OPT-125m

all_results.json

@@ -0,0 +1 @@
+{"perplexity": 15.926894938231403, "model.decoder.final_layer_norm": 101.738686936684, "model.decoder.layers.0": 4.3256651348254405, "model.decoder.layers.1": 4.275809898141448, "model.decoder.layers.2": 41.31426679226056, "model.decoder.layers.3": 64.36433341500052, "model.decoder.layers.4": 73.64383063984289, "model.decoder.layers.5": 83.42217588424683, "model.decoder.layers.6": 92.80440228829588, "model.decoder.layers.7": 92.80591764709828, "model.decoder.layers.8": 92.6993607033706, "model.decoder.layers.9": 92.56424202900452, "model.decoder.layers.10": 92.11354467191585, "model.decoder.layers.11": 68.70048200991367, "model.decoder.layers.0.fc2": 0.1963057712918744, "model.decoder.layers.1.fc2": 0.13969866820307866, "model.decoder.layers.2.fc2": 0.44056144259850727, "model.decoder.layers.3.fc2": 0.9506042097706043, "model.decoder.layers.4.fc2": 0.3995788167925351, "model.decoder.layers.5.fc2": 0.34522399947472426, "model.decoder.layers.6.fc2": 0.36491712821519484, "model.decoder.layers.7.fc2": 0.3547910836207573, "model.decoder.layers.8.fc2": 0.5253556410162366, "model.decoder.layers.9.fc2": 0.813979407770006, "model.decoder.layers.10.fc2": 0.8213537632066142, "model.decoder.layers.11.fc2": 0.8838782288259724, "model.decoder.layers.0.final_layer_norm": 1.2318393331560897, "model.decoder.layers.1.final_layer_norm": 1.1976495752323204, "model.decoder.layers.2.final_layer_norm": 0.9870215615482562, "model.decoder.layers.3.final_layer_norm": 0.9576551103269881, "model.decoder.layers.4.final_layer_norm": 0.9692467617131424, "model.decoder.layers.5.final_layer_norm": 0.9803548472208216, "model.decoder.layers.6.final_layer_norm": 1.05896514805239, "model.decoder.layers.7.final_layer_norm": 1.1808010678385108, "model.decoder.layers.8.final_layer_norm": 1.780085226995598, "model.decoder.layers.9.final_layer_norm": 1.94102810544352, "model.decoder.layers.10.final_layer_norm": 2.4319016532068765, "model.decoder.layers.11.final_layer_norm": 2.046855243060815, "model.decoder.layers.0.self_attn.out_proj": 1.043669743915167, "model.decoder.layers.1.self_attn.out_proj": 0.4691793241389531, "model.decoder.layers.2.self_attn.out_proj": 0.3312990755113337, "model.decoder.layers.3.self_attn.out_proj": 0.22212465635069614, "model.decoder.layers.4.self_attn.out_proj": 0.24630866935126358, "model.decoder.layers.5.self_attn.out_proj": 0.3148930075876753, "model.decoder.layers.6.self_attn.out_proj": 0.39555091709478357, "model.decoder.layers.7.self_attn.out_proj": 0.5236813833432129, "model.decoder.layers.8.self_attn.out_proj": 1.004827754197572, "model.decoder.layers.9.self_attn.out_proj": 1.571111023503364, "model.decoder.layers.10.self_attn.out_proj": 3.033891056916748, "model.decoder.layers.11.self_attn.out_proj": 64.45151892833982, "model.decoder.layers.0.self_attn_layer_norm": 5.084115235876635, "model.decoder.layers.1.self_attn_layer_norm": 5.141161918253595, "model.decoder.layers.2.self_attn_layer_norm": 10.996598443013994, "model.decoder.layers.3.self_attn_layer_norm": 15.222008785385102, "model.decoder.layers.4.self_attn_layer_norm": 16.28413276001328, "model.decoder.layers.5.self_attn_layer_norm": 14.081257945523342, "model.decoder.layers.6.self_attn_layer_norm": 12.949413010582386, "model.decoder.layers.7.self_attn_layer_norm": 10.108113047252523, "model.decoder.layers.8.self_attn_layer_norm": 10.352879050486129, "model.decoder.layers.9.self_attn_layer_norm": 9.021139857022215, "model.decoder.layers.10.self_attn_layer_norm": 8.513351039277286, "model.decoder.layers.11.self_attn_layer_norm": 9.348919292754855, "max_inf_norm": 101.738686936684, "max_ffn_inf_norm": 0.9506042097706043, "max_layer_inf_norm": 92.80591764709828, "avg_kurtosis": Infinity, "max_kurtosis": Infinity, "max_kurtosis_layers": 17598.41919875485}

checkpoints/checkpoint_125000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3324d9f564bb5ff4c43f585abb654bc113c9cfa58a662ad65a209bd4f3515995
+size 496261008

checkpoints/checkpoint_125000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611c6d787d01efaa084a9b1116b79d48bfd220655786ee8d273f88faa4bc4c85
+size 992641146

checkpoints/checkpoint_125000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943bfb62ea47096a7c942b209c569319742615e25971f7a41046306d04528c12
+size 14540

checkpoints/checkpoint_125000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f99a672d2f6f56225523889be48d691b530390b1a2af964af62ff509b55776
+size 988

checkpoints/checkpoint_125000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5e63f68e0a8a6ddc563e800ced0bbb3bcc153b15e0b0ed636648c1ab13303b
+size 1064

config.json

@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.006,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9134cfd82c99f2df5b14af7f6fd3114dc0959441d471c435f4e362849f4286e0
+size 496305242

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}