Training in progress, step 100

config.json

@@ -0,0 +1,41 @@
+{
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "pad_token_id": 50256,
+  "predict_special_tokens": true,
+  "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": "4.50.2",
+  "use_cache": true,
+  "vocab_size": 50259
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfb342a592cea1ad1552f869bce33a9afbbee287b35de6ed70b3946d4f271f3
+size 1419331072

runs/Apr02_15-29-35_05b589eb3d6d/events.out.tfevents.1743607779.05b589eb3d6d.572.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac48065bd92e26fa153df9cd20969634ec650dc71a3a0b5f364a1d8230b295d
+size 5334

runs/Apr02_15-29-35_05b589eb3d6d/events.out.tfevents.1743607819.05b589eb3d6d.572.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4693ec268ef36e74398641fdda23fffc6ffc91312c84fa3ef65844c55b05b1a2
+size 5334

runs/Apr02_15-29-35_05b589eb3d6d/events.out.tfevents.1743607868.05b589eb3d6d.572.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085802bda1f7d7917ba828b0604f9f611f1d62b351f831e24c96db14b0134773
+size 5334

runs/Apr02_15-29-35_05b589eb3d6d/events.out.tfevents.1743607960.05b589eb3d6d.572.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1205ff6fac9ecea93e373d42e93184a5674942af33ded39cee83105824bec117
+size 5334

runs/Apr02_15-33-13_05b589eb3d6d/events.out.tfevents.1743607998.05b589eb3d6d.572.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6595bbd51f8170bbd6436415be75ba9efa5b12af2390321d7e444add435f2acd
+size 5359

runs/Apr02_15-33-13_05b589eb3d6d/events.out.tfevents.1743608121.05b589eb3d6d.572.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed96b31d465498ed90634e453cea7cfc832cfc3b6bdf005d03edeb059fb328c
+size 5359

runs/Apr02_15-35-54_05b589eb3d6d/events.out.tfevents.1743608157.05b589eb3d6d.572.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d413a30e9354cfb0739dca91cd74a05930c06b45bcf6c10d74453be41fe5975c
+size 5833

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27ce87a7bee2d97d4ce5325d8578caa9eb265d82c9f01c31522a07ef4ec3914
+size 5304