Training in progress, epoch 2, checkpoint

checkpoint-206/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-206/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-206/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998205953c719f0cc586978a6ed5548b7a2b25f029e23d5e609fb52ac02eb30f
+size 392536704

checkpoint-206/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b687a0a17959e8008cae97c61ac59266ceb797c3a993f21fb2b1a2357d4ee0d
+size 785167627

checkpoint-206/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d401a688ce5de6e2432158b45d8dd714a6476386b05fad1aeae81acf0b93f20
+size 14709

checkpoint-206/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2d6ebd06a0bcd24ba208fa653931ba286391c324a8e3e3881be695c03a1b5b
+size 1383

checkpoint-206/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a656c30d344152d2d47fff3f782f133c7788f0a9c7c78e9dd52adb30266b551
+size 1401

checkpoint-206/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-206/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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": "</s>",
+      "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": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-206/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_global_step": 206,
+  "best_metric": 5.94571590423584,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/ads_sh1_fr_13/checkpoint-206",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 206,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009708737864077669,
+      "grad_norm": 16.858198165893555,
+      "learning_rate": 0.0,
+      "loss": 9.7487,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9117469787597656,
+      "learning_rate": 2.04e-05,
+      "loss": 8.0282,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.0722832679748535,
+      "eval_runtime": 3.2339,
+      "eval_samples_per_second": 791.617,
+      "eval_steps_per_second": 3.092,
+      "step": 103
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7483371496200562,
+      "learning_rate": 4.1e-05,
+      "loss": 6.2183,
+      "step": 206
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.94571590423584,
+      "eval_runtime": 3.1682,
+      "eval_samples_per_second": 808.025,
+      "eval_steps_per_second": 3.156,
+      "step": 206
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2060,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 3421096574976000.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-206/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ea9dd4549136ce0710957e49c4d2b5ec11bfb6eb9e92285dc4d43b109e6b78
+size 5905