sedrickkeh commited on
Commit
5fce828
·
verified ·
1 Parent(s): ff59855

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.46.0",
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": "4.46.1",
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 sha256:5bf878fbeddf6e968a310793b197d4fb3a84071ed4559482d2f523425cdafb60
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5654525752a947d518b8d82ccf91f0350401ae31183d4d654ce42ca3e1215652
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:c1e9fd0a892bd36b83f6a0666d4f38640f5263d8fc55cb5615ca786d582aa06b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c3ea4f07fb4e7bfbc84fa1a2cd6e367ceb4c878a1369cb007fffdc497e8e35
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840e62d0c2ecf2920f0ca3913845ea03ffb74c4ddac36b33c10bbf54f81274de
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388c489ba27bc071d62f8aefb961791e4a1f0da5424ddf5d3837b1caaf8c9814
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72660d72f84ad672b5943e40e240c7d281666fd703d4277d3608420f6400d8a1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5254ea363f072317a615d98d6724fff18e0ab30435bf8e9d5d39619bd443c9
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,19 +1,10 @@
1
- {"current_steps": 1, "total_steps": 18, "loss": 1.2879, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:34", "remaining_time": "0:26:38"}
2
- {"current_steps": 2, "total_steps": 18, "loss": 1.3268, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:09", "remaining_time": "0:17:15"}
3
- {"current_steps": 3, "total_steps": 18, "loss": 1.2078, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:02:44", "remaining_time": "0:13:44"}
4
- {"current_steps": 4, "total_steps": 18, "loss": 1.1302, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:03:20", "remaining_time": "0:11:41"}
5
- {"current_steps": 5, "total_steps": 18, "loss": 1.1449, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:03:56", "remaining_time": "0:10:13"}
6
- {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:31", "remaining_time": "0:09:03"}
7
- {"current_steps": 7, "total_steps": 18, "loss": 1.07, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:06:36", "remaining_time": "0:10:23"}
8
- {"current_steps": 8, "total_steps": 18, "loss": 1.0365, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:07:12", "remaining_time": "0:09:00"}
9
- {"current_steps": 9, "total_steps": 18, "loss": 1.0098, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:07:47", "remaining_time": "0:07:47"}
10
- {"current_steps": 10, "total_steps": 18, "loss": 0.9637, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:08:23", "remaining_time": "0:06:42"}
11
- {"current_steps": 11, "total_steps": 18, "loss": 0.9329, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:08:58", "remaining_time": "0:05:42"}
12
- {"current_steps": 12, "total_steps": 18, "loss": 0.9329, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:09:34", "remaining_time": "0:04:47"}
13
- {"current_steps": 13, "total_steps": 18, "loss": 0.9097, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:11:40", "remaining_time": "0:04:29"}
14
- {"current_steps": 14, "total_steps": 18, "loss": 0.8905, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:12:15", "remaining_time": "0:03:30"}
15
- {"current_steps": 15, "total_steps": 18, "loss": 0.9138, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:12:51", "remaining_time": "0:02:34"}
16
- {"current_steps": 16, "total_steps": 18, "loss": 0.9051, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:13:26", "remaining_time": "0:01:40"}
17
- {"current_steps": 17, "total_steps": 18, "loss": 0.902, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:14:02", "remaining_time": "0:00:49"}
18
- {"current_steps": 18, "total_steps": 18, "loss": 0.8931, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:14:37", "remaining_time": "0:00:00"}
19
- {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:11", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 18, "loss": 1.2823, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:37", "remaining_time": "0:27:32"}
2
+ {"current_steps": 2, "total_steps": 18, "loss": 1.3191, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:13", "remaining_time": "0:17:48"}
3
+ {"current_steps": 3, "total_steps": 18, "loss": 1.2057, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:02:49", "remaining_time": "0:14:09"}
4
+ {"current_steps": 4, "total_steps": 18, "loss": 1.1292, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:03:26", "remaining_time": "0:12:02"}
5
+ {"current_steps": 5, "total_steps": 18, "loss": 1.1441, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:04:02", "remaining_time": "0:10:31"}
6
+ {"current_steps": 6, "total_steps": 18, "loss": 1.0849, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:39", "remaining_time": "0:09:19"}
7
+ {"current_steps": 7, "total_steps": 18, "loss": 1.0696, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:06:46", "remaining_time": "0:10:38"}
8
+ {"current_steps": 8, "total_steps": 18, "loss": 1.0377, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:07:23", "remaining_time": "0:09:13"}
9
+ {"current_steps": 9, "total_steps": 18, "loss": 1.0122, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:07:59", "remaining_time": "0:07:59"}
10
+ {"current_steps": 10, "total_steps": 18, "loss": 0.9653, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:08:36", "remaining_time": "0:06:52"}
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8b365ed0cdf388545c48247fbe6a4d729f8b26dbd075887b56bbbb646b12719
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d6af9e96f80aa03660ad0017955d850b0a992f39f66211b64326dabefeb62e
3
  size 7224