Training in progress, step 1000, checkpoint

checkpoint-1000/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-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-1000/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-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f352fe672dbac2b519fa7e404f1dc52b2704bf0cd6c196c6b07c9d620c61771
+size 4943274328

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334709e36df22a67c74dfa305a3c8b3ced95a8f7ce5ddab442fab2e510461a4b
+size 3724602

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d90ec386b7998b205735a72c0b297c7b40445b1a0dd833cf8a44a73d955623
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df79665eb3e88a45c7df20570a32716b1ea33a86ebc5e42040e7fb6f94e64785
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.030636785588456058,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003063678558845606,
+      "grad_norm": 3.035543918609619,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.0534,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.96189546585083,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9361,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.852346420288086,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.9092,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.963131904602051,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.8945,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.8017725944519043,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.8791,
+      "step": 500
+    },
+    {
+      "epoch": 0.018382071353073636,
+      "grad_norm": 2.877586841583252,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 2.8601,
+      "step": 600
+    },
+    {
+      "epoch": 0.02144574991191924,
+      "grad_norm": 2.7040741443634033,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.8706,
+      "step": 700
+    },
+    {
+      "epoch": 0.024509428470764847,
+      "grad_norm": 2.8546905517578125,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 2.8554,
+      "step": 800
+    },
+    {
+      "epoch": 0.027573107029610452,
+      "grad_norm": 2.643134355545044,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 2.8639,
+      "step": 900
+    },
+    {
+      "epoch": 0.030636785588456058,
+      "grad_norm": 2.577639579772949,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.8588,
+      "step": 1000
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.5664155394048e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b061932f4b33e9f6c8cf1360f0fb270eb558cde804dfcf2d83c5d626b8d28ae2
+size 5432