Training in progress, step 16000, checkpoint

checkpoint-16000/config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 256,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 8,
+  "n_positions": 512,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 8192
+}

checkpoint-16000/generation_config.json

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

checkpoint-16000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe1aaaf2bbb0ca436546730c22ca47c2e46583addda4c7b53188f71f4ea880c
+size 51007160

checkpoint-16000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e46647a23734ce6630be3736631a9b5d0713196c889ea09ddd690d2198ff544
+size 102078202

checkpoint-16000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19e1a9a966fd68a5a4962e4e734e85cb147a8ed367f805fff55e346dc9ac87a
+size 14308

checkpoint-16000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a1a30fa50e7f4635a69102c76f792b7f60a5cf5eba8be859ea0d9517b4ab1d
+size 1000

checkpoint-16000/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-16000/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "</s>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-16000/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 5.1074652671813965,
+  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/en_clm/wikipedia_30/checkpoint-16000",
+  "epoch": 8.414409676571129,
+  "eval_steps": 2000,
+  "global_step": 16000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0518012095713911,
+      "eval_loss": 7.518920421600342,
+      "eval_runtime": 2.2399,
+      "eval_samples_per_second": 1422.808,
+      "eval_steps_per_second": 89.288,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1036024191427822,
+      "grad_norm": 1.2947496175765991,
+      "learning_rate": 1e-05,
+      "loss": 7.6141,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1036024191427822,
+      "eval_loss": 6.568221092224121,
+      "eval_runtime": 2.1236,
+      "eval_samples_per_second": 1500.783,
+      "eval_steps_per_second": 94.182,
+      "step": 4000
+    },
+    {
+      "epoch": 3.155403628714173,
+      "eval_loss": 6.16925573348999,
+      "eval_runtime": 2.1624,
+      "eval_samples_per_second": 1473.825,
+      "eval_steps_per_second": 92.49,
+      "step": 6000
+    },
+    {
+      "epoch": 4.2072048382855645,
+      "grad_norm": 2.330080270767212,
+      "learning_rate": 2e-05,
+      "loss": 6.2396,
+      "step": 8000
+    },
+    {
+      "epoch": 4.2072048382855645,
+      "eval_loss": 5.901575088500977,
+      "eval_runtime": 2.1326,
+      "eval_samples_per_second": 1494.388,
+      "eval_steps_per_second": 93.78,
+      "step": 8000
+    },
+    {
+      "epoch": 5.259006047856955,
+      "eval_loss": 5.67369270324707,
+      "eval_runtime": 2.1364,
+      "eval_samples_per_second": 1491.788,
+      "eval_steps_per_second": 93.617,
+      "step": 10000
+    },
+    {
+      "epoch": 6.310807257428346,
+      "grad_norm": 2.565220594406128,
+      "learning_rate": 2.99925e-05,
+      "loss": 5.7217,
+      "step": 12000
+    },
+    {
+      "epoch": 6.310807257428346,
+      "eval_loss": 5.460005760192871,
+      "eval_runtime": 2.1835,
+      "eval_samples_per_second": 1459.563,
+      "eval_steps_per_second": 91.595,
+      "step": 12000
+    },
+    {
+      "epoch": 7.362608466999737,
+      "eval_loss": 5.272489547729492,
+      "eval_runtime": 2.1833,
+      "eval_samples_per_second": 1459.691,
+      "eval_steps_per_second": 91.603,
+      "step": 14000
+    },
+    {
+      "epoch": 8.414409676571129,
+      "grad_norm": 2.7334115505218506,
+      "learning_rate": 3.99875e-05,
+      "loss": 5.3064,
+      "step": 16000
+    },
+    {
+      "epoch": 8.414409676571129,
+      "eval_loss": 5.1074652671813965,
+      "eval_runtime": 2.2402,
+      "eval_samples_per_second": 1422.652,
+      "eval_steps_per_second": 89.278,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 4000,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 53,
+  "save_steps": 4000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4136084771023872.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab68434ec7156d3a63e4783f824871a48d62c7c2fdcc831fdd5471c5f4aec7fe
+size 5368