huggingartists

Browse files

Files changed (13) hide show

README.md +4 -4
config.json +4 -2
evaluation.txt +1 -1
flax_model.msgpack +1 -1
optimizer.pt +1 -1
pytorch_model.bin +2 -2
rng_state.pth +1 -1
scheduler.pt +1 -1
special_tokens_map.json +5 -1
tokenizer.json +0 -0
tokenizer_config.json +10 -1
trainer_state.json +663 -7
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/a23400b7447be0fb91c3c4c839c6efe7.442x442x1.jpg&#39;)">
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/rihanna")
 ```
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3g4a2qa9/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Rihanna's lyrics.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3du2fhxz) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3du2fhxz/artifacts) is logged and versioned.
 ## How to use

 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
+			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/f83548d76e427d0a4fdcafdf2f62b647.1000x1000x1.png&#39;)">
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
 dataset = load_dataset("huggingartists/rihanna")
 ```
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3c5muzh8/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Rihanna's lyrics.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b/artifacts) is logged and versioned.
 ## How to use

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "huggingartists/rihanna",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -18,7 +18,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
   "use_cache": true,
   "vocab_size": 50257
 }

 {
+  "_name_or_path": "rihanna",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
     }
   },
   "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt CHANGED Viewed

	@@ -1 +1 @@
1	- {"eval_loss": 2.~~237405776977539~~, "eval_runtime": 8.~~4305~~, "eval_samples_per_second": 22.~~181~~, "eval_steps_per_second": 2.~~847~~, "epoch": 2.0}


1	+ {"eval_loss": 1.752521276473999, "eval_runtime": 4.2607, "eval_samples_per_second": 45.532, "eval_steps_per_second": 5.868, "epoch": 7.0}

flax_model.msgpack CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6be841db360da1a00ad23a76226c5b19e42247bc72575b241a6f446840b95d
 size 497764120

 version https://git-lfs.github.com/spec/v1
+oid sha256:b41a408893cb0ef0914b7c69fe63100edbcfd9827c5b8d83eff838506cbe6e73
 size 497764120

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a71909dbe3a3827eb2d96903ec0cd4f6475fbd143d3adcebee21e68eb480324
 size 995604017

 version https://git-lfs.github.com/spec/v1
+oid sha256:f3006a0c685ddebea1136f939b292ab67e24da1f0edd23faadf7a85985f46b34
 size 995604017

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c96ee233c3281090b842a4a11ff662f1751f775bd8bd50db7037dbc4bdf1d8
-size 510403817

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e5b73d16cb2c0edc96673fe23be7a5214f61a1c9d00aaf44aacd9f96d1ea618
+size 510396521

rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ebd8f09a6c1db84aa3aaeb1ea1345bcb3c2ae6c124b74ff19c3f608acd9e3c
 size 14503

 version https://git-lfs.github.com/spec/v1
+oid sha256:26e82f1222285d031b8e21d934b74558389b98a783bb42db1010d0f55af3bc16
 size 14503

scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2179c852b9a3c2fc23aeed095aeb8cf7d63d1da7d9c6eca4435ee27bc43703
 size 623

 version https://git-lfs.github.com/spec/v1
+oid sha256:cfc3e0c06b55e5f6cc34f1c4c7ab6e7fc251827bfa5f1b3ed68bfe476fa6cc0c
 size 623

special_tokens_map.json CHANGED Viewed

	@@ -1 +1,5 @@
1	- {~~"bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "unk_token": "<\|endoftext\|>"}~~

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json CHANGED Viewed

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

tokenizer_config.json CHANGED Viewed

	@@ -1 +1,10 @@
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": "huggingartists/rihanna", "tokenizer_class": "GPT2Tokenizer"}

+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingartists/rihanna",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.237405776977539,
-  "best_model_checkpoint": "output/rihanna/checkpoint-262",
-  "epoch": 2.0,
-  "global_step": 262,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -334,11 +334,667 @@
       "eval_samples_per_second": 22.521,
       "eval_steps_per_second": 2.89,
       "step": 262
     }
   ],
-  "max_steps": 262,
-  "num_train_epochs": 2,
-  "total_flos": 272919527424000.0,
   "trial_name": null,
   "trial_params": null
 }

 {
+  "best_metric": 1.752521276473999,
+  "best_model_checkpoint": "output/rihanna/checkpoint-780",
+  "epoch": 6.0,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 22.521,
       "eval_steps_per_second": 2.89,
       "step": 262
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0001366998287631265,
+      "loss": 2.0176,
+      "step": 265
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 2.0043,
+      "step": 270
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00013274211424821946,
+      "loss": 1.743,
+      "step": 275
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00012934228335981023,
+      "loss": 2.0598,
+      "step": 280
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00012505669320030482,
+      "loss": 1.9087,
+      "step": 285
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011994783732453754,
+      "loss": 1.6869,
+      "step": 290
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00011409021435531858,
+      "loss": 1.726,
+      "step": 295
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00010756924162575734,
+      "loss": 1.966,
+      "step": 300
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.00010048000960220251,
+      "loss": 2.0242,
+      "step": 305
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.292589525111797e-05,
+      "loss": 1.804,
+      "step": 310
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.501705457012652e-05,
+      "loss": 1.7316,
+      "step": 315
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.686881626551514e-05,
+      "loss": 2.1338,
+      "step": 320
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 2.067,
+      "step": 325
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.03311837344849e-05,
+      "loss": 1.993,
+      "step": 330
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.218294542987351e-05,
+      "loss": 1.8933,
+      "step": 335
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.427410474888207e-05,
+      "loss": 1.7142,
+      "step": 340
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.6719990397797524e-05,
+      "loss": 1.9927,
+      "step": 345
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.9630758374242683e-05,
+      "loss": 1.8104,
+      "step": 350
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.310978564468145e-05,
+      "loss": 1.8292,
+      "step": 355
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.7252162675462497e-05,
+      "loss": 2.0388,
+      "step": 360
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.214330679969522e-05,
+      "loss": 1.8121,
+      "step": 365
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 7.8577166401898e-06,
+      "loss": 1.8632,
+      "step": 370
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.457885751780558e-06,
+      "loss": 2.0386,
+      "step": 375
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.9933913245728472e-06,
+      "loss": 1.7312,
+      "step": 380
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.001712368734975e-07,
+      "loss": 2.0118,
+      "step": 385
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 1.7726,
+      "step": 390
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.8738644123077393,
+      "eval_runtime": 4.2323,
+      "eval_samples_per_second": 45.838,
+      "eval_steps_per_second": 5.907,
+      "step": 390
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 5.001712368734899e-07,
+      "loss": 1.519,
+      "step": 395
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.9933913245728396e-06,
+      "loss": 1.6714,
+      "step": 400
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.457885751780535e-06,
+      "loss": 1.6067,
+      "step": 405
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 7.857716640189778e-06,
+      "loss": 1.4835,
+      "step": 410
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.2143306799695189e-05,
+      "loss": 1.9692,
+      "step": 415
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.725216267546246e-05,
+      "loss": 1.5852,
+      "step": 420
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 2.310978564468141e-05,
+      "loss": 1.766,
+      "step": 425
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 2.9630758374242642e-05,
+      "loss": 1.7481,
+      "step": 430
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.671999039779748e-05,
+      "loss": 1.9411,
+      "step": 435
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 4.427410474888202e-05,
+      "loss": 1.5399,
+      "step": 440
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 5.218294542987346e-05,
+      "loss": 1.9887,
+      "step": 445
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 6.033118373448485e-05,
+      "loss": 1.6023,
+      "step": 450
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 6.859999999999997e-05,
+      "loss": 1.665,
+      "step": 455
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 7.68688162655151e-05,
+      "loss": 1.6708,
+      "step": 460
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 8.501705457012648e-05,
+      "loss": 1.7596,
+      "step": 465
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 9.292589525111793e-05,
+      "loss": 2.0391,
+      "step": 470
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.00010048000960220248,
+      "loss": 1.6346,
+      "step": 475
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.00010756924162575731,
+      "loss": 1.5059,
+      "step": 480
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.00011409021435531856,
+      "loss": 1.7107,
+      "step": 485
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.0001199478373245375,
+      "loss": 1.6263,
+      "step": 490
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0001250566932003048,
+      "loss": 1.7098,
+      "step": 495
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.00012934228335981018,
+      "loss": 1.5807,
+      "step": 500
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.00013274211424821943,
+      "loss": 1.9171,
+      "step": 505
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 1.6038,
+      "step": 510
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.00013669982876312649,
+      "loss": 1.548,
+      "step": 515
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.8101,
+      "step": 520
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8380614519119263,
+      "eval_runtime": 4.2339,
+      "eval_samples_per_second": 45.821,
+      "eval_steps_per_second": 5.905,
+      "step": 520
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.0001366998287631265,
+      "loss": 1.7809,
+      "step": 525
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.0001352066086754272,
+      "loss": 1.71,
+      "step": 530
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 0.0001327421142482195,
+      "loss": 1.3283,
+      "step": 535
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00012934228335981015,
+      "loss": 1.4905,
+      "step": 540
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 0.00012505669320030482,
+      "loss": 1.2511,
+      "step": 545
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00011994783732453755,
+      "loss": 1.6209,
+      "step": 550
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.00011409021435531858,
+      "loss": 1.6988,
+      "step": 555
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.00010756924162575738,
+      "loss": 1.2228,
+      "step": 560
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.00010048000960220263,
+      "loss": 1.6827,
+      "step": 565
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 9.292589525111788e-05,
+      "loss": 1.6977,
+      "step": 570
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 8.501705457012643e-05,
+      "loss": 1.4269,
+      "step": 575
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 7.686881626551516e-05,
+      "loss": 1.6831,
+      "step": 580
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 6.860000000000003e-05,
+      "loss": 1.0505,
+      "step": 585
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 6.033118373448492e-05,
+      "loss": 1.4459,
+      "step": 590
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 5.218294542987365e-05,
+      "loss": 1.4365,
+      "step": 595
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 4.42741047488822e-05,
+      "loss": 1.6545,
+      "step": 600
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 3.671999039779743e-05,
+      "loss": 1.6826,
+      "step": 605
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 2.9630758374242696e-05,
+      "loss": 1.6816,
+      "step": 610
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 2.3109785644681465e-05,
+      "loss": 1.43,
+      "step": 615
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 1.7252162675462504e-05,
+      "loss": 1.1238,
+      "step": 620
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 1.2143306799695228e-05,
+      "loss": 1.1441,
+      "step": 625
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 7.857716640189861e-06,
+      "loss": 1.5854,
+      "step": 630
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 4.4578857517805195e-06,
+      "loss": 1.2825,
+      "step": 635
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 1.9933913245728244e-06,
+      "loss": 1.3848,
+      "step": 640
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 5.001712368734975e-07,
+      "loss": 1.4917,
+      "step": 645
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.0341,
+      "step": 650
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.7726789712905884,
+      "eval_runtime": 4.2405,
+      "eval_samples_per_second": 45.75,
+      "eval_steps_per_second": 5.896,
+      "step": 650
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 5.001712368734899e-07,
+      "loss": 1.3946,
+      "step": 655
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 1.9933913245728015e-06,
+      "loss": 1.1575,
+      "step": 660
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 4.457885751780535e-06,
+      "loss": 1.2407,
+      "step": 665
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 7.857716640189824e-06,
+      "loss": 1.299,
+      "step": 670
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 1.2143306799695106e-05,
+      "loss": 1.4759,
+      "step": 675
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 1.725216267546245e-05,
+      "loss": 1.2347,
+      "step": 680
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 2.3109785644681495e-05,
+      "loss": 1.4233,
+      "step": 685
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 2.963075837424263e-05,
+      "loss": 1.4062,
+      "step": 690
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 3.6719990397797463e-05,
+      "loss": 1.2485,
+      "step": 695
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 4.4274104748882125e-05,
+      "loss": 1.4536,
+      "step": 700
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 5.2182945429873444e-05,
+      "loss": 1.2116,
+      "step": 705
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 6.033118373448483e-05,
+      "loss": 1.1743,
+      "step": 710
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 6.859999999999984e-05,
+      "loss": 1.2798,
+      "step": 715
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 7.686881626551508e-05,
+      "loss": 1.1637,
+      "step": 720
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 8.501705457012647e-05,
+      "loss": 1.4529,
+      "step": 725
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 9.292589525111778e-05,
+      "loss": 1.1575,
+      "step": 730
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 0.00010048000960220244,
+      "loss": 1.4035,
+      "step": 735
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 0.0001075692416257573,
+      "loss": 1.2311,
+      "step": 740
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 0.00011409021435531843,
+      "loss": 1.3514,
+      "step": 745
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.00011994783732453749,
+      "loss": 1.0519,
+      "step": 750
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 0.00012505669320030485,
+      "loss": 1.39,
+      "step": 755
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00012934228335981013,
+      "loss": 1.2267,
+      "step": 760
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 0.00013274211424821943,
+      "loss": 1.431,
+      "step": 765
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 1.5557,
+      "step": 770
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00013669982876312649,
+      "loss": 1.2241,
+      "step": 775
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.1435,
+      "step": 780
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.752521276473999,
+      "eval_runtime": 4.2466,
+      "eval_samples_per_second": 45.684,
+      "eval_steps_per_second": 5.887,
+      "step": 780
     }
   ],
+  "max_steps": 910,
+  "num_train_epochs": 7,
+  "total_flos": 811181113344000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c710dd5a8d4b67cb50ad0843ddfa8eb650173d3491cfb493f1dda199d69582
-size 2671

 version https://git-lfs.github.com/spec/v1
+oid sha256:1bf17e5c0319daac4eb8decc923d42c574d61cb10c1cc3267a038b27c7c37d44
+size 3311