picocreator commited on
Commit
a64fee1
1 Parent(s): 3ee4ae1

[GHA] experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb result notebooks (#17)

Browse files

- 715a8b6edb467dc7d61ce79795e6fc7d3f73b519493e4f2d7c06cfcc7106186f (cc54ac16531e98926cc725cfd9e4fa6937bf177e)

experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb CHANGED
@@ -3,19 +3,19 @@
3
  {
4
  "cell_type": "code",
5
  "execution_count": 1,
6
- "id": "fbe2a012",
7
  "metadata": {
8
  "execution": {
9
- "iopub.execute_input": "2023-08-24T03:57:18.245198Z",
10
- "iopub.status.busy": "2023-08-24T03:57:18.244865Z",
11
- "iopub.status.idle": "2023-08-24T03:57:18.489940Z",
12
- "shell.execute_reply": "2023-08-24T03:57:18.489209Z"
13
  },
14
  "papermill": {
15
- "duration": 0.249423,
16
- "end_time": "2023-08-24T03:57:18.491807",
17
  "exception": false,
18
- "start_time": "2023-08-24T03:57:18.242384",
19
  "status": "completed"
20
  },
21
  "tags": []
@@ -32,6 +32,123 @@
32
  "source": [
33
  "!echo \"Hello world\" # this file is for debugging the runner"
34
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  }
36
  ],
37
  "metadata": {
@@ -49,14 +166,14 @@
49
  },
50
  "papermill": {
51
  "default_parameters": {},
52
- "duration": 1.423604,
53
- "end_time": "2023-08-24T03:57:18.709651",
54
  "environment_variables": {},
55
  "exception": null,
56
  "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb",
57
  "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb",
58
  "parameters": {},
59
- "start_time": "2023-08-24T03:57:17.286047",
60
  "version": "2.4.0"
61
  }
62
  },
 
3
  {
4
  "cell_type": "code",
5
  "execution_count": 1,
6
+ "id": "5a2bbd3c",
7
  "metadata": {
8
  "execution": {
9
+ "iopub.execute_input": "2023-08-24T04:44:25.040059Z",
10
+ "iopub.status.busy": "2023-08-24T04:44:25.039841Z",
11
+ "iopub.status.idle": "2023-08-24T04:44:25.284633Z",
12
+ "shell.execute_reply": "2023-08-24T04:44:25.283834Z"
13
  },
14
  "papermill": {
15
+ "duration": 0.248685,
16
+ "end_time": "2023-08-24T04:44:25.286190",
17
  "exception": false,
18
+ "start_time": "2023-08-24T04:44:25.037505",
19
  "status": "completed"
20
  },
21
  "tags": []
 
32
  "source": [
33
  "!echo \"Hello world\" # this file is for debugging the runner"
34
  ]
35
+ },
36
+ {
37
+ "cell_type": "code",
38
+ "execution_count": 2,
39
+ "id": "5b3eecbc",
40
+ "metadata": {
41
+ "execution": {
42
+ "iopub.execute_input": "2023-08-24T04:44:25.289218Z",
43
+ "iopub.status.busy": "2023-08-24T04:44:25.289031Z",
44
+ "iopub.status.idle": "2023-08-24T04:44:25.295282Z",
45
+ "shell.execute_reply": "2023-08-24T04:44:25.294543Z"
46
+ },
47
+ "papermill": {
48
+ "duration": 0.009124,
49
+ "end_time": "2023-08-24T04:44:25.296411",
50
+ "exception": false,
51
+ "start_time": "2023-08-24T04:44:25.287287",
52
+ "status": "completed"
53
+ },
54
+ "tags": []
55
+ },
56
+ "outputs": [
57
+ {
58
+ "name": "stdout",
59
+ "output_type": "stream",
60
+ "text": [
61
+ "DEEPSPEED_STRAT: deepspeed_stage_2_offload\n",
62
+ "ENABLE_WANDB: True\n",
63
+ "GPU_DEVICES: auto\n",
64
+ "NOTEBOOK_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-headsize2x\n",
65
+ "INFERENCE_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5headsize2x\n",
66
+ "TRAINER_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5headsize2x\n",
67
+ "PROJECT_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer\n"
68
+ ]
69
+ }
70
+ ],
71
+ "source": [
72
+ "DEEPSPEED_STRAT=\"deepspeed_stage_2_offload\"\n",
73
+ "GPU_DEVICES=\"auto\"\n",
74
+ "ENABLE_WANDB=True\n",
75
+ "\n",
76
+ "RWKV_WAVENET_LAYERS=1\n",
77
+ "\n",
78
+ "EMBED_SCALE=0.1\n",
79
+ "EMBED_SCALE_LABEL=str(EMBED_SCALE).replace(\".\", \"_\")\n",
80
+ "\n",
81
+ "LAYER_COUNT=6\n",
82
+ "EMBED_DIM=4096\n",
83
+ "\n",
84
+ "WANDB_PREFIX=f\"v5-hs2x-L{LAYER_COUNT}-D{EMBED_DIM}-E{EMBED_SCALE}\"\n",
85
+ "FILENAME_PREFIX=f\"v5-hs2x-L{LAYER_COUNT}-D{EMBED_DIM}-E{EMBED_SCALE_LABEL}\"\n",
86
+ "\n",
87
+ "print(\"DEEPSPEED_STRAT:\", DEEPSPEED_STRAT)\n",
88
+ "print(\"ENABLE_WANDB:\", ENABLE_WANDB)\n",
89
+ "print(\"GPU_DEVICES:\", GPU_DEVICES)\n",
90
+ "\n",
91
+ "if ENABLE_WANDB:\n",
92
+ " WANDB_MODE=\"online\"\n",
93
+ "else:\n",
94
+ " WANDB_MODE=\"disabled\"\n",
95
+ "\n",
96
+ "# Computing the notebook, and various paths\n",
97
+ "import os\n",
98
+ "NOTEBOOK_DIR=os.path.dirname(os.path.abspath(\"__file__\"))\n",
99
+ "PROJECT_DIR=os.path.abspath(os.path.join(NOTEBOOK_DIR, \"../../../../\"))\n",
100
+ "TRAINER_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5headsize2x/\"))\n",
101
+ "INFERENCE_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5headsize2x/\"))\n",
102
+ "\n",
103
+ "print(\"NOTEBOOK_DIR:\", NOTEBOOK_DIR)\n",
104
+ "print(\"INFERENCE_DIR:\", INFERENCE_DIR)\n",
105
+ "print(\"TRAINER_DIR:\", TRAINER_DIR)\n",
106
+ "print(\"PROJECT_DIR:\", PROJECT_DIR)"
107
+ ]
108
+ },
109
+ {
110
+ "cell_type": "code",
111
+ "execution_count": 3,
112
+ "id": "39c31880",
113
+ "metadata": {
114
+ "execution": {
115
+ "iopub.execute_input": "2023-08-24T04:44:25.299318Z",
116
+ "iopub.status.busy": "2023-08-24T04:44:25.299143Z",
117
+ "iopub.status.idle": "2023-08-24T04:44:25.772732Z",
118
+ "shell.execute_reply": "2023-08-24T04:44:25.771978Z"
119
+ },
120
+ "papermill": {
121
+ "duration": 0.476676,
122
+ "end_time": "2023-08-24T04:44:25.774132",
123
+ "exception": false,
124
+ "start_time": "2023-08-24T04:44:25.297456",
125
+ "status": "completed"
126
+ },
127
+ "tags": []
128
+ },
129
+ "outputs": [
130
+ {
131
+ "name": "stdout",
132
+ "output_type": "stream",
133
+ "text": [
134
+ "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5headsize2x\r\n"
135
+ ]
136
+ },
137
+ {
138
+ "name": "stdout",
139
+ "output_type": "stream",
140
+ "text": [
141
+ "total 4.0K\r\n",
142
+ "drwxr-xr-x 2 root root 10 Aug 24 04:44 .\r\n",
143
+ "drwxr-xr-x 19 root root 4.0K Aug 24 04:44 ..\r\n"
144
+ ]
145
+ }
146
+ ],
147
+ "source": [
148
+ "# Get the current model listing\n",
149
+ "!cd \"{TRAINER_DIR}\" && pwd\n",
150
+ "!cd \"{TRAINER_DIR}\" && ls -alh \"../model/\""
151
+ ]
152
  }
153
  ],
154
  "metadata": {
 
166
  },
167
  "papermill": {
168
  "default_parameters": {},
169
+ "duration": 1.911028,
170
+ "end_time": "2023-08-24T04:44:25.992833",
171
  "environment_variables": {},
172
  "exception": null,
173
  "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb",
174
  "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-headsize2x/hello-world.ipynb",
175
  "parameters": {},
176
+ "start_time": "2023-08-24T04:44:24.081805",
177
  "version": "2.4.0"
178
  }
179
  },