Training in progress, epoch 4, checkpoint

checkpoint-436/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-436/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-436/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd07064c78de2ff7f84b24ee7d6a52479d733ddec0785af34eeaced4d8e7a422
+size 392536704

checkpoint-436/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f55e9db907ff0d27d3bf4b7633190bc1774196f61de72b25c4bc8b2c2caa8d
+size 785167627

checkpoint-436/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896676187d05c6631b1299741b173244146508302db85fc6e758f3a53911d9df
+size 14709

checkpoint-436/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9052ab427a7e2650cf292bd1cfdcf79d1b25b326d9ca1ad93068bd0704234bea
+size 1383

checkpoint-436/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5132a5f15ca614de967681391099d4d940816d6181f88f22b1a8d70a1ccfc529
+size 1465

checkpoint-436/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-436/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-436/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 436,
+  "best_metric": 4.303887844085693,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/ads_o_fr_13/checkpoint-436",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 436,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009174311926605505,
+      "grad_norm": 17.951679229736328,
+      "learning_rate": 0.0,
+      "loss": 9.7117,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.537048101425171,
+      "learning_rate": 2.16e-05,
+      "loss": 7.4816,
+      "step": 109
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.125095367431641,
+      "eval_runtime": 3.3374,
+      "eval_samples_per_second": 810.812,
+      "eval_steps_per_second": 3.296,
+      "step": 109
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5311152935028076,
+      "learning_rate": 4.3400000000000005e-05,
+      "loss": 5.2479,
+      "step": 218
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.817795753479004,
+      "eval_runtime": 3.4684,
+      "eval_samples_per_second": 780.181,
+      "eval_steps_per_second": 3.171,
+      "step": 218
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4448567628860474,
+      "learning_rate": 6.52e-05,
+      "loss": 4.5633,
+      "step": 327
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.496043682098389,
+      "eval_runtime": 3.3595,
+      "eval_samples_per_second": 805.47,
+      "eval_steps_per_second": 3.274,
+      "step": 327
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4543994665145874,
+      "learning_rate": 8.7e-05,
+      "loss": 4.3166,
+      "step": 436
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.303887844085693,
+      "eval_runtime": 3.3467,
+      "eval_samples_per_second": 808.547,
+      "eval_steps_per_second": 3.287,
+      "step": 436
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2180,
+  "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": 7237266702336000.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-436/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d93deb681371270a2b11ffb08b575a730e512a2a8d3e5c01548c44e1aa4ff7
+size 5905