Model save

Browse files

Files changed (9) hide show

README.md +3 -3
all_results.json +15 -0
generated_predictions.txt +0 -0
predict_results.json +9 -0
pytorch_model.bin +2 -2
tokenizer.json +1 -6
train_results.json +8 -0
trainer_state.json +214 -0
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -31,13 +31,13 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5.0
 ### Training results
@@ -46,6 +46,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 - Transformers 4.34.1
-- Pytorch 2.0.1+cu117
 - Datasets 2.14.5
 - Tokenizers 0.14.0

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 2.0
 ### Training results
 ### Framework versions
 - Transformers 4.34.1
+- Pytorch 2.1.0+cu121
 - Datasets 2.14.5
 - Tokenizers 0.14.0

all_results.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+    "epoch": 5.0,
+    "predict_bleu": 96.1598,
+    "predict_gen_len": 44.3118,
+    "predict_loss": 0.008259225636720657,
+    "predict_runtime": 1335.9792,
+    "predict_samples": 11081,
+    "predict_samples_per_second": 8.294,
+    "predict_steps_per_second": 0.26,
+    "train_loss": 0.020643039299891544,
+    "train_runtime": 4743.0348,
+    "train_samples": 99819,
+    "train_samples_per_second": 105.227,
+    "train_steps_per_second": 3.289
+}

generated_predictions.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

predict_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "predict_bleu": 96.1598,
+    "predict_gen_len": 44.3118,
+    "predict_loss": 0.008259225636720657,
+    "predict_runtime": 1335.9792,
+    "predict_samples": 11081,
+    "predict_samples_per_second": 8.294,
+    "predict_steps_per_second": 0.26
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff8bcfe64967f26a0dea83f1092302bbbc42cc9485554e3c56bf1318ffd2178
-size 561625501

 version https://git-lfs.github.com/spec/v1
+oid sha256:d4bdbf561c3a493a253d9e14d5f17e6ecdcab7afccce0384c4e1294e4afec3ad
+size 561625946

tokenizer.json CHANGED Viewed

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 5.0,
+    "train_loss": 0.020643039299891544,
+    "train_runtime": 4743.0348,
+    "train_samples": 99819,
+    "train_samples_per_second": 105.227,
+    "train_steps_per_second": 3.289
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,214 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00029038461538461537,
+      "loss": 0.0701,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00028076923076923076,
+      "loss": 0.0536,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00027115384615384615,
+      "loss": 0.0466,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00026153846153846154,
+      "loss": 0.0412,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002519230769230769,
+      "loss": 0.0373,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002423076923076923,
+      "loss": 0.0324,
+      "step": 3000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00023269230769230767,
+      "loss": 0.0289,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00022307692307692306,
+      "loss": 0.0276,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00021346153846153845,
+      "loss": 0.0244,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00020384615384615385,
+      "loss": 0.0291,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0001942307692307692,
+      "loss": 0.0221,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001846153846153846,
+      "loss": 0.0216,
+      "step": 6000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.000175,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0001653846153846154,
+      "loss": 0.017,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00015576923076923076,
+      "loss": 0.0165,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.015,
+      "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.00013653846153846152,
+      "loss": 0.0156,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.0001269230769230769,
+      "loss": 0.014,
+      "step": 9000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.0001173076923076923,
+      "loss": 0.0134,
+      "step": 9500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00010769230769230768,
+      "loss": 0.0113,
+      "step": 10000
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 9.807692307692307e-05,
+      "loss": 0.0103,
+      "step": 10500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 8.846153846153845e-05,
+      "loss": 0.0103,
+      "step": 11000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 7.884615384615384e-05,
+      "loss": 0.0098,
+      "step": 11500
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 6.923076923076922e-05,
+      "loss": 0.0099,
+      "step": 12000
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 5.961538461538461e-05,
+      "loss": 0.0084,
+      "step": 12500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.0065,
+      "step": 13000
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 4.038461538461538e-05,
+      "loss": 0.0066,
+      "step": 13500
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 3.076923076923077e-05,
+      "loss": 0.006,
+      "step": 14000
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 2.115384615384615e-05,
+      "loss": 0.0065,
+      "step": 14500
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 1.1538461538461538e-05,
+      "loss": 0.0056,
+      "step": 15000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 1.923076923076923e-06,
+      "loss": 0.006,
+      "step": 15500
+    },
+    {
+      "epoch": 5.0,
+      "step": 15600,
+      "total_flos": 5.943712364448768e+16,
+      "train_loss": 0.020643039299891544,
+      "train_runtime": 4743.0348,
+      "train_samples_per_second": 105.227,
+      "train_steps_per_second": 3.289
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15600,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 5.943712364448768e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35951e9d751768cf8d7a3492e79ed6ee7ea14a547a15ad5ab6ffc24599c1c5fe
-size 4283

 version https://git-lfs.github.com/spec/v1
+oid sha256:cebec4ed436c943bd44e0d9011196ae08617cb26787eb9d7a2ae3d8eafdf162f
+size 4728