Hugging Face's logo

mlfoundations-dev
/
deepspeed_no_offload_liger_packing

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
6659a79
·
verified ·
1 Parent(s): f7e5500

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. trainer_log.jsonl +8 -19
  7. training_args.bin +1 -1
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.46.1",
26
  "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
 
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
  "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3399dac1749a9eab5ee89d4f4a845a1a0f6ce6a76e8cf94e05f15a14fbe2f88b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c8cd2daeb336055b0612973032136c4e28a64253c61cb70ddd8dd644bdfc14
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4a719d637d8011d0135c4d8af43196f39aa472b82d70e6cc55b85ac4b2cd45d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd23e59e7bb5c2900251762eab61e9d1767807581f057b441e4035e4cb2914a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9b3573fa4f933ed87f02647b83136ce0879e8475034b52dab7a997ea7515db3
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e5345e67565e347d209f7c8d13aee5926e9d04471f35f82ba8b96f63e962db
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a512e2e25dbcc574a6ecbf4303b284dacd76ad8168de09acf9fd3812bc23cbf7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16170744ebbd5098560cf4812191d168e7b3e859eb63d11bd2a378abf8809a3
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,19 +1,8 @@
1
- {"current_steps": 1, "total_steps": 18, "loss": 1.2823, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:22", "remaining_time": "0:23:22"}
2
- {"current_steps": 2, "total_steps": 18, "loss": 1.3191, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:27", "remaining_time": "0:19:42"}
3
- {"current_steps": 3, "total_steps": 18, "loss": 1.2058, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:33", "remaining_time": "0:17:45"}
4
- {"current_steps": 4, "total_steps": 18, "loss": 1.1292, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:38", "remaining_time": "0:16:14"}
5
- {"current_steps": 5, "total_steps": 18, "loss": 1.144, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:43", "remaining_time": "0:14:54"}
6
- {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:39", "remaining_time": "0:13:19"}
7
- {"current_steps": 7, "total_steps": 18, "loss": 1.0696, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:08:38", "remaining_time": "0:13:34"}
8
- {"current_steps": 8, "total_steps": 18, "loss": 1.0376, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:43", "remaining_time": "0:12:09"}
9
- {"current_steps": 9, "total_steps": 18, "loss": 1.0122, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:10:48", "remaining_time": "0:10:48"}
10
- {"current_steps": 10, "total_steps": 18, "loss": 0.9653, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:53", "remaining_time": "0:09:31"}
11
- {"current_steps": 11, "total_steps": 18, "loss": 0.9329, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:59", "remaining_time": "0:08:15"}
12
- {"current_steps": 12, "total_steps": 18, "loss": 0.9327, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:54", "remaining_time": "0:06:57"}
13
- {"current_steps": 13, "total_steps": 18, "loss": 0.9089, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:15:54", "remaining_time": "0:06:07"}
14
- {"current_steps": 14, "total_steps": 18, "loss": 0.8942, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:17:00", "remaining_time": "0:04:51"}
15
- {"current_steps": 15, "total_steps": 18, "loss": 0.914, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:18:05", "remaining_time": "0:03:37"}
16
- {"current_steps": 16, "total_steps": 18, "loss": 0.9051, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:19:10", "remaining_time": "0:02:23"}
17
- {"current_steps": 17, "total_steps": 18, "loss": 0.9043, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:20:16", "remaining_time": "0:01:11"}
18
- {"current_steps": 18, "total_steps": 18, "loss": 0.8928, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:21:11", "remaining_time": "0:00:00"}
19
- {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:22:43", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 18, "loss": 1.2879, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:20", "remaining_time": "0:22:41"}
2
+ {"current_steps": 2, "total_steps": 18, "loss": 1.3268, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:24", "remaining_time": "0:19:14"}
3
+ {"current_steps": 3, "total_steps": 18, "loss": 1.2078, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:28", "remaining_time": "0:17:23"}
4
+ {"current_steps": 4, "total_steps": 18, "loss": 1.1303, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:32", "remaining_time": "0:15:55"}
5
+ {"current_steps": 5, "total_steps": 18, "loss": 1.1449, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:37", "remaining_time": "0:14:36"}
6
+ {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:31", "remaining_time": "0:13:03"}
7
+ {"current_steps": 7, "total_steps": 18, "loss": 1.07, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:08:30", "remaining_time": "0:13:22"}
8
+ {"current_steps": 8, "total_steps": 18, "loss": 1.0364, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:34", "remaining_time": "0:11:58"}
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4b9a874db1b5e9b69292e4cbf335bcc7dca18c8dfafd1a156f951873c8654cb
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22a51bbb652ed5772b9879ad9a5817ee2ffa646998de84610e435d720e3291f
3
  size 7224