Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "asi/gpt-fr-cased-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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,
+  "pad_token_id": 1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93f9139b2ed3f61b0bfb5bed7cdfbdd0e5b5227f6ee460bbc7131dc3a307068
+size 509607017

runs/Dec23_23-00-34_706e3f2c6ddc/1671836449.6304517/events.out.tfevents.1671836449.706e3f2c6ddc.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c1e0ebd3d25dded28dfee3e3701628270e0e3df4325f8c2fc2a629cf7da7bb
+size 5368

runs/Dec23_23-00-34_706e3f2c6ddc/events.out.tfevents.1671836449.706e3f2c6ddc.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c73c872794dd9c6739d04556a7c36fd0352ca996f21003616b541148c983e33
+size 4188

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366cd8f51d5adbc4ba260a77e7b1663f069b6b1b90ad1c2ef7667c5ac8820f67
+size 3311