Training in progress, step 28000, checkpoint

checkpoint-28000/config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 5,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 4,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 256,
+  "n_head": 8,
+  "n_inner": 1024,
+  "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-28000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 4,
+  "transformers_version": "4.45.2"
+}

checkpoint-28000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ee767f3cf9b0fb51cebb03ecec92ff24f8564123af90f9a7990e03e9f4ed06
+size 34197144

checkpoint-28000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576f487af578f97f38ece9af908d06fc8ad11c071321fa8346105091337caedf
+size 68458234

checkpoint-28000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dd01225e011a9c9354b5b7bc3c2d3af3b77aa9b75a8e3007c065784b249b67
+size 14308

checkpoint-28000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5792d2ed49d7c2ed5d038a40282e624fc392959aa27c47451b73a03bbdbf0bab
+size 1000

checkpoint-28000/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[EOS]"
+}

checkpoint-28000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[EOS]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-28000/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 3.2381503582000732,
+  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained_recent/fr/childes_clm_context_30/checkpoint-20000",
+  "epoch": 24.604569420035148,
+  "eval_steps": 4000,
+  "global_step": 28000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.51493848857645,
+      "grad_norm": 1.9854258298873901,
+      "learning_rate": 4e-05,
+      "loss": 5.3831,
+      "step": 4000
+    },
+    {
+      "epoch": 3.51493848857645,
+      "eval_loss": 4.042910099029541,
+      "eval_runtime": 2.2441,
+      "eval_samples_per_second": 993.282,
+      "eval_steps_per_second": 62.387,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0298769771529,
+      "grad_norm": 1.9670228958129883,
+      "learning_rate": 7.999000000000001e-05,
+      "loss": 3.7776,
+      "step": 8000
+    },
+    {
+      "epoch": 7.0298769771529,
+      "eval_loss": 3.598284959793091,
+      "eval_runtime": 1.4725,
+      "eval_samples_per_second": 1513.713,
+      "eval_steps_per_second": 95.074,
+      "step": 8000
+    },
+    {
+      "epoch": 10.54481546572935,
+      "grad_norm": 1.84652578830719,
+      "learning_rate": 0.00011996999999999999,
+      "loss": 3.427,
+      "step": 12000
+    },
+    {
+      "epoch": 10.54481546572935,
+      "eval_loss": 3.393275499343872,
+      "eval_runtime": 1.4732,
+      "eval_samples_per_second": 1513.008,
+      "eval_steps_per_second": 95.03,
+      "step": 12000
+    },
+    {
+      "epoch": 14.0597539543058,
+      "grad_norm": 1.7305121421813965,
+      "learning_rate": 0.00015995,
+      "loss": 3.1929,
+      "step": 16000
+    },
+    {
+      "epoch": 14.0597539543058,
+      "eval_loss": 3.286353349685669,
+      "eval_runtime": 1.4744,
+      "eval_samples_per_second": 1511.776,
+      "eval_steps_per_second": 94.952,
+      "step": 16000
+    },
+    {
+      "epoch": 17.57469244288225,
+      "grad_norm": 1.6044658422470093,
+      "learning_rate": 0.00019993,
+      "loss": 3.0111,
+      "step": 20000
+    },
+    {
+      "epoch": 17.57469244288225,
+      "eval_loss": 3.2381503582000732,
+      "eval_runtime": 1.4881,
+      "eval_samples_per_second": 1497.891,
+      "eval_steps_per_second": 94.08,
+      "step": 20000
+    },
+    {
+      "epoch": 21.0896309314587,
+      "grad_norm": 1.6615808010101318,
+      "learning_rate": 0.00023993000000000002,
+      "loss": 2.865,
+      "step": 24000
+    },
+    {
+      "epoch": 21.0896309314587,
+      "eval_loss": 3.2528979778289795,
+      "eval_runtime": 2.2977,
+      "eval_samples_per_second": 970.119,
+      "eval_steps_per_second": 60.932,
+      "step": 24000
+    },
+    {
+      "epoch": 24.604569420035148,
+      "grad_norm": 1.6422351598739624,
+      "learning_rate": 0.00027993,
+      "loss": 2.7295,
+      "step": 28000
+    },
+    {
+      "epoch": 24.604569420035148,
+      "eval_loss": 3.288562536239624,
+      "eval_runtime": 2.2926,
+      "eval_samples_per_second": 972.244,
+      "eval_steps_per_second": 61.065,
+      "step": 28000
+    }
+  ],
+  "logging_steps": 4000,
+  "max_steps": 400000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 352,
+  "save_steps": 4000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2172951859298304.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-28000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3533dea21aa155a7988b630550cc4a1bba7f119b325cffbe82255aaf19a61f
+size 5496