Upload folder using huggingface_hub

checkpoint-188/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-188/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}

checkpoint-188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6bd33f164dcb0e408e712535d3eae23124a893713157c056c30d58707068a5
+size 1239173352

checkpoint-188/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefbc6315f53ae53ae2d0d1b59ebfbf975a76007140fc31f0461d957896138db
+size 3712102842

checkpoint-188/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8360afcfd63bdfde022670dd9b6ab85040fcff6d7c95604f813ad0aa9ce7db42
+size 1239275353

checkpoint-188/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

checkpoint-188/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

checkpoint-188/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

checkpoint-188/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

checkpoint-188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09909eb413267318bbfda18c09a55769856bdd30674e675b287d21ecf89be94b
+size 1064

checkpoint-188/trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": 1.157950758934021,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-20/checkpoint-188",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "grad_norm": 676.0,
+      "learning_rate": 2.5e-06,
+      "loss": 15.3348,
+      "step": 50
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 16.875,
+      "learning_rate": 5e-06,
+      "loss": 3.911,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.75,
+      "learning_rate": 4.6059265481735295e-06,
+      "loss": 1.1674,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.157950758934021,
+      "eval_runtime": 34.0907,
+      "eval_samples_per_second": 16.573,
+      "eval_steps_per_second": 1.056,
+      "step": 188
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2849842200051712.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed0362465920150b6a43b7c66f144cfd17c4f74e74d2787ed17f2ec04d4be42
+size 5048

checkpoint-376/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-376/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}

checkpoint-376/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fbb01c716da162eb7cda2ac6e39edf62470abf119a7e8098d6dd86bd0c5b17
+size 1239173352

checkpoint-376/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a1365a7fd5e576d118f36c7a171195056090c2e15c019fc224cd8f63945cfe
+size 3712103162

checkpoint-376/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c0e9381942dde5d3683a4aa11fbb5c321a8630ed0c6e06456a6557952d52c8
+size 1239275353

checkpoint-376/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
+size 15024

checkpoint-376/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
+size 15024

checkpoint-376/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
+size 15024

checkpoint-376/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
+size 15024

checkpoint-376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb76bbd6a34792885f955f41f4911956f6dde63e9bca79169199742ef22e6ce
+size 1064

checkpoint-376/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 1.1512998342514038,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-20/checkpoint-376",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "grad_norm": 676.0,
+      "learning_rate": 2.5e-06,
+      "loss": 15.3348,
+      "step": 50
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 16.875,
+      "learning_rate": 5e-06,
+      "loss": 3.911,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.75,
+      "learning_rate": 4.6059265481735295e-06,
+      "loss": 1.1674,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.157950758934021,
+      "eval_runtime": 34.0907,
+      "eval_samples_per_second": 16.573,
+      "eval_steps_per_second": 1.056,
+      "step": 188
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 6.46875,
+      "learning_rate": 3.5479413010416606e-06,
+      "loss": 1.1863,
+      "step": 200
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.78125,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 1.1619,
+      "step": 250
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.46875,
+      "learning_rate": 8.785447763431101e-07,
+      "loss": 1.1292,
+      "step": 300
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.0868414100166314e-07,
+      "loss": 1.1423,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1512998342514038,
+      "eval_runtime": 34.1097,
+      "eval_samples_per_second": 16.564,
+      "eval_steps_per_second": 1.055,
+      "step": 376
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 5699684433657856.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed0362465920150b6a43b7c66f144cfd17c4f74e74d2787ed17f2ec04d4be42
+size 5048

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fbb01c716da162eb7cda2ac6e39edf62470abf119a7e8098d6dd86bd0c5b17
+size 1239173352

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed0362465920150b6a43b7c66f144cfd17c4f74e74d2787ed17f2ec04d4be42
+size 5048