Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb2cfd26c748ce7b48d58f2655e9fc99793b873ac432ad7f764b08e9295fe2a
+size 4943274328

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced91beb35b4c110dec543c8ff74286f0a2207bdd943bd4628740e97b171dba6
+size 3724602

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bdca7f170012db71238c04c78dc1a3402c78b1d255f75d5622f29551afc717
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fdf17d77d34a6dc43fb505d89df155af8f574eb1ddc8da3e2d900c61723cd5
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07659196397114015,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003063678558845606,
+      "grad_norm": 2.937537670135498,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.9979,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.9786553382873535,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9223,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.899183750152588,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.9009,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.9656615257263184,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.8884,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.785738468170166,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.8738,
+      "step": 500
+    },
+    {
+      "epoch": 0.018382071353073636,
+      "grad_norm": 2.8539676666259766,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 2.8555,
+      "step": 600
+    },
+    {
+      "epoch": 0.02144574991191924,
+      "grad_norm": 2.6807861328125,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.8666,
+      "step": 700
+    },
+    {
+      "epoch": 0.024509428470764847,
+      "grad_norm": 2.81980037689209,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 2.8515,
+      "step": 800
+    },
+    {
+      "epoch": 0.027573107029610452,
+      "grad_norm": 2.636308193206787,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 2.8603,
+      "step": 900
+    },
+    {
+      "epoch": 0.030636785588456058,
+      "grad_norm": 2.5829219818115234,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.8555,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03370046414730166,
+      "grad_norm": 2.622443914413452,
+      "learning_rate": 6.873032967079562e-06,
+      "loss": 2.8287,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03676414270614727,
+      "grad_norm": 2.57558274269104,
+      "learning_rate": 6.209609477998339e-06,
+      "loss": 2.8294,
+      "step": 1200
+    },
+    {
+      "epoch": 0.039827821264992874,
+      "grad_norm": 2.6264266967773438,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 2.8315,
+      "step": 1300
+    },
+    {
+      "epoch": 0.04289149982383848,
+      "grad_norm": 2.575040578842163,
+      "learning_rate": 4.825502516487497e-06,
+      "loss": 2.8338,
+      "step": 1400
+    },
+    {
+      "epoch": 0.04595517838268409,
+      "grad_norm": 2.7474663257598877,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 2.8179,
+      "step": 1500
+    },
+    {
+      "epoch": 0.049018856941529694,
+      "grad_norm": 2.669630527496338,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 2.8021,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0520825355003753,
+      "grad_norm": 2.631849527359009,
+      "learning_rate": 2.8081442660546126e-06,
+      "loss": 2.8077,
+      "step": 1700
+    },
+    {
+      "epoch": 0.055146214059220905,
+      "grad_norm": 2.609309673309326,
+      "learning_rate": 2.204035482646267e-06,
+      "loss": 2.8177,
+      "step": 1800
+    },
+    {
+      "epoch": 0.058209892618066514,
+      "grad_norm": 2.68284273147583,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 2.8051,
+      "step": 1900
+    },
+    {
+      "epoch": 0.061273571176912116,
+      "grad_norm": 2.7649335861206055,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 2.8117,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06433724973575772,
+      "grad_norm": 2.7510080337524414,
+      "learning_rate": 7.597595192178702e-07,
+      "loss": 2.7962,
+      "step": 2100
+    },
+    {
+      "epoch": 0.06740092829460333,
+      "grad_norm": 2.663290500640869,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 2.8059,
+      "step": 2200
+    },
+    {
+      "epoch": 0.07046460685344894,
+      "grad_norm": 2.672750949859619,
+      "learning_rate": 1.9369152030840553e-07,
+      "loss": 2.8047,
+      "step": 2300
+    },
+    {
+      "epoch": 0.07352828541229454,
+      "grad_norm": 2.7145726680755615,
+      "learning_rate": 4.865965629214819e-08,
+      "loss": 2.7968,
+      "step": 2400
+    },
+    {
+      "epoch": 0.07659196397114015,
+      "grad_norm": 2.74078631401062,
+      "learning_rate": 0.0,
+      "loss": 2.7981,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3916038848512e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143b5f6c6fe08f3f5ae3c56265d9e4157a9e86249acdc63737a238135515a88f
+size 5432