Hugging Face's logo

mlfoundations-dev
/
ds_no_offload_liger_packing_torchcompile

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
aa9c3c5
·
verified ·
1 Parent(s): 669b144

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:d5e90dfd813ae936b44bebf3d0aa8714a6af661cfafc29d3fc1284dabee34ae6
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714c07b54fa4180277788a3be838b7fae81f2e00f32180fe4ab208a16c070201
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:215a63771c83b2425b1a4c49d858a28be24d4cdcf5501b7ee90ebdbb48b54653
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef3775145863d74aba4ac7bf584af8386d24888d2d0f462dfb66ed4fb7d1306
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5581f5cea63166758780d3ebd3865d7bbf2d59f51df9d8f33fa048e085e0e2a4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e121c7627ed1bd76595ea2f2337c57579c3fcdbe72731b308e70d3a54b75371
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31cb1ac4948b26c18e5873329ce88620f136d37a8fbe0dc08729eb87cd00e25b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a03372d67e493f699fd005165442d4d1e7a6c701054f133eb7080ef6d158d53
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": "0:01:21", "remaining_time": "0:23:04"}
2
- {"current_steps": 2, "total_steps": 18, "loss": 1.3191, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:24", "remaining_time": "0:19:17"}
3
- {"current_steps": 3, "total_steps": 18, "loss": 1.287, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:27", "remaining_time": "0:17:19"}
4
- {"current_steps": 4, "total_steps": 18, "loss": 1.2686, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:31", "remaining_time": "0:15:49"}
5
- {"current_steps": 5, "total_steps": 18, "loss": 1.294, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:34", "remaining_time": "0:14:30"}
6
- {"current_steps": 6, "total_steps": 18, "loss": 1.2551, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:28", "remaining_time": "0:12:57"}
7
- {"current_steps": 7, "total_steps": 18, "loss": 1.2267, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:07:55", "remaining_time": "0:12:27"}
8
- {"current_steps": 8, "total_steps": 18, "loss": 1.2174, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:08:59", "remaining_time": "0:11:13"}
9
- {"current_steps": 9, "total_steps": 18, "loss": 1.2134, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:10:02", "remaining_time": "0:10:02"}
10
- {"current_steps": 10, "total_steps": 18, "loss": 1.1716, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:05", "remaining_time": "0:08:52"}
11
- {"current_steps": 11, "total_steps": 18, "loss": 1.1606, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:09", "remaining_time": "0:07:43"}
12
- {"current_steps": 12, "total_steps": 18, "loss": 1.1714, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:02", "remaining_time": "0:06:31"}
13
- {"current_steps": 13, "total_steps": 18, "loss": 1.1518, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:14:29", "remaining_time": "0:05:34"}
14
- {"current_steps": 14, "total_steps": 18, "loss": 1.1449, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:15:33", "remaining_time": "0:04:26"}
15
- {"current_steps": 15, "total_steps": 18, "loss": 1.167, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:16:36", "remaining_time": "0:03:19"}
16
- {"current_steps": 16, "total_steps": 18, "loss": 1.1749, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:17:39", "remaining_time": "0:02:12"}
17
- {"current_steps": 17, "total_steps": 18, "loss": 1.1597, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:18:43", "remaining_time": "0:01:06"}
18
- {"current_steps": 18, "total_steps": 18, "loss": 1.1474, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:19:36", "remaining_time": "0:00:00"}
19
- {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:20:03", "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": "0:22:47"}
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": "0:19:16"}
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": 1.1302, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:32", "remaining_time": "0:15:54"}
5
+ {"current_steps": 5, "total_steps": 18, "loss": 1.1449, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:36", "remaining_time": "0:14:34"}
6
+ {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:30", "remaining_time": "0:13:01"}
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": "0:13:21"}
8
+ {"current_steps": 8, "total_steps": 18, "loss": 1.0365, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:34", "remaining_time": "0:11:57"}
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18dde55e6e0031fae769fe4bfcde9bbf091e3587da8a8a9b624bd654aa093b7e
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b581c25497b383abbb40df73067b872b793343cc4f37f2e34ddf62a51211fbec
3
  size 7224