Training in progress, step 1000

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": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gpt2-small-mcpc.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a800f96e5ad0b1c3601d4a903d44a06202424593e1fc04848743945f77542b3a
+size 462408894

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099a01b04b444e41a63e73f3ed650e203ddd34a5074c84009f09af02d1e62351
+size 497774208

runs/Mar13_17-14-08_pasteur-hgx-1/events.out.tfevents.1710375249.pasteur-hgx-1.485158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7e18e667d7e08405f002606a9983868a08057101d027803bda1e644be50305
+size 371201

runs/Mar13_17-14-08_pasteur-hgx-1/events.out.tfevents.1710375699.pasteur-hgx-1.485158.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f57d3e5733f0e6b91d90d1b322e6556781c312a1d4fee3f3ade98879737ef0e
+size 359

runs/Mar13_17-35-18_pasteur-hgx-1/events.out.tfevents.1710376519.pasteur-hgx-1.538033.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6783833fa08ea4a7d5241e780748dc8f0aee7cd34eb354fdf6ce8d45731097a9
+size 168989

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8826445a830d2ec0f001505b2753e18a2f5b600bcadeb235e02c207d17f780b7
+size 4347