End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 499.67,
-    "eval_loss": 5.67578125,
-    "eval_runtime": 0.0865,
+    "epoch": 50.0,
+    "eval_loss": 3.314453125,
+    "eval_runtime": 2.4382,
     "eval_samples": 9,
-    "eval_samples_per_second": 104.106,
-    "eval_steps_per_second": 23.135,
-    "perplexity": 291.71615278815983,
-    "train_loss": 0.8276048583984374,
-    "train_runtime": 639.1734,
+    "eval_samples_per_second": 3.691,
+    "eval_steps_per_second": 0.82,
+    "perplexity": 27.507346790200362,
+    "train_loss": 2.098372395833333,
+    "train_runtime": 956.5249,
     "train_samples": 23,
-    "train_samples_per_second": 17.992,
-    "train_steps_per_second": 0.782
+    "train_samples_per_second": 1.202,
+    "train_steps_per_second": 0.157
 }

config.json

@@ -8,7 +8,7 @@
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
-  "eos_token_id": 198,
+  "eos_token_id": 50256,
   "id2label": {
     "0": "LABEL_0"
   },
@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "float16",
-  "transformers_version": "4.13.0",
-  "use_cache": false,
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
   "vocab_size": 50257
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 499.67,
-    "eval_loss": 5.67578125,
-    "eval_runtime": 0.0865,
+    "epoch": 50.0,
+    "eval_loss": 3.314453125,
+    "eval_runtime": 2.4382,
     "eval_samples": 9,
-    "eval_samples_per_second": 104.106,
-    "eval_steps_per_second": 23.135,
-    "perplexity": 291.71615278815983
+    "eval_samples_per_second": 3.691,
+    "eval_steps_per_second": 0.82,
+    "perplexity": 27.507346790200362
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c7af5912efddf9ae72108390b7309f5d4ad68284e8a323ec5afc556aa87595
-size 170133371
+oid sha256:344184e25d9e8e50e4b826bf02c7dabb381a18803cb8fdb6179f808fbd4ffcac
+size 170133438

runs/Jan27_09-27-06_06c694df2bc7/1643276178.1144845/events.out.tfevents.1643276178.06c694df2bc7.575.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7e1ba97a3a5e2658a57ab94a08db0be875d882bb4da52b90dd3011d56b69ff
+size 4787

runs/Jan27_09-27-06_06c694df2bc7/events.out.tfevents.1643276178.06c694df2bc7.575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7977b6667779ac4f6cdaebedbc59dd92256551fd458a60cdbb835499a2febc1
+size 3672

runs/Jan27_09-43-10_06c694df2bc7/1643276611.652044/events.out.tfevents.1643276611.06c694df2bc7.801.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6718261aedf038a075cb1f0986e635880e8048c1b23be1e78a4405e6cf3c2f
+size 4787

runs/Jan27_09-43-10_06c694df2bc7/events.out.tfevents.1643276611.06c694df2bc7.801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe66840afc59e6cd3241b4f8e807ca40381bcaa0448553f5070b148581e593e5
+size 4026

runs/Jan27_09-43-10_06c694df2bc7/events.out.tfevents.1643277571.06c694df2bc7.801.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa64d4865a15c18233f25d5f6d0e99e941479473a1d00155b532424e4b1c421
+size 311

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{"bos_token": "<|endoftext|>", "eos_token": "198", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "198", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 499.67,
-    "train_loss": 0.8276048583984374,
-    "train_runtime": 639.1734,
+    "epoch": 50.0,
+    "train_loss": 2.098372395833333,
+    "train_runtime": 956.5249,
     "train_samples": 23,
-    "train_samples_per_second": 17.992,
-    "train_steps_per_second": 0.782
+    "train_samples_per_second": 1.202,
+    "train_steps_per_second": 0.157
 }

trainer_state.json

@@ -1,47 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 499.6666666666667,
-  "global_step": 500,
+  "epoch": 50.0,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 199.67,
-      "eval_loss": 4.546875,
-      "eval_runtime": 0.0857,
-      "eval_samples_per_second": 105.046,
-      "eval_steps_per_second": 23.344,
-      "step": 200
-    },
-    {
-      "epoch": 399.67,
-      "eval_loss": 5.43359375,
-      "eval_runtime": 0.0856,
-      "eval_samples_per_second": 105.16,
-      "eval_steps_per_second": 23.369,
-      "step": 400
-    },
-    {
-      "epoch": 499.67,
-      "learning_rate": 5e-05,
-      "loss": 0.8276,
-      "step": 500
-    },
-    {
-      "epoch": 499.67,
-      "step": 500,
-      "total_flos": 3003083546165248.0,
-      "train_loss": 0.8276048583984374,
-      "train_runtime": 639.1734,
-      "train_samples_per_second": 17.992,
-      "train_steps_per_second": 0.782
+      "epoch": 50.0,
+      "step": 150,
+      "total_flos": 300491279958016.0,
+      "train_loss": 2.098372395833333,
+      "train_runtime": 956.5249,
+      "train_samples_per_second": 1.202,
+      "train_steps_per_second": 0.157
     }
   ],
-  "max_steps": 500,
-  "num_train_epochs": 500,
-  "total_flos": 3003083546165248.0,
+  "max_steps": 150,
+  "num_train_epochs": 50,
+  "total_flos": 300491279958016.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20f7e55570ae3c982208f96205c5ae8fcc5abf26d55c695a4a61956d3109dad
-size 3887
+oid sha256:7e43700f0bfe93c297af47c96114b00d27d85b8b7707d998bdab63ea39f976fc
+size 4143