Payoto commited on
Commit
a651931
1 Parent(s): 4281089

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. ipu_config.json +3 -6
  3. pytorch_model.bin +1 -1
  4. training_args.bin +2 -2
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float16",
23
- "transformers_version": "4.24.0",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 50265
 
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float16",
23
+ "transformers_version": "4.20.1",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 50265
ipu_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "decompose_grad_sum": false,
3
  "device_iterations": 1,
4
  "embedding_serialization_factor": 0,
5
- "enable_half_first_order_momentum": true,
6
  "enable_half_partials": true,
7
  "executable_cache_dir": "/tmp/exe_cache",
8
  "execute_encoder_on_cpu_for_generation": false,
@@ -20,14 +19,12 @@
20
  0.25
21
  ],
22
  "optimizer_state_offchip": true,
23
- "optimum_version": "1.4.1",
24
  "output_mode": "final",
25
- "profile_dir": "",
26
  "recompute_checkpoint_every_layer": true,
27
  "replicated_tensor_sharding": false,
28
  "replication_factor": 1,
29
  "seed": 42,
30
  "sharded_execution_for_inference": false,
31
- "transformers_version": "4.24.0",
32
- "use_popdist": false
33
  }
 
1
  {
2
+ "auto_loss_scaling": false,
3
  "device_iterations": 1,
4
  "embedding_serialization_factor": 0,
 
5
  "enable_half_partials": true,
6
  "executable_cache_dir": "/tmp/exe_cache",
7
  "execute_encoder_on_cpu_for_generation": false,
 
19
  0.25
20
  ],
21
  "optimizer_state_offchip": true,
22
+ "optimum_version": "1.5.0",
23
  "output_mode": "final",
 
24
  "recompute_checkpoint_every_layer": true,
25
  "replicated_tensor_sharding": false,
26
  "replication_factor": 1,
27
  "seed": 42,
28
  "sharded_execution_for_inference": false,
29
+ "transformers_version": "4.20.1"
 
30
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47ea93dbcc63d6c53bc5d3a8a9b6df66a62185083bf6e787b831b1f036039669
3
  size 249361645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c1379f33bd67409aedabb3c7779827cdadfa8268a8649b3c74b5daa2f08083
3
  size 249361645
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:289af17c2cc930989397aff4a5aa4b60661acf488970848eb18b1b14ae06a2d1
3
- size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1440d9b094939f46d60953bf6b35a663a09e723d5df1530c1084afb6bc78115c
3
+ size 2735