Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/proj/memorization/FK/warrior/model_weights/deepseek-coder-6.7b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.46.1"
+}

global_step845/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccefdfe826d745fe932138070b0c28fd1bd878e46f10aa5a6fd9a6d758c3bb4
+size 10110774092

global_step845/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d68ea212a0139e2bc64b1b69dbd0df142d4f1d842981a2eca90e71a5cf2b8d
+size 10110774092

global_step845/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25ffe04cc2c287e3127f1aa82636e8e05159f8beb5af4a1356e52e1485232ea
+size 10110774092

global_step845/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cde4d07d796c36e8b46f02a8421e515d3ac437278106289d127da3fd05436b
+size 10110774092

global_step845/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e8e12cf991b48a9cac61cd55df77a1388e4e864fdb27c3bad5004fb413ce23
+size 10110774092

global_step845/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fde39be3aa5ca691815f343e8f95728494eb43fe3b3bbf6331cf6539965461
+size 10110774092

global_step845/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a118611fe77d30cce932b5db4295b6f765df16126f4ecca7d296bb3857d12d06
+size 10110774092

global_step845/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3bf700c7517f78586cff8be96f0348ecc298f08675e3ba440b628c4c16fbaa
+size 10110774092

global_step845/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c670b34855ce48d046252cebca25737de74c89fa95c338e3c2f04dc45c0e98
+size 150693

global_step845/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f6dc5f51e30dde964227dafabb3826597e062ce4f0f4fe4dd809fa66054dd3
+size 150693

global_step845/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d93e246a780702d227587bcc0db822d5b5e33b37b51ff77de98ce2d64c8a16
+size 150693

global_step845/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5cda5a571b28b183f1ae5bbd12254a96d94b5dcdc195e703242482e2b5aec4
+size 150693

global_step845/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d3a3a79a849947f7eacc4df8922719ad6bf28b9ef62d882f5fd8f4e52298ab
+size 150693

global_step845/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0205119767e816464210965642d7d02a0de7dade8bd98a4301cd1c47795b5399
+size 150693

global_step845/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e431dd3a59e8f2a1119123b6f8cad74ecda28f3ac32c77c4992ac817ecdb0d80
+size 150693

global_step845/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffc3ab12332875c98030184cdcbf151d8ccab74ee300a5199d075ca9ac1b621
+size 150693

latest

@@ -0,0 +1 @@
+global_step845

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c40b50f38df6d2adb7ea1955b2f47b186f6fec960ea1085113b403cf88ab1fc
+size 4941082504

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c4c00831d451cecc8c1db7863da78f7e843fe6552d600b729436c686839e90
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4605e8caf2c02e20f56574afb3090fc5137da316e511b98884e133423529cbee
+size 3592585968

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13481025536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037fd64165ffd3201e22e4503898a667abbe1bfd941762d4e7bce996d8cdac74
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1255 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.985250737463127,
+  "eval_steps": 500,
+  "global_step": 845,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0058997050147492625,
+      "grad_norm": 1.106083567904979,
+      "learning_rate": 1.1764705882352942e-07,
+      "loss": 0.7816,
+      "step": 1
+    },
+    {
+      "epoch": 0.029498525073746312,
+      "grad_norm": 1.1433080381542629,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.7757,
+      "step": 5
+    },
+    {
+      "epoch": 0.058997050147492625,
+      "grad_norm": 0.997014214705184,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.7736,
+      "step": 10
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 1.304994737635826,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.7594,
+      "step": 15
+    },
+    {
+      "epoch": 0.11799410029498525,
+      "grad_norm": 0.5741459890364078,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.7332,
+      "step": 20
+    },
+    {
+      "epoch": 0.14749262536873156,
+      "grad_norm": 0.4736057964790196,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.7054,
+      "step": 25
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.28699264838960103,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.6613,
+      "step": 30
+    },
+    {
+      "epoch": 0.20648967551622419,
+      "grad_norm": 1.92856903253004,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.6422,
+      "step": 35
+    },
+    {
+      "epoch": 0.2359882005899705,
+      "grad_norm": 0.346137515731761,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.6165,
+      "step": 40
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.17870145514430266,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.6133,
+      "step": 45
+    },
+    {
+      "epoch": 0.2949852507374631,
+      "grad_norm": 0.1437606973005659,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.5986,
+      "step": 50
+    },
+    {
+      "epoch": 0.32448377581120946,
+      "grad_norm": 0.2706264861398608,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.5884,
+      "step": 55
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.6332617880988516,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.5818,
+      "step": 60
+    },
+    {
+      "epoch": 0.3834808259587021,
+      "grad_norm": 0.1015116079049458,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.5798,
+      "step": 65
+    },
+    {
+      "epoch": 0.41297935103244837,
+      "grad_norm": 0.12119348356809045,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.5751,
+      "step": 70
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.07879965059698645,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.5708,
+      "step": 75
+    },
+    {
+      "epoch": 0.471976401179941,
+      "grad_norm": 0.05646247242948782,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.5683,
+      "step": 80
+    },
+    {
+      "epoch": 0.5014749262536873,
+      "grad_norm": 0.25525240715915204,
+      "learning_rate": 1e-05,
+      "loss": 0.5662,
+      "step": 85
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.05365048303720814,
+      "learning_rate": 9.998932083939657e-06,
+      "loss": 0.5598,
+      "step": 90
+    },
+    {
+      "epoch": 0.56047197640118,
+      "grad_norm": 0.1595860307142945,
+      "learning_rate": 9.995728791936505e-06,
+      "loss": 0.5538,
+      "step": 95
+    },
+    {
+      "epoch": 0.5899705014749262,
+      "grad_norm": 0.06609453133465848,
+      "learning_rate": 9.990391492329341e-06,
+      "loss": 0.5529,
+      "step": 100
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 1.6293266027560704,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 0.5527,
+      "step": 105
+    },
+    {
+      "epoch": 0.6489675516224189,
+      "grad_norm": 1.050544643875783,
+      "learning_rate": 9.973324900566214e-06,
+      "loss": 0.5477,
+      "step": 110
+    },
+    {
+      "epoch": 0.6784660766961652,
+      "grad_norm": 0.052879637742834044,
+      "learning_rate": 9.961602898685225e-06,
+      "loss": 0.5474,
+      "step": 115
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.04928862663129842,
+      "learning_rate": 9.947761466636014e-06,
+      "loss": 0.5553,
+      "step": 120
+    },
+    {
+      "epoch": 0.7374631268436578,
+      "grad_norm": 0.052753160381468045,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.5464,
+      "step": 125
+    },
+    {
+      "epoch": 0.7669616519174042,
+      "grad_norm": 0.045802114899820966,
+      "learning_rate": 9.913744865236798e-06,
+      "loss": 0.5404,
+      "step": 130
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.11489905003299361,
+      "learning_rate": 9.893584226636773e-06,
+      "loss": 0.5317,
+      "step": 135
+    },
+    {
+      "epoch": 0.8259587020648967,
+      "grad_norm": 0.4919380291913098,
+      "learning_rate": 9.871333213161438e-06,
+      "loss": 0.5481,
+      "step": 140
+    },
+    {
+      "epoch": 0.855457227138643,
+      "grad_norm": 0.3232334093103194,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 0.5339,
+      "step": 145
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.05048150556921708,
+      "learning_rate": 9.820598970006068e-06,
+      "loss": 0.5325,
+      "step": 150
+    },
+    {
+      "epoch": 0.9144542772861357,
+      "grad_norm": 0.058183934565565226,
+      "learning_rate": 9.792137412291265e-06,
+      "loss": 0.5373,
+      "step": 155
+    },
+    {
+      "epoch": 0.943952802359882,
+      "grad_norm": 2.1026211814523927,
+      "learning_rate": 9.761628814374074e-06,
+      "loss": 0.535,
+      "step": 160
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.05037291432057576,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.5392,
+      "step": 165
+    },
+    {
+      "epoch": 0.9970501474926253,
+      "eval_loss": 0.5948278307914734,
+      "eval_runtime": 7.8455,
+      "eval_samples_per_second": 16.825,
+      "eval_steps_per_second": 0.382,
+      "step": 169
+    },
+    {
+      "epoch": 1.0029498525073746,
+      "grad_norm": 0.07970296331803481,
+      "learning_rate": 9.694523495787149e-06,
+      "loss": 0.5852,
+      "step": 170
+    },
+    {
+      "epoch": 1.0324483775811208,
+      "grad_norm": 0.06217085534785087,
+      "learning_rate": 9.657955440256396e-06,
+      "loss": 0.5318,
+      "step": 175
+    },
+    {
+      "epoch": 1.0619469026548674,
+      "grad_norm": 0.4533798599174413,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.5265,
+      "step": 180
+    },
+    {
+      "epoch": 1.0914454277286136,
+      "grad_norm": 0.0843198746785751,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 0.525,
+      "step": 185
+    },
+    {
+      "epoch": 1.12094395280236,
+      "grad_norm": 0.0514110786588162,
+      "learning_rate": 9.536379665907801e-06,
+      "loss": 0.5244,
+      "step": 190
+    },
+    {
+      "epoch": 1.1504424778761062,
+      "grad_norm": 0.08421706916029806,
+      "learning_rate": 9.491954909459895e-06,
+      "loss": 0.5241,
+      "step": 195
+    },
+    {
+      "epoch": 1.1799410029498525,
+      "grad_norm": 0.058452224546329916,
+      "learning_rate": 9.445611340695926e-06,
+      "loss": 0.5274,
+      "step": 200
+    },
+    {
+      "epoch": 1.2094395280235988,
+      "grad_norm": 1.2314254826441438,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.5247,
+      "step": 205
+    },
+    {
+      "epoch": 1.238938053097345,
+      "grad_norm": 0.04772904502073005,
+      "learning_rate": 9.347247763081834e-06,
+      "loss": 0.5276,
+      "step": 210
+    },
+    {
+      "epoch": 1.2684365781710913,
+      "grad_norm": 0.05022705703233357,
+      "learning_rate": 9.295269771849426e-06,
+      "loss": 0.5179,
+      "step": 215
+    },
+    {
+      "epoch": 1.2979351032448379,
+      "grad_norm": 0.2724781073186335,
+      "learning_rate": 9.241456985587868e-06,
+      "loss": 0.5229,
+      "step": 220
+    },
+    {
+      "epoch": 1.3274336283185841,
+      "grad_norm": 0.07955839264628826,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 0.5222,
+      "step": 225
+    },
+    {
+      "epoch": 1.3569321533923304,
+      "grad_norm": 0.047043054214154625,
+      "learning_rate": 9.12841974998278e-06,
+      "loss": 0.5195,
+      "step": 230
+    },
+    {
+      "epoch": 1.3864306784660767,
+      "grad_norm": 0.045497809508961325,
+      "learning_rate": 9.069243586350976e-06,
+      "loss": 0.5148,
+      "step": 235
+    },
+    {
+      "epoch": 1.415929203539823,
+      "grad_norm": 0.8566869256944054,
+      "learning_rate": 9.008329178487442e-06,
+      "loss": 0.5207,
+      "step": 240
+    },
+    {
+      "epoch": 1.4454277286135693,
+      "grad_norm": 0.06712694488880502,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.5219,
+      "step": 245
+    },
+    {
+      "epoch": 1.4749262536873156,
+      "grad_norm": 0.134636628527114,
+      "learning_rate": 8.881390443828788e-06,
+      "loss": 0.5164,
+      "step": 250
+    },
+    {
+      "epoch": 1.504424778761062,
+      "grad_norm": 1.017642297039446,
+      "learning_rate": 8.815420340999034e-06,
+      "loss": 0.5164,
+      "step": 255
+    },
+    {
+      "epoch": 1.5339233038348081,
+      "grad_norm": 0.8748816419357938,
+      "learning_rate": 8.747820418705632e-06,
+      "loss": 0.519,
+      "step": 260
+    },
+    {
+      "epoch": 1.5634218289085546,
+      "grad_norm": 0.05916211446645424,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 0.5132,
+      "step": 265
+    },
+    {
+      "epoch": 1.592920353982301,
+      "grad_norm": 0.06267760570910012,
+      "learning_rate": 8.607847305265312e-06,
+      "loss": 0.5119,
+      "step": 270
+    },
+    {
+      "epoch": 1.6224188790560472,
+      "grad_norm": 0.053722149220927,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.514,
+      "step": 275
+    },
+    {
+      "epoch": 1.6519174041297935,
+      "grad_norm": 0.055409146579795114,
+      "learning_rate": 8.461710245224149e-06,
+      "loss": 0.5231,
+      "step": 280
+    },
+    {
+      "epoch": 1.6814159292035398,
+      "grad_norm": 0.049718992850954775,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.5127,
+      "step": 285
+    },
+    {
+      "epoch": 1.7109144542772863,
+      "grad_norm": 0.0443810313683345,
+      "learning_rate": 8.309658911297833e-06,
+      "loss": 0.5116,
+      "step": 290
+    },
+    {
+      "epoch": 1.7404129793510323,
+      "grad_norm": 0.05127452771633588,
+      "learning_rate": 8.231496189304704e-06,
+      "loss": 0.5078,
+      "step": 295
+    },
+    {
+      "epoch": 1.7699115044247788,
+      "grad_norm": 0.04591077767546143,
+      "learning_rate": 8.151953080639777e-06,
+      "loss": 0.5125,
+      "step": 300
+    },
+    {
+      "epoch": 1.799410029498525,
+      "grad_norm": 0.04535715037949931,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.5131,
+      "step": 305
+    },
+    {
+      "epoch": 1.8289085545722714,
+      "grad_norm": 0.045271495366352554,
+      "learning_rate": 7.988862191016204e-06,
+      "loss": 0.5123,
+      "step": 310
+    },
+    {
+      "epoch": 1.8584070796460177,
+      "grad_norm": 0.056004335836578926,
+      "learning_rate": 7.905384077009693e-06,
+      "loss": 0.5097,
+      "step": 315
+    },
+    {
+      "epoch": 1.887905604719764,
+      "grad_norm": 0.04430378987199138,
+      "learning_rate": 7.820664880476257e-06,
+      "loss": 0.5143,
+      "step": 320
+    },
+    {
+      "epoch": 1.9174041297935103,
+      "grad_norm": 0.04609433007960605,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.5086,
+      "step": 325
+    },
+    {
+      "epoch": 1.9469026548672566,
+      "grad_norm": 0.7820689144245092,
+      "learning_rate": 7.647648511303545e-06,
+      "loss": 0.5095,
+      "step": 330
+    },
+    {
+      "epoch": 1.976401179941003,
+      "grad_norm": 0.049876695974305066,
+      "learning_rate": 7.559425245448006e-06,
+      "loss": 0.5116,
+      "step": 335
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.569428026676178,
+      "eval_runtime": 7.9223,
+      "eval_samples_per_second": 16.662,
+      "eval_steps_per_second": 0.379,
+      "step": 339
+    },
+    {
+      "epoch": 2.005899705014749,
+      "grad_norm": 0.059860668705846505,
+      "learning_rate": 7.470108679062521e-06,
+      "loss": 0.5565,
+      "step": 340
+    },
+    {
+      "epoch": 2.0353982300884956,
+      "grad_norm": 0.045373657400373905,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 0.5022,
+      "step": 345
+    },
+    {
+      "epoch": 2.0648967551622417,
+      "grad_norm": 0.04575003134013503,
+      "learning_rate": 7.288348707578409e-06,
+      "loss": 0.5009,
+      "step": 350
+    },
+    {
+      "epoch": 2.094395280235988,
+      "grad_norm": 0.0764963225778181,
+      "learning_rate": 7.195982944236853e-06,
+      "loss": 0.5023,
+      "step": 355
+    },
+    {
+      "epoch": 2.1238938053097347,
+      "grad_norm": 0.2864046551111833,
+      "learning_rate": 7.102679130713538e-06,
+      "loss": 0.5027,
+      "step": 360
+    },
+    {
+      "epoch": 2.1533923303834808,
+      "grad_norm": 0.0726950183868685,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.4995,
+      "step": 365
+    },
+    {
+      "epoch": 2.1828908554572273,
+      "grad_norm": 0.047612550060808626,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.5073,
+      "step": 370
+    },
+    {
+      "epoch": 2.2123893805309733,
+      "grad_norm": 0.045980323605959564,
+      "learning_rate": 6.817539852819149e-06,
+      "loss": 0.5066,
+      "step": 375
+    },
+    {
+      "epoch": 2.24188790560472,
+      "grad_norm": 0.05019367448115624,
+      "learning_rate": 6.720886151813194e-06,
+      "loss": 0.5054,
+      "step": 380
+    },
+    {
+      "epoch": 2.271386430678466,
+      "grad_norm": 0.04465323510528684,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 0.5003,
+      "step": 385
+    },
+    {
+      "epoch": 2.3008849557522124,
+      "grad_norm": 0.08235286259691993,
+      "learning_rate": 6.525415036677745e-06,
+      "loss": 0.5001,
+      "step": 390
+    },
+    {
+      "epoch": 2.330383480825959,
+      "grad_norm": 0.050999382045359705,
+      "learning_rate": 6.426681121245527e-06,
+      "loss": 0.498,
+      "step": 395
+    },
+    {
+      "epoch": 2.359882005899705,
+      "grad_norm": 0.04526036928138616,
+      "learning_rate": 6.327337775540362e-06,
+      "loss": 0.5018,
+      "step": 400
+    },
+    {
+      "epoch": 2.3893805309734515,
+      "grad_norm": 0.05806925044679012,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.4955,
+      "step": 405
+    },
+    {
+      "epoch": 2.4188790560471976,
+      "grad_norm": 0.06164688967940204,
+      "learning_rate": 6.126992780079032e-06,
+      "loss": 0.4971,
+      "step": 410
+    },
+    {
+      "epoch": 2.448377581120944,
+      "grad_norm": 0.5078396005551373,
+      "learning_rate": 6.026076710978172e-06,
+      "loss": 0.5015,
+      "step": 415
+    },
+    {
+      "epoch": 2.47787610619469,
+      "grad_norm": 0.046783560822131726,
+      "learning_rate": 5.924722336357793e-06,
+      "loss": 0.4975,
+      "step": 420
+    },
+    {
+      "epoch": 2.5073746312684366,
+      "grad_norm": 0.04594136178012529,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 0.4996,
+      "step": 425
+    },
+    {
+      "epoch": 2.5368731563421827,
+      "grad_norm": 0.05594049666474868,
+      "learning_rate": 5.720872020036734e-06,
+      "loss": 0.5001,
+      "step": 430
+    },
+    {
+      "epoch": 2.566371681415929,
+      "grad_norm": 0.04465947789722648,
+      "learning_rate": 5.61846315634674e-06,
+      "loss": 0.4924,
+      "step": 435
+    },
+    {
+      "epoch": 2.5958702064896757,
+      "grad_norm": 0.060580400184871375,
+      "learning_rate": 5.515790105961785e-06,
+      "loss": 0.5022,
+      "step": 440
+    },
+    {
+      "epoch": 2.6253687315634218,
+      "grad_norm": 0.12381786538248248,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.4972,
+      "step": 445
+    },
+    {
+      "epoch": 2.6548672566371683,
+      "grad_norm": 0.05202660251491312,
+      "learning_rate": 5.309826973142974e-06,
+      "loss": 0.5071,
+      "step": 450
+    },
+    {
+      "epoch": 2.6843657817109143,
+      "grad_norm": 0.10377000214654016,
+      "learning_rate": 5.206624871244066e-06,
+      "loss": 0.4995,
+      "step": 455
+    },
+    {
+      "epoch": 2.713864306784661,
+      "grad_norm": 0.044378951816130024,
+      "learning_rate": 5.103334506137773e-06,
+      "loss": 0.4974,
+      "step": 460
+    },
+    {
+      "epoch": 2.7433628318584073,
+      "grad_norm": 0.04467225886658485,
+      "learning_rate": 5e-06,
+      "loss": 0.497,
+      "step": 465
+    },
+    {
+      "epoch": 2.7728613569321534,
+      "grad_norm": 0.051986874546360556,
+      "learning_rate": 4.89666549386223e-06,
+      "loss": 0.4971,
+      "step": 470
+    },
+    {
+      "epoch": 2.8023598820058995,
+      "grad_norm": 0.12453400877778924,
+      "learning_rate": 4.793375128755934e-06,
+      "loss": 0.4989,
+      "step": 475
+    },
+    {
+      "epoch": 2.831858407079646,
+      "grad_norm": 0.04420192438109124,
+      "learning_rate": 4.690173026857028e-06,
+      "loss": 0.4965,
+      "step": 480
+    },
+    {
+      "epoch": 2.8613569321533925,
+      "grad_norm": 0.043489134164912784,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.5001,
+      "step": 485
+    },
+    {
+      "epoch": 2.8908554572271385,
+      "grad_norm": 0.057345889273731514,
+      "learning_rate": 4.4842098940382155e-06,
+      "loss": 0.4965,
+      "step": 490
+    },
+    {
+      "epoch": 2.920353982300885,
+      "grad_norm": 0.04346872325174773,
+      "learning_rate": 4.381536843653262e-06,
+      "loss": 0.4973,
+      "step": 495
+    },
+    {
+      "epoch": 2.949852507374631,
+      "grad_norm": 0.05768914593482109,
+      "learning_rate": 4.279127979963266e-06,
+      "loss": 0.5033,
+      "step": 500
+    },
+    {
+      "epoch": 2.9793510324483776,
+      "grad_norm": 0.07469078383028477,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 0.4932,
+      "step": 505
+    },
+    {
+      "epoch": 2.9970501474926254,
+      "eval_loss": 0.5568187236785889,
+      "eval_runtime": 7.8687,
+      "eval_samples_per_second": 16.775,
+      "eval_steps_per_second": 0.381,
+      "step": 508
+    },
+    {
+      "epoch": 3.0088495575221237,
+      "grad_norm": 0.2325348943012431,
+      "learning_rate": 4.075277663642208e-06,
+      "loss": 0.5464,
+      "step": 510
+    },
+    {
+      "epoch": 3.03834808259587,
+      "grad_norm": 0.05925612576951284,
+      "learning_rate": 3.973923289021829e-06,
+      "loss": 0.4879,
+      "step": 515
+    },
+    {
+      "epoch": 3.0678466076696167,
+      "grad_norm": 0.04576359473331283,
+      "learning_rate": 3.8730072199209705e-06,
+      "loss": 0.4958,
+      "step": 520
+    },
+    {
+      "epoch": 3.0973451327433628,
+      "grad_norm": 0.04411225192878531,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.4937,
+      "step": 525
+    },
+    {
+      "epoch": 3.1268436578171093,
+      "grad_norm": 0.04681950811111515,
+      "learning_rate": 3.67266222445964e-06,
+      "loss": 0.497,
+      "step": 530
+    },
+    {
+      "epoch": 3.1563421828908553,
+      "grad_norm": 0.05140593649320022,
+      "learning_rate": 3.573318878754475e-06,
+      "loss": 0.4908,
+      "step": 535
+    },
+    {
+      "epoch": 3.185840707964602,
+      "grad_norm": 0.04848431413605644,
+      "learning_rate": 3.4745849633222566e-06,
+      "loss": 0.4907,
+      "step": 540
+    },
+    {
+      "epoch": 3.215339233038348,
+      "grad_norm": 0.11169113540037036,
+      "learning_rate": 3.3765026539765832e-06,
+      "loss": 0.4954,
+      "step": 545
+    },
+    {
+      "epoch": 3.2448377581120944,
+      "grad_norm": 0.045625351277697936,
+      "learning_rate": 3.2791138481868084e-06,
+      "loss": 0.4875,
+      "step": 550
+    },
+    {
+      "epoch": 3.274336283185841,
+      "grad_norm": 0.04470601186507566,
+      "learning_rate": 3.1824601471808504e-06,
+      "loss": 0.4913,
+      "step": 555
+    },
+    {
+      "epoch": 3.303834808259587,
+      "grad_norm": 0.04510846620481134,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.4977,
+      "step": 560
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.04641841941445331,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 0.492,
+      "step": 565
+    },
+    {
+      "epoch": 3.3628318584070795,
+      "grad_norm": 0.044008859582161636,
+      "learning_rate": 2.8973208692864623e-06,
+      "loss": 0.4927,
+      "step": 570
+    },
+    {
+      "epoch": 3.392330383480826,
+      "grad_norm": 0.058212049337815264,
+      "learning_rate": 2.804017055763149e-06,
+      "loss": 0.4934,
+      "step": 575
+    },
+    {
+      "epoch": 3.421828908554572,
+      "grad_norm": 0.04488763032020628,
+      "learning_rate": 2.711651292421593e-06,
+      "loss": 0.4896,
+      "step": 580
+    },
+    {
+      "epoch": 3.4513274336283186,
+      "grad_norm": 0.06877731409673225,
+      "learning_rate": 2.6202630348146323e-06,
+      "loss": 0.4927,
+      "step": 585
+    },
+    {
+      "epoch": 3.4808259587020647,
+      "grad_norm": 0.04405767793752617,
+      "learning_rate": 2.529891320937481e-06,
+      "loss": 0.4885,
+      "step": 590
+    },
+    {
+      "epoch": 3.510324483775811,
+      "grad_norm": 0.046525497495949794,
+      "learning_rate": 2.4405747545519966e-06,
+      "loss": 0.493,
+      "step": 595
+    },
+    {
+      "epoch": 3.5398230088495577,
+      "grad_norm": 0.04464423997103832,
+      "learning_rate": 2.352351488696457e-06,
+      "loss": 0.4871,
+      "step": 600
+    },
+    {
+      "epoch": 3.5693215339233038,
+      "grad_norm": 0.04487754260652396,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 0.4897,
+      "step": 605
+    },
+    {
+      "epoch": 3.5988200589970503,
+      "grad_norm": 0.06310865942039023,
+      "learning_rate": 2.179335119523745e-06,
+      "loss": 0.4929,
+      "step": 610
+    },
+    {
+      "epoch": 3.6283185840707963,
+      "grad_norm": 0.04443946832576421,
+      "learning_rate": 2.094615922990309e-06,
+      "loss": 0.4938,
+      "step": 615
+    },
+    {
+      "epoch": 3.657817109144543,
+      "grad_norm": 0.04515597574554685,
+      "learning_rate": 2.0111378089837958e-06,
+      "loss": 0.4882,
+      "step": 620
+    },
+    {
+      "epoch": 3.6873156342182893,
+      "grad_norm": 0.04358107380856759,
+      "learning_rate": 1.928936436551661e-06,
+      "loss": 0.4903,
+      "step": 625
+    },
+    {
+      "epoch": 3.7168141592920354,
+      "grad_norm": 0.045563864404630304,
+      "learning_rate": 1.848046919360225e-06,
+      "loss": 0.4921,
+      "step": 630
+    },
+    {
+      "epoch": 3.7463126843657815,
+      "grad_norm": 0.04666731006378484,
+      "learning_rate": 1.7685038106952952e-06,
+      "loss": 0.4934,
+      "step": 635
+    },
+    {
+      "epoch": 3.775811209439528,
+      "grad_norm": 0.07117810484547947,
+      "learning_rate": 1.6903410887021676e-06,
+      "loss": 0.4892,
+      "step": 640
+    },
+    {
+      "epoch": 3.8053097345132745,
+      "grad_norm": 0.23100334767483371,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 0.493,
+      "step": 645
+    },
+    {
+      "epoch": 3.8348082595870205,
+      "grad_norm": 0.04506424951487985,
+      "learning_rate": 1.5382897547758513e-06,
+      "loss": 0.484,
+      "step": 650
+    },
+    {
+      "epoch": 3.864306784660767,
+      "grad_norm": 0.10488547297270173,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.4877,
+      "step": 655
+    },
+    {
+      "epoch": 3.893805309734513,
+      "grad_norm": 0.04390462723720627,
+      "learning_rate": 1.3921526947346902e-06,
+      "loss": 0.4887,
+      "step": 660
+    },
+    {
+      "epoch": 3.9233038348082596,
+      "grad_norm": 0.059362742241561586,
+      "learning_rate": 1.321380446634342e-06,
+      "loss": 0.4943,
+      "step": 665
+    },
+    {
+      "epoch": 3.952802359882006,
+      "grad_norm": 0.05424105447849983,
+      "learning_rate": 1.2521795812943704e-06,
+      "loss": 0.4871,
+      "step": 670
+    },
+    {
+      "epoch": 3.982300884955752,
+      "grad_norm": 0.04260561612932512,
+      "learning_rate": 1.1845796590009684e-06,
+      "loss": 0.4874,
+      "step": 675
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5515686869621277,
+      "eval_runtime": 7.9174,
+      "eval_samples_per_second": 16.672,
+      "eval_steps_per_second": 0.379,
+      "step": 678
+    },
+    {
+      "epoch": 4.011799410029498,
+      "grad_norm": 0.04414788535025088,
+      "learning_rate": 1.118609556171213e-06,
+      "loss": 0.535,
+      "step": 680
+    },
+    {
+      "epoch": 4.041297935103245,
+      "grad_norm": 0.04732115155993842,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 0.4859,
+      "step": 685
+    },
+    {
+      "epoch": 4.070796460176991,
+      "grad_norm": 0.04337501922937707,
+      "learning_rate": 9.916708215125586e-07,
+      "loss": 0.4893,
+      "step": 690
+    },
+    {
+      "epoch": 4.100294985250738,
+      "grad_norm": 0.052054539750301554,
+      "learning_rate": 9.307564136490255e-07,
+      "loss": 0.4837,
+      "step": 695
+    },
+    {
+      "epoch": 4.129793510324483,
+      "grad_norm": 0.043254413851663974,
+      "learning_rate": 8.715802500172215e-07,
+      "loss": 0.4897,
+      "step": 700
+    },
+    {
+      "epoch": 4.15929203539823,
+      "grad_norm": 0.05537638890929335,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 0.4893,
+      "step": 705
+    },
+    {
+      "epoch": 4.188790560471976,
+      "grad_norm": 0.04519429234937821,
+      "learning_rate": 7.585430144121319e-07,
+      "loss": 0.4871,
+      "step": 710
+    },
+    {
+      "epoch": 4.218289085545723,
+      "grad_norm": 0.09284032958781858,
+      "learning_rate": 7.047302281505735e-07,
+      "loss": 0.4829,
+      "step": 715
+    },
+    {
+      "epoch": 4.247787610619469,
+      "grad_norm": 0.05759138824322539,
+      "learning_rate": 6.527522369181655e-07,
+      "loss": 0.4904,
+      "step": 720
+    },
+    {
+      "epoch": 4.277286135693215,
+      "grad_norm": 0.04524068280213349,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 0.4841,
+      "step": 725
+    },
+    {
+      "epoch": 4.3067846607669615,
+      "grad_norm": 0.04432058714882555,
+      "learning_rate": 5.543886593040737e-07,
+      "loss": 0.4843,
+      "step": 730
+    },
+    {
+      "epoch": 4.336283185840708,
+      "grad_norm": 0.04232360342920672,
+      "learning_rate": 5.080450905401057e-07,
+      "loss": 0.4928,
+      "step": 735
+    },
+    {
+      "epoch": 4.3657817109144545,
+      "grad_norm": 0.12702550471244367,
+      "learning_rate": 4.6362033409220077e-07,
+      "loss": 0.4951,
+      "step": 740
+    },
+    {
+      "epoch": 4.395280235988201,
+      "grad_norm": 0.0473973137647136,
+      "learning_rate": 4.211333667247125e-07,
+      "loss": 0.4931,
+      "step": 745
+    },
+    {
+      "epoch": 4.424778761061947,
+      "grad_norm": 0.043912927697138504,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.4883,
+      "step": 750
+    },
+    {
+      "epoch": 4.454277286135693,
+      "grad_norm": 0.04305758726287443,
+      "learning_rate": 3.420445597436056e-07,
+      "loss": 0.4877,
+      "step": 755
+    },
+    {
+      "epoch": 4.48377581120944,
+      "grad_norm": 0.04286327782385863,
+      "learning_rate": 3.0547650421285216e-07,
+      "loss": 0.4865,
+      "step": 760
+    },
+    {
+      "epoch": 4.513274336283186,
+      "grad_norm": 0.04387385477938106,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 0.4891,
+      "step": 765
+    },
+    {
+      "epoch": 4.542772861356932,
+      "grad_norm": 0.042851842666364756,
+      "learning_rate": 2.3837118562592799e-07,
+      "loss": 0.4886,
+      "step": 770
+    },
+    {
+      "epoch": 4.572271386430678,
+      "grad_norm": 0.04267358478101285,
+      "learning_rate": 2.0786258770873647e-07,
+      "loss": 0.4896,
+      "step": 775
+    },
+    {
+      "epoch": 4.601769911504425,
+      "grad_norm": 0.050416063074236905,
+      "learning_rate": 1.7940102999393194e-07,
+      "loss": 0.4875,
+      "step": 780
+    },
+    {
+      "epoch": 4.631268436578171,
+      "grad_norm": 0.043881002529456536,
+      "learning_rate": 1.5299867030334815e-07,
+      "loss": 0.4854,
+      "step": 785
+    },
+    {
+      "epoch": 4.660766961651918,
+      "grad_norm": 0.06742603559290723,
+      "learning_rate": 1.286667868385627e-07,
+      "loss": 0.4833,
+      "step": 790
+    },
+    {
+      "epoch": 4.6902654867256635,
+      "grad_norm": 0.04689112762822426,
+      "learning_rate": 1.0641577336322761e-07,
+      "loss": 0.4859,
+      "step": 795
+    },
+    {
+      "epoch": 4.71976401179941,
+      "grad_norm": 0.04458797008950871,
+      "learning_rate": 8.625513476320291e-08,
+      "loss": 0.486,
+      "step": 800
+    },
+    {
+      "epoch": 4.7492625368731565,
+      "grad_norm": 0.043403401141790046,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 0.4835,
+      "step": 805
+    },
+    {
+      "epoch": 4.778761061946903,
+      "grad_norm": 0.04203084473909298,
+      "learning_rate": 5.223853336398632e-08,
+      "loss": 0.4846,
+      "step": 810
+    },
+    {
+      "epoch": 4.808259587020649,
+      "grad_norm": 0.046069003410869176,
+      "learning_rate": 3.839710131477492e-08,
+      "loss": 0.4887,
+      "step": 815
+    },
+    {
+      "epoch": 4.837758112094395,
+      "grad_norm": 0.04757707619938308,
+      "learning_rate": 2.6675099433787212e-08,
+      "loss": 0.4878,
+      "step": 820
+    },
+    {
+      "epoch": 4.867256637168142,
+      "grad_norm": 0.042268713033133586,
+      "learning_rate": 1.7077534966650767e-08,
+      "loss": 0.4882,
+      "step": 825
+    },
+    {
+      "epoch": 4.896755162241888,
+      "grad_norm": 0.04302102116033562,
+      "learning_rate": 9.608507670659239e-09,
+      "loss": 0.4888,
+      "step": 830
+    },
+    {
+      "epoch": 4.926253687315635,
+      "grad_norm": 0.07913283260437641,
+      "learning_rate": 4.2712080634949024e-09,
+      "loss": 0.4839,
+      "step": 835
+    },
+    {
+      "epoch": 4.95575221238938,
+      "grad_norm": 0.04332335955644444,
+      "learning_rate": 1.0679160603449533e-09,
+      "loss": 0.4917,
+      "step": 840
+    },
+    {
+      "epoch": 4.985250737463127,
+      "grad_norm": 0.04328053326566176,
+      "learning_rate": 0.0,
+      "loss": 0.4883,
+      "step": 845
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 845,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 56,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2830394185482240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f27fc52499c8b2f1bf89674f1a19c9294567ac70a0201773bfcffc7da26321
+size 6968

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)