Training in progress, step 1500, checkpoint

checkpoint-1500/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "Grogros/gpt2-kgw-k1-delta2.0-Scratch",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 50263
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.45.2"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea87db83c8b05dc56637e5d0f5d8666eaabc387a282d2d1d1f83e360200f789b
+size 497792640

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6727ba1ccfd0596c59f2c086867145b39d9ea70f4fdd869d3550277f04daae
+size 1385018

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368f7cb61a038c1dd4b8110f94c42f15d41eea3c64f1e1bd85e75bc9deb5bfcd
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e0fa899b9afe4b9f410a947b2e82b267a415e5e533180013057e8a556bdbd5
+size 1064

checkpoint-1500/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1002539767410774,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00334179922470258,
+      "grad_norm": 11.090287208557129,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 5.1739,
+      "step": 50
+    },
+    {
+      "epoch": 0.00668359844940516,
+      "grad_norm": 0.2740594446659088,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0311,
+      "step": 100
+    },
+    {
+      "epoch": 0.01002539767410774,
+      "grad_norm": 0.2221425324678421,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8728,
+      "step": 150
+    },
+    {
+      "epoch": 0.01336719689881032,
+      "grad_norm": 0.20594573020935059,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7991,
+      "step": 200
+    },
+    {
+      "epoch": 0.016708996123512898,
+      "grad_norm": 0.19108366966247559,
+      "learning_rate": 2e-05,
+      "loss": 0.7699,
+      "step": 250
+    },
+    {
+      "epoch": 0.02005079534821548,
+      "grad_norm": 0.22920449078083038,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.7129,
+      "step": 300
+    },
+    {
+      "epoch": 0.02339259457291806,
+      "grad_norm": 0.16409973800182343,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.6788,
+      "step": 350
+    },
+    {
+      "epoch": 0.02673439379762064,
+      "grad_norm": 0.21055717766284943,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.647,
+      "step": 400
+    },
+    {
+      "epoch": 0.030076193022323217,
+      "grad_norm": 0.18021100759506226,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.6656,
+      "step": 450
+    },
+    {
+      "epoch": 0.033417992247025796,
+      "grad_norm": 0.20338550209999084,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.03675979147172838,
+      "grad_norm": 0.16770771145820618,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.6256,
+      "step": 550
+    },
+    {
+      "epoch": 0.04010159069643096,
+      "grad_norm": 0.185317724943161,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.6258,
+      "step": 600
+    },
+    {
+      "epoch": 0.043443389921133536,
+      "grad_norm": 0.15783734619617462,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.6059,
+      "step": 650
+    },
+    {
+      "epoch": 0.04678518914583612,
+      "grad_norm": 0.1717253476381302,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.6023,
+      "step": 700
+    },
+    {
+      "epoch": 0.0501269883705387,
+      "grad_norm": 0.1728314906358719,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5959,
+      "step": 750
+    },
+    {
+      "epoch": 0.05346878759524128,
+      "grad_norm": 0.17687861621379852,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.5894,
+      "step": 800
+    },
+    {
+      "epoch": 0.05681058681994386,
+      "grad_norm": 0.18289047479629517,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.5898,
+      "step": 850
+    },
+    {
+      "epoch": 0.060152386044646435,
+      "grad_norm": 0.177517369389534,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.5883,
+      "step": 900
+    },
+    {
+      "epoch": 0.06349418526934902,
+      "grad_norm": 0.17740458250045776,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.5913,
+      "step": 950
+    },
+    {
+      "epoch": 0.06683598449405159,
+      "grad_norm": 0.16404500603675842,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5842,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07017778371875417,
+      "grad_norm": 0.18010100722312927,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.568,
+      "step": 1050
+    },
+    {
+      "epoch": 0.07351958294345676,
+      "grad_norm": 0.1666346937417984,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.5667,
+      "step": 1100
+    },
+    {
+      "epoch": 0.07686138216815934,
+      "grad_norm": 0.18164004385471344,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.562,
+      "step": 1150
+    },
+    {
+      "epoch": 0.08020318139286192,
+      "grad_norm": 0.16982343792915344,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.5564,
+      "step": 1200
+    },
+    {
+      "epoch": 0.08354498061756449,
+      "grad_norm": 0.17339172959327698,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.5596,
+      "step": 1250
+    },
+    {
+      "epoch": 0.08688677984226707,
+      "grad_norm": 0.16654901206493378,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.5726,
+      "step": 1300
+    },
+    {
+      "epoch": 0.09022857906696966,
+      "grad_norm": 0.1794307380914688,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.5403,
+      "step": 1350
+    },
+    {
+      "epoch": 0.09357037829167224,
+      "grad_norm": 0.15099531412124634,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.552,
+      "step": 1400
+    },
+    {
+      "epoch": 0.09691217751637482,
+      "grad_norm": 0.17503619194030762,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.5529,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1002539767410774,
+      "grad_norm": 0.1650569587945938,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.5504,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "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": 2.5084035072e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4451be6363a6c8a91ad6bed776efd247ea772e27fca4be46257c99e33d9272
+size 5304