Training in progress, step 15

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": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc2413613fa76b2f436810197fbf78355f192c015b9c7b32d43d5f8d93e65d3
+size 497774208

runs/Dec22_01-01-48_421935ec94bc/events.out.tfevents.1734829313.421935ec94bc.2099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a47055cceab64705d7bf1ba8d2992c600004703fa6d1a9ae451d493dfd9ceb7
+size 88

runs/Dec22_01-04-04_421935ec94bc/events.out.tfevents.1734829446.421935ec94bc.4303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77571c005348786cec2049c07351dcce2418ddc78f81a1ea15a731791ca07244
+size 88

runs/Dec22_01-07-52_421935ec94bc/events.out.tfevents.1734829674.421935ec94bc.4868.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c6589d9f6f267f41d23633d87ba00f34c0eb6ffae2a9c2422a1faa3d1fc791
+size 5266

runs/Dec22_01-11-10_421935ec94bc/events.out.tfevents.1734829871.421935ec94bc.4868.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f90680858c4b81dc627f99cd938dcec9b7dcfea419b4b97ae6d4f562d966f76
+size 5266

runs/Dec22_01-13-09_421935ec94bc/events.out.tfevents.1734829991.421935ec94bc.4868.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554075db8d2d1ea3da43bc412147e6f28ed5560c06ec85f575c50c80f0dc1617
+size 5266

runs/Dec22_01-14-02_421935ec94bc/events.out.tfevents.1734830043.421935ec94bc.4868.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e7a450426ec87a244234f573ce57544f67785631547667d2c80e0ba15b9176
+size 5266

runs/Dec22_01-14-17_421935ec94bc/events.out.tfevents.1734830058.421935ec94bc.4868.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba75a20a9d7510139e079817c11b8c1814f0b4542853df67349b0ddb16969e27
+size 5266

runs/Dec22_01-15-18_421935ec94bc/events.out.tfevents.1734830120.421935ec94bc.4868.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0f8500d8382a7fe358fee1a867223f75fdd0d1f34876fbbe9d43ef13b0c8d0
+size 5704

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2f80621e1d7da492d9763bb6a0976ff947bdaeca9b9958993cbdbe4cef08bc
+size 5304