SummerSigh
commited on
Commit
•
e101d57
1
Parent(s):
1870bb6
Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +28 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.ptrom +3 -0
- rng_state.pth +3 -0
- scheduler.ptrom +0 -0
- trainer_state.json +137 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
optimizer.ptrom filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 64,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 256,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"mlp_bias": false,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 8,
|
17 |
+
"num_hidden_layers": 8,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.41.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32001
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a823b3b13b4b9e9a6aafe0472d4fad914f6f7e62545377835609a764415eff
|
3 |
+
size 18494040
|
optimizer.ptrom
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2180c643d0cc5b3fff66227c71ce3682aad53b8ff96a5c1b2e1bcdb8bdbb9ff9
|
3 |
+
size 37035002
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
3 |
+
size 14244
|
scheduler.ptrom
ADDED
Binary file (1.06 kB). View file
|
|
trainer_state.json
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2507601166034542,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.018807008745259066,
|
13 |
+
"grad_norm": 0.7771628499031067,
|
14 |
+
"learning_rate": 1.9877931524601816e-05,
|
15 |
+
"loss": 10.1462,
|
16 |
+
"num_input_tokens_seen": 19660800,
|
17 |
+
"step": 150
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.03761401749051813,
|
21 |
+
"grad_norm": 0.841651201248169,
|
22 |
+
"learning_rate": 1.97525187074119e-05,
|
23 |
+
"loss": 9.8974,
|
24 |
+
"num_input_tokens_seen": 39321600,
|
25 |
+
"step": 300
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.0564210262357772,
|
29 |
+
"grad_norm": 0.7740743160247803,
|
30 |
+
"learning_rate": 1.9627105890221982e-05,
|
31 |
+
"loss": 9.6653,
|
32 |
+
"num_input_tokens_seen": 58982400,
|
33 |
+
"step": 450
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.07522803498103627,
|
37 |
+
"grad_norm": 0.8001583218574524,
|
38 |
+
"learning_rate": 1.9501693073032066e-05,
|
39 |
+
"loss": 9.4506,
|
40 |
+
"num_input_tokens_seen": 78643200,
|
41 |
+
"step": 600
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.09403504372629533,
|
45 |
+
"grad_norm": 0.8240243792533875,
|
46 |
+
"learning_rate": 1.937628025584215e-05,
|
47 |
+
"loss": 9.2539,
|
48 |
+
"num_input_tokens_seen": 98304000,
|
49 |
+
"step": 750
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.1128420524715544,
|
53 |
+
"grad_norm": 0.7667157053947449,
|
54 |
+
"learning_rate": 1.9250867438652233e-05,
|
55 |
+
"loss": 9.0693,
|
56 |
+
"num_input_tokens_seen": 117964800,
|
57 |
+
"step": 900
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.13164906121681347,
|
61 |
+
"grad_norm": 0.8228150010108948,
|
62 |
+
"learning_rate": 1.9125454621462316e-05,
|
63 |
+
"loss": 8.8967,
|
64 |
+
"num_input_tokens_seen": 137625600,
|
65 |
+
"step": 1050
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15045606996207253,
|
69 |
+
"grad_norm": 0.8424794673919678,
|
70 |
+
"learning_rate": 1.9000041804272396e-05,
|
71 |
+
"loss": 8.7364,
|
72 |
+
"num_input_tokens_seen": 157286400,
|
73 |
+
"step": 1200
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.1692630787073316,
|
77 |
+
"grad_norm": 0.7859320640563965,
|
78 |
+
"learning_rate": 1.8874628987082483e-05,
|
79 |
+
"loss": 8.5903,
|
80 |
+
"num_input_tokens_seen": 176947200,
|
81 |
+
"step": 1350
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.18807008745259066,
|
85 |
+
"grad_norm": 0.7881995439529419,
|
86 |
+
"learning_rate": 1.8749216169892567e-05,
|
87 |
+
"loss": 8.4497,
|
88 |
+
"num_input_tokens_seen": 196608000,
|
89 |
+
"step": 1500
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.20687709619784972,
|
93 |
+
"grad_norm": 0.8333655595779419,
|
94 |
+
"learning_rate": 1.8623803352702647e-05,
|
95 |
+
"loss": 8.3184,
|
96 |
+
"num_input_tokens_seen": 216268800,
|
97 |
+
"step": 1650
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.2256841049431088,
|
101 |
+
"grad_norm": 0.7956089973449707,
|
102 |
+
"learning_rate": 1.849839053551273e-05,
|
103 |
+
"loss": 8.1998,
|
104 |
+
"num_input_tokens_seen": 235929600,
|
105 |
+
"step": 1800
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.24449111368836787,
|
109 |
+
"grad_norm": 0.8068310022354126,
|
110 |
+
"learning_rate": 1.8372977718322814e-05,
|
111 |
+
"loss": 8.0871,
|
112 |
+
"num_input_tokens_seen": 255590400,
|
113 |
+
"step": 1950
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"logging_steps": 150,
|
117 |
+
"max_steps": 23925,
|
118 |
+
"num_input_tokens_seen": 262144000,
|
119 |
+
"num_train_epochs": 3,
|
120 |
+
"save_steps": 500,
|
121 |
+
"stateful_callbacks": {
|
122 |
+
"TrainerControl": {
|
123 |
+
"args": {
|
124 |
+
"should_epoch_stop": false,
|
125 |
+
"should_evaluate": false,
|
126 |
+
"should_log": false,
|
127 |
+
"should_save": true,
|
128 |
+
"should_training_stop": false
|
129 |
+
},
|
130 |
+
"attributes": {}
|
131 |
+
}
|
132 |
+
},
|
133 |
+
"total_flos": 4047671132160000.0,
|
134 |
+
"train_batch_size": 32,
|
135 |
+
"trial_name": null,
|
136 |
+
"trial_params": null
|
137 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cde99b26e6ad0be4341c488ddc29911f5c5e44dd52e53c785a43dc3f89cfc61e
|
3 |
+
size 5112
|