Training in progress, step 1000

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "ai-forever/rugpt3large_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d0d630acc3cffdedb54c675ffa764434238ec93f2ba7387f739916c33babdb
+size 3041230624

runs/Dec29_10-30-29_f584ed272cfa/events.out.tfevents.1703845833.f584ed272cfa.579.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcec1d78f69606709ad36eecdfcc0d11032bcaf0e0fba366f5b059375b4b8288
+size 4184

runs/Dec29_10-32-35_f584ed272cfa/events.out.tfevents.1703845957.f584ed272cfa.1753.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd383ea10b57894fc30e655274eaa5f9ef6a45cf430b874271682b75da421ee
+size 4184

runs/Dec29_10-33-48_f584ed272cfa/events.out.tfevents.1703846032.f584ed272cfa.1753.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9304b5854d15f035ad818d974f0f2f594765279289e46cc89a534b103527df79
+size 4184

runs/Dec29_10-35-08_f584ed272cfa/events.out.tfevents.1703846113.f584ed272cfa.2452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f93185080f3b615ec70ba3633bac1ff46969086d7637cb73e667780ddd2698
+size 4184

runs/Dec29_10-36-37_f584ed272cfa/events.out.tfevents.1703846199.f584ed272cfa.2912.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddccc8a921273c3178daa5a3b5cc2e1eb52b22f9ef0f2c79f70d22cdd908a3f1
+size 21522

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70889b2339127f882cd1cd0d3321270d966f494f47f2dd424221f15b28be705
+size 4600