Training in progress, epoch 0

.gitignore

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "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,
+  "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/1672680026.553644/events.out.tfevents.1672680026.tristan-olm-training-a100-80.97506.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d55cada293cf7937c658b03319d262b1fd1eb2af8bf4bd340395b0520397531
+size 5500

logs/1672680410.3099709/events.out.tfevents.1672680410.tristan-olm-training-a100-80.101195.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85710cd20c6303dc637ccd0e516aa8761ac82884da22a39245f18521e8701750
+size 5500

logs/1672680510.7320256/events.out.tfevents.1672680510.tristan-olm-training-a100-80.104556.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cb00f5120cc48672175bc3e42486f40d63b3f2ff2c862efc69674d1185844f
+size 5500

logs/1672680710.2332163/events.out.tfevents.1672680710.tristan-olm-training-a100-80.107943.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337045cd794d084162abe53f2e58094502ca24493691feaa08602ec919a7c47c
+size 5495

logs/1672681285.8309555/events.out.tfevents.1672681285.tristan-olm-training-a100-80.111576.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de7177520ca325b4744bce7bc6eb78f769749bc1c08314286f06abaf73fabb6
+size 5495

logs/1672681495.1712687/events.out.tfevents.1672681495.tristan-olm-training-a100-80.115679.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa3057c09d085f8c84bbf006a6ea84c78f837e3387666c576bb2f5e25970919
+size 5495

logs/1672681775.8689537/events.out.tfevents.1672681775.tristan-olm-training-a100-80.119314.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86129e43b3d84334b2892400c9cab0525c6d576de0a463b6214ee96f9692c928
+size 5495

logs/1672682182.0067658/events.out.tfevents.1672682182.tristan-olm-training-a100-80.123038.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb5479d16803853694f36094e4a3e6915852d16e6403834e481f52225b80d40
+size 5483

logs/1672705969.2600806/events.out.tfevents.1672705969.tristan-olm-training-a100-80.138319.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7044c9e849377b1f8035578063fd93fa61054e87e5d459587d8356964bb7011
+size 5483

logs/events.out.tfevents.1672680026.tristan-olm-training-a100-80.97506.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4a9ae3520d3eb6c49d8e36ff71e24f171b4e740d9305f001dc1302f799399b
+size 4133

logs/events.out.tfevents.1672680410.tristan-olm-training-a100-80.101195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8eae39626cef36bf5317d4b114d72e6ce5d8c6bfa020f419ede147c6fab3606
+size 3980

logs/events.out.tfevents.1672680510.tristan-olm-training-a100-80.104556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7f17024d92fdaf0594b449450071258bd1a674f3211cdbcb53b3bcc625f31d
+size 3980

logs/events.out.tfevents.1672680710.tristan-olm-training-a100-80.107943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9ce39d22ac949f9815fc93dd0a30d7b3b708e7cad2f5cdc629498c5a7b79c0
+size 4128

logs/events.out.tfevents.1672681285.tristan-olm-training-a100-80.111576.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81d6a5b9483b8a84cb8d49b66d019389dd70609cb94a0c0effa2e8c156ef87f
+size 3974

logs/events.out.tfevents.1672681495.tristan-olm-training-a100-80.115679.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f12719bff2c5cbc76ff8445d8f99867d2bcf8e16af08e20029d3a73f1eeef6a
+size 3974

logs/events.out.tfevents.1672681775.tristan-olm-training-a100-80.119314.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5e660e61ca28c40e55515e892f81a60e57ecd378cc4dd27def2bf91e4572fa
+size 3974

logs/events.out.tfevents.1672682181.tristan-olm-training-a100-80.123038.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e328b81155b5cd8429bf8b81ba9f931e2e58080fd765bd5f38e3f00e154b6b
+size 19814

logs/events.out.tfevents.1672705969.tristan-olm-training-a100-80.138319.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c4e23503db43e1ac594bc100af0a6598bb9e319a493f940fbf7c600258168a
+size 47148

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c0e28bb45961c113c876b056dbbde32f8f4e9eb4c514c4f92ed324a3a32697
+size 510422589

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 sha256:01df519a89a223188624b16e2f3b882b77a5f58fe4d896d0f81d46e593acf45b
+size 3387