Add checkpoint checkpoint-4000 - ME5 instruct model for African languages

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip 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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large-instruct",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c98b262e7f77f6ccd882828963d8021b6e2419d7b5fb75c6ce85f83ffef6a0
+size 2239607176

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbcb06e967648bc3860b87f5fd2ff60328136bd308fa7f8a44f380f8b49180b
+size 4471061702

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a954564a7f6351d3a5151052a710b2030c8bfaf5a9a149b216b0dcffbadcae5a
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a34168d6bf00fef11b56abaead6231fcca7f7ccd10d8150dbd5040a06d9b98a
+size 1465

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.30644296330345516,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007661074082586378,
+      "grad_norm": 101.71317291259766,
+      "learning_rate": 7.350689127105667e-08,
+      "loss": 3.3393,
+      "step": 100
+    },
+    {
+      "epoch": 0.015322148165172756,
+      "grad_norm": 31.139225006103516,
+      "learning_rate": 1.5007656967840735e-07,
+      "loss": 3.0671,
+      "step": 200
+    },
+    {
+      "epoch": 0.022983222247759137,
+      "grad_norm": 40.13219451904297,
+      "learning_rate": 2.26646248085758e-07,
+      "loss": 2.4152,
+      "step": 300
+    },
+    {
+      "epoch": 0.030644296330345513,
+      "grad_norm": 40.68937683105469,
+      "learning_rate": 3.0321592649310873e-07,
+      "loss": 2.1563,
+      "step": 400
+    },
+    {
+      "epoch": 0.038305370412931895,
+      "grad_norm": 14.248607635498047,
+      "learning_rate": 3.797856049004594e-07,
+      "loss": 2.0665,
+      "step": 500
+    },
+    {
+      "epoch": 0.045966444495518274,
+      "grad_norm": 59.703857421875,
+      "learning_rate": 4.563552833078101e-07,
+      "loss": 2.1346,
+      "step": 600
+    },
+    {
+      "epoch": 0.05362751857810465,
+      "grad_norm": 24.38258934020996,
+      "learning_rate": 5.329249617151608e-07,
+      "loss": 1.9339,
+      "step": 700
+    },
+    {
+      "epoch": 0.061288592660691026,
+      "grad_norm": 51.95455551147461,
+      "learning_rate": 6.094946401225115e-07,
+      "loss": 1.9002,
+      "step": 800
+    },
+    {
+      "epoch": 0.0689496667432774,
+      "grad_norm": 30.304096221923828,
+      "learning_rate": 6.860643185298621e-07,
+      "loss": 1.9943,
+      "step": 900
+    },
+    {
+      "epoch": 0.07661074082586379,
+      "grad_norm": 60.5661506652832,
+      "learning_rate": 7.626339969372128e-07,
+      "loss": 1.9459,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08427181490845016,
+      "grad_norm": 14.830733299255371,
+      "learning_rate": 8.392036753445635e-07,
+      "loss": 1.8775,
+      "step": 1100
+    },
+    {
+      "epoch": 0.09193288899103655,
+      "grad_norm": 33.56428146362305,
+      "learning_rate": 9.157733537519142e-07,
+      "loss": 1.8554,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09959396307362292,
+      "grad_norm": 31.33570671081543,
+      "learning_rate": 9.92343032159265e-07,
+      "loss": 1.9377,
+      "step": 1300
+    },
+    {
+      "epoch": 0.1072550371562093,
+      "grad_norm": 34.497676849365234,
+      "learning_rate": 9.923384693964416e-07,
+      "loss": 1.8444,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11491611123879568,
+      "grad_norm": 50.38022994995117,
+      "learning_rate": 9.838256576147102e-07,
+      "loss": 1.8652,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12257718532138205,
+      "grad_norm": 20.895923614501953,
+      "learning_rate": 9.753128458329787e-07,
+      "loss": 1.7354,
+      "step": 1600
+    },
+    {
+      "epoch": 0.13023825940396844,
+      "grad_norm": 30.610666275024414,
+      "learning_rate": 9.66800034051247e-07,
+      "loss": 1.851,
+      "step": 1700
+    },
+    {
+      "epoch": 0.1378993334865548,
+      "grad_norm": 23.91990852355957,
+      "learning_rate": 9.582872222695155e-07,
+      "loss": 1.8025,
+      "step": 1800
+    },
+    {
+      "epoch": 0.14556040756914118,
+      "grad_norm": 25.79492950439453,
+      "learning_rate": 9.497744104877841e-07,
+      "loss": 1.8883,
+      "step": 1900
+    },
+    {
+      "epoch": 0.15322148165172758,
+      "grad_norm": 40.9505500793457,
+      "learning_rate": 9.413467268238699e-07,
+      "loss": 1.8133,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16088255573431395,
+      "grad_norm": 15.241936683654785,
+      "learning_rate": 9.328339150421384e-07,
+      "loss": 1.8268,
+      "step": 2100
+    },
+    {
+      "epoch": 0.16854362981690033,
+      "grad_norm": 29.481456756591797,
+      "learning_rate": 9.243211032604069e-07,
+      "loss": 1.7925,
+      "step": 2200
+    },
+    {
+      "epoch": 0.1762047038994867,
+      "grad_norm": 22.76151466369629,
+      "learning_rate": 9.158082914786754e-07,
+      "loss": 1.7218,
+      "step": 2300
+    },
+    {
+      "epoch": 0.1838657779820731,
+      "grad_norm": 35.234901428222656,
+      "learning_rate": 9.072954796969439e-07,
+      "loss": 1.7647,
+      "step": 2400
+    },
+    {
+      "epoch": 0.19152685206465947,
+      "grad_norm": 29.202571868896484,
+      "learning_rate": 8.987826679152124e-07,
+      "loss": 1.8084,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19918792614724584,
+      "grad_norm": 29.16272735595703,
+      "learning_rate": 8.902698561334808e-07,
+      "loss": 1.7772,
+      "step": 2600
+    },
+    {
+      "epoch": 0.20684900022983221,
+      "grad_norm": 20.253196716308594,
+      "learning_rate": 8.817570443517494e-07,
+      "loss": 1.754,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2145100743124186,
+      "grad_norm": 15.704442977905273,
+      "learning_rate": 8.732442325700179e-07,
+      "loss": 1.8346,
+      "step": 2800
+    },
+    {
+      "epoch": 0.22217114839500499,
+      "grad_norm": 20.612945556640625,
+      "learning_rate": 8.647314207882863e-07,
+      "loss": 1.8684,
+      "step": 2900
+    },
+    {
+      "epoch": 0.22983222247759136,
+      "grad_norm": 24.869367599487305,
+      "learning_rate": 8.562186090065549e-07,
+      "loss": 1.7856,
+      "step": 3000
+    },
+    {
+      "epoch": 0.23749329656017773,
+      "grad_norm": 21.364919662475586,
+      "learning_rate": 8.477057972248233e-07,
+      "loss": 1.9965,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2451543706427641,
+      "grad_norm": 28.2412052154541,
+      "learning_rate": 8.391929854430918e-07,
+      "loss": 1.8412,
+      "step": 3200
+    },
+    {
+      "epoch": 0.2528154447253505,
+      "grad_norm": 22.827234268188477,
+      "learning_rate": 8.306801736613604e-07,
+      "loss": 1.7012,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2604765188079369,
+      "grad_norm": 24.38725471496582,
+      "learning_rate": 8.221673618796288e-07,
+      "loss": 1.7401,
+      "step": 3400
+    },
+    {
+      "epoch": 0.26813759289052325,
+      "grad_norm": 19.78017807006836,
+      "learning_rate": 8.136545500978973e-07,
+      "loss": 1.7862,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2757986669731096,
+      "grad_norm": 21.21510887145996,
+      "learning_rate": 8.051417383161659e-07,
+      "loss": 1.8333,
+      "step": 3600
+    },
+    {
+      "epoch": 0.283459741055696,
+      "grad_norm": 34.275203704833984,
+      "learning_rate": 7.966289265344343e-07,
+      "loss": 1.8345,
+      "step": 3700
+    },
+    {
+      "epoch": 0.29112081513828236,
+      "grad_norm": 21.573719024658203,
+      "learning_rate": 7.881161147527028e-07,
+      "loss": 1.7381,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2987818892208688,
+      "grad_norm": 25.18048095703125,
+      "learning_rate": 7.796033029709714e-07,
+      "loss": 1.8019,
+      "step": 3900
+    },
+    {
+      "epoch": 0.30644296330345516,
+      "grad_norm": 16.440776824951172,
+      "learning_rate": 7.710904911892397e-07,
+      "loss": 1.6649,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 13053,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f8a470a64c9815bee62bd7de09edf84e08884f4f680c77aea3569b5b587ae0
+size 6033