Training in progress, step 20000

.gitignore

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

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/1669193348.7292657/events.out.tfevents.1669193348.helen-pytorch-xla-vm-vm.36480.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07382bf39b63c0ab960d00d78f146408b9298e6ae64df2b6cffce3fbf26ae37
+size 5539

logs/1669193545.402253/events.out.tfevents.1669193545.helen-pytorch-xla-vm-vm.37254.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29f2e1a346c2ae1db43290fa4d9ebfee3595424032c556b82d72abae8b7cf90
+size 5546

logs/1669194183.4841528/events.out.tfevents.1669194183.helen-pytorch-xla-vm-vm.38388.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c485b7ecad3816dcfaa86795efee3e60597a1097cd05fb45eb720d78d9336c3
+size 5546

logs/1669195418.7645125/events.out.tfevents.1669195418.helen-pytorch-xla-vm-vm.40518.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35bc0ab696c1411e0d89bb3897f5fed60001a53d0987be0374ed182dfb5c6b6
+size 5546

logs/1669195541.478093/events.out.tfevents.1669195541.helen-pytorch-xla-vm-vm.41308.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4099a90c5f86ac19a823800fac21b092caec170ca68ee879ec2c4aeb17640c72
+size 5546

logs/1669195669.2123573/events.out.tfevents.1669195669.helen-pytorch-xla-vm-vm.42090.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c04008000a774adb0f85cf1405039e57243de639cc4e38688e9ec6d8eed450
+size 5546

logs/1669195797.3350801/events.out.tfevents.1669195797.helen-pytorch-xla-vm-vm.42877.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab4b6ef490d4264ce96c7619e297319d8fef66302cbc0c5ffafae81ee127f39
+size 5546

logs/events.out.tfevents.1669193348.helen-pytorch-xla-vm-vm.36480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715012a7f299b4d2d533341a9287e74353ae92c928bb51e8a392a68ee042b6c3
+size 4085

logs/events.out.tfevents.1669193545.helen-pytorch-xla-vm-vm.37254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30dcd6333f966006ed70279a7168ac4e286709b093832629ac6660ff4cd0eb49
+size 4083

logs/events.out.tfevents.1669194183.helen-pytorch-xla-vm-vm.38388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3796397e51d448f0813e0c5bd682f79990015515a7e0567296f08f71c7a291b1
+size 4085

logs/events.out.tfevents.1669195418.helen-pytorch-xla-vm-vm.40518.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6998db7e2ad03fa382cfd1e1aaaf121e39bd09ffc71a30c2b32e3498408f396
+size 4085

logs/events.out.tfevents.1669195541.helen-pytorch-xla-vm-vm.41308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa5458fa5b7195c7aa689087fae5571f6be29e7aba8d463734e256489157843
+size 4085

logs/events.out.tfevents.1669195669.helen-pytorch-xla-vm-vm.42090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e751a577360b9d5ba2086dded324fbf9a18fabeeed2477951dcf97dab1116702
+size 4085

logs/events.out.tfevents.1669195797.helen-pytorch-xla-vm-vm.42877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950541d6c9e4103b40f33bf35a088895d5ab9400d509a8beccf12fe0352cef3e
+size 35593

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7703f1818f03191a55d3155509a6be7c2fda52e89468175813d9f6d3c2560cc2
+size 1444602141

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "Tristan/olm-tokenizer",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0013a3044db87f1dde2c04d9ba3f5fe8f90b8f0bdbad2fd399ebe799e005e205
+size 3451