Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.528412807299072e+16,
+    "train_loss": 0.12713232355097756,
+    "train_runtime": 177593.1778,
+    "train_samples_per_second": 3.064,
+    "train_steps_per_second": 0.017
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/apdcephfs_sh4/share_300001476/trenousqiu/models/models--meta-llama--Meta-Llama-3-70B/snapshots/b4d08b7db49d488da3ac49adf25a6b9ac01ae338",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d59d488d64ead0f289880f363cc60c207f9263003aa328912fd44981590729
+size 4584408808

model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c989fd79f3ed3edb3850259022b5b08ac6d492d0145d642878e692494b2911b
+size 4664167376

model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c0671e568b79c20106ce80d922632e92fe4aa019cc5aed0e8154a5b7f64a56
+size 4999711704

model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29491da9f1ffb3616aa44f24b7297d8086ba68f335eb035eabb5c1e4222af560
+size 4966157032

model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288aaa6003c48db865ed6f8235970bf05c983b573f298cda99304859aed98683
+size 4664134408

model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e8c3514fd1bf80556ad3b1e9c1784493e88e27505ec7271bbceca83365068c
+size 4664167408

model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffb8248b1a13a1ac7af46cafe44b5dc4d9f53f4fc16f742eecb9c2dca191fe3
+size 4664167408

model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5b89cc4295b746ca99320ecb960113271616c48fa3aee6c682f2cea4e22b3a
+size 4999711728

model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24051e96e8bab544722f14907c0fb4e0592af8e4d78e228451c77c708b7818f3
+size 4966157056

model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd07af38452894441a7533f849b6a177a75eba1e74fc8d9189d59c092640873
+size 4664134408

model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c06326fef8e77de97cac838148cca2926d2ef2d2d8dec2f802cb29c5638590c
+size 4664167408

model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5a7cf34b0c4123aef88742743b73ee1c655bb355b9ea7d167ac22e474920b3
+size 4664167408

model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ccb237ff195cbdd060bf20dc80a84c6b8c7adebb8d44480c701793237e161a
+size 4999711728

model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499dab78c5413e20af2fc49851389c6531f0fca65451ef69961b57d111cddea0
+size 4966157056

model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22dbf2e1901f096e758ac40503cbb465670c9f480452c10a2585e69cfdf370bc
+size 4664134408

model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb41dc3cdbbaf6bc37f767353fc5e94b0f5392d4419af79df272e6611de941e
+size 4664167408

model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeced71d5536d4ab18d30ce6eb0df984d842cf941b8614a150f24fd0d04775ec
+size 4664167408

model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a5d51d8143ebdb9c98746275ec7ca0bde084526615700bada996c631d76274
+size 4999711728

model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce8ed4f30d1f4f61927c8b1008bd5a4ecc6ffda0adb64f7d63dbba838b7b6ac
+size 4966157056

model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a691ef524b752078f7c73720c97693769e1e45b8dc99b94ebc035ed220ec32a5
+size 4664134408

model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f18612b1306e32870b005b88e8551a1b40b52daf0293b92cfe74e7cb02e04e8
+size 4664167408

model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99573d9934fb065e84b0a3c3490f44a13c3a8b84404fa1a04b6b9eeca082330
+size 4664167408

model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bc405183c377b9f7bb2968b072c72c26fa7fbac7e864c278571da6582ddd2a
+size 4999711728

model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c063474f7fd71ad13f4b18e648989b44d87f5b652dff6a1ff5803ec20637a77
+size 4966157056

model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd832454ad8f96a80af0fbe17602dc4614d84000574c4bcf78a69c5fba201a7
+size 4664134408

model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d9cf439f28ac7c64802eb5e327350c86a6da71184a116f92b9250db89b4901
+size 4664167408

model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7393f2f2e5844fa610ec1c0e961fee9a8b265588090595654dc8eea4686d8c
+size 4664167408

model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9866603104f08f5ca3afcb0d1cdd0622df02f49ebbc8c8b17f7d183120b639
+size 4999711728

model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad71be32fa65cd7b9f6a65473e7eb3fa89d06389b87daf5ecbe5e8c2b5951f0
+size 4966173536

model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d54ccae0c56a9168c76d6a78e4d90a756a3d13385db04791122298d823ee40
+size 2101346432

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 141107412992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00030-of-00030.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "model.norm.weight": "model-00029-of-00030.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.528412807299072e+16,
+    "train_loss": 0.12713232355097756,
+    "train_runtime": 177593.1778,
+    "train_samples_per_second": 3.064,
+    "train_steps_per_second": 0.017
+}

trainer_log.jsonl

@@ -0,0 +1,310 @@
+{"current_steps": 10, "total_steps": 3093, "loss": 0.3895, "learning_rate": 1.0752688172043011e-06, "epoch": 0.009699321047526674, "percentage": 0.32, "elapsed_time": "0:09:45", "remaining_time": "2 days, 2:08:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 3093, "loss": 0.3209, "learning_rate": 2.1505376344086023e-06, "epoch": 0.019398642095053348, "percentage": 0.65, "elapsed_time": "0:19:14", "remaining_time": "2 days, 1:15:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 3093, "loss": 0.2648, "learning_rate": 3.225806451612903e-06, "epoch": 0.029097963142580018, "percentage": 0.97, "elapsed_time": "0:28:42", "remaining_time": "2 days, 0:51:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 3093, "loss": 0.2353, "learning_rate": 4.3010752688172045e-06, "epoch": 0.038797284190106696, "percentage": 1.29, "elapsed_time": "0:38:11", "remaining_time": "2 days, 0:34:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 3093, "loss": 0.2211, "learning_rate": 5.376344086021506e-06, "epoch": 0.04849660523763336, "percentage": 1.62, "elapsed_time": "0:47:40", "remaining_time": "2 days, 0:21:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 3093, "loss": 0.2065, "learning_rate": 6.451612903225806e-06, "epoch": 0.058195926285160036, "percentage": 1.94, "elapsed_time": "0:57:08", "remaining_time": "2 days, 0:08:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 3093, "loss": 0.2, "learning_rate": 7.526881720430108e-06, "epoch": 0.06789524733268672, "percentage": 2.26, "elapsed_time": "1:06:37", "remaining_time": "1 day, 23:57:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 3093, "loss": 0.1932, "learning_rate": 8.602150537634409e-06, "epoch": 0.07759456838021339, "percentage": 2.59, "elapsed_time": "1:16:06", "remaining_time": "1 day, 23:46:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 3093, "loss": 0.1888, "learning_rate": 9.67741935483871e-06, "epoch": 0.08729388942774007, "percentage": 2.91, "elapsed_time": "1:25:34", "remaining_time": "1 day, 23:35:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 3093, "loss": 0.186, "learning_rate": 9.999865664319414e-06, "epoch": 0.09699321047526673, "percentage": 3.23, "elapsed_time": "1:35:04", "remaining_time": "1 day, 23:25:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 3093, "loss": 0.182, "learning_rate": 9.999207711016081e-06, "epoch": 0.1066925315227934, "percentage": 3.56, "elapsed_time": "1:44:32", "remaining_time": "1 day, 23:15:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 120, "total_steps": 3093, "loss": 0.1779, "learning_rate": 9.998001538251283e-06, "epoch": 0.11639185257032007, "percentage": 3.88, "elapsed_time": "1:54:01", "remaining_time": "1 day, 23:04:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 130, "total_steps": 3093, "loss": 0.1743, "learning_rate": 9.99624727829546e-06, "epoch": 0.12609117361784675, "percentage": 4.2, "elapsed_time": "2:03:30", "remaining_time": "1 day, 22:54:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 140, "total_steps": 3093, "loss": 0.176, "learning_rate": 9.99394512352298e-06, "epoch": 0.13579049466537343, "percentage": 4.53, "elapsed_time": "2:12:59", "remaining_time": "1 day, 22:45:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 3093, "loss": 0.1741, "learning_rate": 9.991095326391061e-06, "epoch": 0.1454898157129001, "percentage": 4.85, "elapsed_time": "2:22:27", "remaining_time": "1 day, 22:35:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 3093, "loss": 0.1702, "learning_rate": 9.98769819941207e-06, "epoch": 0.15518913676042678, "percentage": 5.17, "elapsed_time": "2:31:56", "remaining_time": "1 day, 22:25:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 3093, "loss": 0.1727, "learning_rate": 9.983754115119262e-06, "epoch": 0.16488845780795344, "percentage": 5.5, "elapsed_time": "2:41:24", "remaining_time": "1 day, 22:15:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 3093, "loss": 0.1701, "learning_rate": 9.97926350602593e-06, "epoch": 0.17458777885548013, "percentage": 5.82, "elapsed_time": "2:50:53", "remaining_time": "1 day, 22:05:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 3093, "loss": 0.1678, "learning_rate": 9.97422686457796e-06, "epoch": 0.1842870999030068, "percentage": 6.14, "elapsed_time": "3:00:21", "remaining_time": "1 day, 21:55:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 3093, "loss": 0.1641, "learning_rate": 9.968644743099848e-06, "epoch": 0.19398642095053345, "percentage": 6.47, "elapsed_time": "3:09:50", "remaining_time": "1 day, 21:46:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 3093, "loss": 0.167, "learning_rate": 9.96251775373412e-06, "epoch": 0.20368574199806014, "percentage": 6.79, "elapsed_time": "3:19:19", "remaining_time": "1 day, 21:36:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 3093, "loss": 0.1655, "learning_rate": 9.955846568374201e-06, "epoch": 0.2133850630455868, "percentage": 7.11, "elapsed_time": "3:28:47", "remaining_time": "1 day, 21:26:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 3093, "loss": 0.1617, "learning_rate": 9.948631918590746e-06, "epoch": 0.22308438409311349, "percentage": 7.44, "elapsed_time": "3:38:16", "remaining_time": "1 day, 21:17:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 3093, "loss": 0.1626, "learning_rate": 9.940874595551403e-06, "epoch": 0.23278370514064015, "percentage": 7.76, "elapsed_time": "3:47:45", "remaining_time": "1 day, 21:07:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 3093, "loss": 0.1644, "learning_rate": 9.932575449934063e-06, "epoch": 0.24248302618816683, "percentage": 8.08, "elapsed_time": "3:57:14", "remaining_time": "1 day, 20:57:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 260, "total_steps": 3093, "loss": 0.1618, "learning_rate": 9.923735391833564e-06, "epoch": 0.2521823472356935, "percentage": 8.41, "elapsed_time": "4:06:42", "remaining_time": "1 day, 20:48:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 270, "total_steps": 3093, "loss": 0.1588, "learning_rate": 9.914355390661897e-06, "epoch": 0.2618816682832202, "percentage": 8.73, "elapsed_time": "4:16:11", "remaining_time": "1 day, 20:38:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 280, "total_steps": 3093, "loss": 0.1599, "learning_rate": 9.904436475041892e-06, "epoch": 0.27158098933074687, "percentage": 9.05, "elapsed_time": "4:25:39", "remaining_time": "1 day, 20:28:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 290, "total_steps": 3093, "loss": 0.1608, "learning_rate": 9.893979732694422e-06, "epoch": 0.2812803103782735, "percentage": 9.38, "elapsed_time": "4:35:08", "remaining_time": "1 day, 20:19:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 300, "total_steps": 3093, "loss": 0.1571, "learning_rate": 9.882986310319124e-06, "epoch": 0.2909796314258002, "percentage": 9.7, "elapsed_time": "4:44:37", "remaining_time": "1 day, 20:09:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 310, "total_steps": 3093, "loss": 0.1602, "learning_rate": 9.871457413468645e-06, "epoch": 0.3006789524733269, "percentage": 10.02, "elapsed_time": "4:54:05", "remaining_time": "1 day, 20:00:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 320, "total_steps": 3093, "loss": 0.1587, "learning_rate": 9.859394306416443e-06, "epoch": 0.31037827352085356, "percentage": 10.35, "elapsed_time": "5:03:34", "remaining_time": "1 day, 19:50:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 330, "total_steps": 3093, "loss": 0.1593, "learning_rate": 9.846798312018147e-06, "epoch": 0.3200775945683802, "percentage": 10.67, "elapsed_time": "5:13:03", "remaining_time": "1 day, 19:41:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 340, "total_steps": 3093, "loss": 0.1555, "learning_rate": 9.833670811566485e-06, "epoch": 0.3297769156159069, "percentage": 10.99, "elapsed_time": "5:22:32", "remaining_time": "1 day, 19:31:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 3093, "loss": 0.1575, "learning_rate": 9.820013244639817e-06, "epoch": 0.3394762366634336, "percentage": 11.32, "elapsed_time": "5:32:01", "remaining_time": "1 day, 19:22:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 360, "total_steps": 3093, "loss": 0.1573, "learning_rate": 9.80582710894426e-06, "epoch": 0.34917555771096026, "percentage": 11.64, "elapsed_time": "5:41:29", "remaining_time": "1 day, 19:12:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 370, "total_steps": 3093, "loss": 0.1549, "learning_rate": 9.791113960149458e-06, "epoch": 0.3588748787584869, "percentage": 11.96, "elapsed_time": "5:50:58", "remaining_time": "1 day, 19:02:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 380, "total_steps": 3093, "loss": 0.1559, "learning_rate": 9.775875411717981e-06, "epoch": 0.3685741998060136, "percentage": 12.29, "elapsed_time": "6:00:27", "remaining_time": "1 day, 18:53:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 390, "total_steps": 3093, "loss": 0.156, "learning_rate": 9.760113134728383e-06, "epoch": 0.37827352085354027, "percentage": 12.61, "elapsed_time": "6:09:56", "remaining_time": "1 day, 18:43:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 400, "total_steps": 3093, "loss": 0.1549, "learning_rate": 9.743828857691964e-06, "epoch": 0.3879728419010669, "percentage": 12.93, "elapsed_time": "6:19:24", "remaining_time": "1 day, 18:34:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 3093, "loss": 0.1546, "learning_rate": 9.727024366363208e-06, "epoch": 0.3976721629485936, "percentage": 13.26, "elapsed_time": "6:28:53", "remaining_time": "1 day, 18:24:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 3093, "loss": 0.1541, "learning_rate": 9.709701503543954e-06, "epoch": 0.4073714839961203, "percentage": 13.58, "elapsed_time": "6:38:22", "remaining_time": "1 day, 18:15:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 3093, "loss": 0.153, "learning_rate": 9.691862168881325e-06, "epoch": 0.41707080504364696, "percentage": 13.9, "elapsed_time": "6:47:51", "remaining_time": "1 day, 18:05:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 3093, "loss": 0.1514, "learning_rate": 9.673508318659399e-06, "epoch": 0.4267701260911736, "percentage": 14.23, "elapsed_time": "6:57:19", "remaining_time": "1 day, 17:56:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 3093, "loss": 0.1507, "learning_rate": 9.65464196558468e-06, "epoch": 0.4364694471387003, "percentage": 14.55, "elapsed_time": "7:06:48", "remaining_time": "1 day, 17:46:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 3093, "loss": 0.1529, "learning_rate": 9.635265178565386e-06, "epoch": 0.44616876818622697, "percentage": 14.87, "elapsed_time": "7:16:17", "remaining_time": "1 day, 17:37:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 3093, "loss": 0.1524, "learning_rate": 9.615380082484573e-06, "epoch": 0.45586808923375366, "percentage": 15.2, "elapsed_time": "7:25:45", "remaining_time": "1 day, 17:27:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 3093, "loss": 0.1519, "learning_rate": 9.594988857967107e-06, "epoch": 0.4655674102812803, "percentage": 15.52, "elapsed_time": "7:35:14", "remaining_time": "1 day, 17:18:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 3093, "loss": 0.1503, "learning_rate": 9.574093741140549e-06, "epoch": 0.475266731328807, "percentage": 15.84, "elapsed_time": "7:44:43", "remaining_time": "1 day, 17:08:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 3093, "loss": 0.15, "learning_rate": 9.552697023389923e-06, "epoch": 0.48496605237633367, "percentage": 16.17, "elapsed_time": "7:54:12", "remaining_time": "1 day, 16:59:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 3093, "loss": 0.1505, "learning_rate": 9.530801051106449e-06, "epoch": 0.49466537342386036, "percentage": 16.49, "elapsed_time": "8:07:17", "remaining_time": "1 day, 17:07:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 3093, "loss": 0.1512, "learning_rate": 9.508408225430237e-06, "epoch": 0.504364694471387, "percentage": 16.81, "elapsed_time": "8:16:45", "remaining_time": "1 day, 16:58:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 3093, "loss": 0.1438, "learning_rate": 9.485521001986961e-06, "epoch": 0.5140640155189137, "percentage": 17.14, "elapsed_time": "8:26:14", "remaining_time": "1 day, 16:48:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 3093, "loss": 0.1513, "learning_rate": 9.46214189061859e-06, "epoch": 0.5237633365664404, "percentage": 17.46, "elapsed_time": "8:35:42", "remaining_time": "1 day, 16:38:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 3093, "loss": 0.1489, "learning_rate": 9.438273455108145e-06, "epoch": 0.533462657613967, "percentage": 17.78, "elapsed_time": "8:45:11", "remaining_time": "1 day, 16:28:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 3093, "loss": 0.1496, "learning_rate": 9.41391831289855e-06, "epoch": 0.5431619786614937, "percentage": 18.11, "elapsed_time": "8:54:40", "remaining_time": "1 day, 16:18:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 3093, "loss": 0.1457, "learning_rate": 9.38907913480561e-06, "epoch": 0.5528612997090203, "percentage": 18.43, "elapsed_time": "9:04:09", "remaining_time": "1 day, 16:08:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 3093, "loss": 0.1443, "learning_rate": 9.36375864472511e-06, "epoch": 0.562560620756547, "percentage": 18.75, "elapsed_time": "9:13:37", "remaining_time": "1 day, 15:58:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 3093, "loss": 0.1476, "learning_rate": 9.337959619334125e-06, "epoch": 0.5722599418040737, "percentage": 19.08, "elapsed_time": "9:23:06", "remaining_time": "1 day, 15:48:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 3093, "loss": 0.1476, "learning_rate": 9.31168488778652e-06, "epoch": 0.5819592628516004, "percentage": 19.4, "elapsed_time": "9:32:35", "remaining_time": "1 day, 15:39:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 3093, "loss": 0.1468, "learning_rate": 9.284937331402697e-06, "epoch": 0.5916585838991271, "percentage": 19.72, "elapsed_time": "9:42:03", "remaining_time": "1 day, 15:29:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 3093, "loss": 0.1482, "learning_rate": 9.25771988335363e-06, "epoch": 0.6013579049466538, "percentage": 20.05, "elapsed_time": "9:51:32", "remaining_time": "1 day, 15:19:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 3093, "loss": 0.1455, "learning_rate": 9.230035528339212e-06, "epoch": 0.6110572259941804, "percentage": 20.37, "elapsed_time": "10:01:01", "remaining_time": "1 day, 15:09:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 3093, "loss": 0.1485, "learning_rate": 9.201887302260943e-06, "epoch": 0.6207565470417071, "percentage": 20.69, "elapsed_time": "10:10:29", "remaining_time": "1 day, 14:59:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 3093, "loss": 0.1466, "learning_rate": 9.173278291889016e-06, "epoch": 0.6304558680892337, "percentage": 21.02, "elapsed_time": "10:19:58", "remaining_time": "1 day, 14:50:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 660, "total_steps": 3093, "loss": 0.1466, "learning_rate": 9.14421163452381e-06, "epoch": 0.6401551891367604, "percentage": 21.34, "elapsed_time": "10:29:27", "remaining_time": "1 day, 14:40:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 3093, "loss": 0.1464, "learning_rate": 9.11469051765186e-06, "epoch": 0.6498545101842871, "percentage": 21.66, "elapsed_time": "10:38:56", "remaining_time": "1 day, 14:30:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 3093, "loss": 0.1452, "learning_rate": 9.084718178596301e-06, "epoch": 0.6595538312318138, "percentage": 21.99, "elapsed_time": "10:48:25", "remaining_time": "1 day, 14:20:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 3093, "loss": 0.1439, "learning_rate": 9.054297904161868e-06, "epoch": 0.6692531522793405, "percentage": 22.31, "elapsed_time": "10:57:54", "remaining_time": "1 day, 14:11:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 3093, "loss": 0.1465, "learning_rate": 9.02343303027446e-06, "epoch": 0.6789524733268671, "percentage": 22.63, "elapsed_time": "11:07:23", "remaining_time": "1 day, 14:01:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 710, "total_steps": 3093, "loss": 0.1458, "learning_rate": 8.992126941615314e-06, "epoch": 0.6886517943743938, "percentage": 22.96, "elapsed_time": "11:16:52", "remaining_time": "1 day, 13:51:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 720, "total_steps": 3093, "loss": 0.1451, "learning_rate": 8.960383071249837e-06, "epoch": 0.6983511154219205, "percentage": 23.28, "elapsed_time": "11:26:21", "remaining_time": "1 day, 13:42:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 730, "total_steps": 3093, "loss": 0.1452, "learning_rate": 8.928204900251136e-06, "epoch": 0.7080504364694471, "percentage": 23.6, "elapsed_time": "11:35:49", "remaining_time": "1 day, 13:32:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 740, "total_steps": 3093, "loss": 0.146, "learning_rate": 8.895595957318277e-06, "epoch": 0.7177497575169738, "percentage": 23.92, "elapsed_time": "11:45:18", "remaining_time": "1 day, 13:22:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 3093, "loss": 0.1418, "learning_rate": 8.862559818389322e-06, "epoch": 0.7274490785645005, "percentage": 24.25, "elapsed_time": "11:54:47", "remaining_time": "1 day, 13:12:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 760, "total_steps": 3093, "loss": 0.1429, "learning_rate": 8.829100106249189e-06, "epoch": 0.7371483996120272, "percentage": 24.57, "elapsed_time": "12:04:15", "remaining_time": "1 day, 13:03:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 770, "total_steps": 3093, "loss": 0.1461, "learning_rate": 8.795220490132369e-06, "epoch": 0.7468477206595538, "percentage": 24.89, "elapsed_time": "12:13:44", "remaining_time": "1 day, 12:53:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 780, "total_steps": 3093, "loss": 0.1426, "learning_rate": 8.760924685320558e-06, "epoch": 0.7565470417070805, "percentage": 25.22, "elapsed_time": "12:23:13", "remaining_time": "1 day, 12:43:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 790, "total_steps": 3093, "loss": 0.1427, "learning_rate": 8.726216452735233e-06, "epoch": 0.7662463627546072, "percentage": 25.54, "elapsed_time": "12:32:41", "remaining_time": "1 day, 12:34:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 3093, "loss": 0.1425, "learning_rate": 8.691099598525222e-06, "epoch": 0.7759456838021338, "percentage": 25.86, "elapsed_time": "12:42:10", "remaining_time": "1 day, 12:24:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 3093, "loss": 0.1447, "learning_rate": 8.655577973649322e-06, "epoch": 0.7856450048496605, "percentage": 26.19, "elapsed_time": "12:51:39", "remaining_time": "1 day, 12:14:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 3093, "loss": 0.1431, "learning_rate": 8.61965547345399e-06, "epoch": 0.7953443258971872, "percentage": 26.51, "elapsed_time": "13:01:07", "remaining_time": "1 day, 12:05:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 3093, "loss": 0.1436, "learning_rate": 8.583336037246187e-06, "epoch": 0.8050436469447139, "percentage": 26.83, "elapsed_time": "13:10:36", "remaining_time": "1 day, 11:55:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 3093, "loss": 0.1447, "learning_rate": 8.54662364786137e-06, "epoch": 0.8147429679922406, "percentage": 27.16, "elapsed_time": "13:20:05", "remaining_time": "1 day, 11:45:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 3093, "loss": 0.139, "learning_rate": 8.509522331226751e-06, "epoch": 0.8244422890397672, "percentage": 27.48, "elapsed_time": "13:29:33", "remaining_time": "1 day, 11:36:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 3093, "loss": 0.1427, "learning_rate": 8.47203615591979e-06, "epoch": 0.8341416100872939, "percentage": 27.8, "elapsed_time": "13:39:02", "remaining_time": "1 day, 11:26:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 3093, "loss": 0.1404, "learning_rate": 8.434169232722043e-06, "epoch": 0.8438409311348206, "percentage": 28.13, "elapsed_time": "13:48:31", "remaining_time": "1 day, 11:17:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 3093, "loss": 0.1412, "learning_rate": 8.395925714168356e-06, "epoch": 0.8535402521823472, "percentage": 28.45, "elapsed_time": "13:58:00", "remaining_time": "1 day, 11:07:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 3093, "loss": 0.1413, "learning_rate": 8.357309794091508e-06, "epoch": 0.8632395732298739, "percentage": 28.77, "elapsed_time": "14:07:28", "remaining_time": "1 day, 10:57:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 3093, "loss": 0.1413, "learning_rate": 8.318325707162293e-06, "epoch": 0.8729388942774006, "percentage": 29.1, "elapsed_time": "14:16:57", "remaining_time": "1 day, 10:48:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 3093, "loss": 0.1419, "learning_rate": 8.278977728425157e-06, "epoch": 0.8826382153249273, "percentage": 29.42, "elapsed_time": "14:26:26", "remaining_time": "1 day, 10:38:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 3093, "loss": 0.1416, "learning_rate": 8.239270172829379e-06, "epoch": 0.8923375363724539, "percentage": 29.74, "elapsed_time": "14:35:55", "remaining_time": "1 day, 10:28:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 3093, "loss": 0.1407, "learning_rate": 8.199207394755892e-06, "epoch": 0.9020368574199806, "percentage": 30.07, "elapsed_time": "14:45:24", "remaining_time": "1 day, 10:19:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 3093, "loss": 0.1426, "learning_rate": 8.158793787539782e-06, "epoch": 0.9117361784675073, "percentage": 30.39, "elapsed_time": "14:54:52", "remaining_time": "1 day, 10:09:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 3093, "loss": 0.1425, "learning_rate": 8.118033782988496e-06, "epoch": 0.9214354995150339, "percentage": 30.71, "elapsed_time": "15:04:21", "remaining_time": "1 day, 10:00:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 960, "total_steps": 3093, "loss": 0.1406, "learning_rate": 8.076931850895858e-06, "epoch": 0.9311348205625606, "percentage": 31.04, "elapsed_time": "15:13:50", "remaining_time": "1 day, 9:50:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 970, "total_steps": 3093, "loss": 0.1404, "learning_rate": 8.0354924985519e-06, "epoch": 0.9408341416100873, "percentage": 31.36, "elapsed_time": "15:23:19", "remaining_time": "1 day, 9:40:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 980, "total_steps": 3093, "loss": 0.1367, "learning_rate": 7.993720270248583e-06, "epoch": 0.950533462657614, "percentage": 31.68, "elapsed_time": "15:32:47", "remaining_time": "1 day, 9:31:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 990, "total_steps": 3093, "loss": 0.1404, "learning_rate": 7.951619746781474e-06, "epoch": 0.9602327837051406, "percentage": 32.01, "elapsed_time": "15:42:16", "remaining_time": "1 day, 9:21:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1000, "total_steps": 3093, "loss": 0.1379, "learning_rate": 7.909195544947398e-06, "epoch": 0.9699321047526673, "percentage": 32.33, "elapsed_time": "15:51:45", "remaining_time": "1 day, 9:12:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1010, "total_steps": 3093, "loss": 0.1407, "learning_rate": 7.866452317038164e-06, "epoch": 0.979631425800194, "percentage": 32.65, "elapsed_time": "16:04:58", "remaining_time": "1 day, 9:10:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1020, "total_steps": 3093, "loss": 0.1378, "learning_rate": 7.823394750330386e-06, "epoch": 0.9893307468477207, "percentage": 32.98, "elapsed_time": "16:14:26", "remaining_time": "1 day, 9:00:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1030, "total_steps": 3093, "loss": 0.1381, "learning_rate": 7.780027566571467e-06, "epoch": 0.9990300678952473, "percentage": 33.3, "elapsed_time": "16:23:55", "remaining_time": "1 day, 8:50:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1040, "total_steps": 3093, "loss": 0.1289, "learning_rate": 7.736355521461812e-06, "epoch": 1.008729388942774, "percentage": 33.62, "elapsed_time": "16:33:30", "remaining_time": "1 day, 8:41:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 3093, "loss": 0.1251, "learning_rate": 7.692383404133302e-06, "epoch": 1.0184287099903007, "percentage": 33.95, "elapsed_time": "16:42:58", "remaining_time": "1 day, 8:31:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1060, "total_steps": 3093, "loss": 0.1256, "learning_rate": 7.648116036624125e-06, "epoch": 1.0281280310378274, "percentage": 34.27, "elapsed_time": "16:52:27", "remaining_time": "1 day, 8:21:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1070, "total_steps": 3093, "loss": 0.1255, "learning_rate": 7.6035582733499805e-06, "epoch": 1.037827352085354, "percentage": 34.59, "elapsed_time": "17:01:55", "remaining_time": "1 day, 8:12:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1080, "total_steps": 3093, "loss": 0.1241, "learning_rate": 7.5587150005717256e-06, "epoch": 1.0475266731328807, "percentage": 34.92, "elapsed_time": "17:11:24", "remaining_time": "1 day, 8:02:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1090, "total_steps": 3093, "loss": 0.1273, "learning_rate": 7.5135911358595615e-06, "epoch": 1.0572259941804074, "percentage": 35.24, "elapsed_time": "17:20:53", "remaining_time": "1 day, 7:52:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 3093, "loss": 0.1264, "learning_rate": 7.468191627553752e-06, "epoch": 1.066925315227934, "percentage": 35.56, "elapsed_time": "17:30:21", "remaining_time": "1 day, 7:43:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1110, "total_steps": 3093, "loss": 0.1293, "learning_rate": 7.42252145422199e-06, "epoch": 1.0766246362754608, "percentage": 35.89, "elapsed_time": "17:39:50", "remaining_time": "1 day, 7:33:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1120, "total_steps": 3093, "loss": 0.1244, "learning_rate": 7.376585624113438e-06, "epoch": 1.0863239573229875, "percentage": 36.21, "elapsed_time": "17:49:19", "remaining_time": "1 day, 7:23:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1130, "total_steps": 3093, "loss": 0.1264, "learning_rate": 7.330389174609516e-06, "epoch": 1.0960232783705142, "percentage": 36.53, "elapsed_time": "17:58:47", "remaining_time": "1 day, 7:14:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1140, "total_steps": 3093, "loss": 0.128, "learning_rate": 7.283937171671498e-06, "epoch": 1.1057225994180406, "percentage": 36.86, "elapsed_time": "18:08:16", "remaining_time": "1 day, 7:04:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1150, "total_steps": 3093, "loss": 0.1268, "learning_rate": 7.2372347092849744e-06, "epoch": 1.1154219204655673, "percentage": 37.18, "elapsed_time": "18:17:45", "remaining_time": "1 day, 6:54:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1160, "total_steps": 3093, "loss": 0.127, "learning_rate": 7.190286908901234e-06, "epoch": 1.125121241513094, "percentage": 37.5, "elapsed_time": "18:27:14", "remaining_time": "1 day, 6:45:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1170, "total_steps": 3093, "loss": 0.1239, "learning_rate": 7.143098918875643e-06, "epoch": 1.1348205625606207, "percentage": 37.83, "elapsed_time": "18:36:42", "remaining_time": "1 day, 6:35:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1180, "total_steps": 3093, "loss": 0.1252, "learning_rate": 7.095675913903067e-06, "epoch": 1.1445198836081474, "percentage": 38.15, "elapsed_time": "18:46:11", "remaining_time": "1 day, 6:25:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1190, "total_steps": 3093, "loss": 0.1255, "learning_rate": 7.048023094450412e-06, "epoch": 1.154219204655674, "percentage": 38.47, "elapsed_time": "18:55:40", "remaining_time": "1 day, 6:16:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1200, "total_steps": 3093, "loss": 0.125, "learning_rate": 7.0001456861863236e-06, "epoch": 1.1639185257032008, "percentage": 38.8, "elapsed_time": "19:05:08", "remaining_time": "1 day, 6:06:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1210, "total_steps": 3093, "loss": 0.126, "learning_rate": 6.952048939408156e-06, "epoch": 1.1736178467507274, "percentage": 39.12, "elapsed_time": "19:14:37", "remaining_time": "1 day, 5:56:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1220, "total_steps": 3093, "loss": 0.1244, "learning_rate": 6.903738128466189e-06, "epoch": 1.1833171677982541, "percentage": 39.44, "elapsed_time": "19:24:07", "remaining_time": "1 day, 5:47:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1230, "total_steps": 3093, "loss": 0.1257, "learning_rate": 6.8552185511852555e-06, "epoch": 1.1930164888457808, "percentage": 39.77, "elapsed_time": "19:33:36", "remaining_time": "1 day, 5:37:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1240, "total_steps": 3093, "loss": 0.1247, "learning_rate": 6.806495528283772e-06, "epoch": 1.2027158098933075, "percentage": 40.09, "elapsed_time": "19:43:04", "remaining_time": "1 day, 5:27:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 3093, "loss": 0.1266, "learning_rate": 6.75757440279026e-06, "epoch": 1.2124151309408342, "percentage": 40.41, "elapsed_time": "19:52:33", "remaining_time": "1 day, 5:18:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1260, "total_steps": 3093, "loss": 0.1259, "learning_rate": 6.708460539457418e-06, "epoch": 1.2221144519883609, "percentage": 40.74, "elapsed_time": "20:02:02", "remaining_time": "1 day, 5:08:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1270, "total_steps": 3093, "loss": 0.1264, "learning_rate": 6.659159324173823e-06, "epoch": 1.2318137730358876, "percentage": 41.06, "elapsed_time": "20:11:30", "remaining_time": "1 day, 4:59:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1280, "total_steps": 3093, "loss": 0.1212, "learning_rate": 6.6096761633733065e-06, "epoch": 1.2415130940834143, "percentage": 41.38, "elapsed_time": "20:20:59", "remaining_time": "1 day, 4:49:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1290, "total_steps": 3093, "loss": 0.1232, "learning_rate": 6.5600164834420754e-06, "epoch": 1.251212415130941, "percentage": 41.71, "elapsed_time": "20:30:27", "remaining_time": "1 day, 4:39:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1300, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.510185730123646e-06, "epoch": 1.2609117361784676, "percentage": 42.03, "elapsed_time": "20:39:56", "remaining_time": "1 day, 4:30:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1310, "total_steps": 3093, "loss": 0.1222, "learning_rate": 6.460189367921663e-06, "epoch": 1.270611057225994, "percentage": 42.35, "elapsed_time": "20:49:25", "remaining_time": "1 day, 4:20:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1320, "total_steps": 3093, "loss": 0.1237, "learning_rate": 6.410032879500647e-06, "epoch": 1.2803103782735208, "percentage": 42.68, "elapsed_time": "20:58:53", "remaining_time": "1 day, 4:10:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1330, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.35972176508477e-06, "epoch": 1.2900096993210475, "percentage": 43.0, "elapsed_time": "21:08:22", "remaining_time": "1 day, 4:01:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1340, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.309261541854679e-06, "epoch": 1.2997090203685742, "percentage": 43.32, "elapsed_time": "21:17:51", "remaining_time": "1 day, 3:51:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 3093, "loss": 0.1214, "learning_rate": 6.258657743342486e-06, "epoch": 1.3094083414161009, "percentage": 43.65, "elapsed_time": "21:27:19", "remaining_time": "1 day, 3:42:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1360, "total_steps": 3093, "loss": 0.1261, "learning_rate": 6.207915918824952e-06, "epoch": 1.3191076624636275, "percentage": 43.97, "elapsed_time": "21:36:48", "remaining_time": "1 day, 3:32:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1370, "total_steps": 3093, "loss": 0.1255, "learning_rate": 6.157041632714945e-06, "epoch": 1.3288069835111542, "percentage": 44.29, "elapsed_time": "21:46:17", "remaining_time": "1 day, 3:22:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1380, "total_steps": 3093, "loss": 0.1236, "learning_rate": 6.106040463951237e-06, "epoch": 1.338506304558681, "percentage": 44.62, "elapsed_time": "21:55:45", "remaining_time": "1 day, 3:13:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1390, "total_steps": 3093, "loss": 0.1198, "learning_rate": 6.0549180053867114e-06, "epoch": 1.3482056256062076, "percentage": 44.94, "elapsed_time": "22:05:14", "remaining_time": "1 day, 3:03:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1400, "total_steps": 3093, "loss": 0.1241, "learning_rate": 6.003679863175052e-06, "epoch": 1.3579049466537343, "percentage": 45.26, "elapsed_time": "22:14:43", "remaining_time": "1 day, 2:54:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1410, "total_steps": 3093, "loss": 0.1263, "learning_rate": 5.952331656155951e-06, "epoch": 1.367604267701261, "percentage": 45.59, "elapsed_time": "22:24:11", "remaining_time": "1 day, 2:44:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1420, "total_steps": 3093, "loss": 0.126, "learning_rate": 5.900879015238948e-06, "epoch": 1.3773035887487877, "percentage": 45.91, "elapsed_time": "22:33:40", "remaining_time": "1 day, 2:34:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1430, "total_steps": 3093, "loss": 0.1269, "learning_rate": 5.849327582785943e-06, "epoch": 1.3870029097963141, "percentage": 46.23, "elapsed_time": "22:43:09", "remaining_time": "1 day, 2:25:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1440, "total_steps": 3093, "loss": 0.1203, "learning_rate": 5.797683011992432e-06, "epoch": 1.3967022308438408, "percentage": 46.56, "elapsed_time": "22:52:38", "remaining_time": "1 day, 2:15:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1450, "total_steps": 3093, "loss": 0.1248, "learning_rate": 5.745950966267586e-06, "epoch": 1.4064015518913675, "percentage": 46.88, "elapsed_time": "23:02:07", "remaining_time": "1 day, 2:06:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1460, "total_steps": 3093, "loss": 0.1208, "learning_rate": 5.694137118613185e-06, "epoch": 1.4161008729388942, "percentage": 47.2, "elapsed_time": "23:11:36", "remaining_time": "1 day, 1:56:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1470, "total_steps": 3093, "loss": 0.1219, "learning_rate": 5.642247151001515e-06, "epoch": 1.4258001939864209, "percentage": 47.53, "elapsed_time": "23:21:05", "remaining_time": "1 day, 1:46:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1480, "total_steps": 3093, "loss": 0.1246, "learning_rate": 5.590286753752269e-06, "epoch": 1.4354995150339476, "percentage": 47.85, "elapsed_time": "23:30:33", "remaining_time": "1 day, 1:37:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1490, "total_steps": 3093, "loss": 0.1238, "learning_rate": 5.5382616249085476e-06, "epoch": 1.4451988360814743, "percentage": 48.17, "elapsed_time": "23:40:02", "remaining_time": "1 day, 1:27:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 3093, "loss": 0.1218, "learning_rate": 5.486177469611999e-06, "epoch": 1.454898157129001, "percentage": 48.5, "elapsed_time": "23:49:31", "remaining_time": "1 day, 1:18:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1510, "total_steps": 3093, "loss": 0.1217, "learning_rate": 5.434039999477182e-06, "epoch": 1.4645974781765276, "percentage": 48.82, "elapsed_time": "1 day, 0:03:06", "remaining_time": "1 day, 1:12:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1520, "total_steps": 3093, "loss": 0.1212, "learning_rate": 5.381854931965238e-06, "epoch": 1.4742967992240543, "percentage": 49.14, "elapsed_time": "1 day, 0:12:35", "remaining_time": "1 day, 1:03:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1530, "total_steps": 3093, "loss": 0.1221, "learning_rate": 5.32962798975689e-06, "epoch": 1.483996120271581, "percentage": 49.47, "elapsed_time": "1 day, 0:22:03", "remaining_time": "1 day, 0:53:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1540, "total_steps": 3093, "loss": 0.1201, "learning_rate": 5.2773649001248965e-06, "epoch": 1.4936954413191077, "percentage": 49.79, "elapsed_time": "1 day, 0:31:32", "remaining_time": "1 day, 0:43:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1550, "total_steps": 3093, "loss": 0.1222, "learning_rate": 5.2250713943059826e-06, "epoch": 1.5033947623666344, "percentage": 50.11, "elapsed_time": "1 day, 0:41:01", "remaining_time": "1 day, 0:34:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1560, "total_steps": 3093, "loss": 0.1209, "learning_rate": 5.172753206872363e-06, "epoch": 1.513094083414161, "percentage": 50.44, "elapsed_time": "1 day, 0:50:30", "remaining_time": "1 day, 0:24:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1570, "total_steps": 3093, "loss": 0.1257, "learning_rate": 5.120416075102855e-06, "epoch": 1.5227934044616878, "percentage": 50.76, "elapsed_time": "1 day, 0:59:58", "remaining_time": "1 day, 0:15:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1580, "total_steps": 3093, "loss": 0.124, "learning_rate": 5.068065738353748e-06, "epoch": 1.5324927255092144, "percentage": 51.08, "elapsed_time": "1 day, 1:09:27", "remaining_time": "1 day, 0:05:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1590, "total_steps": 3093, "loss": 0.1192, "learning_rate": 5.015707937429398e-06, "epoch": 1.5421920465567411, "percentage": 51.41, "elapsed_time": "1 day, 1:18:56", "remaining_time": "23:55:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1600, "total_steps": 3093, "loss": 0.1225, "learning_rate": 4.9633484139526975e-06, "epoch": 1.5518913676042678, "percentage": 51.73, "elapsed_time": "1 day, 1:28:24", "remaining_time": "23:46:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1610, "total_steps": 3093, "loss": 0.1201, "learning_rate": 4.910992909735432e-06, "epoch": 1.5615906886517945, "percentage": 52.05, "elapsed_time": "1 day, 1:37:53", "remaining_time": "23:36:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1620, "total_steps": 3093, "loss": 0.1227, "learning_rate": 4.8586471661486345e-06, "epoch": 1.5712900096993212, "percentage": 52.38, "elapsed_time": "1 day, 1:47:22", "remaining_time": "23:26:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1630, "total_steps": 3093, "loss": 0.1232, "learning_rate": 4.80631692349297e-06, "epoch": 1.5809893307468477, "percentage": 52.7, "elapsed_time": "1 day, 1:56:51", "remaining_time": "23:17:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1640, "total_steps": 3093, "loss": 0.1213, "learning_rate": 4.754007920369252e-06, "epoch": 1.5906886517943744, "percentage": 53.02, "elapsed_time": "1 day, 2:06:19", "remaining_time": "23:07:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1650, "total_steps": 3093, "loss": 0.1194, "learning_rate": 4.7017258930491474e-06, "epoch": 1.600387972841901, "percentage": 53.35, "elapsed_time": "1 day, 2:15:48", "remaining_time": "22:58:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1660, "total_steps": 3093, "loss": 0.1206, "learning_rate": 4.649476574846113e-06, "epoch": 1.6100872938894277, "percentage": 53.67, "elapsed_time": "1 day, 2:25:17", "remaining_time": "22:48:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1670, "total_steps": 3093, "loss": 0.122, "learning_rate": 4.597265695486685e-06, "epoch": 1.6197866149369544, "percentage": 53.99, "elapsed_time": "1 day, 2:34:45", "remaining_time": "22:38:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1680, "total_steps": 3093, "loss": 0.1217, "learning_rate": 4.545098980482151e-06, "epoch": 1.629485935984481, "percentage": 54.32, "elapsed_time": "1 day, 2:44:14", "remaining_time": "22:29:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1690, "total_steps": 3093, "loss": 0.1222, "learning_rate": 4.492982150500677e-06, "epoch": 1.6391852570320078, "percentage": 54.64, "elapsed_time": "1 day, 2:53:43", "remaining_time": "22:19:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1700, "total_steps": 3093, "loss": 0.1203, "learning_rate": 4.44092092073997e-06, "epoch": 1.6488845780795345, "percentage": 54.96, "elapsed_time": "1 day, 3:03:12", "remaining_time": "22:10:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1710, "total_steps": 3093, "loss": 0.1195, "learning_rate": 4.388921000300553e-06, "epoch": 1.658583899127061, "percentage": 55.29, "elapsed_time": "1 day, 3:12:40", "remaining_time": "22:00:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1720, "total_steps": 3093, "loss": 0.1179, "learning_rate": 4.336988091559688e-06, "epoch": 1.6682832201745876, "percentage": 55.61, "elapsed_time": "1 day, 3:22:09", "remaining_time": "21:50:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1730, "total_steps": 3093, "loss": 0.1214, "learning_rate": 4.285127889546049e-06, "epoch": 1.6779825412221143, "percentage": 55.93, "elapsed_time": "1 day, 3:31:38", "remaining_time": "21:41:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1740, "total_steps": 3093, "loss": 0.1197, "learning_rate": 4.233346081315197e-06, "epoch": 1.687681862269641, "percentage": 56.26, "elapsed_time": "1 day, 3:41:07", "remaining_time": "21:31:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1750, "total_steps": 3093, "loss": 0.1173, "learning_rate": 4.181648345325934e-06, "epoch": 1.6973811833171677, "percentage": 56.58, "elapsed_time": "1 day, 3:50:36", "remaining_time": "21:22:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1760, "total_steps": 3093, "loss": 0.1177, "learning_rate": 4.13004035081759e-06, "epoch": 1.7070805043646944, "percentage": 56.9, "elapsed_time": "1 day, 4:00:04", "remaining_time": "21:12:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1770, "total_steps": 3093, "loss": 0.1193, "learning_rate": 4.078527757188333e-06, "epoch": 1.716779825412221, "percentage": 57.23, "elapsed_time": "1 day, 4:09:33", "remaining_time": "21:02:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1780, "total_steps": 3093, "loss": 0.1237, "learning_rate": 4.02711621337455e-06, "epoch": 1.7264791464597478, "percentage": 57.55, "elapsed_time": "1 day, 4:19:03", "remaining_time": "20:53:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1790, "total_steps": 3093, "loss": 0.1189, "learning_rate": 3.9758113572313735e-06, "epoch": 1.7361784675072744, "percentage": 57.87, "elapsed_time": "1 day, 4:28:32", "remaining_time": "20:43:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1800, "total_steps": 3093, "loss": 0.119, "learning_rate": 3.924618814914435e-06, "epoch": 1.7458777885548011, "percentage": 58.2, "elapsed_time": "1 day, 4:38:00", "remaining_time": "20:34:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1810, "total_steps": 3093, "loss": 0.1202, "learning_rate": 3.873544200262882e-06, "epoch": 1.7555771096023278, "percentage": 58.52, "elapsed_time": "1 day, 4:47:29", "remaining_time": "20:24:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1820, "total_steps": 3093, "loss": 0.1203, "learning_rate": 3.822593114183777e-06, "epoch": 1.7652764306498545, "percentage": 58.84, "elapsed_time": "1 day, 4:56:58", "remaining_time": "20:14:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1830, "total_steps": 3093, "loss": 0.1197, "learning_rate": 3.7717711440378695e-06, "epoch": 1.7749757516973812, "percentage": 59.17, "elapsed_time": "1 day, 5:06:27", "remaining_time": "20:05:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1840, "total_steps": 3093, "loss": 0.1185, "learning_rate": 3.7210838630268986e-06, "epoch": 1.7846750727449079, "percentage": 59.49, "elapsed_time": "1 day, 5:15:55", "remaining_time": "19:55:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1850, "total_steps": 3093, "loss": 0.1191, "learning_rate": 3.670536829582424e-06, "epoch": 1.7943743937924346, "percentage": 59.81, "elapsed_time": "1 day, 5:25:24", "remaining_time": "19:46:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1860, "total_steps": 3093, "loss": 0.1191, "learning_rate": 3.6201355867562725e-06, "epoch": 1.8040737148399613, "percentage": 60.14, "elapsed_time": "1 day, 5:34:53", "remaining_time": "19:36:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1870, "total_steps": 3093, "loss": 0.1195, "learning_rate": 3.569885661612691e-06, "epoch": 1.813773035887488, "percentage": 60.46, "elapsed_time": "1 day, 5:44:22", "remaining_time": "19:26:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1880, "total_steps": 3093, "loss": 0.1204, "learning_rate": 3.5197925646222387e-06, "epoch": 1.8234723569350146, "percentage": 60.78, "elapsed_time": "1 day, 5:53:51", "remaining_time": "19:17:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1890, "total_steps": 3093, "loss": 0.1187, "learning_rate": 3.4698617890574972e-06, "epoch": 1.8331716779825413, "percentage": 61.11, "elapsed_time": "1 day, 6:03:19", "remaining_time": "19:07:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1900, "total_steps": 3093, "loss": 0.1181, "learning_rate": 3.4200988103906747e-06, "epoch": 1.842870999030068, "percentage": 61.43, "elapsed_time": "1 day, 6:12:48", "remaining_time": "18:58:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1910, "total_steps": 3093, "loss": 0.1189, "learning_rate": 3.3705090856931626e-06, "epoch": 1.8525703200775947, "percentage": 61.75, "elapsed_time": "1 day, 6:22:17", "remaining_time": "18:48:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1920, "total_steps": 3093, "loss": 0.1163, "learning_rate": 3.3210980530370974e-06, "epoch": 1.8622696411251214, "percentage": 62.08, "elapsed_time": "1 day, 6:31:46", "remaining_time": "18:39:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1930, "total_steps": 3093, "loss": 0.1173, "learning_rate": 3.2718711308990226e-06, "epoch": 1.871968962172648, "percentage": 62.4, "elapsed_time": "1 day, 6:41:15", "remaining_time": "18:29:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1940, "total_steps": 3093, "loss": 0.1175, "learning_rate": 3.2228337175656856e-06, "epoch": 1.8816682832201745, "percentage": 62.72, "elapsed_time": "1 day, 6:50:43", "remaining_time": "18:19:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1950, "total_steps": 3093, "loss": 0.1157, "learning_rate": 3.1739911905420617e-06, "epoch": 1.8913676042677012, "percentage": 63.05, "elapsed_time": "1 day, 7:00:12", "remaining_time": "18:10:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1960, "total_steps": 3093, "loss": 0.1206, "learning_rate": 3.1253489059616448e-06, "epoch": 1.901066925315228, "percentage": 63.37, "elapsed_time": "1 day, 7:09:41", "remaining_time": "18:00:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1970, "total_steps": 3093, "loss": 0.1176, "learning_rate": 3.0769121979990845e-06, "epoch": 1.9107662463627546, "percentage": 63.69, "elapsed_time": "1 day, 7:19:09", "remaining_time": "17:51:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1980, "total_steps": 3093, "loss": 0.1188, "learning_rate": 3.028686378285245e-06, "epoch": 1.9204655674102813, "percentage": 64.02, "elapsed_time": "1 day, 7:28:38", "remaining_time": "17:41:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1990, "total_steps": 3093, "loss": 0.1199, "learning_rate": 2.9806767353247127e-06, "epoch": 1.930164888457808, "percentage": 64.34, "elapsed_time": "1 day, 7:38:07", "remaining_time": "17:32:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2000, "total_steps": 3093, "loss": 0.118, "learning_rate": 2.9328885339158554e-06, "epoch": 1.9398642095053347, "percentage": 64.66, "elapsed_time": "1 day, 7:47:36", "remaining_time": "17:22:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2010, "total_steps": 3093, "loss": 0.1185, "learning_rate": 2.8853270145734846e-06, "epoch": 1.9495635305528611, "percentage": 64.99, "elapsed_time": "1 day, 8:01:25", "remaining_time": "17:15:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2020, "total_steps": 3093, "loss": 0.116, "learning_rate": 2.837997392954165e-06, "epoch": 1.9592628516003878, "percentage": 65.31, "elapsed_time": "1 day, 8:10:54", "remaining_time": "17:05:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2030, "total_steps": 3093, "loss": 0.1152, "learning_rate": 2.7909048592842602e-06, "epoch": 1.9689621726479145, "percentage": 65.63, "elapsed_time": "1 day, 8:20:23", "remaining_time": "16:56:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2040, "total_steps": 3093, "loss": 0.1159, "learning_rate": 2.7440545777907747e-06, "epoch": 1.9786614936954412, "percentage": 65.96, "elapsed_time": "1 day, 8:29:51", "remaining_time": "16:46:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2050, "total_steps": 3093, "loss": 0.1186, "learning_rate": 2.697451686135031e-06, "epoch": 1.9883608147429679, "percentage": 66.28, "elapsed_time": "1 day, 8:39:21", "remaining_time": "16:36:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2060, "total_steps": 3093, "loss": 0.1172, "learning_rate": 2.6511012948492625e-06, "epoch": 1.9980601357904946, "percentage": 66.6, "elapsed_time": "1 day, 8:48:49", "remaining_time": "16:27:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2070, "total_steps": 3093, "loss": 0.1045, "learning_rate": 2.6050084867761953e-06, "epoch": 2.0077594568380213, "percentage": 66.93, "elapsed_time": "1 day, 8:58:25", "remaining_time": "16:17:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2080, "total_steps": 3093, "loss": 0.105, "learning_rate": 2.5591783165116563e-06, "epoch": 2.017458777885548, "percentage": 67.25, "elapsed_time": "1 day, 9:07:54", "remaining_time": "16:08:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2090, "total_steps": 3093, "loss": 0.1038, "learning_rate": 2.51361580985027e-06, "epoch": 2.0271580989330746, "percentage": 67.57, "elapsed_time": "1 day, 9:17:23", "remaining_time": "15:58:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2100, "total_steps": 3093, "loss": 0.101, "learning_rate": 2.4683259632343363e-06, "epoch": 2.0368574199806013, "percentage": 67.9, "elapsed_time": "1 day, 9:26:52", "remaining_time": "15:48:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2110, "total_steps": 3093, "loss": 0.1023, "learning_rate": 2.42331374320591e-06, "epoch": 2.046556741028128, "percentage": 68.22, "elapsed_time": "1 day, 9:36:20", "remaining_time": "15:39:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2120, "total_steps": 3093, "loss": 0.1038, "learning_rate": 2.3785840858621556e-06, "epoch": 2.0562560620756547, "percentage": 68.54, "elapsed_time": "1 day, 9:45:49", "remaining_time": "15:29:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2130, "total_steps": 3093, "loss": 0.1015, "learning_rate": 2.334141896314057e-06, "epoch": 2.0659553831231814, "percentage": 68.87, "elapsed_time": "1 day, 9:55:18", "remaining_time": "15:20:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2140, "total_steps": 3093, "loss": 0.1006, "learning_rate": 2.2899920481485192e-06, "epoch": 2.075654704170708, "percentage": 69.19, "elapsed_time": "1 day, 10:04:47", "remaining_time": "15:10:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2150, "total_steps": 3093, "loss": 0.103, "learning_rate": 2.246139382893915e-06, "epoch": 2.0853540252182348, "percentage": 69.51, "elapsed_time": "1 day, 10:14:15", "remaining_time": "15:01:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2160, "total_steps": 3093, "loss": 0.1021, "learning_rate": 2.2025887094891657e-06, "epoch": 2.0950533462657615, "percentage": 69.84, "elapsed_time": "1 day, 10:23:44", "remaining_time": "14:51:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2170, "total_steps": 3093, "loss": 0.1012, "learning_rate": 2.1593448037563795e-06, "epoch": 2.104752667313288, "percentage": 70.16, "elapsed_time": "1 day, 10:33:13", "remaining_time": "14:41:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2180, "total_steps": 3093, "loss": 0.0989, "learning_rate": 2.116412407877138e-06, "epoch": 2.114451988360815, "percentage": 70.48, "elapsed_time": "1 day, 10:42:42", "remaining_time": "14:32:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2190, "total_steps": 3093, "loss": 0.1028, "learning_rate": 2.0737962298724513e-06, "epoch": 2.1241513094083415, "percentage": 70.81, "elapsed_time": "1 day, 10:52:11", "remaining_time": "14:22:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2200, "total_steps": 3093, "loss": 0.0981, "learning_rate": 2.0315009430864762e-06, "epoch": 2.133850630455868, "percentage": 71.13, "elapsed_time": "1 day, 11:01:39", "remaining_time": "14:13:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2210, "total_steps": 3093, "loss": 0.1006, "learning_rate": 1.989531185674037e-06, "epoch": 2.143549951503395, "percentage": 71.45, "elapsed_time": "1 day, 11:11:08", "remaining_time": "14:03:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2220, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.9478915600919877e-06, "epoch": 2.1532492725509216, "percentage": 71.77, "elapsed_time": "1 day, 11:20:37", "remaining_time": "13:53:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2230, "total_steps": 3093, "loss": 0.1006, "learning_rate": 1.9065866325945099e-06, "epoch": 2.1629485935984483, "percentage": 72.1, "elapsed_time": "1 day, 11:30:05", "remaining_time": "13:44:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2240, "total_steps": 3093, "loss": 0.1032, "learning_rate": 1.8656209327323704e-06, "epoch": 2.172647914645975, "percentage": 72.42, "elapsed_time": "1 day, 11:39:34", "remaining_time": "13:34:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2250, "total_steps": 3093, "loss": 0.0995, "learning_rate": 1.824998952856198e-06, "epoch": 2.1823472356935016, "percentage": 72.74, "elapsed_time": "1 day, 11:49:03", "remaining_time": "13:25:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2260, "total_steps": 3093, "loss": 0.1014, "learning_rate": 1.784725147623853e-06, "epoch": 2.1920465567410283, "percentage": 73.07, "elapsed_time": "1 day, 11:58:32", "remaining_time": "13:15:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2270, "total_steps": 3093, "loss": 0.1002, "learning_rate": 1.7448039335119272e-06, "epoch": 2.2017458777885546, "percentage": 73.39, "elapsed_time": "1 day, 12:08:01", "remaining_time": "13:06:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2280, "total_steps": 3093, "loss": 0.1007, "learning_rate": 1.7052396883314154e-06, "epoch": 2.2114451988360813, "percentage": 73.71, "elapsed_time": "1 day, 12:17:29", "remaining_time": "12:56:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2290, "total_steps": 3093, "loss": 0.1032, "learning_rate": 1.6660367507476539e-06, "epoch": 2.221144519883608, "percentage": 74.04, "elapsed_time": "1 day, 12:26:58", "remaining_time": "12:46:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2300, "total_steps": 3093, "loss": 0.0974, "learning_rate": 1.627199419804522e-06, "epoch": 2.2308438409311346, "percentage": 74.36, "elapsed_time": "1 day, 12:36:27", "remaining_time": "12:37:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2310, "total_steps": 3093, "loss": 0.0993, "learning_rate": 1.5887319544530182e-06, "epoch": 2.2405431619786613, "percentage": 74.68, "elapsed_time": "1 day, 12:45:56", "remaining_time": "12:27:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2320, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.5506385730842062e-06, "epoch": 2.250242483026188, "percentage": 75.01, "elapsed_time": "1 day, 12:55:25", "remaining_time": "12:18:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2330, "total_steps": 3093, "loss": 0.0996, "learning_rate": 1.5129234530666232e-06, "epoch": 2.2599418040737147, "percentage": 75.33, "elapsed_time": "1 day, 13:04:54", "remaining_time": "12:08:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2340, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.4755907302881927e-06, "epoch": 2.2696411251212414, "percentage": 75.65, "elapsed_time": "1 day, 13:14:23", "remaining_time": "11:59:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2350, "total_steps": 3093, "loss": 0.1008, "learning_rate": 1.4386444987026705e-06, "epoch": 2.279340446168768, "percentage": 75.98, "elapsed_time": "1 day, 13:23:52", "remaining_time": "11:49:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2360, "total_steps": 3093, "loss": 0.1012, "learning_rate": 1.4020888098806924e-06, "epoch": 2.2890397672162948, "percentage": 76.3, "elapsed_time": "1 day, 13:33:21", "remaining_time": "11:39:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2370, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.3659276725654863e-06, "epoch": 2.2987390882638215, "percentage": 76.62, "elapsed_time": "1 day, 13:42:51", "remaining_time": "11:30:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2380, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.3301650522332566e-06, "epoch": 2.308438409311348, "percentage": 76.95, "elapsed_time": "1 day, 13:52:20", "remaining_time": "11:20:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2390, "total_steps": 3093, "loss": 0.1011, "learning_rate": 1.2948048706583284e-06, "epoch": 2.318137730358875, "percentage": 77.27, "elapsed_time": "1 day, 14:01:49", "remaining_time": "11:11:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2400, "total_steps": 3093, "loss": 0.1026, "learning_rate": 1.2598510054830888e-06, "epoch": 2.3278370514064015, "percentage": 77.59, "elapsed_time": "1 day, 14:11:17", "remaining_time": "11:01:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2410, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.2253072897927437e-06, "epoch": 2.337536372453928, "percentage": 77.92, "elapsed_time": "1 day, 14:20:46", "remaining_time": "10:52:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2420, "total_steps": 3093, "loss": 0.1026, "learning_rate": 1.1911775116949958e-06, "epoch": 2.347235693501455, "percentage": 78.24, "elapsed_time": "1 day, 14:30:15", "remaining_time": "10:42:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2430, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.1574654139046171e-06, "epoch": 2.3569350145489816, "percentage": 78.56, "elapsed_time": "1 day, 14:39:44", "remaining_time": "10:32:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2440, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.1241746933330338e-06, "epoch": 2.3666343355965083, "percentage": 78.89, "elapsed_time": "1 day, 14:49:12", "remaining_time": "10:23:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2450, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.0913090006829085e-06, "epoch": 2.376333656644035, "percentage": 79.21, "elapsed_time": "1 day, 14:58:41", "remaining_time": "10:13:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2460, "total_steps": 3093, "loss": 0.0977, "learning_rate": 1.0588719400478004e-06, "epoch": 2.3860329776915616, "percentage": 79.53, "elapsed_time": "1 day, 15:08:10", "remaining_time": "10:04:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2470, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.026867068516943e-06, "epoch": 2.3957322987390883, "percentage": 79.86, "elapsed_time": "1 day, 15:17:39", "remaining_time": "9:54:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2480, "total_steps": 3093, "loss": 0.098, "learning_rate": 9.952978957851622e-07, "epoch": 2.405431619786615, "percentage": 80.18, "elapsed_time": "1 day, 15:27:08", "remaining_time": "9:45:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2490, "total_steps": 3093, "loss": 0.1, "learning_rate": 9.641678837679985e-07, "epoch": 2.4151309408341417, "percentage": 80.5, "elapsed_time": "1 day, 15:36:36", "remaining_time": "9:35:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2500, "total_steps": 3093, "loss": 0.0968, "learning_rate": 9.334804462220748e-07, "epoch": 2.4248302618816684, "percentage": 80.83, "elapsed_time": "1 day, 15:46:05", "remaining_time": "9:25:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2510, "total_steps": 3093, "loss": 0.0985, "learning_rate": 9.032389483707332e-07, "epoch": 2.434529582929195, "percentage": 81.15, "elapsed_time": "1 day, 15:59:28", "remaining_time": "9:17:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2520, "total_steps": 3093, "loss": 0.1011, "learning_rate": 8.734467065350022e-07, "epoch": 2.4442289039767218, "percentage": 81.47, "elapsed_time": "1 day, 16:08:57", "remaining_time": "9:07:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2530, "total_steps": 3093, "loss": 0.0988, "learning_rate": 8.441069877699287e-07, "epoch": 2.4539282250242485, "percentage": 81.8, "elapsed_time": "1 day, 16:18:25", "remaining_time": "8:58:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2540, "total_steps": 3093, "loss": 0.1002, "learning_rate": 8.152230095063051e-07, "epoch": 2.463627546071775, "percentage": 82.12, "elapsed_time": "1 day, 16:27:54", "remaining_time": "8:48:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2550, "total_steps": 3093, "loss": 0.1007, "learning_rate": 7.867979391978398e-07, "epoch": 2.473326867119302, "percentage": 82.44, "elapsed_time": "1 day, 16:37:23", "remaining_time": "8:39:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2560, "total_steps": 3093, "loss": 0.0986, "learning_rate": 7.588348939738116e-07, "epoch": 2.4830261881668285, "percentage": 82.77, "elapsed_time": "1 day, 16:46:51", "remaining_time": "8:29:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2570, "total_steps": 3093, "loss": 0.0992, "learning_rate": 7.31336940297247e-07, "epoch": 2.492725509214355, "percentage": 83.09, "elapsed_time": "1 day, 16:56:21", "remaining_time": "8:19:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2580, "total_steps": 3093, "loss": 0.0978, "learning_rate": 7.043070936286395e-07, "epoch": 2.502424830261882, "percentage": 83.41, "elapsed_time": "1 day, 17:05:49", "remaining_time": "8:10:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2590, "total_steps": 3093, "loss": 0.1012, "learning_rate": 6.777483180952732e-07, "epoch": 2.5121241513094086, "percentage": 83.74, "elapsed_time": "1 day, 17:15:18", "remaining_time": "8:00:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2600, "total_steps": 3093, "loss": 0.0974, "learning_rate": 6.516635261661775e-07, "epoch": 2.5218234723569353, "percentage": 84.06, "elapsed_time": "1 day, 17:24:47", "remaining_time": "7:51:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2610, "total_steps": 3093, "loss": 0.0966, "learning_rate": 6.260555783327366e-07, "epoch": 2.531522793404462, "percentage": 84.38, "elapsed_time": "1 day, 17:34:16", "remaining_time": "7:41:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2620, "total_steps": 3093, "loss": 0.0999, "learning_rate": 6.009272827950042e-07, "epoch": 2.541222114451988, "percentage": 84.71, "elapsed_time": "1 day, 17:43:45", "remaining_time": "7:32:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2630, "total_steps": 3093, "loss": 0.101, "learning_rate": 5.762813951537582e-07, "epoch": 2.550921435499515, "percentage": 85.03, "elapsed_time": "1 day, 17:53:15", "remaining_time": "7:22:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2640, "total_steps": 3093, "loss": 0.0978, "learning_rate": 5.521206181083111e-07, "epoch": 2.5606207565470416, "percentage": 85.35, "elapsed_time": "1 day, 18:02:44", "remaining_time": "7:12:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2650, "total_steps": 3093, "loss": 0.0965, "learning_rate": 5.28447601160132e-07, "epoch": 2.5703200775945683, "percentage": 85.68, "elapsed_time": "1 day, 18:12:13", "remaining_time": "7:03:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2660, "total_steps": 3093, "loss": 0.0976, "learning_rate": 5.052649403223015e-07, "epoch": 2.580019398642095, "percentage": 86.0, "elapsed_time": "1 day, 18:21:42", "remaining_time": "6:53:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2670, "total_steps": 3093, "loss": 0.0981, "learning_rate": 4.825751778348259e-07, "epoch": 2.5897187196896216, "percentage": 86.32, "elapsed_time": "1 day, 18:31:11", "remaining_time": "6:44:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2680, "total_steps": 3093, "loss": 0.0992, "learning_rate": 4.6038080188585135e-07, "epoch": 2.5994180407371483, "percentage": 86.65, "elapsed_time": "1 day, 18:40:40", "remaining_time": "6:34:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2690, "total_steps": 3093, "loss": 0.0987, "learning_rate": 4.38684246338808e-07, "epoch": 2.609117361784675, "percentage": 86.97, "elapsed_time": "1 day, 18:50:09", "remaining_time": "6:25:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2700, "total_steps": 3093, "loss": 0.0978, "learning_rate": 4.1748789046551055e-07, "epoch": 2.6188166828322017, "percentage": 87.29, "elapsed_time": "1 day, 18:59:38", "remaining_time": "6:15:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2710, "total_steps": 3093, "loss": 0.0976, "learning_rate": 3.967940586852409e-07, "epoch": 2.6285160038797284, "percentage": 87.62, "elapsed_time": "1 day, 19:09:07", "remaining_time": "6:05:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2720, "total_steps": 3093, "loss": 0.0988, "learning_rate": 3.7660502030985203e-07, "epoch": 2.638215324927255, "percentage": 87.94, "elapsed_time": "1 day, 19:18:35", "remaining_time": "5:56:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2730, "total_steps": 3093, "loss": 0.0999, "learning_rate": 3.569229892949133e-07, "epoch": 2.6479146459747818, "percentage": 88.26, "elapsed_time": "1 day, 19:28:04", "remaining_time": "5:46:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2740, "total_steps": 3093, "loss": 0.0989, "learning_rate": 3.3775012399692055e-07, "epoch": 2.6576139670223085, "percentage": 88.59, "elapsed_time": "1 day, 19:37:33", "remaining_time": "5:37:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2750, "total_steps": 3093, "loss": 0.0994, "learning_rate": 3.1908852693661116e-07, "epoch": 2.667313288069835, "percentage": 88.91, "elapsed_time": "1 day, 19:47:02", "remaining_time": "5:27:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2760, "total_steps": 3093, "loss": 0.0987, "learning_rate": 3.0094024456840176e-07, "epoch": 2.677012609117362, "percentage": 89.23, "elapsed_time": "1 day, 19:56:31", "remaining_time": "5:18:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2770, "total_steps": 3093, "loss": 0.0981, "learning_rate": 2.833072670559661e-07, "epoch": 2.6867119301648885, "percentage": 89.56, "elapsed_time": "1 day, 20:06:00", "remaining_time": "5:08:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2780, "total_steps": 3093, "loss": 0.098, "learning_rate": 2.6619152805399286e-07, "epoch": 2.696411251212415, "percentage": 89.88, "elapsed_time": "1 day, 20:15:28", "remaining_time": "4:58:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2790, "total_steps": 3093, "loss": 0.0972, "learning_rate": 2.49594904496141e-07, "epoch": 2.706110572259942, "percentage": 90.2, "elapsed_time": "1 day, 20:24:57", "remaining_time": "4:49:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2800, "total_steps": 3093, "loss": 0.0986, "learning_rate": 2.3351921638921193e-07, "epoch": 2.7158098933074686, "percentage": 90.53, "elapsed_time": "1 day, 20:34:26", "remaining_time": "4:39:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2810, "total_steps": 3093, "loss": 0.1005, "learning_rate": 2.1796622661356238e-07, "epoch": 2.7255092143549953, "percentage": 90.85, "elapsed_time": "1 day, 20:43:54", "remaining_time": "4:30:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2820, "total_steps": 3093, "loss": 0.1017, "learning_rate": 2.0293764072978618e-07, "epoch": 2.735208535402522, "percentage": 91.17, "elapsed_time": "1 day, 20:53:23", "remaining_time": "4:20:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2830, "total_steps": 3093, "loss": 0.0969, "learning_rate": 1.8843510679168341e-07, "epoch": 2.7449078564500486, "percentage": 91.5, "elapsed_time": "1 day, 21:02:52", "remaining_time": "4:11:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2840, "total_steps": 3093, "loss": 0.0967, "learning_rate": 1.744602151655289e-07, "epoch": 2.7546071774975753, "percentage": 91.82, "elapsed_time": "1 day, 21:12:21", "remaining_time": "4:01:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2850, "total_steps": 3093, "loss": 0.097, "learning_rate": 1.6101449835567273e-07, "epoch": 2.7643064985451016, "percentage": 92.14, "elapsed_time": "1 day, 21:21:50", "remaining_time": "3:52:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2860, "total_steps": 3093, "loss": 0.0966, "learning_rate": 1.4809943083648194e-07, "epoch": 2.7740058195926283, "percentage": 92.47, "elapsed_time": "1 day, 21:31:19", "remaining_time": "3:42:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2870, "total_steps": 3093, "loss": 0.0965, "learning_rate": 1.3571642889064984e-07, "epoch": 2.783705140640155, "percentage": 92.79, "elapsed_time": "1 day, 21:40:48", "remaining_time": "3:32:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2880, "total_steps": 3093, "loss": 0.0934, "learning_rate": 1.2386685045388313e-07, "epoch": 2.7934044616876816, "percentage": 93.11, "elapsed_time": "1 day, 21:50:17", "remaining_time": "3:23:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2890, "total_steps": 3093, "loss": 0.1002, "learning_rate": 1.1255199496599034e-07, "epoch": 2.8031037827352083, "percentage": 93.44, "elapsed_time": "1 day, 21:59:46", "remaining_time": "3:13:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2900, "total_steps": 3093, "loss": 0.0984, "learning_rate": 1.0177310322838251e-07, "epoch": 2.812803103782735, "percentage": 93.76, "elapsed_time": "1 day, 22:09:14", "remaining_time": "3:04:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2910, "total_steps": 3093, "loss": 0.0991, "learning_rate": 9.153135726800599e-08, "epoch": 2.8225024248302617, "percentage": 94.08, "elapsed_time": "1 day, 22:18:44", "remaining_time": "2:54:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2920, "total_steps": 3093, "loss": 0.0995, "learning_rate": 8.182788020771826e-08, "epoch": 2.8322017458777884, "percentage": 94.41, "elapsed_time": "1 day, 22:28:14", "remaining_time": "2:45:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2930, "total_steps": 3093, "loss": 0.0997, "learning_rate": 7.266373614312927e-08, "epoch": 2.841901066925315, "percentage": 94.73, "elapsed_time": "1 day, 22:37:43", "remaining_time": "2:35:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2940, "total_steps": 3093, "loss": 0.099, "learning_rate": 6.403993002590425e-08, "epoch": 2.8516003879728418, "percentage": 95.05, "elapsed_time": "1 day, 22:47:13", "remaining_time": "2:26:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2950, "total_steps": 3093, "loss": 0.0961, "learning_rate": 5.595740755356627e-08, "epoch": 2.8612997090203685, "percentage": 95.38, "elapsed_time": "1 day, 22:56:42", "remaining_time": "2:16:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2960, "total_steps": 3093, "loss": 0.0984, "learning_rate": 4.841705506578587e-08, "epoch": 2.870999030067895, "percentage": 95.7, "elapsed_time": "1 day, 23:06:11", "remaining_time": "2:06:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2970, "total_steps": 3093, "loss": 0.0995, "learning_rate": 4.1419699447186045e-08, "epoch": 2.880698351115422, "percentage": 96.02, "elapsed_time": "1 day, 23:15:40", "remaining_time": "1:57:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2980, "total_steps": 3093, "loss": 0.0987, "learning_rate": 3.4966108036662006e-08, "epoch": 2.8903976721629485, "percentage": 96.35, "elapsed_time": "1 day, 23:25:09", "remaining_time": "1:47:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2990, "total_steps": 3093, "loss": 0.1002, "learning_rate": 2.9056988543239018e-08, "epoch": 2.900096993210475, "percentage": 96.67, "elapsed_time": "1 day, 23:34:38", "remaining_time": "1:38:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3000, "total_steps": 3093, "loss": 0.0966, "learning_rate": 2.3692988968458398e-08, "epoch": 2.909796314258002, "percentage": 96.99, "elapsed_time": "1 day, 23:44:06", "remaining_time": "1:28:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3010, "total_steps": 3093, "loss": 0.0965, "learning_rate": 1.8874697535319897e-08, "epoch": 2.9194956353055286, "percentage": 97.32, "elapsed_time": "1 day, 23:57:20", "remaining_time": "1:19:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3020, "total_steps": 3093, "loss": 0.0992, "learning_rate": 1.4602642623777752e-08, "epoch": 2.9291949563530553, "percentage": 97.64, "elapsed_time": "2 days, 0:06:49", "remaining_time": "1:09:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3030, "total_steps": 3093, "loss": 0.0954, "learning_rate": 1.0877292712792586e-08, "epoch": 2.938894277400582, "percentage": 97.96, "elapsed_time": "2 days, 0:16:18", "remaining_time": "1:00:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3040, "total_steps": 3093, "loss": 0.0985, "learning_rate": 7.699056328964726e-09, "epoch": 2.9485935984481086, "percentage": 98.29, "elapsed_time": "2 days, 0:25:47", "remaining_time": "0:50:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3050, "total_steps": 3093, "loss": 0.1001, "learning_rate": 5.06828200172893e-09, "epoch": 2.9582929194956353, "percentage": 98.61, "elapsed_time": "2 days, 0:35:15", "remaining_time": "0:41:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3060, "total_steps": 3093, "loss": 0.0979, "learning_rate": 2.9852582251355124e-09, "epoch": 2.967992240543162, "percentage": 98.93, "elapsed_time": "2 days, 0:44:44", "remaining_time": "0:31:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3070, "total_steps": 3093, "loss": 0.0973, "learning_rate": 1.4502134262156519e-09, "epoch": 2.9776915615906887, "percentage": 99.26, "elapsed_time": "2 days, 0:54:13", "remaining_time": "0:21:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3080, "total_steps": 3093, "loss": 0.0973, "learning_rate": 4.6331593993032e-10, "epoch": 2.9873908826382154, "percentage": 99.58, "elapsed_time": "2 days, 1:03:41", "remaining_time": "0:12:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3090, "total_steps": 3093, "loss": 0.0964, "learning_rate": 2.467399070893439e-11, "epoch": 2.997090203685742, "percentage": 99.9, "elapsed_time": "2 days, 1:13:10", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 3093, "total_steps": 3093, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2 days, 1:19:53", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,2205 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3093,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009699321047526674,
+      "grad_norm": 1.020737016686291,
+      "learning_rate": 1.0752688172043011e-06,
+      "loss": 0.3895,
+      "step": 10
+    },
+    {
+      "epoch": 0.019398642095053348,
+      "grad_norm": 0.7534117886463607,
+      "learning_rate": 2.1505376344086023e-06,
+      "loss": 0.3209,
+      "step": 20
+    },
+    {
+      "epoch": 0.029097963142580018,
+      "grad_norm": 0.4377375711052428,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.2648,
+      "step": 30
+    },
+    {
+      "epoch": 0.038797284190106696,
+      "grad_norm": 0.3125953720371267,
+      "learning_rate": 4.3010752688172045e-06,
+      "loss": 0.2353,
+      "step": 40
+    },
+    {
+      "epoch": 0.04849660523763336,
+      "grad_norm": 0.26931955183857703,
+      "learning_rate": 5.376344086021506e-06,
+      "loss": 0.2211,
+      "step": 50
+    },
+    {
+      "epoch": 0.058195926285160036,
+      "grad_norm": 0.26461533217537725,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.2065,
+      "step": 60
+    },
+    {
+      "epoch": 0.06789524733268672,
+      "grad_norm": 0.8264176079441389,
+      "learning_rate": 7.526881720430108e-06,
+      "loss": 0.2,
+      "step": 70
+    },
+    {
+      "epoch": 0.07759456838021339,
+      "grad_norm": 0.2983222843388067,
+      "learning_rate": 8.602150537634409e-06,
+      "loss": 0.1932,
+      "step": 80
+    },
+    {
+      "epoch": 0.08729388942774007,
+      "grad_norm": 0.581254385336681,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.1888,
+      "step": 90
+    },
+    {
+      "epoch": 0.09699321047526673,
+      "grad_norm": 0.3121423374050484,
+      "learning_rate": 9.999865664319414e-06,
+      "loss": 0.186,
+      "step": 100
+    },
+    {
+      "epoch": 0.1066925315227934,
+      "grad_norm": 0.2650187228146991,
+      "learning_rate": 9.999207711016081e-06,
+      "loss": 0.182,
+      "step": 110
+    },
+    {
+      "epoch": 0.11639185257032007,
+      "grad_norm": 0.26944373713294145,
+      "learning_rate": 9.998001538251283e-06,
+      "loss": 0.1779,
+      "step": 120
+    },
+    {
+      "epoch": 0.12609117361784675,
+      "grad_norm": 0.32148775806687896,
+      "learning_rate": 9.99624727829546e-06,
+      "loss": 0.1743,
+      "step": 130
+    },
+    {
+      "epoch": 0.13579049466537343,
+      "grad_norm": 0.23147855380574123,
+      "learning_rate": 9.99394512352298e-06,
+      "loss": 0.176,
+      "step": 140
+    },
+    {
+      "epoch": 0.1454898157129001,
+      "grad_norm": 0.5006127662496982,
+      "learning_rate": 9.991095326391061e-06,
+      "loss": 0.1741,
+      "step": 150
+    },
+    {
+      "epoch": 0.15518913676042678,
+      "grad_norm": 0.4320980518392451,
+      "learning_rate": 9.98769819941207e-06,
+      "loss": 0.1702,
+      "step": 160
+    },
+    {
+      "epoch": 0.16488845780795344,
+      "grad_norm": 0.3889487478872514,
+      "learning_rate": 9.983754115119262e-06,
+      "loss": 0.1727,
+      "step": 170
+    },
+    {
+      "epoch": 0.17458777885548013,
+      "grad_norm": 0.27135352703963794,
+      "learning_rate": 9.97926350602593e-06,
+      "loss": 0.1701,
+      "step": 180
+    },
+    {
+      "epoch": 0.1842870999030068,
+      "grad_norm": 0.25440030820854326,
+      "learning_rate": 9.97422686457796e-06,
+      "loss": 0.1678,
+      "step": 190
+    },
+    {
+      "epoch": 0.19398642095053345,
+      "grad_norm": 0.236255441704788,
+      "learning_rate": 9.968644743099848e-06,
+      "loss": 0.1641,
+      "step": 200
+    },
+    {
+      "epoch": 0.20368574199806014,
+      "grad_norm": 0.45878670927299864,
+      "learning_rate": 9.96251775373412e-06,
+      "loss": 0.167,
+      "step": 210
+    },
+    {
+      "epoch": 0.2133850630455868,
+      "grad_norm": 0.22778682431164834,
+      "learning_rate": 9.955846568374201e-06,
+      "loss": 0.1655,
+      "step": 220
+    },
+    {
+      "epoch": 0.22308438409311349,
+      "grad_norm": 0.23943633515604867,
+      "learning_rate": 9.948631918590746e-06,
+      "loss": 0.1617,
+      "step": 230
+    },
+    {
+      "epoch": 0.23278370514064015,
+      "grad_norm": 0.24350940452858558,
+      "learning_rate": 9.940874595551403e-06,
+      "loss": 0.1626,
+      "step": 240
+    },
+    {
+      "epoch": 0.24248302618816683,
+      "grad_norm": 0.22335875945360728,
+      "learning_rate": 9.932575449934063e-06,
+      "loss": 0.1644,
+      "step": 250
+    },
+    {
+      "epoch": 0.2521823472356935,
+      "grad_norm": 0.23496059802926855,
+      "learning_rate": 9.923735391833564e-06,
+      "loss": 0.1618,
+      "step": 260
+    },
+    {
+      "epoch": 0.2618816682832202,
+      "grad_norm": 0.22613625236616156,
+      "learning_rate": 9.914355390661897e-06,
+      "loss": 0.1588,
+      "step": 270
+    },
+    {
+      "epoch": 0.27158098933074687,
+      "grad_norm": 0.28310779926466306,
+      "learning_rate": 9.904436475041892e-06,
+      "loss": 0.1599,
+      "step": 280
+    },
+    {
+      "epoch": 0.2812803103782735,
+      "grad_norm": 0.23716946411046663,
+      "learning_rate": 9.893979732694422e-06,
+      "loss": 0.1608,
+      "step": 290
+    },
+    {
+      "epoch": 0.2909796314258002,
+      "grad_norm": 0.22939002583419776,
+      "learning_rate": 9.882986310319124e-06,
+      "loss": 0.1571,
+      "step": 300
+    },
+    {
+      "epoch": 0.3006789524733269,
+      "grad_norm": 0.1829019556630992,
+      "learning_rate": 9.871457413468645e-06,
+      "loss": 0.1602,
+      "step": 310
+    },
+    {
+      "epoch": 0.31037827352085356,
+      "grad_norm": 0.2862249824823463,
+      "learning_rate": 9.859394306416443e-06,
+      "loss": 0.1587,
+      "step": 320
+    },
+    {
+      "epoch": 0.3200775945683802,
+      "grad_norm": 0.1916670538928815,
+      "learning_rate": 9.846798312018147e-06,
+      "loss": 0.1593,
+      "step": 330
+    },
+    {
+      "epoch": 0.3297769156159069,
+      "grad_norm": 0.19602376121876022,
+      "learning_rate": 9.833670811566485e-06,
+      "loss": 0.1555,
+      "step": 340
+    },
+    {
+      "epoch": 0.3394762366634336,
+      "grad_norm": 0.24177047491392098,
+      "learning_rate": 9.820013244639817e-06,
+      "loss": 0.1575,
+      "step": 350
+    },
+    {
+      "epoch": 0.34917555771096026,
+      "grad_norm": 0.1876075373970573,
+      "learning_rate": 9.80582710894426e-06,
+      "loss": 0.1573,
+      "step": 360
+    },
+    {
+      "epoch": 0.3588748787584869,
+      "grad_norm": 0.2927139950691107,
+      "learning_rate": 9.791113960149458e-06,
+      "loss": 0.1549,
+      "step": 370
+    },
+    {
+      "epoch": 0.3685741998060136,
+      "grad_norm": 0.24672228818761555,
+      "learning_rate": 9.775875411717981e-06,
+      "loss": 0.1559,
+      "step": 380
+    },
+    {
+      "epoch": 0.37827352085354027,
+      "grad_norm": 0.25633769481093877,
+      "learning_rate": 9.760113134728383e-06,
+      "loss": 0.156,
+      "step": 390
+    },
+    {
+      "epoch": 0.3879728419010669,
+      "grad_norm": 0.22368063952475076,
+      "learning_rate": 9.743828857691964e-06,
+      "loss": 0.1549,
+      "step": 400
+    },
+    {
+      "epoch": 0.3976721629485936,
+      "grad_norm": 0.42577732642751726,
+      "learning_rate": 9.727024366363208e-06,
+      "loss": 0.1546,
+      "step": 410
+    },
+    {
+      "epoch": 0.4073714839961203,
+      "grad_norm": 0.30290230685059993,
+      "learning_rate": 9.709701503543954e-06,
+      "loss": 0.1541,
+      "step": 420
+    },
+    {
+      "epoch": 0.41707080504364696,
+      "grad_norm": 0.19793407217815825,
+      "learning_rate": 9.691862168881325e-06,
+      "loss": 0.153,
+      "step": 430
+    },
+    {
+      "epoch": 0.4267701260911736,
+      "grad_norm": 0.21683658128298464,
+      "learning_rate": 9.673508318659399e-06,
+      "loss": 0.1514,
+      "step": 440
+    },
+    {
+      "epoch": 0.4364694471387003,
+      "grad_norm": 0.2542785033568332,
+      "learning_rate": 9.65464196558468e-06,
+      "loss": 0.1507,
+      "step": 450
+    },
+    {
+      "epoch": 0.44616876818622697,
+      "grad_norm": 0.18399976352178382,
+      "learning_rate": 9.635265178565386e-06,
+      "loss": 0.1529,
+      "step": 460
+    },
+    {
+      "epoch": 0.45586808923375366,
+      "grad_norm": 0.16248682082363208,
+      "learning_rate": 9.615380082484573e-06,
+      "loss": 0.1524,
+      "step": 470
+    },
+    {
+      "epoch": 0.4655674102812803,
+      "grad_norm": 0.24408305032393154,
+      "learning_rate": 9.594988857967107e-06,
+      "loss": 0.1519,
+      "step": 480
+    },
+    {
+      "epoch": 0.475266731328807,
+      "grad_norm": 0.24001150201316104,
+      "learning_rate": 9.574093741140549e-06,
+      "loss": 0.1503,
+      "step": 490
+    },
+    {
+      "epoch": 0.48496605237633367,
+      "grad_norm": 0.21337935060277946,
+      "learning_rate": 9.552697023389923e-06,
+      "loss": 0.15,
+      "step": 500
+    },
+    {
+      "epoch": 0.49466537342386036,
+      "grad_norm": 0.17464159632335755,
+      "learning_rate": 9.530801051106449e-06,
+      "loss": 0.1505,
+      "step": 510
+    },
+    {
+      "epoch": 0.504364694471387,
+      "grad_norm": 0.16833615600888802,
+      "learning_rate": 9.508408225430237e-06,
+      "loss": 0.1512,
+      "step": 520
+    },
+    {
+      "epoch": 0.5140640155189137,
+      "grad_norm": 0.18834381819632562,
+      "learning_rate": 9.485521001986961e-06,
+      "loss": 0.1438,
+      "step": 530
+    },
+    {
+      "epoch": 0.5237633365664404,
+      "grad_norm": 0.20243272397310594,
+      "learning_rate": 9.46214189061859e-06,
+      "loss": 0.1513,
+      "step": 540
+    },
+    {
+      "epoch": 0.533462657613967,
+      "grad_norm": 0.200191598724974,
+      "learning_rate": 9.438273455108145e-06,
+      "loss": 0.1489,
+      "step": 550
+    },
+    {
+      "epoch": 0.5431619786614937,
+      "grad_norm": 0.16174114410966278,
+      "learning_rate": 9.41391831289855e-06,
+      "loss": 0.1496,
+      "step": 560
+    },
+    {
+      "epoch": 0.5528612997090203,
+      "grad_norm": 0.3626796052816055,
+      "learning_rate": 9.38907913480561e-06,
+      "loss": 0.1457,
+      "step": 570
+    },
+    {
+      "epoch": 0.562560620756547,
+      "grad_norm": 0.18785993468756543,
+      "learning_rate": 9.36375864472511e-06,
+      "loss": 0.1443,
+      "step": 580
+    },
+    {
+      "epoch": 0.5722599418040737,
+      "grad_norm": 0.17772800871532357,
+      "learning_rate": 9.337959619334125e-06,
+      "loss": 0.1476,
+      "step": 590
+    },
+    {
+      "epoch": 0.5819592628516004,
+      "grad_norm": 0.15601447310629252,
+      "learning_rate": 9.31168488778652e-06,
+      "loss": 0.1476,
+      "step": 600
+    },
+    {
+      "epoch": 0.5916585838991271,
+      "grad_norm": 0.19821208464194934,
+      "learning_rate": 9.284937331402697e-06,
+      "loss": 0.1468,
+      "step": 610
+    },
+    {
+      "epoch": 0.6013579049466538,
+      "grad_norm": 0.19029097473240159,
+      "learning_rate": 9.25771988335363e-06,
+      "loss": 0.1482,
+      "step": 620
+    },
+    {
+      "epoch": 0.6110572259941804,
+      "grad_norm": 0.18175837679945547,
+      "learning_rate": 9.230035528339212e-06,
+      "loss": 0.1455,
+      "step": 630
+    },
+    {
+      "epoch": 0.6207565470417071,
+      "grad_norm": 0.18340667052442786,
+      "learning_rate": 9.201887302260943e-06,
+      "loss": 0.1485,
+      "step": 640
+    },
+    {
+      "epoch": 0.6304558680892337,
+      "grad_norm": 0.15339041315406826,
+      "learning_rate": 9.173278291889016e-06,
+      "loss": 0.1466,
+      "step": 650
+    },
+    {
+      "epoch": 0.6401551891367604,
+      "grad_norm": 0.15699088899673416,
+      "learning_rate": 9.14421163452381e-06,
+      "loss": 0.1466,
+      "step": 660
+    },
+    {
+      "epoch": 0.6498545101842871,
+      "grad_norm": 0.24981887731533495,
+      "learning_rate": 9.11469051765186e-06,
+      "loss": 0.1464,
+      "step": 670
+    },
+    {
+      "epoch": 0.6595538312318138,
+      "grad_norm": 0.16649549015322454,
+      "learning_rate": 9.084718178596301e-06,
+      "loss": 0.1452,
+      "step": 680
+    },
+    {
+      "epoch": 0.6692531522793405,
+      "grad_norm": 0.16481654938724005,
+      "learning_rate": 9.054297904161868e-06,
+      "loss": 0.1439,
+      "step": 690
+    },
+    {
+      "epoch": 0.6789524733268671,
+      "grad_norm": 0.24499406154651857,
+      "learning_rate": 9.02343303027446e-06,
+      "loss": 0.1465,
+      "step": 700
+    },
+    {
+      "epoch": 0.6886517943743938,
+      "grad_norm": 0.1496332910263056,
+      "learning_rate": 8.992126941615314e-06,
+      "loss": 0.1458,
+      "step": 710
+    },
+    {
+      "epoch": 0.6983511154219205,
+      "grad_norm": 0.16548997088070388,
+      "learning_rate": 8.960383071249837e-06,
+      "loss": 0.1451,
+      "step": 720
+    },
+    {
+      "epoch": 0.7080504364694471,
+      "grad_norm": 0.20683623207389146,
+      "learning_rate": 8.928204900251136e-06,
+      "loss": 0.1452,
+      "step": 730
+    },
+    {
+      "epoch": 0.7177497575169738,
+      "grad_norm": 0.20126316747636905,
+      "learning_rate": 8.895595957318277e-06,
+      "loss": 0.146,
+      "step": 740
+    },
+    {
+      "epoch": 0.7274490785645005,
+      "grad_norm": 0.14334846077395094,
+      "learning_rate": 8.862559818389322e-06,
+      "loss": 0.1418,
+      "step": 750
+    },
+    {
+      "epoch": 0.7371483996120272,
+      "grad_norm": 0.17612864303411396,
+      "learning_rate": 8.829100106249189e-06,
+      "loss": 0.1429,
+      "step": 760
+    },
+    {
+      "epoch": 0.7468477206595538,
+      "grad_norm": 0.15223827251186925,
+      "learning_rate": 8.795220490132369e-06,
+      "loss": 0.1461,
+      "step": 770
+    },
+    {
+      "epoch": 0.7565470417070805,
+      "grad_norm": 0.17586006541625654,
+      "learning_rate": 8.760924685320558e-06,
+      "loss": 0.1426,
+      "step": 780
+    },
+    {
+      "epoch": 0.7662463627546072,
+      "grad_norm": 0.2495465089144099,
+      "learning_rate": 8.726216452735233e-06,
+      "loss": 0.1427,
+      "step": 790
+    },
+    {
+      "epoch": 0.7759456838021338,
+      "grad_norm": 0.16231569101956547,
+      "learning_rate": 8.691099598525222e-06,
+      "loss": 0.1425,
+      "step": 800
+    },
+    {
+      "epoch": 0.7856450048496605,
+      "grad_norm": 0.20643117512106057,
+      "learning_rate": 8.655577973649322e-06,
+      "loss": 0.1447,
+      "step": 810
+    },
+    {
+      "epoch": 0.7953443258971872,
+      "grad_norm": 0.19353894695637477,
+      "learning_rate": 8.61965547345399e-06,
+      "loss": 0.1431,
+      "step": 820
+    },
+    {
+      "epoch": 0.8050436469447139,
+      "grad_norm": 0.1632307697067024,
+      "learning_rate": 8.583336037246187e-06,
+      "loss": 0.1436,
+      "step": 830
+    },
+    {
+      "epoch": 0.8147429679922406,
+      "grad_norm": 0.17216990615447947,
+      "learning_rate": 8.54662364786137e-06,
+      "loss": 0.1447,
+      "step": 840
+    },
+    {
+      "epoch": 0.8244422890397672,
+      "grad_norm": 0.1651724707314526,
+      "learning_rate": 8.509522331226751e-06,
+      "loss": 0.139,
+      "step": 850
+    },
+    {
+      "epoch": 0.8341416100872939,
+      "grad_norm": 0.1568458339839126,
+      "learning_rate": 8.47203615591979e-06,
+      "loss": 0.1427,
+      "step": 860
+    },
+    {
+      "epoch": 0.8438409311348206,
+      "grad_norm": 0.17852618591230168,
+      "learning_rate": 8.434169232722043e-06,
+      "loss": 0.1404,
+      "step": 870
+    },
+    {
+      "epoch": 0.8535402521823472,
+      "grad_norm": 0.20639355600204873,
+      "learning_rate": 8.395925714168356e-06,
+      "loss": 0.1412,
+      "step": 880
+    },
+    {
+      "epoch": 0.8632395732298739,
+      "grad_norm": 0.15073817817287644,
+      "learning_rate": 8.357309794091508e-06,
+      "loss": 0.1413,
+      "step": 890
+    },
+    {
+      "epoch": 0.8729388942774006,
+      "grad_norm": 0.15904000752733416,
+      "learning_rate": 8.318325707162293e-06,
+      "loss": 0.1413,
+      "step": 900
+    },
+    {
+      "epoch": 0.8826382153249273,
+      "grad_norm": 0.1552685969985047,
+      "learning_rate": 8.278977728425157e-06,
+      "loss": 0.1419,
+      "step": 910
+    },
+    {
+      "epoch": 0.8923375363724539,
+      "grad_norm": 0.15706230396222723,
+      "learning_rate": 8.239270172829379e-06,
+      "loss": 0.1416,
+      "step": 920
+    },
+    {
+      "epoch": 0.9020368574199806,
+      "grad_norm": 0.17255106752775495,
+      "learning_rate": 8.199207394755892e-06,
+      "loss": 0.1407,
+      "step": 930
+    },
+    {
+      "epoch": 0.9117361784675073,
+      "grad_norm": 0.2129566296657695,
+      "learning_rate": 8.158793787539782e-06,
+      "loss": 0.1426,
+      "step": 940
+    },
+    {
+      "epoch": 0.9214354995150339,
+      "grad_norm": 0.1520917555155708,
+      "learning_rate": 8.118033782988496e-06,
+      "loss": 0.1425,
+      "step": 950
+    },
+    {
+      "epoch": 0.9311348205625606,
+      "grad_norm": 0.14387577079486796,
+      "learning_rate": 8.076931850895858e-06,
+      "loss": 0.1406,
+      "step": 960
+    },
+    {
+      "epoch": 0.9408341416100873,
+      "grad_norm": 0.156372446996249,
+      "learning_rate": 8.0354924985519e-06,
+      "loss": 0.1404,
+      "step": 970
+    },
+    {
+      "epoch": 0.950533462657614,
+      "grad_norm": 0.13415353564550458,
+      "learning_rate": 7.993720270248583e-06,
+      "loss": 0.1367,
+      "step": 980
+    },
+    {
+      "epoch": 0.9602327837051406,
+      "grad_norm": 0.15260385024231266,
+      "learning_rate": 7.951619746781474e-06,
+      "loss": 0.1404,
+      "step": 990
+    },
+    {
+      "epoch": 0.9699321047526673,
+      "grad_norm": 0.14296007598794033,
+      "learning_rate": 7.909195544947398e-06,
+      "loss": 0.1379,
+      "step": 1000
+    },
+    {
+      "epoch": 0.979631425800194,
+      "grad_norm": 0.1439203772713178,
+      "learning_rate": 7.866452317038164e-06,
+      "loss": 0.1407,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9893307468477207,
+      "grad_norm": 0.15601557591631698,
+      "learning_rate": 7.823394750330386e-06,
+      "loss": 0.1378,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9990300678952473,
+      "grad_norm": 0.1521155491141262,
+      "learning_rate": 7.780027566571467e-06,
+      "loss": 0.1381,
+      "step": 1030
+    },
+    {
+      "epoch": 1.008729388942774,
+      "grad_norm": 0.18883092497874396,
+      "learning_rate": 7.736355521461812e-06,
+      "loss": 0.1289,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0184287099903007,
+      "grad_norm": 0.16791508973001082,
+      "learning_rate": 7.692383404133302e-06,
+      "loss": 0.1251,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0281280310378274,
+      "grad_norm": 0.1441774496377216,
+      "learning_rate": 7.648116036624125e-06,
+      "loss": 0.1256,
+      "step": 1060
+    },
+    {
+      "epoch": 1.037827352085354,
+      "grad_norm": 0.13109750689397975,
+      "learning_rate": 7.6035582733499805e-06,
+      "loss": 0.1255,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0475266731328807,
+      "grad_norm": 0.14171432637868595,
+      "learning_rate": 7.5587150005717256e-06,
+      "loss": 0.1241,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0572259941804074,
+      "grad_norm": 0.14162368666044384,
+      "learning_rate": 7.5135911358595615e-06,
+      "loss": 0.1273,
+      "step": 1090
+    },
+    {
+      "epoch": 1.066925315227934,
+      "grad_norm": 0.13418678548273563,
+      "learning_rate": 7.468191627553752e-06,
+      "loss": 0.1264,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0766246362754608,
+      "grad_norm": 0.13196187275552038,
+      "learning_rate": 7.42252145422199e-06,
+      "loss": 0.1293,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0863239573229875,
+      "grad_norm": 0.14552608723341326,
+      "learning_rate": 7.376585624113438e-06,
+      "loss": 0.1244,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0960232783705142,
+      "grad_norm": 0.14422441886749568,
+      "learning_rate": 7.330389174609516e-06,
+      "loss": 0.1264,
+      "step": 1130
+    },
+    {
+      "epoch": 1.1057225994180406,
+      "grad_norm": 0.13834555525544687,
+      "learning_rate": 7.283937171671498e-06,
+      "loss": 0.128,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1154219204655673,
+      "grad_norm": 0.13679812310695327,
+      "learning_rate": 7.2372347092849744e-06,
+      "loss": 0.1268,
+      "step": 1150
+    },
+    {
+      "epoch": 1.125121241513094,
+      "grad_norm": 0.14580868475877667,
+      "learning_rate": 7.190286908901234e-06,
+      "loss": 0.127,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1348205625606207,
+      "grad_norm": 0.14759352493891592,
+      "learning_rate": 7.143098918875643e-06,
+      "loss": 0.1239,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1445198836081474,
+      "grad_norm": 0.16306728409304952,
+      "learning_rate": 7.095675913903067e-06,
+      "loss": 0.1252,
+      "step": 1180
+    },
+    {
+      "epoch": 1.154219204655674,
+      "grad_norm": 0.13619389268479554,
+      "learning_rate": 7.048023094450412e-06,
+      "loss": 0.1255,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1639185257032008,
+      "grad_norm": 0.14865648794317585,
+      "learning_rate": 7.0001456861863236e-06,
+      "loss": 0.125,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1736178467507274,
+      "grad_norm": 0.1352158410960604,
+      "learning_rate": 6.952048939408156e-06,
+      "loss": 0.126,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1833171677982541,
+      "grad_norm": 0.14931606937805553,
+      "learning_rate": 6.903738128466189e-06,
+      "loss": 0.1244,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1930164888457808,
+      "grad_norm": 0.15591971567787935,
+      "learning_rate": 6.8552185511852555e-06,
+      "loss": 0.1257,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2027158098933075,
+      "grad_norm": 0.15987884349569545,
+      "learning_rate": 6.806495528283772e-06,
+      "loss": 0.1247,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2124151309408342,
+      "grad_norm": 0.173600355468448,
+      "learning_rate": 6.75757440279026e-06,
+      "loss": 0.1266,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2221144519883609,
+      "grad_norm": 0.15555585861546212,
+      "learning_rate": 6.708460539457418e-06,
+      "loss": 0.1259,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2318137730358876,
+      "grad_norm": 0.13216223386632905,
+      "learning_rate": 6.659159324173823e-06,
+      "loss": 0.1264,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2415130940834143,
+      "grad_norm": 0.13732331224860048,
+      "learning_rate": 6.6096761633733065e-06,
+      "loss": 0.1212,
+      "step": 1280
+    },
+    {
+      "epoch": 1.251212415130941,
+      "grad_norm": 0.14550514337128806,
+      "learning_rate": 6.5600164834420754e-06,
+      "loss": 0.1232,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2609117361784676,
+      "grad_norm": 0.1395324855091477,
+      "learning_rate": 6.510185730123646e-06,
+      "loss": 0.1246,
+      "step": 1300
+    },
+    {
+      "epoch": 1.270611057225994,
+      "grad_norm": 0.15143922372224142,
+      "learning_rate": 6.460189367921663e-06,
+      "loss": 0.1222,
+      "step": 1310
+    },
+    {
+      "epoch": 1.2803103782735208,
+      "grad_norm": 0.14430877735904407,
+      "learning_rate": 6.410032879500647e-06,
+      "loss": 0.1237,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2900096993210475,
+      "grad_norm": 0.15435173824185056,
+      "learning_rate": 6.35972176508477e-06,
+      "loss": 0.1246,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2997090203685742,
+      "grad_norm": 0.14283758578201033,
+      "learning_rate": 6.309261541854679e-06,
+      "loss": 0.1246,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3094083414161009,
+      "grad_norm": 0.13781861198691472,
+      "learning_rate": 6.258657743342486e-06,
+      "loss": 0.1214,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3191076624636275,
+      "grad_norm": 0.13748643897048052,
+      "learning_rate": 6.207915918824952e-06,
+      "loss": 0.1261,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3288069835111542,
+      "grad_norm": 0.14790322688240057,
+      "learning_rate": 6.157041632714945e-06,
+      "loss": 0.1255,
+      "step": 1370
+    },
+    {
+      "epoch": 1.338506304558681,
+      "grad_norm": 0.13278715076830586,
+      "learning_rate": 6.106040463951237e-06,
+      "loss": 0.1236,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3482056256062076,
+      "grad_norm": 0.13946856628394763,
+      "learning_rate": 6.0549180053867114e-06,
+      "loss": 0.1198,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3579049466537343,
+      "grad_norm": 0.12852192262109208,
+      "learning_rate": 6.003679863175052e-06,
+      "loss": 0.1241,
+      "step": 1400
+    },
+    {
+      "epoch": 1.367604267701261,
+      "grad_norm": 0.14143420891866582,
+      "learning_rate": 5.952331656155951e-06,
+      "loss": 0.1263,
+      "step": 1410
+    },
+    {
+      "epoch": 1.3773035887487877,
+      "grad_norm": 0.1282297410386555,
+      "learning_rate": 5.900879015238948e-06,
+      "loss": 0.126,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3870029097963141,
+      "grad_norm": 0.13873942443095202,
+      "learning_rate": 5.849327582785943e-06,
+      "loss": 0.1269,
+      "step": 1430
+    },
+    {
+      "epoch": 1.3967022308438408,
+      "grad_norm": 0.13656175147704938,
+      "learning_rate": 5.797683011992432e-06,
+      "loss": 0.1203,
+      "step": 1440
+    },
+    {
+      "epoch": 1.4064015518913675,
+      "grad_norm": 0.1525890999931462,
+      "learning_rate": 5.745950966267586e-06,
+      "loss": 0.1248,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4161008729388942,
+      "grad_norm": 0.1378029168356388,
+      "learning_rate": 5.694137118613185e-06,
+      "loss": 0.1208,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4258001939864209,
+      "grad_norm": 0.1349917266146262,
+      "learning_rate": 5.642247151001515e-06,
+      "loss": 0.1219,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4354995150339476,
+      "grad_norm": 0.13532958442842166,
+      "learning_rate": 5.590286753752269e-06,
+      "loss": 0.1246,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4451988360814743,
+      "grad_norm": 0.13590965633443314,
+      "learning_rate": 5.5382616249085476e-06,
+      "loss": 0.1238,
+      "step": 1490
+    },
+    {
+      "epoch": 1.454898157129001,
+      "grad_norm": 0.1302293751307389,
+      "learning_rate": 5.486177469611999e-06,
+      "loss": 0.1218,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4645974781765276,
+      "grad_norm": 0.13212636179350218,
+      "learning_rate": 5.434039999477182e-06,
+      "loss": 0.1217,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4742967992240543,
+      "grad_norm": 0.15765907573882082,
+      "learning_rate": 5.381854931965238e-06,
+      "loss": 0.1212,
+      "step": 1520
+    },
+    {
+      "epoch": 1.483996120271581,
+      "grad_norm": 0.13087502137063067,
+      "learning_rate": 5.32962798975689e-06,
+      "loss": 0.1221,
+      "step": 1530
+    },
+    {
+      "epoch": 1.4936954413191077,
+      "grad_norm": 0.1809256405824013,
+      "learning_rate": 5.2773649001248965e-06,
+      "loss": 0.1201,
+      "step": 1540
+    },
+    {
+      "epoch": 1.5033947623666344,
+      "grad_norm": 0.12904018631952519,
+      "learning_rate": 5.2250713943059826e-06,
+      "loss": 0.1222,
+      "step": 1550
+    },
+    {
+      "epoch": 1.513094083414161,
+      "grad_norm": 0.1293740910081746,
+      "learning_rate": 5.172753206872363e-06,
+      "loss": 0.1209,
+      "step": 1560
+    },
+    {
+      "epoch": 1.5227934044616878,
+      "grad_norm": 0.30179091402220243,
+      "learning_rate": 5.120416075102855e-06,
+      "loss": 0.1257,
+      "step": 1570
+    },
+    {
+      "epoch": 1.5324927255092144,
+      "grad_norm": 0.1385162792200683,
+      "learning_rate": 5.068065738353748e-06,
+      "loss": 0.124,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5421920465567411,
+      "grad_norm": 0.1255449193902108,
+      "learning_rate": 5.015707937429398e-06,
+      "loss": 0.1192,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5518913676042678,
+      "grad_norm": 0.15408459889574322,
+      "learning_rate": 4.9633484139526975e-06,
+      "loss": 0.1225,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5615906886517945,
+      "grad_norm": 0.13856983999023262,
+      "learning_rate": 4.910992909735432e-06,
+      "loss": 0.1201,
+      "step": 1610
+    },
+    {
+      "epoch": 1.5712900096993212,
+      "grad_norm": 0.12207611538378375,
+      "learning_rate": 4.8586471661486345e-06,
+      "loss": 0.1227,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5809893307468477,
+      "grad_norm": 0.1266119474511833,
+      "learning_rate": 4.80631692349297e-06,
+      "loss": 0.1232,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5906886517943744,
+      "grad_norm": 0.14230780661161255,
+      "learning_rate": 4.754007920369252e-06,
+      "loss": 0.1213,
+      "step": 1640
+    },
+    {
+      "epoch": 1.600387972841901,
+      "grad_norm": 0.13743035777356707,
+      "learning_rate": 4.7017258930491474e-06,
+      "loss": 0.1194,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6100872938894277,
+      "grad_norm": 0.1386159724833024,
+      "learning_rate": 4.649476574846113e-06,
+      "loss": 0.1206,
+      "step": 1660
+    },
+    {
+      "epoch": 1.6197866149369544,
+      "grad_norm": 0.12379147527691,
+      "learning_rate": 4.597265695486685e-06,
+      "loss": 0.122,
+      "step": 1670
+    },
+    {
+      "epoch": 1.629485935984481,
+      "grad_norm": 0.13597192298584537,
+      "learning_rate": 4.545098980482151e-06,
+      "loss": 0.1217,
+      "step": 1680
+    },
+    {
+      "epoch": 1.6391852570320078,
+      "grad_norm": 0.1281728134758131,
+      "learning_rate": 4.492982150500677e-06,
+      "loss": 0.1222,
+      "step": 1690
+    },
+    {
+      "epoch": 1.6488845780795345,
+      "grad_norm": 0.14452895293267878,
+      "learning_rate": 4.44092092073997e-06,
+      "loss": 0.1203,
+      "step": 1700
+    },
+    {
+      "epoch": 1.658583899127061,
+      "grad_norm": 0.734748232446473,
+      "learning_rate": 4.388921000300553e-06,
+      "loss": 0.1195,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6682832201745876,
+      "grad_norm": 0.13007786192950554,
+      "learning_rate": 4.336988091559688e-06,
+      "loss": 0.1179,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6779825412221143,
+      "grad_norm": 0.12183531013572281,
+      "learning_rate": 4.285127889546049e-06,
+      "loss": 0.1214,
+      "step": 1730
+    },
+    {
+      "epoch": 1.687681862269641,
+      "grad_norm": 0.13118954244252978,
+      "learning_rate": 4.233346081315197e-06,
+      "loss": 0.1197,
+      "step": 1740
+    },
+    {
+      "epoch": 1.6973811833171677,
+      "grad_norm": 0.13481540424732633,
+      "learning_rate": 4.181648345325934e-06,
+      "loss": 0.1173,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7070805043646944,
+      "grad_norm": 0.13368272764953815,
+      "learning_rate": 4.13004035081759e-06,
+      "loss": 0.1177,
+      "step": 1760
+    },
+    {
+      "epoch": 1.716779825412221,
+      "grad_norm": 0.1405384765881231,
+      "learning_rate": 4.078527757188333e-06,
+      "loss": 0.1193,
+      "step": 1770
+    },
+    {
+      "epoch": 1.7264791464597478,
+      "grad_norm": 0.1492903635536138,
+      "learning_rate": 4.02711621337455e-06,
+      "loss": 0.1237,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7361784675072744,
+      "grad_norm": 0.13618911961601582,
+      "learning_rate": 3.9758113572313735e-06,
+      "loss": 0.1189,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7458777885548011,
+      "grad_norm": 0.12113555025079864,
+      "learning_rate": 3.924618814914435e-06,
+      "loss": 0.119,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7555771096023278,
+      "grad_norm": 0.12580610174287832,
+      "learning_rate": 3.873544200262882e-06,
+      "loss": 0.1202,
+      "step": 1810
+    },
+    {
+      "epoch": 1.7652764306498545,
+      "grad_norm": 0.12160650948969177,
+      "learning_rate": 3.822593114183777e-06,
+      "loss": 0.1203,
+      "step": 1820
+    },
+    {
+      "epoch": 1.7749757516973812,
+      "grad_norm": 0.11538378695593902,
+      "learning_rate": 3.7717711440378695e-06,
+      "loss": 0.1197,
+      "step": 1830
+    },
+    {
+      "epoch": 1.7846750727449079,
+      "grad_norm": 0.12474760124557903,
+      "learning_rate": 3.7210838630268986e-06,
+      "loss": 0.1185,
+      "step": 1840
+    },
+    {
+      "epoch": 1.7943743937924346,
+      "grad_norm": 0.12741060176067462,
+      "learning_rate": 3.670536829582424e-06,
+      "loss": 0.1191,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8040737148399613,
+      "grad_norm": 0.12351598125613471,
+      "learning_rate": 3.6201355867562725e-06,
+      "loss": 0.1191,
+      "step": 1860
+    },
+    {
+      "epoch": 1.813773035887488,
+      "grad_norm": 0.14188987252511706,
+      "learning_rate": 3.569885661612691e-06,
+      "loss": 0.1195,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8234723569350146,
+      "grad_norm": 0.13634330984512036,
+      "learning_rate": 3.5197925646222387e-06,
+      "loss": 0.1204,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8331716779825413,
+      "grad_norm": 0.2373069723174238,
+      "learning_rate": 3.4698617890574972e-06,
+      "loss": 0.1187,
+      "step": 1890
+    },
+    {
+      "epoch": 1.842870999030068,
+      "grad_norm": 0.13261383960841805,
+      "learning_rate": 3.4200988103906747e-06,
+      "loss": 0.1181,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8525703200775947,
+      "grad_norm": 0.13269073521254607,
+      "learning_rate": 3.3705090856931626e-06,
+      "loss": 0.1189,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8622696411251214,
+      "grad_norm": 0.11857183586240762,
+      "learning_rate": 3.3210980530370974e-06,
+      "loss": 0.1163,
+      "step": 1920
+    },
+    {
+      "epoch": 1.871968962172648,
+      "grad_norm": 0.12514649915266685,
+      "learning_rate": 3.2718711308990226e-06,
+      "loss": 0.1173,
+      "step": 1930
+    },
+    {
+      "epoch": 1.8816682832201745,
+      "grad_norm": 0.13278636126865803,
+      "learning_rate": 3.2228337175656856e-06,
+      "loss": 0.1175,
+      "step": 1940
+    },
+    {
+      "epoch": 1.8913676042677012,
+      "grad_norm": 0.1526458979660249,
+      "learning_rate": 3.1739911905420617e-06,
+      "loss": 0.1157,
+      "step": 1950
+    },
+    {
+      "epoch": 1.901066925315228,
+      "grad_norm": 0.12356959999521902,
+      "learning_rate": 3.1253489059616448e-06,
+      "loss": 0.1206,
+      "step": 1960
+    },
+    {
+      "epoch": 1.9107662463627546,
+      "grad_norm": 0.12931045840893188,
+      "learning_rate": 3.0769121979990845e-06,
+      "loss": 0.1176,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9204655674102813,
+      "grad_norm": 0.13043271523994618,
+      "learning_rate": 3.028686378285245e-06,
+      "loss": 0.1188,
+      "step": 1980
+    },
+    {
+      "epoch": 1.930164888457808,
+      "grad_norm": 0.1511393413072713,
+      "learning_rate": 2.9806767353247127e-06,
+      "loss": 0.1199,
+      "step": 1990
+    },
+    {
+      "epoch": 1.9398642095053347,
+      "grad_norm": 0.1313911423759091,
+      "learning_rate": 2.9328885339158554e-06,
+      "loss": 0.118,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9495635305528611,
+      "grad_norm": 0.1264515550648061,
+      "learning_rate": 2.8853270145734846e-06,
+      "loss": 0.1185,
+      "step": 2010
+    },
+    {
+      "epoch": 1.9592628516003878,
+      "grad_norm": 0.12231144466512428,
+      "learning_rate": 2.837997392954165e-06,
+      "loss": 0.116,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9689621726479145,
+      "grad_norm": 0.14521506304206808,
+      "learning_rate": 2.7909048592842602e-06,
+      "loss": 0.1152,
+      "step": 2030
+    },
+    {
+      "epoch": 1.9786614936954412,
+      "grad_norm": 0.126711825889384,
+      "learning_rate": 2.7440545777907747e-06,
+      "loss": 0.1159,
+      "step": 2040
+    },
+    {
+      "epoch": 1.9883608147429679,
+      "grad_norm": 0.1681227374854468,
+      "learning_rate": 2.697451686135031e-06,
+      "loss": 0.1186,
+      "step": 2050
+    },
+    {
+      "epoch": 1.9980601357904946,
+      "grad_norm": 0.13008493981139174,
+      "learning_rate": 2.6511012948492625e-06,
+      "loss": 0.1172,
+      "step": 2060
+    },
+    {
+      "epoch": 2.0077594568380213,
+      "grad_norm": 0.1413967651108439,
+      "learning_rate": 2.6050084867761953e-06,
+      "loss": 0.1045,
+      "step": 2070
+    },
+    {
+      "epoch": 2.017458777885548,
+      "grad_norm": 0.1549924427730225,
+      "learning_rate": 2.5591783165116563e-06,
+      "loss": 0.105,
+      "step": 2080
+    },
+    {
+      "epoch": 2.0271580989330746,
+      "grad_norm": 0.13493394435352007,
+      "learning_rate": 2.51361580985027e-06,
+      "loss": 0.1038,
+      "step": 2090
+    },
+    {
+      "epoch": 2.0368574199806013,
+      "grad_norm": 0.14278275935536047,
+      "learning_rate": 2.4683259632343363e-06,
+      "loss": 0.101,
+      "step": 2100
+    },
+    {
+      "epoch": 2.046556741028128,
+      "grad_norm": 0.12912222827072362,
+      "learning_rate": 2.42331374320591e-06,
+      "loss": 0.1023,
+      "step": 2110
+    },
+    {
+      "epoch": 2.0562560620756547,
+      "grad_norm": 0.13486110619768377,
+      "learning_rate": 2.3785840858621556e-06,
+      "loss": 0.1038,
+      "step": 2120
+    },
+    {
+      "epoch": 2.0659553831231814,
+      "grad_norm": 0.12322475049858893,
+      "learning_rate": 2.334141896314057e-06,
+      "loss": 0.1015,
+      "step": 2130
+    },
+    {
+      "epoch": 2.075654704170708,
+      "grad_norm": 0.12313226259292803,
+      "learning_rate": 2.2899920481485192e-06,
+      "loss": 0.1006,
+      "step": 2140
+    },
+    {
+      "epoch": 2.0853540252182348,
+      "grad_norm": 0.13084594004574415,
+      "learning_rate": 2.246139382893915e-06,
+      "loss": 0.103,
+      "step": 2150
+    },
+    {
+      "epoch": 2.0950533462657615,
+      "grad_norm": 0.11766251876256842,
+      "learning_rate": 2.2025887094891657e-06,
+      "loss": 0.1021,
+      "step": 2160
+    },
+    {
+      "epoch": 2.104752667313288,
+      "grad_norm": 0.12060852673739084,
+      "learning_rate": 2.1593448037563795e-06,
+      "loss": 0.1012,
+      "step": 2170
+    },
+    {
+      "epoch": 2.114451988360815,
+      "grad_norm": 0.12567405538629176,
+      "learning_rate": 2.116412407877138e-06,
+      "loss": 0.0989,
+      "step": 2180
+    },
+    {
+      "epoch": 2.1241513094083415,
+      "grad_norm": 0.1365525172002471,
+      "learning_rate": 2.0737962298724513e-06,
+      "loss": 0.1028,
+      "step": 2190
+    },
+    {
+      "epoch": 2.133850630455868,
+      "grad_norm": 0.13749139478988584,
+      "learning_rate": 2.0315009430864762e-06,
+      "loss": 0.0981,
+      "step": 2200
+    },
+    {
+      "epoch": 2.143549951503395,
+      "grad_norm": 0.12483408419665704,
+      "learning_rate": 1.989531185674037e-06,
+      "loss": 0.1006,
+      "step": 2210
+    },
+    {
+      "epoch": 2.1532492725509216,
+      "grad_norm": 0.12889816969916387,
+      "learning_rate": 1.9478915600919877e-06,
+      "loss": 0.0994,
+      "step": 2220
+    },
+    {
+      "epoch": 2.1629485935984483,
+      "grad_norm": 0.13722687929380498,
+      "learning_rate": 1.9065866325945099e-06,
+      "loss": 0.1006,
+      "step": 2230
+    },
+    {
+      "epoch": 2.172647914645975,
+      "grad_norm": 0.12731978697579938,
+      "learning_rate": 1.8656209327323704e-06,
+      "loss": 0.1032,
+      "step": 2240
+    },
+    {
+      "epoch": 2.1823472356935016,
+      "grad_norm": 0.12992560572466144,
+      "learning_rate": 1.824998952856198e-06,
+      "loss": 0.0995,
+      "step": 2250
+    },
+    {
+      "epoch": 2.1920465567410283,
+      "grad_norm": 0.12461701158829513,
+      "learning_rate": 1.784725147623853e-06,
+      "loss": 0.1014,
+      "step": 2260
+    },
+    {
+      "epoch": 2.2017458777885546,
+      "grad_norm": 0.12197881380183824,
+      "learning_rate": 1.7448039335119272e-06,
+      "loss": 0.1002,
+      "step": 2270
+    },
+    {
+      "epoch": 2.2114451988360813,
+      "grad_norm": 0.12027153954201142,
+      "learning_rate": 1.7052396883314154e-06,
+      "loss": 0.1007,
+      "step": 2280
+    },
+    {
+      "epoch": 2.221144519883608,
+      "grad_norm": 0.14042894762171168,
+      "learning_rate": 1.6660367507476539e-06,
+      "loss": 0.1032,
+      "step": 2290
+    },
+    {
+      "epoch": 2.2308438409311346,
+      "grad_norm": 0.1304473662542888,
+      "learning_rate": 1.627199419804522e-06,
+      "loss": 0.0974,
+      "step": 2300
+    },
+    {
+      "epoch": 2.2405431619786613,
+      "grad_norm": 0.13385797988412498,
+      "learning_rate": 1.5887319544530182e-06,
+      "loss": 0.0993,
+      "step": 2310
+    },
+    {
+      "epoch": 2.250242483026188,
+      "grad_norm": 0.12152842920119761,
+      "learning_rate": 1.5506385730842062e-06,
+      "loss": 0.0994,
+      "step": 2320
+    },
+    {
+      "epoch": 2.2599418040737147,
+      "grad_norm": 0.15097037450611273,
+      "learning_rate": 1.5129234530666232e-06,
+      "loss": 0.0996,
+      "step": 2330
+    },
+    {
+      "epoch": 2.2696411251212414,
+      "grad_norm": 0.13232561112805757,
+      "learning_rate": 1.4755907302881927e-06,
+      "loss": 0.1021,
+      "step": 2340
+    },
+    {
+      "epoch": 2.279340446168768,
+      "grad_norm": 0.13689860207073964,
+      "learning_rate": 1.4386444987026705e-06,
+      "loss": 0.1008,
+      "step": 2350
+    },
+    {
+      "epoch": 2.2890397672162948,
+      "grad_norm": 0.12697227778436346,
+      "learning_rate": 1.4020888098806924e-06,
+      "loss": 0.1012,
+      "step": 2360
+    },
+    {
+      "epoch": 2.2987390882638215,
+      "grad_norm": 0.1306372848154384,
+      "learning_rate": 1.3659276725654863e-06,
+      "loss": 0.0994,
+      "step": 2370
+    },
+    {
+      "epoch": 2.308438409311348,
+      "grad_norm": 0.1417516277044696,
+      "learning_rate": 1.3301650522332566e-06,
+      "loss": 0.1021,
+      "step": 2380
+    },
+    {
+      "epoch": 2.318137730358875,
+      "grad_norm": 0.12583750650057704,
+      "learning_rate": 1.2948048706583284e-06,
+      "loss": 0.1011,
+      "step": 2390
+    },
+    {
+      "epoch": 2.3278370514064015,
+      "grad_norm": 0.12210301430641879,
+      "learning_rate": 1.2598510054830888e-06,
+      "loss": 0.1026,
+      "step": 2400
+    },
+    {
+      "epoch": 2.337536372453928,
+      "grad_norm": 0.14086208814152623,
+      "learning_rate": 1.2253072897927437e-06,
+      "loss": 0.1004,
+      "step": 2410
+    },
+    {
+      "epoch": 2.347235693501455,
+      "grad_norm": 0.12702340474503365,
+      "learning_rate": 1.1911775116949958e-06,
+      "loss": 0.1026,
+      "step": 2420
+    },
+    {
+      "epoch": 2.3569350145489816,
+      "grad_norm": 0.1325904746306228,
+      "learning_rate": 1.1574654139046171e-06,
+      "loss": 0.1004,
+      "step": 2430
+    },
+    {
+      "epoch": 2.3666343355965083,
+      "grad_norm": 0.1232419911088865,
+      "learning_rate": 1.1241746933330338e-06,
+      "loss": 0.1021,
+      "step": 2440
+    },
+    {
+      "epoch": 2.376333656644035,
+      "grad_norm": 0.11926188716205782,
+      "learning_rate": 1.0913090006829085e-06,
+      "loss": 0.1004,
+      "step": 2450
+    },
+    {
+      "epoch": 2.3860329776915616,
+      "grad_norm": 0.1309045847253476,
+      "learning_rate": 1.0588719400478004e-06,
+      "loss": 0.0977,
+      "step": 2460
+    },
+    {
+      "epoch": 2.3957322987390883,
+      "grad_norm": 0.13504405075095502,
+      "learning_rate": 1.026867068516943e-06,
+      "loss": 0.1021,
+      "step": 2470
+    },
+    {
+      "epoch": 2.405431619786615,
+      "grad_norm": 0.1326298312074988,
+      "learning_rate": 9.952978957851622e-07,
+      "loss": 0.098,
+      "step": 2480
+    },
+    {
+      "epoch": 2.4151309408341417,
+      "grad_norm": 0.13381141022665327,
+      "learning_rate": 9.641678837679985e-07,
+      "loss": 0.1,
+      "step": 2490
+    },
+    {
+      "epoch": 2.4248302618816684,
+      "grad_norm": 0.12764187585028094,
+      "learning_rate": 9.334804462220748e-07,
+      "loss": 0.0968,
+      "step": 2500
+    },
+    {
+      "epoch": 2.434529582929195,
+      "grad_norm": 0.12451918444105284,
+      "learning_rate": 9.032389483707332e-07,
+      "loss": 0.0985,
+      "step": 2510
+    },
+    {
+      "epoch": 2.4442289039767218,
+      "grad_norm": 0.1231163492324899,
+      "learning_rate": 8.734467065350022e-07,
+      "loss": 0.1011,
+      "step": 2520
+    },
+    {
+      "epoch": 2.4539282250242485,
+      "grad_norm": 0.11884056049855944,
+      "learning_rate": 8.441069877699287e-07,
+      "loss": 0.0988,
+      "step": 2530
+    },
+    {
+      "epoch": 2.463627546071775,
+      "grad_norm": 0.12149227620777672,
+      "learning_rate": 8.152230095063051e-07,
+      "loss": 0.1002,
+      "step": 2540
+    },
+    {
+      "epoch": 2.473326867119302,
+      "grad_norm": 0.12036233836849276,
+      "learning_rate": 7.867979391978398e-07,
+      "loss": 0.1007,
+      "step": 2550
+    },
+    {
+      "epoch": 2.4830261881668285,
+      "grad_norm": 0.12618686097566623,
+      "learning_rate": 7.588348939738116e-07,
+      "loss": 0.0986,
+      "step": 2560
+    },
+    {
+      "epoch": 2.492725509214355,
+      "grad_norm": 0.12028662540848738,
+      "learning_rate": 7.31336940297247e-07,
+      "loss": 0.0992,
+      "step": 2570
+    },
+    {
+      "epoch": 2.502424830261882,
+      "grad_norm": 0.11545036923542605,
+      "learning_rate": 7.043070936286395e-07,
+      "loss": 0.0978,
+      "step": 2580
+    },
+    {
+      "epoch": 2.5121241513094086,
+      "grad_norm": 0.12019777054976608,
+      "learning_rate": 6.777483180952732e-07,
+      "loss": 0.1012,
+      "step": 2590
+    },
+    {
+      "epoch": 2.5218234723569353,
+      "grad_norm": 0.11782278703441862,
+      "learning_rate": 6.516635261661775e-07,
+      "loss": 0.0974,
+      "step": 2600
+    },
+    {
+      "epoch": 2.531522793404462,
+      "grad_norm": 0.12063704346978395,
+      "learning_rate": 6.260555783327366e-07,
+      "loss": 0.0966,
+      "step": 2610
+    },
+    {
+      "epoch": 2.541222114451988,
+      "grad_norm": 0.13985159244922432,
+      "learning_rate": 6.009272827950042e-07,
+      "loss": 0.0999,
+      "step": 2620
+    },
+    {
+      "epoch": 2.550921435499515,
+      "grad_norm": 0.1344038669131746,
+      "learning_rate": 5.762813951537582e-07,
+      "loss": 0.101,
+      "step": 2630
+    },
+    {
+      "epoch": 2.5606207565470416,
+      "grad_norm": 0.12488293218956574,
+      "learning_rate": 5.521206181083111e-07,
+      "loss": 0.0978,
+      "step": 2640
+    },
+    {
+      "epoch": 2.5703200775945683,
+      "grad_norm": 0.12688963896793887,
+      "learning_rate": 5.28447601160132e-07,
+      "loss": 0.0965,
+      "step": 2650
+    },
+    {
+      "epoch": 2.580019398642095,
+      "grad_norm": 0.12551768173775268,
+      "learning_rate": 5.052649403223015e-07,
+      "loss": 0.0976,
+      "step": 2660
+    },
+    {
+      "epoch": 2.5897187196896216,
+      "grad_norm": 0.11519577314916575,
+      "learning_rate": 4.825751778348259e-07,
+      "loss": 0.0981,
+      "step": 2670
+    },
+    {
+      "epoch": 2.5994180407371483,
+      "grad_norm": 0.11984916882145599,
+      "learning_rate": 4.6038080188585135e-07,
+      "loss": 0.0992,
+      "step": 2680
+    },
+    {
+      "epoch": 2.609117361784675,
+      "grad_norm": 0.1175248528788484,
+      "learning_rate": 4.38684246338808e-07,
+      "loss": 0.0987,
+      "step": 2690
+    },
+    {
+      "epoch": 2.6188166828322017,
+      "grad_norm": 0.13159038738087242,
+      "learning_rate": 4.1748789046551055e-07,
+      "loss": 0.0978,
+      "step": 2700
+    },
+    {
+      "epoch": 2.6285160038797284,
+      "grad_norm": 0.12093588925930802,
+      "learning_rate": 3.967940586852409e-07,
+      "loss": 0.0976,
+      "step": 2710
+    },
+    {
+      "epoch": 2.638215324927255,
+      "grad_norm": 0.11669957994474343,
+      "learning_rate": 3.7660502030985203e-07,
+      "loss": 0.0988,
+      "step": 2720
+    },
+    {
+      "epoch": 2.6479146459747818,
+      "grad_norm": 0.11770882115889388,
+      "learning_rate": 3.569229892949133e-07,
+      "loss": 0.0999,
+      "step": 2730
+    },
+    {
+      "epoch": 2.6576139670223085,
+      "grad_norm": 0.11899985694439451,
+      "learning_rate": 3.3775012399692055e-07,
+      "loss": 0.0989,
+      "step": 2740
+    },
+    {
+      "epoch": 2.667313288069835,
+      "grad_norm": 0.12610632399439725,
+      "learning_rate": 3.1908852693661116e-07,
+      "loss": 0.0994,
+      "step": 2750
+    },
+    {
+      "epoch": 2.677012609117362,
+      "grad_norm": 0.11520791632519826,
+      "learning_rate": 3.0094024456840176e-07,
+      "loss": 0.0987,
+      "step": 2760
+    },
+    {
+      "epoch": 2.6867119301648885,
+      "grad_norm": 0.12311171355367961,
+      "learning_rate": 2.833072670559661e-07,
+      "loss": 0.0981,
+      "step": 2770
+    },
+    {
+      "epoch": 2.696411251212415,
+      "grad_norm": 0.12430861035520042,
+      "learning_rate": 2.6619152805399286e-07,
+      "loss": 0.098,
+      "step": 2780
+    },
+    {
+      "epoch": 2.706110572259942,
+      "grad_norm": 0.1256391775818187,
+      "learning_rate": 2.49594904496141e-07,
+      "loss": 0.0972,
+      "step": 2790
+    },
+    {
+      "epoch": 2.7158098933074686,
+      "grad_norm": 0.1132674415609218,
+      "learning_rate": 2.3351921638921193e-07,
+      "loss": 0.0986,
+      "step": 2800
+    },
+    {
+      "epoch": 2.7255092143549953,
+      "grad_norm": 0.12235997624262486,
+      "learning_rate": 2.1796622661356238e-07,
+      "loss": 0.1005,
+      "step": 2810
+    },
+    {
+      "epoch": 2.735208535402522,
+      "grad_norm": 0.11873323598735666,
+      "learning_rate": 2.0293764072978618e-07,
+      "loss": 0.1017,
+      "step": 2820
+    },
+    {
+      "epoch": 2.7449078564500486,
+      "grad_norm": 0.11502932974467346,
+      "learning_rate": 1.8843510679168341e-07,
+      "loss": 0.0969,
+      "step": 2830
+    },
+    {
+      "epoch": 2.7546071774975753,
+      "grad_norm": 0.11893095537270826,
+      "learning_rate": 1.744602151655289e-07,
+      "loss": 0.0967,
+      "step": 2840
+    },
+    {
+      "epoch": 2.7643064985451016,
+      "grad_norm": 0.11664278880666168,
+      "learning_rate": 1.6101449835567273e-07,
+      "loss": 0.097,
+      "step": 2850
+    },
+    {
+      "epoch": 2.7740058195926283,
+      "grad_norm": 0.11762507721842773,
+      "learning_rate": 1.4809943083648194e-07,
+      "loss": 0.0966,
+      "step": 2860
+    },
+    {
+      "epoch": 2.783705140640155,
+      "grad_norm": 0.11533591737174845,
+      "learning_rate": 1.3571642889064984e-07,
+      "loss": 0.0965,
+      "step": 2870
+    },
+    {
+      "epoch": 2.7934044616876816,
+      "grad_norm": 0.11593673764859609,
+      "learning_rate": 1.2386685045388313e-07,
+      "loss": 0.0934,
+      "step": 2880
+    },
+    {
+      "epoch": 2.8031037827352083,
+      "grad_norm": 0.11623880074957675,
+      "learning_rate": 1.1255199496599034e-07,
+      "loss": 0.1002,
+      "step": 2890
+    },
+    {
+      "epoch": 2.812803103782735,
+      "grad_norm": 0.11273238019620804,
+      "learning_rate": 1.0177310322838251e-07,
+      "loss": 0.0984,
+      "step": 2900
+    },
+    {
+      "epoch": 2.8225024248302617,
+      "grad_norm": 0.11740279413666126,
+      "learning_rate": 9.153135726800599e-08,
+      "loss": 0.0991,
+      "step": 2910
+    },
+    {
+      "epoch": 2.8322017458777884,
+      "grad_norm": 0.1279718420944925,
+      "learning_rate": 8.182788020771826e-08,
+      "loss": 0.0995,
+      "step": 2920
+    },
+    {
+      "epoch": 2.841901066925315,
+      "grad_norm": 0.1128016665542334,
+      "learning_rate": 7.266373614312927e-08,
+      "loss": 0.0997,
+      "step": 2930
+    },
+    {
+      "epoch": 2.8516003879728418,
+      "grad_norm": 0.115197840258161,
+      "learning_rate": 6.403993002590425e-08,
+      "loss": 0.099,
+      "step": 2940
+    },
+    {
+      "epoch": 2.8612997090203685,
+      "grad_norm": 0.11734253101361407,
+      "learning_rate": 5.595740755356627e-08,
+      "loss": 0.0961,
+      "step": 2950
+    },
+    {
+      "epoch": 2.870999030067895,
+      "grad_norm": 0.11746949240153405,
+      "learning_rate": 4.841705506578587e-08,
+      "loss": 0.0984,
+      "step": 2960
+    },
+    {
+      "epoch": 2.880698351115422,
+      "grad_norm": 0.11752266068577234,
+      "learning_rate": 4.1419699447186045e-08,
+      "loss": 0.0995,
+      "step": 2970
+    },
+    {
+      "epoch": 2.8903976721629485,
+      "grad_norm": 0.11630585391542382,
+      "learning_rate": 3.4966108036662006e-08,
+      "loss": 0.0987,
+      "step": 2980
+    },
+    {
+      "epoch": 2.900096993210475,
+      "grad_norm": 0.12834768725602652,
+      "learning_rate": 2.9056988543239018e-08,
+      "loss": 0.1002,
+      "step": 2990
+    },
+    {
+      "epoch": 2.909796314258002,
+      "grad_norm": 0.11104514790150172,
+      "learning_rate": 2.3692988968458398e-08,
+      "loss": 0.0966,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9194956353055286,
+      "grad_norm": 0.1262237252529426,
+      "learning_rate": 1.8874697535319897e-08,
+      "loss": 0.0965,
+      "step": 3010
+    },
+    {
+      "epoch": 2.9291949563530553,
+      "grad_norm": 0.11707823484874674,
+      "learning_rate": 1.4602642623777752e-08,
+      "loss": 0.0992,
+      "step": 3020
+    },
+    {
+      "epoch": 2.938894277400582,
+      "grad_norm": 0.11846337746129845,
+      "learning_rate": 1.0877292712792586e-08,
+      "loss": 0.0954,
+      "step": 3030
+    },
+    {
+      "epoch": 2.9485935984481086,
+      "grad_norm": 0.1144938540856074,
+      "learning_rate": 7.699056328964726e-09,
+      "loss": 0.0985,
+      "step": 3040
+    },
+    {
+      "epoch": 2.9582929194956353,
+      "grad_norm": 0.1287666028823606,
+      "learning_rate": 5.06828200172893e-09,
+      "loss": 0.1001,
+      "step": 3050
+    },
+    {
+      "epoch": 2.967992240543162,
+      "grad_norm": 0.11479880891480539,
+      "learning_rate": 2.9852582251355124e-09,
+      "loss": 0.0979,
+      "step": 3060
+    },
+    {
+      "epoch": 2.9776915615906887,
+      "grad_norm": 0.13479592940306032,
+      "learning_rate": 1.4502134262156519e-09,
+      "loss": 0.0973,
+      "step": 3070
+    },
+    {
+      "epoch": 2.9873908826382154,
+      "grad_norm": 0.14403422269717034,
+      "learning_rate": 4.6331593993032e-10,
+      "loss": 0.0973,
+      "step": 3080
+    },
+    {
+      "epoch": 2.997090203685742,
+      "grad_norm": 0.11557815982586303,
+      "learning_rate": 2.467399070893439e-11,
+      "loss": 0.0964,
+      "step": 3090
+    },
+    {
+      "epoch": 3.0,
+      "step": 3093,
+      "total_flos": 3.528412807299072e+16,
+      "train_loss": 0.12713232355097756,
+      "train_runtime": 177593.1778,
+      "train_samples_per_second": 3.064,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3093,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.528412807299072e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660e7a5e308fdce84bc69ebb74a653f0853c61ca29f30f750f0288438778452b
+size 7224