Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.95

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
33f1957
·
verified ·
1 Parent(s): 2153b8c

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +44 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0deee133a73aa2af6b879353f29cf32487ae9f1306550ac344188ecd8b70e9b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9690e60c7f4fec6477a1616d8905b8ac3a36542bba9dffb0c5a7862ddf4150be
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:c7b6e6b1ae23ab10d1f1b5f5d0b26b8e3305d89ca9f97d329be4201388b186ae
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90476652d8fd391722814e3d84167d097d53ea41706090f5eb9e9fe95b31356b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51e83badaa97e84761721d92f1947f7e388d36fd16d9f53b518a34494e85d748
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b9c0a0379f9199a74f7e2b7f6ce21eacf6cf86b7d4165661b5d2593dd0dd4c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05efecb163a8fd1816f07aeb17bef0de7b62e416ef36869e737151760f349043
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a3a6e917a147b32ea0e45cfc546be91fef3931f8e888a6f196c48486b7b36b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -43,3 +43,47 @@
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6346, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:20:28", "remaining_time": "13:02:10"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251624226570129, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:35:24", "remaining_time": "13:10:49"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6473, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:37:48", "remaining_time": "13:10:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6346, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:20:28", "remaining_time": "13:02:10"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251624226570129, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:35:24", "remaining_time": "13:10:49"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6473, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:37:48", "remaining_time": "13:10:11"}
46
+ {"current_steps": 450, "total_steps": 1314, "loss": 0.602, "learning_rate": 5e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:46:39", "remaining_time": "13:00:46"}
47
+ {"current_steps": 460, "total_steps": 1314, "loss": 0.5954, "learning_rate": 5e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:55:29", "remaining_time": "12:51:22"}
48
+ {"current_steps": 470, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "7:04:21", "remaining_time": "12:42:02"}
49
+ {"current_steps": 480, "total_steps": 1314, "loss": 0.6035, "learning_rate": 5e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:13:11", "remaining_time": "12:32:40"}
50
+ {"current_steps": 490, "total_steps": 1314, "loss": 0.6084, "learning_rate": 5e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:22:03", "remaining_time": "12:23:23"}
51
+ {"current_steps": 500, "total_steps": 1314, "loss": 0.5983, "learning_rate": 5e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:30:56", "remaining_time": "12:14:07"}
52
+ {"current_steps": 510, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:39:48", "remaining_time": "12:04:52"}
53
+ {"current_steps": 520, "total_steps": 1314, "loss": 0.6018, "learning_rate": 5e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:48:41", "remaining_time": "11:55:38"}
54
+ {"current_steps": 530, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:57:31", "remaining_time": "11:46:22"}
55
+ {"current_steps": 540, "total_steps": 1314, "loss": 0.6051, "learning_rate": 5e-06, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "8:06:22", "remaining_time": "11:37:08"}
56
+ {"current_steps": 550, "total_steps": 1314, "loss": 0.6017, "learning_rate": 5e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:15:13", "remaining_time": "11:27:55"}
57
+ {"current_steps": 560, "total_steps": 1314, "loss": 0.6032, "learning_rate": 5e-06, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:24:04", "remaining_time": "11:18:42"}
58
+ {"current_steps": 570, "total_steps": 1314, "loss": 0.5973, "learning_rate": 5e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:32:56", "remaining_time": "11:09:31"}
59
+ {"current_steps": 580, "total_steps": 1314, "loss": 0.5958, "learning_rate": 5e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:41:48", "remaining_time": "11:00:21"}
60
+ {"current_steps": 590, "total_steps": 1314, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:50:40", "remaining_time": "10:51:11"}
61
+ {"current_steps": 600, "total_steps": 1314, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:59:31", "remaining_time": "10:42:02"}
62
+ {"current_steps": 610, "total_steps": 1314, "loss": 0.6012, "learning_rate": 5e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:08:23", "remaining_time": "10:32:53"}
63
+ {"current_steps": 620, "total_steps": 1314, "loss": 0.6037, "learning_rate": 5e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:17:14", "remaining_time": "10:23:45"}
64
+ {"current_steps": 630, "total_steps": 1314, "loss": 0.6018, "learning_rate": 5e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:26:05", "remaining_time": "10:14:37"}
65
+ {"current_steps": 640, "total_steps": 1314, "loss": 0.5966, "learning_rate": 5e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:34:57", "remaining_time": "10:05:30"}
66
+ {"current_steps": 650, "total_steps": 1314, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:43:47", "remaining_time": "9:56:22"}
67
+ {"current_steps": 660, "total_steps": 1314, "loss": 0.5942, "learning_rate": 5e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:52:37", "remaining_time": "9:47:14"}
68
+ {"current_steps": 670, "total_steps": 1314, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "10:01:28", "remaining_time": "9:38:08"}
69
+ {"current_steps": 680, "total_steps": 1314, "loss": 0.5904, "learning_rate": 5e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:10:20", "remaining_time": "9:29:03"}
70
+ {"current_steps": 690, "total_steps": 1314, "loss": 0.5944, "learning_rate": 5e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:19:12", "remaining_time": "9:19:58"}
71
+ {"current_steps": 700, "total_steps": 1314, "loss": 0.61, "learning_rate": 5e-06, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:28:04", "remaining_time": "9:10:54"}
72
+ {"current_steps": 710, "total_steps": 1314, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:36:55", "remaining_time": "9:01:50"}
73
+ {"current_steps": 720, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:45:47", "remaining_time": "8:52:47"}
74
+ {"current_steps": 730, "total_steps": 1314, "loss": 0.5947, "learning_rate": 5e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:54:40", "remaining_time": "8:43:44"}
75
+ {"current_steps": 740, "total_steps": 1314, "loss": 0.5957, "learning_rate": 5e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "11:03:32", "remaining_time": "8:34:41"}
76
+ {"current_steps": 750, "total_steps": 1314, "loss": 0.5932, "learning_rate": 5e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:12:24", "remaining_time": "8:25:39"}
77
+ {"current_steps": 760, "total_steps": 1314, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:21:17", "remaining_time": "8:16:37"}
78
+ {"current_steps": 770, "total_steps": 1314, "loss": 0.5935, "learning_rate": 5e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:30:07", "remaining_time": "8:07:34"}
79
+ {"current_steps": 780, "total_steps": 1314, "loss": 0.6007, "learning_rate": 5e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:38:59", "remaining_time": "7:58:32"}
80
+ {"current_steps": 790, "total_steps": 1314, "loss": 0.5982, "learning_rate": 5e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:47:50", "remaining_time": "7:49:30"}
81
+ {"current_steps": 800, "total_steps": 1314, "loss": 0.5851, "learning_rate": 5e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:56:42", "remaining_time": "7:40:29"}
82
+ {"current_steps": 810, "total_steps": 1314, "loss": 0.5929, "learning_rate": 5e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "12:05:32", "remaining_time": "7:31:26"}
83
+ {"current_steps": 820, "total_steps": 1314, "loss": 0.5906, "learning_rate": 5e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:14:22", "remaining_time": "7:22:25"}
84
+ {"current_steps": 830, "total_steps": 1314, "loss": 0.5945, "learning_rate": 5e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:23:12", "remaining_time": "7:13:23"}
85
+ {"current_steps": 840, "total_steps": 1314, "loss": 0.599, "learning_rate": 5e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:32:04", "remaining_time": "7:04:22"}
86
+ {"current_steps": 850, "total_steps": 1314, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:40:55", "remaining_time": "6:55:22"}
87
+ {"current_steps": 860, "total_steps": 1314, "loss": 0.5983, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:49:47", "remaining_time": "6:46:22"}
88
+ {"current_steps": 870, "total_steps": 1314, "loss": 0.5958, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:58:38", "remaining_time": "6:37:22"}
89
+ {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.618757426738739, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:12:11", "remaining_time": "6:34:44"}