Training in progress, step 10000, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "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": 152000
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76e4efb092536f3309de21ffac9b613f901cabd01d8dc96eb2a66c4fb3abb4c
+size 641630264

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364da8f254e8bbbd78bd7a6ef8df75e0a14619618c684963e9b9f8730dea4e6b
+size 1283324282

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5711e5f007c75c647bc78e026d3890cd962c100502f75cc4e0986dd8cf03994f
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f447d9a4f8170e7dd44eff4ee3d3c6484c4396542223768e0dc445c0ef9466a0
+size 988

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e3f02e9f5699d79cb9cdeec60a8ddd33d4a4ee63c6581d724dba10a6775ffe
+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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3326df9ec64ce5af70e1eff5ba7070351a3c08ddec98cac0c7b843f58fad66ec
+size 10959617

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": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24831148192292413,
+  "eval_steps": 5000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012415574096146206,
+      "grad_norm": 2.5669469833374023,
+      "learning_rate": 0.00025,
+      "loss": 7.7958,
+      "step": 500
+    },
+    {
+      "epoch": 0.024831148192292412,
+      "grad_norm": 2.7620863914489746,
+      "learning_rate": 0.0005,
+      "loss": 6.1015,
+      "step": 1000
+    },
+    {
+      "epoch": 0.037246722288438616,
+      "grad_norm": 4.076244354248047,
+      "learning_rate": 0.0004993083375755296,
+      "loss": 5.7026,
+      "step": 1500
+    },
+    {
+      "epoch": 0.049662296384584824,
+      "grad_norm": 2.8926515579223633,
+      "learning_rate": 0.0004986166751510591,
+      "loss": 5.4064,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06207787048073103,
+      "grad_norm": 2.5285441875457764,
+      "learning_rate": 0.0004979250127265886,
+      "loss": 5.2292,
+      "step": 2500
+    },
+    {
+      "epoch": 0.07449344457687723,
+      "grad_norm": 2.443577766418457,
+      "learning_rate": 0.0004972333503021182,
+      "loss": 5.0374,
+      "step": 3000
+    },
+    {
+      "epoch": 0.08690901867302345,
+      "grad_norm": 3.3200581073760986,
+      "learning_rate": 0.0004965416878776477,
+      "loss": 4.8467,
+      "step": 3500
+    },
+    {
+      "epoch": 0.09932459276916965,
+      "grad_norm": 3.622572183609009,
+      "learning_rate": 0.0004958500254531773,
+      "loss": 4.6069,
+      "step": 4000
+    },
+    {
+      "epoch": 0.11174016686531585,
+      "grad_norm": 2.4103891849517822,
+      "learning_rate": 0.0004951583630287068,
+      "loss": 4.2064,
+      "step": 4500
+    },
+    {
+      "epoch": 0.12415574096146206,
+      "grad_norm": 2.76577091217041,
+      "learning_rate": 0.0004944667006042363,
+      "loss": 3.9799,
+      "step": 5000
+    },
+    {
+      "epoch": 0.12415574096146206,
+      "eval_loss": 2.73461651802063,
+      "eval_runtime": 4555.6821,
+      "eval_samples_per_second": 282.876,
+      "eval_steps_per_second": 8.84,
+      "step": 5000
+    },
+    {
+      "epoch": 0.13657131505760825,
+      "grad_norm": 3.056166172027588,
+      "learning_rate": 0.0004937750381797658,
+      "loss": 3.8228,
+      "step": 5500
+    },
+    {
+      "epoch": 0.14898688915375446,
+      "grad_norm": 2.7611379623413086,
+      "learning_rate": 0.0004930833757552954,
+      "loss": 3.7499,
+      "step": 6000
+    },
+    {
+      "epoch": 0.16140246324990068,
+      "grad_norm": 3.347247362136841,
+      "learning_rate": 0.0004923930966556738,
+      "loss": 3.6592,
+      "step": 6500
+    },
+    {
+      "epoch": 0.1738180373460469,
+      "grad_norm": 2.724517822265625,
+      "learning_rate": 0.0004917014342312034,
+      "loss": 3.6058,
+      "step": 7000
+    },
+    {
+      "epoch": 0.18623361144219308,
+      "grad_norm": 2.5716731548309326,
+      "learning_rate": 0.0004910097718067329,
+      "loss": 3.4979,
+      "step": 7500
+    },
+    {
+      "epoch": 0.1986491855383393,
+      "grad_norm": 2.978942632675171,
+      "learning_rate": 0.0004903194927071113,
+      "loss": 3.4583,
+      "step": 8000
+    },
+    {
+      "epoch": 0.2110647596344855,
+      "grad_norm": 3.8726186752319336,
+      "learning_rate": 0.000489627830282641,
+      "loss": 3.387,
+      "step": 8500
+    },
+    {
+      "epoch": 0.2234803337306317,
+      "grad_norm": 2.9747536182403564,
+      "learning_rate": 0.0004889361678581704,
+      "loss": 3.3215,
+      "step": 9000
+    },
+    {
+      "epoch": 0.2358959078267779,
+      "grad_norm": 2.828449249267578,
+      "learning_rate": 0.00048824450543370003,
+      "loss": 3.2716,
+      "step": 9500
+    },
+    {
+      "epoch": 0.24831148192292413,
+      "grad_norm": 2.614732503890991,
+      "learning_rate": 0.0004875542263340785,
+      "loss": 3.2215,
+      "step": 10000
+    },
+    {
+      "epoch": 0.24831148192292413,
+      "eval_loss": 2.174846887588501,
+      "eval_runtime": 4452.1206,
+      "eval_samples_per_second": 289.456,
+      "eval_steps_per_second": 9.046,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 362448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 4.198923773519462e+16,
+  "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:a2a298c5ff0ea9bb209da31c0572140e7e88623e0916acbb364dfd81b6f51344
+size 5368