Add step_4000 checkpoint
Browse files- state/step_4000/policy/cosmos_config +174 -0
- state/step_4000/policy/extra_info_rank_0.pth +3 -0
- state/step_4000/policy/extra_info_rank_1.pth +3 -0
- state/step_4000/policy/extra_info_rank_2.pth +3 -0
- state/step_4000/policy/extra_info_rank_3.pth +3 -0
- state/step_4000/policy/extra_info_rank_4.pth +3 -0
- state/step_4000/policy/extra_info_rank_5.pth +3 -0
- state/step_4000/policy/extra_info_rank_6.pth +3 -0
- state/step_4000/policy/extra_info_rank_7.pth +3 -0
- state/step_4000/policy/model_rank_0.pth +3 -0
- state/step_4000/policy/model_rank_1.pth +3 -0
- state/step_4000/policy/model_rank_2.pth +3 -0
- state/step_4000/policy/model_rank_3.pth +3 -0
- state/step_4000/policy/model_rank_4.pth +3 -0
- state/step_4000/policy/model_rank_5.pth +3 -0
- state/step_4000/policy/model_rank_6.pth +3 -0
- state/step_4000/policy/model_rank_7.pth +3 -0
- state/step_4000/policy/optimizer_rank_0.pth +3 -0
- state/step_4000/policy/optimizer_rank_1.pth +3 -0
- state/step_4000/policy/optimizer_rank_2.pth +3 -0
- state/step_4000/policy/optimizer_rank_3.pth +3 -0
- state/step_4000/policy/optimizer_rank_4.pth +3 -0
- state/step_4000/policy/optimizer_rank_5.pth +3 -0
- state/step_4000/policy/optimizer_rank_6.pth +3 -0
- state/step_4000/policy/optimizer_rank_7.pth +3 -0
- state/step_4000/policy/scheduler_rank_0.pth +3 -0
- state/step_4000/policy/scheduler_rank_1.pth +3 -0
- state/step_4000/policy/scheduler_rank_2.pth +3 -0
- state/step_4000/policy/scheduler_rank_3.pth +3 -0
- state/step_4000/policy/scheduler_rank_4.pth +3 -0
- state/step_4000/policy/scheduler_rank_5.pth +3 -0
- state/step_4000/policy/scheduler_rank_6.pth +3 -0
- state/step_4000/policy/scheduler_rank_7.pth +3 -0
state/step_4000/policy/cosmos_config
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"custom": {},
|
| 3 |
+
"train": {
|
| 4 |
+
"train_policy": {
|
| 5 |
+
"type": "sft",
|
| 6 |
+
"dataset": {
|
| 7 |
+
"name": "LNTANOooo/sharegpt52k",
|
| 8 |
+
"subset": "",
|
| 9 |
+
"revision": "",
|
| 10 |
+
"split": [
|
| 11 |
+
"train"
|
| 12 |
+
],
|
| 13 |
+
"test_size": 0.1
|
| 14 |
+
},
|
| 15 |
+
"mini_batch": 8,
|
| 16 |
+
"dataloader_shuffle": true,
|
| 17 |
+
"enable_dataset_cache": false,
|
| 18 |
+
"dataloader_num_workers": 0,
|
| 19 |
+
"dataloader_prefetch_factor": null,
|
| 20 |
+
"conversation_column_name": "conversation",
|
| 21 |
+
"system_prompt": ""
|
| 22 |
+
},
|
| 23 |
+
"optm_name": "AdamW",
|
| 24 |
+
"optm_lr": 0.0002,
|
| 25 |
+
"optm_impl": "fused",
|
| 26 |
+
"optm_weight_decay": 0.01,
|
| 27 |
+
"optm_betas": [
|
| 28 |
+
0.9,
|
| 29 |
+
0.999
|
| 30 |
+
],
|
| 31 |
+
"optm_warmup_steps": 20,
|
| 32 |
+
"optm_decay_ratio": null,
|
| 33 |
+
"optm_decay_type": null,
|
| 34 |
+
"optm_min_lr_factor": 0.0,
|
| 35 |
+
"optm_grad_norm_clip": 1.0,
|
| 36 |
+
"master_dtype": "float32",
|
| 37 |
+
"param_dtype": "bfloat16",
|
| 38 |
+
"transfer_dtype": "bfloat16",
|
| 39 |
+
"fsdp_reduce_dtype": "float32",
|
| 40 |
+
"fsdp_offload": false,
|
| 41 |
+
"fsdp_reshard_after_forward": "default",
|
| 42 |
+
"train_batch_per_replica": 32,
|
| 43 |
+
"enable_validation": false,
|
| 44 |
+
"validation_step": 20,
|
| 45 |
+
"validation_batch_per_replica": 24,
|
| 46 |
+
"fp8": {
|
| 47 |
+
"enable_fp8": false,
|
| 48 |
+
"fp8_recipe": "dynamic_scaling",
|
| 49 |
+
"quant_recipe": "rowwise"
|
| 50 |
+
},
|
| 51 |
+
"ckpt": {
|
| 52 |
+
"enable_checkpoint": true,
|
| 53 |
+
"save_freq": 2000,
|
| 54 |
+
"save_mode": "async",
|
| 55 |
+
"max_keep": 5,
|
| 56 |
+
"export_safetensors": true,
|
| 57 |
+
"upload_hf": false,
|
| 58 |
+
"hf_repo_name": "Comos-Reason1",
|
| 59 |
+
"upload_s3": false,
|
| 60 |
+
"s3_bucket": null,
|
| 61 |
+
"s3_prefix": "outputs"
|
| 62 |
+
},
|
| 63 |
+
"resume": true,
|
| 64 |
+
"epoch": 1000,
|
| 65 |
+
"output_dir": "./outputs/qwen2-5-3b-tp1-sft/20251001112805",
|
| 66 |
+
"timestamp": "20251001112805",
|
| 67 |
+
"epsilon": 1e-06,
|
| 68 |
+
"async_tp_enabled": false,
|
| 69 |
+
"compile": false,
|
| 70 |
+
"sync_weight_interval": 1,
|
| 71 |
+
"deterministic": false,
|
| 72 |
+
"seed": null,
|
| 73 |
+
"max_num_steps": null,
|
| 74 |
+
"sequence_packing": false
|
| 75 |
+
},
|
| 76 |
+
"rollout": {
|
| 77 |
+
"parallelism": {
|
| 78 |
+
"n_init_replicas": 1,
|
| 79 |
+
"tp_size": 2,
|
| 80 |
+
"cp_size": 1,
|
| 81 |
+
"ep_size": 1,
|
| 82 |
+
"dp_shard_size": -1,
|
| 83 |
+
"pp_size": 1,
|
| 84 |
+
"pp_dynamic_shape": false,
|
| 85 |
+
"pp_micro_batch_size": 1,
|
| 86 |
+
"dp_replicate_size": 1
|
| 87 |
+
},
|
| 88 |
+
"enforce_eager": true,
|
| 89 |
+
"include_stop_str_in_output": false,
|
| 90 |
+
"gpu_memory_utilization": 0.8,
|
| 91 |
+
"enable_chunked_prefill": false,
|
| 92 |
+
"max_response_length": 2048,
|
| 93 |
+
"n_generation": 16,
|
| 94 |
+
"batch_size": 1,
|
| 95 |
+
"val_batch_size": null,
|
| 96 |
+
"quantization": "none",
|
| 97 |
+
"seed": null,
|
| 98 |
+
"sampling_config": {
|
| 99 |
+
"temperature": 1.0,
|
| 100 |
+
"top_p": 1.0,
|
| 101 |
+
"top_k": -1,
|
| 102 |
+
"repetition_penalty": 1.0,
|
| 103 |
+
"use_flashinfer": false
|
| 104 |
+
},
|
| 105 |
+
"vllm_use_flashinfer": false,
|
| 106 |
+
"backend": "vllm"
|
| 107 |
+
},
|
| 108 |
+
"policy": {
|
| 109 |
+
"parallelism": {
|
| 110 |
+
"n_init_replicas": 1,
|
| 111 |
+
"tp_size": 1,
|
| 112 |
+
"cp_size": 1,
|
| 113 |
+
"ep_size": 1,
|
| 114 |
+
"dp_shard_size": 8,
|
| 115 |
+
"pp_size": 1,
|
| 116 |
+
"pp_dynamic_shape": false,
|
| 117 |
+
"pp_micro_batch_size": 1,
|
| 118 |
+
"dp_replicate_size": 8
|
| 119 |
+
},
|
| 120 |
+
"model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
|
| 121 |
+
"model_revision": null,
|
| 122 |
+
"model_max_length": 4096,
|
| 123 |
+
"model_gradient_checkpointing": true,
|
| 124 |
+
"lora": null,
|
| 125 |
+
"trainable_map": null,
|
| 126 |
+
"enable_liger_kernel": false
|
| 127 |
+
},
|
| 128 |
+
"logging": {
|
| 129 |
+
"logger": [
|
| 130 |
+
"console",
|
| 131 |
+
"wandb"
|
| 132 |
+
],
|
| 133 |
+
"project_name": "cosmos_rl",
|
| 134 |
+
"experiment_name": "None",
|
| 135 |
+
"report_mfu": false
|
| 136 |
+
},
|
| 137 |
+
"profiler": {
|
| 138 |
+
"enable_profiler": false,
|
| 139 |
+
"enable_nsys": false,
|
| 140 |
+
"sub_profiler_config": {
|
| 141 |
+
"do_profile": false,
|
| 142 |
+
"active_steps": 1,
|
| 143 |
+
"warmup_steps": 1,
|
| 144 |
+
"wait_steps": 1,
|
| 145 |
+
"rank_filter": [],
|
| 146 |
+
"record_shape": false,
|
| 147 |
+
"profile_memory": false,
|
| 148 |
+
"with_stack": false,
|
| 149 |
+
"with_modules": false
|
| 150 |
+
}
|
| 151 |
+
},
|
| 152 |
+
"validation": {
|
| 153 |
+
"dataset": {
|
| 154 |
+
"name": "",
|
| 155 |
+
"subset": "",
|
| 156 |
+
"revision": "",
|
| 157 |
+
"split": [
|
| 158 |
+
""
|
| 159 |
+
],
|
| 160 |
+
"test_size": null
|
| 161 |
+
},
|
| 162 |
+
"temperature": 0.0,
|
| 163 |
+
"top_p": null,
|
| 164 |
+
"top_k": 1,
|
| 165 |
+
"repetition_penalty": 1.0,
|
| 166 |
+
"n_generation": 1,
|
| 167 |
+
"max_response_length": null,
|
| 168 |
+
"reward_function": {
|
| 169 |
+
"single_choice": 1.0
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"redis": "12800",
|
| 173 |
+
"eth_ips": "10.0.0.171;172.17.0.1;100.64.0.5;10.50.83.240;10.50.154.240;169.254.66.66;172.20.0.10"
|
| 174 |
+
}
|
state/step_4000/policy/extra_info_rank_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b8cc561ee911783e7ac124a4f3fdb7f81662fbe60858660d562679a3e4ec825
|
| 3 |
+
size 14773
|
state/step_4000/policy/extra_info_rank_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:593a38d8bc6878496dc8467412758aacc5c62d36c99cdcdaceeef29f01b360a2
|
| 3 |
+
size 14837
|
state/step_4000/policy/extra_info_rank_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:291ac76689aae90c9c593f9757ba9186ba734e5f6a86208f4d3a3ccd1c263377
|
| 3 |
+
size 14773
|
state/step_4000/policy/extra_info_rank_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b4b8c6dd2e4bdd1c5ad21d446ec3bcbe64cc9256470a5ccc8bfcd3bd1e625ab
|
| 3 |
+
size 14773
|
state/step_4000/policy/extra_info_rank_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d9749429cc906af846545822873231aa3125766a00f8ee03ae42e44bea803b2
|
| 3 |
+
size 14837
|
state/step_4000/policy/extra_info_rank_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4426520e25071e32a151d37a2742f1b08782cd678aa5c905eb66f6bc43542b0e
|
| 3 |
+
size 14837
|
state/step_4000/policy/extra_info_rank_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:626867806157e0a6ab9e6563f98b0bdaf360ff5cad6c15a1c535fbaeb3562671
|
| 3 |
+
size 14837
|
state/step_4000/policy/extra_info_rank_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd462091564031cf935dff3b621092ec872a1e56f0d98569e7093211166fb812
|
| 3 |
+
size 14773
|
state/step_4000/policy/model_rank_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:318f344dddd21afb040dee04e3ebf8c93199c86e1be5925d234b6e3d6cd9a472
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53b92ebca9c3a18688d49077b9b67c5dabc8bfdac72beed3bffa2452a340f285
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e910d6c5a43dd07d2f4f540ad1f0f27783cbaf6b8252e0f3a90d61b6d39dc17
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89134859794aac648a26f1028705c9994df55ffb3f4617f9a3d8cc8a4dd2379a
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d71fdf7bb38e1d3633c3fa694a17326c49fa655eb10519e3aafa47932255cfc
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39b8fd06bb5a08d734297729caa370d82b94a0cfcadc11efba768a4c8610bfac
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0df24098c15e6bd5fe9bea651009adbbebe1c9681bfb1be53ef60629844de44c
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/model_rank_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb0ec704ca23bf78a82db72c822d0d21d1d7a3ca101e2d31e42db8df022b695
|
| 3 |
+
size 5401670733
|
state/step_4000/policy/optimizer_rank_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99ee1000126c4ddb05e1428456bfcee40939dee9c641a66857c46b7165cc22ba
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0acd1ba168448c0cd163047902f5796e12863a6796571d704a8991d57347561e
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1de9d352499255383fcbdd9f4f6e27723d3cffe499ba25f77e2516d6486fc9
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75d72db36e3880cd5a2a2bae590f82519dcacfde78203058019b3580dc9d6149
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdce74f1d35af6dd8cdd7df33e380d94c7df5f43de9d815147ab341bd20326c1
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc47994e82ec3a4931ca998d36eb204a8fc60b3cd6ea2abb7539e84b8832aafd
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:145a563b29b9059b03f18c1d5e1bf982ee5987c603edbf7fcacbe121a29bdcda
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/optimizer_rank_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aed4ce3d08a9d3241e1a18581d0c692882a8f9f0214f99d128c34f5632a35e96
|
| 3 |
+
size 4127060133
|
state/step_4000/policy/scheduler_rank_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a6301c98b88bc7af9c87f0b4b95f84a47ef173b82a417576d4c2b80f0eba4db
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:733e3ad940e7de685d1b37aa6b0bb520005c66f43df038c419ff80664756587f
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9f90bf5dbfb2101c3dbfa27c3a5eb47cfb70f3b7f238a088c9cf400abd2a7bd
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36f2240f9a703b031c02de6501ec780908f196e9cdd994d3e2e8ca6fd4270dd0
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a213f5f244b7c46365825ccff667ee83b359a32f360fae136754758015ee7b46
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd6026ea9a105e343cf0eae40c994f7bad8da0e4e3c844c51e27e4dcd87cc7e
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51cd050dfbad53d213eda7970921adc28250132e874fb0fdd4af19eb32348e53
|
| 3 |
+
size 1507
|
state/step_4000/policy/scheduler_rank_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66de8be17fc918fb85cb9e78a157c7f84826928493d2ee2577d71ca89985052b
|
| 3 |
+
size 1507
|