Delete checkpoint-1000

checkpoint-1000/config.json

@@ -1,28 +0,0 @@
-{
-  "_name_or_path": "google/gemma-2b",
-  "architectures": [
-    "GemmaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 16384,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 1,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
-  "vocab_size": 256000
-}

checkpoint-1000/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.39.0.dev0"
-}

checkpoint-1000/model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0368dc4194ee2fdbe49909e4846ccc81d0b9fb3d1a1fd9c9d3b26a72c7895653
-size 4911635192

checkpoint-1000/model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f92fd384fe15130d9e13c2dc3394517b4fd642d7af96d5e734699919ff39a365
-size 4978830584

checkpoint-1000/model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:585b62412105f82990495f02d7c75c28b5e3c5777ce25a5021ffb17ee4c151e5
-size 134242760

checkpoint-1000/model.safetensors.index.json

@@ -1,171 +0,0 @@
-{
-  "metadata": {
-    "total_size": 10024689664
-  },
-  "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
-  }
-}

checkpoint-1000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7015da0998d2376a75ff258403df7cc2e7ccd73d5263d78ab3e8265f255037cc
-size 20049522541

checkpoint-1000/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1eafe3d5e0585dde8c5033613de99a5d4f23df4284a488f4007b3944580c0b97
-size 17655

checkpoint-1000/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7e34eb456d2d003a2839f2daa9425e99bdd79ed7e24a1de9fc7d5738476bfb4b
-size 17655

checkpoint-1000/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b374af4a2765d8771cee7a72921d3c2e438b9bee34f0b2d098ce6071afeb65e4
-size 17655

checkpoint-1000/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5df75d8477fcc69c7abb03025313915ebfe3ac18c54a7c57aaa455c0099e13e5
-size 17655

checkpoint-1000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20cd9ebcbc893aaeed7a3e32a2a0eeb344f999c91a3ede9cd26c28f6dd8957bb
-size 627

checkpoint-1000/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "bos_token": {
-    "content": "<bos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<eos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint-1000/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
-size 4241003

checkpoint-1000/tokenizer_config.json

@@ -1,51 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<eos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<bos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<bos>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
-  "legacy": null,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "split_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

checkpoint-1000/trainer_state.json

@@ -1,721 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.6310143555765894,
-  "eval_steps": 500,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.01,
-      "grad_norm": 3.7190074920654297,
-      "learning_rate": 4.9995083170283816e-05,
-      "loss": 2.9245,
-      "step": 10
-    },
-    {
-      "epoch": 0.01,
-      "grad_norm": 3.431870222091675,
-      "learning_rate": 4.998033461515242e-05,
-      "loss": 2.0053,
-      "step": 20
-    },
-    {
-      "epoch": 0.02,
-      "grad_norm": 2.3315682411193848,
-      "learning_rate": 4.9955760135896534e-05,
-      "loss": 1.888,
-      "step": 30
-    },
-    {
-      "epoch": 0.03,
-      "grad_norm": 3.2937276363372803,
-      "learning_rate": 4.992136939879856e-05,
-      "loss": 1.8447,
-      "step": 40
-    },
-    {
-      "epoch": 0.03,
-      "grad_norm": 2.7375714778900146,
-      "learning_rate": 4.9877175931330346e-05,
-      "loss": 1.8212,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "grad_norm": 2.15061092376709,
-      "learning_rate": 4.982319711683221e-05,
-      "loss": 1.793,
-      "step": 60
-    },
-    {
-      "epoch": 0.04,
-      "grad_norm": 2.0427424907684326,
-      "learning_rate": 4.975945418767529e-05,
-      "loss": 1.756,
-      "step": 70
-    },
-    {
-      "epoch": 0.05,
-      "grad_norm": 2.107785224914551,
-      "learning_rate": 4.968597221690986e-05,
-      "loss": 1.7285,
-      "step": 80
-    },
-    {
-      "epoch": 0.06,
-      "grad_norm": 2.100552558898926,
-      "learning_rate": 4.96027801084029e-05,
-      "loss": 1.7297,
-      "step": 90
-    },
-    {
-      "epoch": 0.06,
-      "grad_norm": 2.2227377891540527,
-      "learning_rate": 4.950991058546893e-05,
-      "loss": 1.7602,
-      "step": 100
-    },
-    {
-      "epoch": 0.07,
-      "grad_norm": 1.535144567489624,
-      "learning_rate": 4.940740017799833e-05,
-      "loss": 1.7433,
-      "step": 110
-    },
-    {
-      "epoch": 0.08,
-      "grad_norm": 1.6522979736328125,
-      "learning_rate": 4.929528920808854e-05,
-      "loss": 1.7363,
-      "step": 120
-    },
-    {
-      "epoch": 0.08,
-      "grad_norm": 2.8091869354248047,
-      "learning_rate": 4.917362177418342e-05,
-      "loss": 1.6872,
-      "step": 130
-    },
-    {
-      "epoch": 0.09,
-      "grad_norm": 2.1017510890960693,
-      "learning_rate": 4.904244573372733e-05,
-      "loss": 1.7084,
-      "step": 140
-    },
-    {
-      "epoch": 0.09,
-      "grad_norm": 1.6424258947372437,
-      "learning_rate": 4.8901812684340564e-05,
-      "loss": 1.6997,
-      "step": 150
-    },
-    {
-      "epoch": 0.1,
-      "grad_norm": 1.4547488689422607,
-      "learning_rate": 4.8751777943523634e-05,
-      "loss": 1.6747,
-      "step": 160
-    },
-    {
-      "epoch": 0.11,
-      "grad_norm": 1.6251146793365479,
-      "learning_rate": 4.8592400526898314e-05,
-      "loss": 1.6836,
-      "step": 170
-    },
-    {
-      "epoch": 0.11,
-      "grad_norm": 2.098386526107788,
-      "learning_rate": 4.842374312499405e-05,
-      "loss": 1.6552,
-      "step": 180
-    },
-    {
-      "epoch": 0.12,
-      "grad_norm": 2.2387640476226807,
-      "learning_rate": 4.824587207858888e-05,
-      "loss": 1.6489,
-      "step": 190
-    },
-    {
-      "epoch": 0.13,
-      "grad_norm": 1.7299611568450928,
-      "learning_rate": 4.805885735261454e-05,
-      "loss": 1.6576,
-      "step": 200
-    },
-    {
-      "epoch": 0.13,
-      "grad_norm": 1.5701665878295898,
-      "learning_rate": 4.786277250863599e-05,
-      "loss": 1.6533,
-      "step": 210
-    },
-    {
-      "epoch": 0.14,
-      "grad_norm": 2.417296886444092,
-      "learning_rate": 4.765769467591625e-05,
-      "loss": 1.6356,
-      "step": 220
-    },
-    {
-      "epoch": 0.15,
-      "grad_norm": 1.2636029720306396,
-      "learning_rate": 4.744370452107789e-05,
-      "loss": 1.6389,
-      "step": 230
-    },
-    {
-      "epoch": 0.15,
-      "grad_norm": 1.576324224472046,
-      "learning_rate": 4.722088621637309e-05,
-      "loss": 1.6546,
-      "step": 240
-    },
-    {
-      "epoch": 0.16,
-      "grad_norm": 1.9720542430877686,
-      "learning_rate": 4.698932740657479e-05,
-      "loss": 1.6354,
-      "step": 250
-    },
-    {
-      "epoch": 0.16,
-      "grad_norm": 1.5250279903411865,
-      "learning_rate": 4.6749119174501975e-05,
-      "loss": 1.6342,
-      "step": 260
-    },
-    {
-      "epoch": 0.17,
-      "grad_norm": 2.4737966060638428,
-      "learning_rate": 4.6500356005192514e-05,
-      "loss": 1.6407,
-      "step": 270
-    },
-    {
-      "epoch": 0.18,
-      "grad_norm": 1.2792372703552246,
-      "learning_rate": 4.6243135748737864e-05,
-      "loss": 1.6339,
-      "step": 280
-    },
-    {
-      "epoch": 0.18,
-      "grad_norm": 1.5593037605285645,
-      "learning_rate": 4.597755958179406e-05,
-      "loss": 1.6095,
-      "step": 290
-    },
-    {
-      "epoch": 0.19,
-      "grad_norm": 1.3141404390335083,
-      "learning_rate": 4.570373196778427e-05,
-      "loss": 1.6036,
-      "step": 300
-    },
-    {
-      "epoch": 0.2,
-      "grad_norm": 1.2617065906524658,
-      "learning_rate": 4.5421760615808474e-05,
-      "loss": 1.6244,
-      "step": 310
-    },
-    {
-      "epoch": 0.2,
-      "grad_norm": 1.64117431640625,
-      "learning_rate": 4.513175643827647e-05,
-      "loss": 1.6449,
-      "step": 320
-    },
-    {
-      "epoch": 0.21,
-      "grad_norm": 1.7132749557495117,
-      "learning_rate": 4.4833833507280884e-05,
-      "loss": 1.5948,
-      "step": 330
-    },
-    {
-      "epoch": 0.21,
-      "grad_norm": 2.1323654651641846,
-      "learning_rate": 4.4528109009727336e-05,
-      "loss": 1.627,
-      "step": 340
-    },
-    {
-      "epoch": 0.22,
-      "grad_norm": 2.253115653991699,
-      "learning_rate": 4.42147032012394e-05,
-      "loss": 1.6151,
-      "step": 350
-    },
-    {
-      "epoch": 0.23,
-      "grad_norm": 1.6143097877502441,
-      "learning_rate": 4.389373935885646e-05,
-      "loss": 1.5838,
-      "step": 360
-    },
-    {
-      "epoch": 0.23,
-      "grad_norm": 1.3353707790374756,
-      "learning_rate": 4.356534373254316e-05,
-      "loss": 1.5935,
-      "step": 370
-    },
-    {
-      "epoch": 0.24,
-      "grad_norm": 1.283742904663086,
-      "learning_rate": 4.322964549552943e-05,
-      "loss": 1.6015,
-      "step": 380
-    },
-    {
-      "epoch": 0.25,
-      "grad_norm": 1.437249779701233,
-      "learning_rate": 4.288677669350066e-05,
-      "loss": 1.577,
-      "step": 390
-    },
-    {
-      "epoch": 0.25,
-      "grad_norm": 1.5190638303756714,
-      "learning_rate": 4.2536872192658036e-05,
-      "loss": 1.5843,
-      "step": 400
-    },
-    {
-      "epoch": 0.26,
-      "grad_norm": 2.1320886611938477,
-      "learning_rate": 4.218006962666934e-05,
-      "loss": 1.6145,
-      "step": 410
-    },
-    {
-      "epoch": 0.27,
-      "grad_norm": 1.0696591138839722,
-      "learning_rate": 4.181650934253132e-05,
-      "loss": 1.5601,
-      "step": 420
-    },
-    {
-      "epoch": 0.27,
-      "grad_norm": 1.3149545192718506,
-      "learning_rate": 4.144633434536467e-05,
-      "loss": 1.5664,
-      "step": 430
-    },
-    {
-      "epoch": 0.28,
-      "grad_norm": 1.3661577701568604,
-      "learning_rate": 4.1069690242163484e-05,
-      "loss": 1.6002,
-      "step": 440
-    },
-    {
-      "epoch": 0.28,
-      "grad_norm": 1.6984481811523438,
-      "learning_rate": 4.06867251845213e-05,
-      "loss": 1.576,
-      "step": 450
-    },
-    {
-      "epoch": 0.29,
-      "grad_norm": 1.2728784084320068,
-      "learning_rate": 4.0297589810356165e-05,
-      "loss": 1.5448,
-      "step": 460
-    },
-    {
-      "epoch": 0.3,
-      "grad_norm": 1.4147616624832153,
-      "learning_rate": 3.9902437184657784e-05,
-      "loss": 1.5595,
-      "step": 470
-    },
-    {
-      "epoch": 0.3,
-      "grad_norm": 1.2289011478424072,
-      "learning_rate": 3.9501422739279956e-05,
-      "loss": 1.5628,
-      "step": 480
-    },
-    {
-      "epoch": 0.31,
-      "grad_norm": 1.5690233707427979,
-      "learning_rate": 3.909470421180201e-05,
-      "loss": 1.5731,
-      "step": 490
-    },
-    {
-      "epoch": 0.32,
-      "grad_norm": 1.4935098886489868,
-      "learning_rate": 3.8682441583483314e-05,
-      "loss": 1.545,
-      "step": 500
-    },
-    {
-      "epoch": 0.32,
-      "grad_norm": 1.2939772605895996,
-      "learning_rate": 3.8264797016335205e-05,
-      "loss": 1.5793,
-      "step": 510
-    },
-    {
-      "epoch": 0.33,
-      "grad_norm": 1.2150651216506958,
-      "learning_rate": 3.7841934789335164e-05,
-      "loss": 1.5378,
-      "step": 520
-    },
-    {
-      "epoch": 0.33,
-      "grad_norm": 1.2153139114379883,
-      "learning_rate": 3.741402123380828e-05,
-      "loss": 1.5345,
-      "step": 530
-    },
-    {
-      "epoch": 0.34,
-      "grad_norm": 1.290591835975647,
-      "learning_rate": 3.6981224668001424e-05,
-      "loss": 1.5517,
-      "step": 540
-    },
-    {
-      "epoch": 0.35,
-      "grad_norm": 1.1924967765808105,
-      "learning_rate": 3.654371533087586e-05,
-      "loss": 1.5472,
-      "step": 550
-    },
-    {
-      "epoch": 0.35,
-      "grad_norm": 1.6345056295394897,
-      "learning_rate": 3.610166531514436e-05,
-      "loss": 1.5564,
-      "step": 560
-    },
-    {
-      "epoch": 0.36,
-      "grad_norm": 2.185119867324829,
-      "learning_rate": 3.565524849957921e-05,
-      "loss": 1.5574,
-      "step": 570
-    },
-    {
-      "epoch": 0.37,
-      "grad_norm": 1.3646321296691895,
-      "learning_rate": 3.520464048061758e-05,
-      "loss": 1.5584,
-      "step": 580
-    },
-    {
-      "epoch": 0.37,
-      "grad_norm": 1.2333228588104248,
-      "learning_rate": 3.47500185032913e-05,
-      "loss": 1.518,
-      "step": 590
-    },
-    {
-      "epoch": 0.38,
-      "grad_norm": 1.3945318460464478,
-      "learning_rate": 3.4291561391508185e-05,
-      "loss": 1.5339,
-      "step": 600
-    },
-    {
-      "epoch": 0.38,
-      "grad_norm": 1.304306149482727,
-      "learning_rate": 3.3829449477712324e-05,
-      "loss": 1.5339,
-      "step": 610
-    },
-    {
-      "epoch": 0.39,
-      "grad_norm": 1.6393932104110718,
-      "learning_rate": 3.336386453195088e-05,
-      "loss": 1.5399,
-      "step": 620
-    },
-    {
-      "epoch": 0.4,
-      "grad_norm": 1.2000635862350464,
-      "learning_rate": 3.2894989690375626e-05,
-      "loss": 1.5233,
-      "step": 630
-    },
-    {
-      "epoch": 0.4,
-      "grad_norm": 1.1479601860046387,
-      "learning_rate": 3.2423009383206876e-05,
-      "loss": 1.538,
-      "step": 640
-    },
-    {
-      "epoch": 0.41,
-      "grad_norm": 1.1483389139175415,
-      "learning_rate": 3.194810926218861e-05,
-      "loss": 1.528,
-      "step": 650
-    },
-    {
-      "epoch": 0.42,
-      "grad_norm": 1.2403253316879272,
-      "learning_rate": 3.147047612756302e-05,
-      "loss": 1.5307,
-      "step": 660
-    },
-    {
-      "epoch": 0.42,
-      "grad_norm": 1.3997712135314941,
-      "learning_rate": 3.099029785459328e-05,
-      "loss": 1.4915,
-      "step": 670
-    },
-    {
-      "epoch": 0.43,
-      "grad_norm": 1.2010352611541748,
-      "learning_rate": 3.0507763319663517e-05,
-      "loss": 1.5268,
-      "step": 680
-    },
-    {
-      "epoch": 0.44,
-      "grad_norm": 1.0670932531356812,
-      "learning_rate": 3.002306232598497e-05,
-      "loss": 1.5273,
-      "step": 690
-    },
-    {
-      "epoch": 0.44,
-      "grad_norm": 1.2283655405044556,
-      "learning_rate": 2.9536385528937567e-05,
-      "loss": 1.5273,
-      "step": 700
-    },
-    {
-      "epoch": 0.45,
-      "grad_norm": 1.1306476593017578,
-      "learning_rate": 2.9047924361076345e-05,
-      "loss": 1.5072,
-      "step": 710
-    },
-    {
-      "epoch": 0.45,
-      "grad_norm": 1.1699943542480469,
-      "learning_rate": 2.8557870956832132e-05,
-      "loss": 1.4856,
-      "step": 720
-    },
-    {
-      "epoch": 0.46,
-      "grad_norm": 1.2550854682922363,
-      "learning_rate": 2.8066418076936167e-05,
-      "loss": 1.4983,
-      "step": 730
-    },
-    {
-      "epoch": 0.47,
-      "grad_norm": 1.0610970258712769,
-      "learning_rate": 2.7573759032598366e-05,
-      "loss": 1.5518,
-      "step": 740
-    },
-    {
-      "epoch": 0.47,
-      "grad_norm": 1.1754754781723022,
-      "learning_rate": 2.7080087609469062e-05,
-      "loss": 1.4998,
-      "step": 750
-    },
-    {
-      "epoch": 0.48,
-      "grad_norm": 1.1955766677856445,
-      "learning_rate": 2.6585597991414114e-05,
-      "loss": 1.5109,
-      "step": 760
-    },
-    {
-      "epoch": 0.49,
-      "grad_norm": 1.0891656875610352,
-      "learning_rate": 2.6090484684133404e-05,
-      "loss": 1.5007,
-      "step": 770
-    },
-    {
-      "epoch": 0.49,
-      "grad_norm": 1.0880335569381714,
-      "learning_rate": 2.5594942438652688e-05,
-      "loss": 1.5049,
-      "step": 780
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 1.345954418182373,
-      "learning_rate": 2.509916617471903e-05,
-      "loss": 1.5154,
-      "step": 790
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 1.1668224334716797,
-      "learning_rate": 2.46033509041298e-05,
-      "loss": 1.4883,
-      "step": 800
-    },
-    {
-      "epoch": 0.51,
-      "grad_norm": 1.055127501487732,
-      "learning_rate": 2.410769165402549e-05,
-      "loss": 1.5053,
-      "step": 810
-    },
-    {
-      "epoch": 0.52,
-      "grad_norm": 1.0528500080108643,
-      "learning_rate": 2.3612383390176503e-05,
-      "loss": 1.4871,
-      "step": 820
-    },
-    {
-      "epoch": 0.52,
-      "grad_norm": 1.328258991241455,
-      "learning_rate": 2.3117620940294048e-05,
-      "loss": 1.5037,
-      "step": 830
-    },
-    {
-      "epoch": 0.53,
-      "grad_norm": 1.0326772928237915,
-      "learning_rate": 2.2623598917395438e-05,
-      "loss": 1.4525,
-      "step": 840
-    },
-    {
-      "epoch": 0.54,
-      "grad_norm": 3.057058811187744,
-      "learning_rate": 2.213051164325366e-05,
-      "loss": 1.4898,
-      "step": 850
-    },
-    {
-      "epoch": 0.54,
-      "grad_norm": 1.1190940141677856,
-      "learning_rate": 2.1638553071961708e-05,
-      "loss": 1.488,
-      "step": 860
-    },
-    {
-      "epoch": 0.55,
-      "grad_norm": 1.1501041650772095,
-      "learning_rate": 2.1147916713641367e-05,
-      "loss": 1.4711,
-      "step": 870
-    },
-    {
-      "epoch": 0.56,
-      "grad_norm": 1.090022325515747,
-      "learning_rate": 2.0658795558326743e-05,
-      "loss": 1.488,
-      "step": 880
-    },
-    {
-      "epoch": 0.56,
-      "grad_norm": 1.0642565488815308,
-      "learning_rate": 2.017138200005236e-05,
-      "loss": 1.4791,
-      "step": 890
-    },
-    {
-      "epoch": 0.57,
-      "grad_norm": 1.3562296628952026,
-      "learning_rate": 1.9685867761175584e-05,
-      "loss": 1.4956,
-      "step": 900
-    },
-    {
-      "epoch": 0.57,
-      "grad_norm": 1.2069261074066162,
-      "learning_rate": 1.9202443816963425e-05,
-      "loss": 1.4918,
-      "step": 910
-    },
-    {
-      "epoch": 0.58,
-      "grad_norm": 1.3227437734603882,
-      "learning_rate": 1.872130032047302e-05,
-      "loss": 1.4577,
-      "step": 920
-    },
-    {
-      "epoch": 0.59,
-      "grad_norm": 1.0784181356430054,
-      "learning_rate": 1.824262652775568e-05,
-      "loss": 1.4888,
-      "step": 930
-    },
-    {
-      "epoch": 0.59,
-      "grad_norm": 1.000135898590088,
-      "learning_rate": 1.7766610723413684e-05,
-      "loss": 1.4673,
-      "step": 940
-    },
-    {
-      "epoch": 0.6,
-      "grad_norm": 1.136026382446289,
-      "learning_rate": 1.7293440146539196e-05,
-      "loss": 1.4779,
-      "step": 950
-    },
-    {
-      "epoch": 0.61,
-      "grad_norm": 1.123252272605896,
-      "learning_rate": 1.682330091706446e-05,
-      "loss": 1.4583,
-      "step": 960
-    },
-    {
-      "epoch": 0.61,
-      "grad_norm": 1.0559343099594116,
-      "learning_rate": 1.6356377962552238e-05,
-      "loss": 1.4471,
-      "step": 970
-    },
-    {
-      "epoch": 0.62,
-      "grad_norm": 1.0266658067703247,
-      "learning_rate": 1.589285494545514e-05,
-      "loss": 1.4632,
-      "step": 980
-    },
-    {
-      "epoch": 0.62,
-      "grad_norm": 1.1371444463729858,
-      "learning_rate": 1.5432914190872757e-05,
-      "loss": 1.4732,
-      "step": 990
-    },
-    {
-      "epoch": 0.63,
-      "grad_norm": 1.1203784942626953,
-      "learning_rate": 1.4976736614834664e-05,
-      "loss": 1.452,
-      "step": 1000
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1584,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1000,
-  "total_flos": 7.003073868034212e+17,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5f270ab83bb6b8b6198abab8938484e33528253ff0e05545853f6357e16e105
-size 4603