log_odds_chosen": 0.41053691506385803,
+      "log_odds_ratio": -0.6060739755630493,
+      "logits/chosen": -2.929229974746704,
+      "logits/rejected": -2.935241222381592,
+      "logps/chosen": -0.7071143388748169,
+      "logps/rejected": -0.9274543523788452,
+      "loss": 0.8393,
+      "nll_loss": 0.7697780728340149,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.035355716943740845,
+      "rewards/margins": 0.011016997508704662,
+      "rewards/rejected": -0.04637271165847778,
+      "step": 210
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 6.569557403751905,
+      "learning_rate": 2.0459078725514089e-07,
+      "log_odds_chosen": 0.5315035581588745,
+      "log_odds_ratio": -0.5512046217918396,
+      "logits/chosen": -2.9326529502868652,
+      "logits/rejected": -2.9516549110412598,
+      "logps/chosen": -0.6680026054382324,
+      "logps/rejected": -0.9493370056152344,
+      "loss": 0.7857,
+      "nll_loss": 0.7278756499290466,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.03340013325214386,
+      "rewards/margins": 0.014066715724766254,
+      "rewards/rejected": -0.04746684432029724,
+      "step": 220
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 7.403484208884281,
+      "learning_rate": 1.692798988071385e-07,
+      "log_odds_chosen": 0.5616401433944702,
+      "log_odds_ratio": -0.5525184869766235,
+      "logits/chosen": -2.958536386489868,
+      "logits/rejected": -2.961232900619507,
+      "logps/chosen": -0.6798023581504822,
+      "logps/rejected": -0.9693242311477661,
+      "loss": 0.797,
+      "nll_loss": 0.7711700201034546,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.03399012237787247,
+      "rewards/margins": 0.014476092532277107,
+      "rewards/rejected": -0.048466216772794724,
+      "step": 230
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 7.412336007524852,
+      "learning_rate": 1.3568941917384036e-07,
+      "log_odds_chosen": 0.5311576128005981,
+      "log_odds_ratio": -0.549420177936554,
+      "logits/chosen": -2.9735727310180664,
+      "logits/rejected": -2.9537353515625,
+      "logps/chosen": -0.6970270872116089,
+      "logps/rejected": -1.0076513290405273,
+      "loss": 0.777,
+      "nll_loss": 0.7482173442840576,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.034851353615522385,
+      "rewards/margins": 0.015531214885413647,
+      "rewards/rejected": -0.050382573157548904,
+      "step": 240
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 7.1315381997262595,
+      "learning_rate": 1.0453527111051183e-07,
+      "log_odds_chosen": 0.5468025207519531,
+      "log_odds_ratio": -0.555133044719696,
+      "logits/chosen": -2.922816276550293,
+      "logits/rejected": -2.945639133453369,
+      "logps/chosen": -0.6493021249771118,
+      "logps/rejected": -0.951339840888977,
+      "loss": 0.7778,
+      "nll_loss": 0.6916720271110535,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.03246510773897171,
+      "rewards/margins": 0.015101884491741657,
+      "rewards/rejected": -0.04756699129939079,
+      "step": 250
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 7.696203106269843,
+      "learning_rate": 7.648145119484151e-08,
+      "log_odds_chosen": 0.5281956195831299,
+      "log_odds_ratio": -0.5637919306755066,
+      "logits/chosen": -2.925053358078003,
+      "logits/rejected": -2.9243857860565186,
+      "logps/chosen": -0.7035914659500122,
+      "logps/rejected": -0.9652328491210938,
+      "loss": 0.7943,
+      "nll_loss": 0.7686626315116882,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.03517957404255867,
+      "rewards/margins": 0.013082069344818592,
+      "rewards/rejected": -0.048261649906635284,
+      "step": 260
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 7.643756100288896,
+      "learning_rate": 5.212587789268649e-08,
+      "log_odds_chosen": 0.5132555365562439,
+      "log_odds_ratio": -0.5936566591262817,
+      "logits/chosen": -2.9285006523132324,
+      "logits/rejected": -2.9404940605163574,
+      "logps/chosen": -0.7124043703079224,
+      "logps/rejected": -0.936718761920929,
+      "loss": 0.7934,
+      "nll_loss": 0.7723904252052307,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.035620223730802536,
+      "rewards/margins": 0.011215712875127792,
+      "rewards/rejected": -0.04683593660593033,
+      "step": 270
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 7.291634915542113,
+      "learning_rate": 3.198764796404807e-08,
+      "log_odds_chosen": 0.5429651737213135,
+      "log_odds_ratio": -0.5288026332855225,
+      "logits/chosen": -2.9601218700408936,
+      "logits/rejected": -2.968656063079834,
+      "logps/chosen": -0.6723442673683167,
+      "logps/rejected": -0.9517607688903809,
+      "loss": 0.7803,
+      "nll_loss": 0.7490439414978027,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.03361721709370613,
+      "rewards/margins": 0.013970823958516121,
+      "rewards/rejected": -0.047588035464286804,
+      "step": 280
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 7.508067041552727,
+      "learning_rate": 1.649597281686302e-08,
+      "log_odds_chosen": 0.45766550302505493,
+      "log_odds_ratio": -0.5674511790275574,
+      "logits/chosen": -2.960801362991333,
+      "logits/rejected": -2.9700140953063965,
+      "logps/chosen": -0.6948236227035522,
+      "logps/rejected": -0.9299477338790894,
+      "loss": 0.7893,
+      "nll_loss": 0.7552822232246399,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.03474118560552597,
+      "rewards/margins": 0.011756205931305885,
+      "rewards/rejected": -0.04649738967418671,
+      "step": 290
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 7.2033125147888954,
+      "learning_rate": 5.981030611018234e-09,
+      "log_odds_chosen": 0.5772581696510315,
+      "log_odds_ratio": -0.534927248954773,
+      "logits/chosen": -2.9540858268737793,
+      "logits/rejected": -2.9668896198272705,
+      "logps/chosen": -0.715768039226532,
+      "logps/rejected": -0.9969004392623901,
+      "loss": 0.7952,
+      "nll_loss": 0.8036004900932312,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.035788409411907196,
+      "rewards/margins": 0.014056617394089699,
+      "rewards/rejected": -0.04984502121806145,
+      "step": 300
+    },
+    {
+      "epoch": 2.84,
+      "eval_log_odds_chosen": 0.3606046140193939,
+      "eval_log_odds_ratio": -0.6238030791282654,
+      "eval_logits/chosen": -2.939861297607422,
+      "eval_logits/rejected": -2.9506702423095703,
+      "eval_logps/chosen": -0.7880411148071289,
+      "eval_logps/rejected": -0.9708888530731201,
+      "eval_loss": 0.8561561107635498,
+      "eval_nll_loss": 0.8317036628723145,
+      "eval_rewards/accuracies": 0.6614583134651184,
+      "eval_rewards/chosen": -0.03940205276012421,
+      "eval_rewards/margins": 0.009142386727035046,
+      "eval_rewards/rejected": -0.04854444041848183,
+      "eval_runtime": 32.7358,
+      "eval_samples_per_second": 22.911,
+      "eval_steps_per_second": 0.733,
+      "step": 300
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 7.47712107069191,
+      "learning_rate": 6.66929084112089e-10,
+      "log_odds_chosen": 0.49705371260643005,
+      "log_odds_ratio": -0.5786138772964478,
+      "logits/chosen": -2.950911521911621,
+      "logits/rejected": -2.9691450595855713,
+      "logps/chosen": -0.6968633532524109,
+      "logps/rejected": -0.9362894296646118,
+      "loss": 0.79,
+      "nll_loss": 0.76046222448349,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.034843169152736664,
+      "rewards/margins": 0.011971303261816502,
+      "rewards/rejected": -0.04681447520852089,
+      "step": 310
+    },
+    {
+      "epoch": 2.99,
+      "step": 315,
+      "total_flos": 0.0,
+      "train_loss": 0.8898289559379456,
+      "train_runtime": 3406.8155,
+      "train_samples_per_second": 5.944,
+      "train_steps_per_second": 0.092
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d9875fe26519d505b6587f43987109a592f7656b554c8b427553abfa31ec5b
+size 6456