internetoftim commited on
Commit
3f38fd7
1 Parent(s): 48233c6

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +39 -0
  3. ipu_config.json +35 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PoptorchPipelinedGPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
ipu_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decompose_grad_sum": false,
3
+ "device_iterations": 2,
4
+ "embedding_serialization_factor": 5,
5
+ "enable_half_first_order_momentum": true,
6
+ "enable_half_partials": true,
7
+ "executable_cache_dir": "./exe_cache",
8
+ "execute_encoder_on_cpu_for_generation": false,
9
+ "gradient_accumulation_steps": 16,
10
+ "inference_device_iterations": 9,
11
+ "inference_replication_factor": 2,
12
+ "ipus_per_replica": 8,
13
+ "layers_per_ipu": [
14
+ 0,
15
+ 3,
16
+ 3,
17
+ 3,
18
+ 3,
19
+ 4,
20
+ 4,
21
+ 4
22
+ ],
23
+ "matmul_proportion": 0.25,
24
+ "optimizer_state_offchip": true,
25
+ "optimum_version": "1.4.1",
26
+ "output_mode": "final",
27
+ "profile_dir": "",
28
+ "recompute_checkpoint_every_layer": true,
29
+ "replicated_tensor_sharding": true,
30
+ "replication_factor": 2,
31
+ "seed": 42,
32
+ "sharded_execution_for_inference": false,
33
+ "transformers_version": "4.24.0",
34
+ "use_popdist": false
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5fa0ef830b017112b4e02302cccdf7d08d9b8f2d564137be32f6456481402ce
3
+ size 261514473
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f37b29e7f66c21e2f8754c578d6b94a281a94893bab5da0fb569abd09f83ba
3
+ size 2671