Training in progress, step 5000

.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": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": null,
+  "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": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 100000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47054c7da6236f097feab4ef7f39087dbed74a0742bfbe9af672d1b3a5e472c
+size 663208509

runs/Apr22_13-24-39_882c126a211a/1682169927.6039846/events.out.tfevents.1682169927.882c126a211a.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bee1530d57767307ad34c2b2787d07e411008ef8c037d360eb5f4a9dd3e5beb
+size 5764

runs/Apr22_13-24-39_882c126a211a/events.out.tfevents.1682169927.882c126a211a.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aee02fd47c4267b18becad5fe2febb8018cd46122f3513092764068de41dd58
+size 4211

runs/Apr22_13-31-32_882c126a211a/1682170297.8022246/events.out.tfevents.1682170297.882c126a211a.23.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0642180f37595402d5059d31ba3256db9c8c9726fdc4f0d58d609d60d94108a
+size 5764

runs/Apr22_13-31-32_882c126a211a/events.out.tfevents.1682170297.882c126a211a.23.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a255993a46b4bff2aaa634cdd5a4eac4687e7d86437d0f7a0cfe829e7df9d50d
+size 4151

runs/Apr22_13-33-45_882c126a211a/1682170428.9409578/events.out.tfevents.1682170428.882c126a211a.23.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a25a7608d3dae44ee7c4a36e666fcfdb85c8fa5019bf3d81ea80d41026f5a529
+size 5764

runs/Apr22_13-33-45_882c126a211a/events.out.tfevents.1682170428.882c126a211a.23.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ccd572c6ca06ae6ddb20b058be9168a906c644cf583693ad10258dd2966e82
+size 4151

runs/Apr22_13-34-04_882c126a211a/1682170448.139144/events.out.tfevents.1682170448.882c126a211a.23.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc6f823749b85b6b2f3fd2622e37f2eb22c5d5aeb5a3bcf4d9101e7a4a2e29f
+size 5764

runs/Apr22_13-34-04_882c126a211a/events.out.tfevents.1682170448.882c126a211a.23.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d096f192a6a252d2f6dd08050e9d24b94c2b4c608b7114646d77959d35b58f8e
+size 4577

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "[PAD]"
+}

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--dagim--amharic_tokenizer/snapshots/d4ff599bced963dc0b58ef4754ffb1e3c0f46da2/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef4dc6cfd2ee363079f2669d72485ad8e65572bc5d32867bbc8c49bc0febc8c
+size 3579