Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": "f79f78df17138d38be1b6aa5041a13bf715c3e86",
+  "_commit_hash": "bf0ba286dd1951b2990a0aa57cf72f5caa2c4bfb",
   "_name_or_path": "JulienRPA/BERT2BERT_pretrained_LC-QuAD_2.0",
   "architectures": [
     "EncoderDecoderModel"
@@ -84,7 +84,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 31560
+    "vocab_size": 34522
   },
   "decoder_start_token_id": 101,
   "early_stopping": true,
@@ -167,7 +167,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 31560
+    "vocab_size": 34522
   },
   "eos_token_id": 102,
   "is_encoder_decoder": true,
@@ -178,5 +178,5 @@
   "pad_token_id": 0,
   "torch_dtype": "float32",
   "transformers_version": null,
-  "vocab_size": 31560
+  "vocab_size": 34522
 }

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": "f79f78df17138d38be1b6aa5041a13bf715c3e86",
+  "_commit_hash": "bf0ba286dd1951b2990a0aa57cf72f5caa2c4bfb",
   "_name_or_path": "JulienRPA/BERT2BERT_pretrained_LC-QuAD_2.0",
   "architectures": [
     "EncoderDecoderModel"
@@ -84,7 +84,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 31560
+    "vocab_size": 34522
   },
   "decoder_start_token_id": 101,
   "early_stopping": true,
@@ -167,7 +167,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 31560
+    "vocab_size": 34522
   },
   "eos_token_id": 102,
   "is_encoder_decoder": true,
@@ -178,5 +178,5 @@
   "pad_token_id": 0,
   "torch_dtype": "float32",
   "transformers_version": null,
-  "vocab_size": 31560
+  "vocab_size": 34522
 }

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c02848fe198317b9df9c7b015be7a5a8d106b3d8c95581e94d368f12e3bd2aa
-size 1987250795
+oid sha256:8166f9df0c99894923580dd1d8f3e44212e0b0ef6371e20f7fa27b1980e7cdcd
+size 2023671531

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
-size 996026489
+oid sha256:cc899faae2d95cfa25532820e4c4876cc4a250be659324f96270d3648acc5d5d
+size 1014236857

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989bf089e99481fed8a0ca8c42df0ebf959c5055d0443690a60cd2739bd951a3
+oid sha256:579b9ad044e049c9d6416c19b90ae0aaf3dfa4d6c410d924a85993ad3cd08d50
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42803a5c9416fe30408add7b6997c032033033ede5cc3b581b72368a5f47393e
+oid sha256:d74cc6285bd526ccecc46e70cc671e33a9af4da21ca6fb0670355de22affc5ab
 size 627

last-checkpoint/trainer_state.json

@@ -1,340 +1,52 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 230.76923076923077,
-  "global_step": 9000,
+  "epoch": 25.641025641025642,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 12.82,
-      "learning_rate": 1.2375000000000001e-05,
-      "loss": 5.1115,
+      "learning_rate": 1.24e-05,
+      "loss": 4.0279,
       "step": 500
     },
     {
       "epoch": 12.82,
-      "eval_bleu": 55.8418,
+      "eval_bleu": 49.841,
       "eval_em": 0.0,
-      "eval_gen_len": 78.6043,
-      "eval_loss": 1.7833343744277954,
+      "eval_gen_len": 51.6403,
+      "eval_loss": 2.4031472206115723,
       "eval_rm": 0.0,
-      "eval_runtime": 216.1632,
-      "eval_samples_per_second": 1.929,
-      "eval_steps_per_second": 0.245,
+      "eval_runtime": 135.1177,
+      "eval_samples_per_second": 3.086,
+      "eval_steps_per_second": 0.392,
       "step": 500
     },
     {
       "epoch": 25.64,
-      "learning_rate": 2.4875e-05,
-      "loss": 0.8877,
+      "learning_rate": 2.4900000000000002e-05,
+      "loss": 1.3442,
       "step": 1000
     },
     {
       "epoch": 25.64,
-      "eval_bleu": 88.9639,
-      "eval_em": 0.2062,
-      "eval_gen_len": 77.9976,
-      "eval_loss": 0.3478254973888397,
-      "eval_rm": 0.2158,
-      "eval_runtime": 173.1336,
-      "eval_samples_per_second": 2.409,
-      "eval_steps_per_second": 0.306,
+      "eval_bleu": 85.0177,
+      "eval_em": 0.0,
+      "eval_gen_len": 57.9784,
+      "eval_loss": 0.501366138458252,
+      "eval_rm": 0.0,
+      "eval_runtime": 188.7983,
+      "eval_samples_per_second": 2.209,
+      "eval_steps_per_second": 0.281,
       "step": 1000
-    },
-    {
-      "epoch": 38.46,
-      "learning_rate": 3.737500000000001e-05,
-      "loss": 0.1085,
-      "step": 1500
-    },
-    {
-      "epoch": 38.46,
-      "eval_bleu": 95.531,
-      "eval_em": 0.3669,
-      "eval_gen_len": 80.2854,
-      "eval_loss": 0.21576985716819763,
-      "eval_rm": 0.4436,
-      "eval_runtime": 170.6947,
-      "eval_samples_per_second": 2.443,
-      "eval_steps_per_second": 0.31,
-      "step": 1500
-    },
-    {
-      "epoch": 51.28,
-      "learning_rate": 4.9875000000000006e-05,
-      "loss": 0.0437,
-      "step": 2000
-    },
-    {
-      "epoch": 51.28,
-      "eval_bleu": 96.2387,
-      "eval_em": 0.5012,
-      "eval_gen_len": 80.8729,
-      "eval_loss": 0.20689286291599274,
-      "eval_rm": 0.5899,
-      "eval_runtime": 169.6593,
-      "eval_samples_per_second": 2.458,
-      "eval_steps_per_second": 0.312,
-      "step": 2000
-    },
-    {
-      "epoch": 64.1,
-      "learning_rate": 4.7448453608247423e-05,
-      "loss": 0.0276,
-      "step": 2500
-    },
-    {
-      "epoch": 64.1,
-      "eval_bleu": 96.2239,
-      "eval_em": 0.5755,
-      "eval_gen_len": 80.2662,
-      "eval_loss": 0.19657467305660248,
-      "eval_rm": 0.6523,
-      "eval_runtime": 171.715,
-      "eval_samples_per_second": 2.428,
-      "eval_steps_per_second": 0.309,
-      "step": 2500
-    },
-    {
-      "epoch": 76.92,
-      "learning_rate": 4.487113402061856e-05,
-      "loss": 0.0187,
-      "step": 3000
-    },
-    {
-      "epoch": 76.92,
-      "eval_bleu": 96.1781,
-      "eval_em": 0.5564,
-      "eval_gen_len": 81.753,
-      "eval_loss": 0.22087490558624268,
-      "eval_rm": 0.6523,
-      "eval_runtime": 178.818,
-      "eval_samples_per_second": 2.332,
-      "eval_steps_per_second": 0.296,
-      "step": 3000
-    },
-    {
-      "epoch": 89.74,
-      "learning_rate": 4.229381443298969e-05,
-      "loss": 0.0154,
-      "step": 3500
-    },
-    {
-      "epoch": 89.74,
-      "eval_bleu": 96.6038,
-      "eval_em": 0.5707,
-      "eval_gen_len": 81.0576,
-      "eval_loss": 0.23550103604793549,
-      "eval_rm": 0.6739,
-      "eval_runtime": 177.0475,
-      "eval_samples_per_second": 2.355,
-      "eval_steps_per_second": 0.299,
-      "step": 3500
-    },
-    {
-      "epoch": 102.56,
-      "learning_rate": 3.9716494845360825e-05,
-      "loss": 0.0128,
-      "step": 4000
-    },
-    {
-      "epoch": 102.56,
-      "eval_bleu": 96.3205,
-      "eval_em": 0.5827,
-      "eval_gen_len": 81.6307,
-      "eval_loss": 0.25351256132125854,
-      "eval_rm": 0.6906,
-      "eval_runtime": 173.3396,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 0.306,
-      "step": 4000
-    },
-    {
-      "epoch": 115.38,
-      "learning_rate": 3.713917525773196e-05,
-      "loss": 0.0096,
-      "step": 4500
-    },
-    {
-      "epoch": 115.38,
-      "eval_bleu": 96.604,
-      "eval_em": 0.6211,
-      "eval_gen_len": 80.7698,
-      "eval_loss": 0.23454025387763977,
-      "eval_rm": 0.7314,
-      "eval_runtime": 177.5772,
-      "eval_samples_per_second": 2.348,
-      "eval_steps_per_second": 0.298,
-      "step": 4500
-    },
-    {
-      "epoch": 128.21,
-      "learning_rate": 3.4561855670103095e-05,
-      "loss": 0.0073,
-      "step": 5000
-    },
-    {
-      "epoch": 128.21,
-      "eval_bleu": 96.5656,
-      "eval_em": 0.6355,
-      "eval_gen_len": 81.6811,
-      "eval_loss": 0.22575555741786957,
-      "eval_rm": 0.7386,
-      "eval_runtime": 171.583,
-      "eval_samples_per_second": 2.43,
-      "eval_steps_per_second": 0.309,
-      "step": 5000
-    },
-    {
-      "epoch": 141.03,
-      "learning_rate": 3.1984536082474226e-05,
-      "loss": 0.0082,
-      "step": 5500
-    },
-    {
-      "epoch": 141.03,
-      "eval_bleu": 96.3627,
-      "eval_em": 0.6019,
-      "eval_gen_len": 80.5396,
-      "eval_loss": 0.24117104709148407,
-      "eval_rm": 0.7122,
-      "eval_runtime": 171.7828,
-      "eval_samples_per_second": 2.427,
-      "eval_steps_per_second": 0.309,
-      "step": 5500
-    },
-    {
-      "epoch": 153.85,
-      "learning_rate": 2.9407216494845364e-05,
-      "loss": 0.0064,
-      "step": 6000
-    },
-    {
-      "epoch": 153.85,
-      "eval_bleu": 96.7404,
-      "eval_em": 0.6331,
-      "eval_gen_len": 81.5659,
-      "eval_loss": 0.23870165646076202,
-      "eval_rm": 0.7338,
-      "eval_runtime": 176.1891,
-      "eval_samples_per_second": 2.367,
-      "eval_steps_per_second": 0.301,
-      "step": 6000
-    },
-    {
-      "epoch": 166.67,
-      "learning_rate": 2.6829896907216496e-05,
-      "loss": 0.0048,
-      "step": 6500
-    },
-    {
-      "epoch": 166.67,
-      "eval_bleu": 96.5993,
-      "eval_em": 0.6211,
-      "eval_gen_len": 81.5779,
-      "eval_loss": 0.2463260143995285,
-      "eval_rm": 0.729,
-      "eval_runtime": 170.4492,
-      "eval_samples_per_second": 2.446,
-      "eval_steps_per_second": 0.311,
-      "step": 6500
-    },
-    {
-      "epoch": 179.49,
-      "learning_rate": 2.425257731958763e-05,
-      "loss": 0.0041,
-      "step": 7000
-    },
-    {
-      "epoch": 179.49,
-      "eval_bleu": 96.447,
-      "eval_em": 0.6307,
-      "eval_gen_len": 80.5324,
-      "eval_loss": 0.2447213977575302,
-      "eval_rm": 0.7386,
-      "eval_runtime": 166.7311,
-      "eval_samples_per_second": 2.501,
-      "eval_steps_per_second": 0.318,
-      "step": 7000
-    },
-    {
-      "epoch": 192.31,
-      "learning_rate": 2.1675257731958766e-05,
-      "loss": 0.0036,
-      "step": 7500
-    },
-    {
-      "epoch": 192.31,
-      "eval_bleu": 96.5899,
-      "eval_em": 0.6163,
-      "eval_gen_len": 80.7794,
-      "eval_loss": 0.2510390877723694,
-      "eval_rm": 0.7314,
-      "eval_runtime": 173.7032,
-      "eval_samples_per_second": 2.401,
-      "eval_steps_per_second": 0.305,
-      "step": 7500
-    },
-    {
-      "epoch": 205.13,
-      "learning_rate": 1.9097938144329897e-05,
-      "loss": 0.0034,
-      "step": 8000
-    },
-    {
-      "epoch": 205.13,
-      "eval_bleu": 96.4759,
-      "eval_em": 0.6331,
-      "eval_gen_len": 81.7578,
-      "eval_loss": 0.2551712095737457,
-      "eval_rm": 0.7434,
-      "eval_runtime": 170.3668,
-      "eval_samples_per_second": 2.448,
-      "eval_steps_per_second": 0.311,
-      "step": 8000
-    },
-    {
-      "epoch": 217.95,
-      "learning_rate": 1.6520618556701032e-05,
-      "loss": 0.0023,
-      "step": 8500
-    },
-    {
-      "epoch": 217.95,
-      "eval_bleu": 96.4892,
-      "eval_em": 0.6379,
-      "eval_gen_len": 81.9424,
-      "eval_loss": 0.25497403740882874,
-      "eval_rm": 0.7482,
-      "eval_runtime": 168.8592,
-      "eval_samples_per_second": 2.47,
-      "eval_steps_per_second": 0.314,
-      "step": 8500
-    },
-    {
-      "epoch": 230.77,
-      "learning_rate": 1.3943298969072165e-05,
-      "loss": 0.0022,
-      "step": 9000
-    },
-    {
-      "epoch": 230.77,
-      "eval_bleu": 96.8559,
-      "eval_em": 0.6475,
-      "eval_gen_len": 81.5635,
-      "eval_loss": 0.2539912760257721,
-      "eval_rm": 0.7506,
-      "eval_runtime": 158.2741,
-      "eval_samples_per_second": 2.635,
-      "eval_steps_per_second": 0.335,
-      "step": 9000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 7171986679845120.0,
+  "total_flos": 810312415883520.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b1498745616fbf0a4cd4c1b6cf32468b15b936a8b11b56029767534510acd1
+oid sha256:ffc9c446a7cf1044793b419a9995d30772c70afe831ef8253e81e0a2b524a602
 size 4155

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
-size 996026489
+oid sha256:cc899faae2d95cfa25532820e4c4876cc4a250be659324f96270d3648acc5d5d
+size 1014236857

last-checkpoint/scaler.pt → runs/Jun01_08-15-55_7b8f3300e052/1685608114.229445/events.out.tfevents.1685608114.7b8f3300e052.20157.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca42b4728e4a3dd46497569040a4bcb0499b808d030d537723afa704d3d5cea
-size 557
+oid sha256:70231ea6ac78bdfb93119ad37a0b717a97fda6ea52c86a06bbe4576fbebdf834
+size 6249

runs/Jun01_08-15-55_7b8f3300e052/events.out.tfevents.1685608114.7b8f3300e052.20157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d5c01100abcc1057fe393c3a7e9a393fcde1b5d1a136fa5563abc64870ed85
+size 9795

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b1498745616fbf0a4cd4c1b6cf32468b15b936a8b11b56029767534510acd1
+oid sha256:ffc9c446a7cf1044793b419a9995d30772c70afe831ef8253e81e0a2b524a602
 size 4155