Training in progress, step 10000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1026,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 62000
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfa600de1f89332937b2a9e291fccb5d6dd93bee03ec6fc02d7acffb74b4d7d
+size 357393656

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09114579e30260ddbd93989b4c67ee0fe81ec35c6625e43d086b8b09ee61fcb
+size 714964666

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a692af930f4760e16973ee91d1256ab5914f9f89d6a2db6baff2ab4286e8b5
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d2a3b37e797e8c28f180ca70f07a3658191721eea4af4adc8b2fad1a8e2173
+size 988

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d6c9d74a1c21aaf6257c8244c550ff35f87d93912ffaa2475eae9be3b1436e
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_len": 1024,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8315316813570597,
+  "eval_steps": 10000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04157658406785299,
+      "grad_norm": 0.2611388564109802,
+      "learning_rate": 0.00025,
+      "loss": 7.95,
+      "step": 500
+    },
+    {
+      "epoch": 0.08315316813570597,
+      "grad_norm": 0.3587435781955719,
+      "learning_rate": 0.0005,
+      "loss": 7.9457,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12472975220355896,
+      "grad_norm": 0.2317708283662796,
+      "learning_rate": 0.000495772027735498,
+      "loss": 7.9714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16630633627141195,
+      "grad_norm": 0.6084672212600708,
+      "learning_rate": 0.0004915440554709961,
+      "loss": 7.9538,
+      "step": 2000
+    },
+    {
+      "epoch": 0.20788292033926492,
+      "grad_norm": 0.3683413863182068,
+      "learning_rate": 0.00048731608320649417,
+      "loss": 7.9606,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24945950440711792,
+      "grad_norm": 0.2715998589992523,
+      "learning_rate": 0.00048308811094199225,
+      "loss": 7.9627,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2910360884749709,
+      "grad_norm": 0.6806758642196655,
+      "learning_rate": 0.0004788601386774903,
+      "loss": 7.9583,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3326126725428239,
+      "grad_norm": 0.2602456212043762,
+      "learning_rate": 0.0004746321664129883,
+      "loss": 7.9584,
+      "step": 4000
+    },
+    {
+      "epoch": 0.37418925661067687,
+      "grad_norm": 0.5907388925552368,
+      "learning_rate": 0.0004704041941484864,
+      "loss": 7.9507,
+      "step": 4500
+    },
+    {
+      "epoch": 0.41576584067852984,
+      "grad_norm": 0.3892901539802551,
+      "learning_rate": 0.00046617622188398444,
+      "loss": 7.9502,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4573424247463828,
+      "grad_norm": 0.5616912841796875,
+      "learning_rate": 0.00046194824961948253,
+      "loss": 7.9486,
+      "step": 5500
+    },
+    {
+      "epoch": 0.49891900881423584,
+      "grad_norm": 0.5943413376808167,
+      "learning_rate": 0.00045772027735498056,
+      "loss": 7.9551,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5404955928820888,
+      "grad_norm": 0.2887517809867859,
+      "learning_rate": 0.0004534923050904786,
+      "loss": 7.9409,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5820721769499418,
+      "grad_norm": 0.3070260286331177,
+      "learning_rate": 0.00044927278877050563,
+      "loss": 7.9389,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6236487610177948,
+      "grad_norm": 0.3042199909687042,
+      "learning_rate": 0.0004450448165060037,
+      "loss": 7.9521,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6652253450856478,
+      "grad_norm": 0.28098851442337036,
+      "learning_rate": 0.00044081684424150176,
+      "loss": 7.9455,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7068019291535007,
+      "grad_norm": 0.7070488333702087,
+      "learning_rate": 0.0004365888719769998,
+      "loss": 7.9564,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7483785132213537,
+      "grad_norm": 0.3044193387031555,
+      "learning_rate": 0.0004323608997124979,
+      "loss": 7.9482,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7899550972892068,
+      "grad_norm": 0.2098478376865387,
+      "learning_rate": 0.00042814138339252497,
+      "loss": 7.9532,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8315316813570597,
+      "grad_norm": 0.29377394914627075,
+      "learning_rate": 0.000423913411128023,
+      "loss": 7.947,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8315316813570597,
+      "eval_loss": 8.870651245117188,
+      "eval_runtime": 2884.426,
+      "eval_samples_per_second": 133.414,
+      "eval_steps_per_second": 4.169,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 60130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1209582928848896e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fdd3caa78e3b33b908b171219d37cc9b26dfb48b47353b50d3538893bf346c
+size 5368