Training in progress, epoch 2, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df1af57c03358833973d8a783ab8e5b08d301d9f44155385f111779b99aa18e
+size 711443456

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d279d5f69a448140ef4fecf6f281a99ed5bc22d49897ff5f008e4342261b3125
+size 1423007994

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38bfb601561e52717fff802e018796c2541c9426ba4a8331b33df5af5ae9f13
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50600782129528a2ff4b6678621fe6db23d95a0ab74c1cd9ca05452600fdbcff
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81876d1039e59895e53265decdd550442122b84a0233b68650d08308dc9a7ba2
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25b7d897b715015da16b3b8dc9f7a8dc4276100b3da41ea979a1f9c6cd7d2e7
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8ef336f350393f864ded0ff9edc01b49345378acdd9754b6ef0a18a583802d
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5658f14fe2cfaea80f40b65fee1b80430d608a69c3e9367cebe76a5e4a08a4
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362f7efe363687ef1d7082c6a9b81dfb6a907f6a0912d2e2c635bf40d3baa6c1
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6009dec19a36d033fdb9480525f1904726957b88b529a1f853bc3888eae73bfe
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6c39ff436bf4ddb14f403ef2ea27c1a42ba666b798c5499195fc9ff1ad1ae1
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,252 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.138775110244751,
+      "learning_rate": 6.142506142506143e-09,
+      "loss": 0.7144,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.9382898807525635,
+      "learning_rate": 1.2285012285012285e-06,
+      "loss": 0.6919,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.854135513305664,
+      "learning_rate": 2.457002457002457e-06,
+      "loss": 0.5159,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 10.978944778442383,
+      "learning_rate": 3.685503685503686e-06,
+      "loss": 0.4512,
+      "step": 600
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.893263816833496,
+      "learning_rate": 4.914004914004914e-06,
+      "loss": 0.4188,
+      "step": 800
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.747641086578369,
+      "learning_rate": 6.1425061425061425e-06,
+      "loss": 0.3966,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.317325115203857,
+      "learning_rate": 7.371007371007372e-06,
+      "loss": 0.38,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.575576066970825,
+      "learning_rate": 8.5995085995086e-06,
+      "loss": 0.3664,
+      "step": 1400
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.714512825012207,
+      "learning_rate": 9.828009828009828e-06,
+      "loss": 0.3571,
+      "step": 1600
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 10.362600326538086,
+      "learning_rate": 9.99660019816015e-06,
+      "loss": 0.3477,
+      "step": 1800
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 7.849954605102539,
+      "learning_rate": 9.984103498544067e-06,
+      "loss": 0.344,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.9534077644348145,
+      "learning_rate": 9.962442770775675e-06,
+      "loss": 0.3286,
+      "step": 2200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 8.997251510620117,
+      "learning_rate": 9.931657841379274e-06,
+      "loss": 0.3187,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.736711263656616,
+      "learning_rate": 9.891805313103928e-06,
+      "loss": 0.3098,
+      "step": 2600
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.244268417358398,
+      "learning_rate": 9.842958460850763e-06,
+      "loss": 0.3154,
+      "step": 2800
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.168263912200928,
+      "learning_rate": 9.785207096945972e-06,
+      "loss": 0.3013,
+      "step": 3000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.536916732788086,
+      "learning_rate": 9.718657406007276e-06,
+      "loss": 0.306,
+      "step": 3200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 4.842708587646484,
+      "learning_rate": 9.643431749707433e-06,
+      "loss": 0.2877,
+      "step": 3400
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 10.104561805725098,
+      "learning_rate": 9.559668441793803e-06,
+      "loss": 0.2735,
+      "step": 3600
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.159233808517456,
+      "learning_rate": 9.467521493777597e-06,
+      "loss": 0.2815,
+      "step": 3800
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 8.2909517288208,
+      "learning_rate": 9.367160331760423e-06,
+      "loss": 0.2771,
+      "step": 4000
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 6.18996000289917,
+      "learning_rate": 9.258769484918773e-06,
+      "loss": 0.2697,
+      "step": 4200
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3391902446746826,
+      "learning_rate": 9.142548246219212e-06,
+      "loss": 0.2659,
+      "step": 4400
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 5.173523426055908,
+      "learning_rate": 9.018710305988126e-06,
+      "loss": 0.2657,
+      "step": 4600
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 2.5208077430725098,
+      "learning_rate": 8.88748335900973e-06,
+      "loss": 0.2558,
+      "step": 4800
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 7.448746681213379,
+      "learning_rate": 8.749108685874764e-06,
+      "loss": 0.2706,
+      "step": 5000
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.4153690338134766,
+      "learning_rate": 8.60384070934964e-06,
+      "loss": 0.2618,
+      "step": 5200
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 5.566818714141846,
+      "learning_rate": 8.4519465265817e-06,
+      "loss": 0.2484,
+      "step": 5400
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 6.106826305389404,
+      "learning_rate": 8.293705418000702e-06,
+      "loss": 0.2625,
+      "step": 5600
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 3.50177001953125,
+      "learning_rate": 8.129408333819524e-06,
+      "loss": 0.2593,
+      "step": 5800
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 3.8748812675476074,
+      "learning_rate": 7.959357359078174e-06,
+      "loss": 0.257,
+      "step": 6000
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.6173479557037354,
+      "learning_rate": 7.783865158214768e-06,
+      "loss": 0.2505,
+      "step": 6200
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 3.0926144123077393,
+      "learning_rate": 7.6032544001846476e-06,
+      "loss": 0.2482,
+      "step": 6400
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 16280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.193125396059259e+17,
+  "train_batch_size": 16,
+  "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:fdd861b621c048ced365c2b245d73c7ba8eb8a0c34c536b9124862e9b8f088c8
+size 5048