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-OpenMathInstruct-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-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 sha256:46f0b26d3a152ec8efb2475230270d1329efa31f2d4b62273234294f348bc786
+size 4943274328

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ff5951f48dcddc3e41665832c4af388966b9e58253d22d0ec1f7f461dcccb1
+size 3725003

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b06e6690afb9c4173a7d5557a252389c98bf7b72b516a20845ed24388f938cd
+size 14645

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb41608c74f0601f51aba42ba070368d58f306fd9096a73c5fc7061ed921c210
+size 1465

checkpoint-2500/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.1648125,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.224301815032959,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.0473,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.7534642219543457,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.9068,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.2999300956726074,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 2.9097,
+      "step": 300
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.1935625076293945,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 2.9126,
+      "step": 400
+    },
+    {
+      "epoch": 1.0329625,
+      "grad_norm": 3.9796504974365234,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 2.8695,
+      "step": 500
+    },
+    {
+      "epoch": 1.0729625,
+      "grad_norm": 3.6588051319122314,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 2.6282,
+      "step": 600
+    },
+    {
+      "epoch": 1.1129625,
+      "grad_norm": 3.0422592163085938,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.4448,
+      "step": 700
+    },
+    {
+      "epoch": 1.1529625000000001,
+      "grad_norm": 3.506638526916504,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 2.3841,
+      "step": 800
+    },
+    {
+      "epoch": 2.025925,
+      "grad_norm": 3.232518434524536,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 2.4055,
+      "step": 900
+    },
+    {
+      "epoch": 2.065925,
+      "grad_norm": 3.5629770755767822,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.1635,
+      "step": 1000
+    },
+    {
+      "epoch": 2.105925,
+      "grad_norm": 4.052393913269043,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 1.91,
+      "step": 1100
+    },
+    {
+      "epoch": 2.145925,
+      "grad_norm": 4.011883735656738,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 1.8443,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0188875,
+      "grad_norm": 4.183358192443848,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 1.9117,
+      "step": 1300
+    },
+    {
+      "epoch": 3.0588875,
+      "grad_norm": 4.792853355407715,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 1.6355,
+      "step": 1400
+    },
+    {
+      "epoch": 3.0988875,
+      "grad_norm": 5.4336256980896,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.4449,
+      "step": 1500
+    },
+    {
+      "epoch": 3.1388875,
+      "grad_norm": 4.874321937561035,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.3494,
+      "step": 1600
+    },
+    {
+      "epoch": 4.01185,
+      "grad_norm": 5.182672500610352,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 1.3964,
+      "step": 1700
+    },
+    {
+      "epoch": 4.05185,
+      "grad_norm": 6.411541938781738,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 1.252,
+      "step": 1800
+    },
+    {
+      "epoch": 4.09185,
+      "grad_norm": 6.957055568695068,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 1.0674,
+      "step": 1900
+    },
+    {
+      "epoch": 4.13185,
+      "grad_norm": 6.159031391143799,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.9957,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0048125,
+      "grad_norm": 5.721092224121094,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 1.0377,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0448125,
+      "grad_norm": 7.575408458709717,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 1.0448,
+      "step": 2200
+    },
+    {
+      "epoch": 5.0848125,
+      "grad_norm": 6.4172844886779785,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.8786,
+      "step": 2300
+    },
+    {
+      "epoch": 5.1248125,
+      "grad_norm": 8.13640022277832,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.8682,
+      "step": 2400
+    },
+    {
+      "epoch": 5.1648125,
+      "grad_norm": 7.7202839851379395,
+      "learning_rate": 0.0,
+      "loss": 0.9273,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2500,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69be0af15408c3724524e63639703ed3d0f3ca4d9af68d60a487e8140b155c05
+size 5777