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": "4.51.3",
+  "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 sha256:6729f208d69b92a792ff581298895d4d21163f2d26a08779d210c97f62588a37
+size 357393656

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73de7fe0e20e7b294ab658ca1a2c5aa918c6889e3a85c324f46b96e3a57050f2
+size 714965067

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe73f21d09f06562f5cbf6e3caa5916c365b976ddb9bf99290f83eb92d6a673d
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579d5684922568407b355eaf4c012955ccd81a7f1aa701edb9e8541cf6f1622a
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0c21f4beed8d5d2bd54d4bd44e1ee8829a8a93c1021ea820328e898dd40e63
+size 1465

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": 0.7096766829490662,
+      "learning_rate": 0.0002495,
+      "loss": 7.9226,
+      "step": 500
+    },
+    {
+      "epoch": 0.08315316813570597,
+      "grad_norm": 0.7341204881668091,
+      "learning_rate": 0.0004995,
+      "loss": 7.933,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12472975220355896,
+      "grad_norm": 0.9115172624588013,
+      "learning_rate": 0.000495780483680027,
+      "loss": 7.9418,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16630633627141195,
+      "grad_norm": 2.1239709854125977,
+      "learning_rate": 0.0004915525114155252,
+      "loss": 7.9371,
+      "step": 2000
+    },
+    {
+      "epoch": 0.20788292033926492,
+      "grad_norm": 0.6690090298652649,
+      "learning_rate": 0.0004873245391510232,
+      "loss": 7.9481,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24945950440711792,
+      "grad_norm": 1.4043654203414917,
+      "learning_rate": 0.00048310502283105026,
+      "loss": 7.9474,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2910360884749709,
+      "grad_norm": 0.21322312951087952,
+      "learning_rate": 0.0004788770505665483,
+      "loss": 7.9376,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3326126725428239,
+      "grad_norm": 0.5360279083251953,
+      "learning_rate": 0.0004746575342465754,
+      "loss": 7.9577,
+      "step": 4000
+    },
+    {
+      "epoch": 0.37418925661067687,
+      "grad_norm": 0.8047875165939331,
+      "learning_rate": 0.0004704295619820734,
+      "loss": 7.946,
+      "step": 4500
+    },
+    {
+      "epoch": 0.41576584067852984,
+      "grad_norm": 0.8072593212127686,
+      "learning_rate": 0.0004662015897175715,
+      "loss": 7.9355,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4573424247463828,
+      "grad_norm": 0.40493592619895935,
+      "learning_rate": 0.00046197361745306954,
+      "loss": 7.9412,
+      "step": 5500
+    },
+    {
+      "epoch": 0.49891900881423584,
+      "grad_norm": 0.3306567668914795,
+      "learning_rate": 0.00045774564518856757,
+      "loss": 7.947,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5404955928820888,
+      "grad_norm": 0.5670518279075623,
+      "learning_rate": 0.00045351767292406566,
+      "loss": 7.9363,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5820721769499418,
+      "grad_norm": 0.23186080157756805,
+      "learning_rate": 0.0004492897006595637,
+      "loss": 7.9351,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6236487610177948,
+      "grad_norm": 1.0985664129257202,
+      "learning_rate": 0.0004450617283950618,
+      "loss": 7.9501,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6652253450856478,
+      "grad_norm": 0.6351549625396729,
+      "learning_rate": 0.00044084221207508876,
+      "loss": 7.9431,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7068019291535007,
+      "grad_norm": 0.17430244386196136,
+      "learning_rate": 0.00043661423981058685,
+      "loss": 7.9432,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7483785132213537,
+      "grad_norm": 3.46504807472229,
+      "learning_rate": 0.0004323862675460849,
+      "loss": 7.9329,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7899550972892068,
+      "grad_norm": 0.22453179955482483,
+      "learning_rate": 0.000428158295281583,
+      "loss": 7.9377,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8315316813570597,
+      "grad_norm": 0.8656890988349915,
+      "learning_rate": 0.00042393877896161006,
+      "loss": 7.9415,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8315316813570597,
+      "eval_loss": 8.933103561401367,
+      "eval_runtime": 2799.3018,
+      "eval_samples_per_second": 137.472,
+      "eval_steps_per_second": 4.296,
+      "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": 1.1209402132305408e+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 sha256:7f8ff06714d81ac2a6d3f10818fb7fa82a1929e9df7d834622489f169dbd5824
+size 5713